Award type：Award from Japanese society, conference, symposium, etc. 

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1002/minf.202300262

DOI： 10.1002/minf.202300262

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1021/acs.jcim.3c00824

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1186/s13072-023-00510-w

DOI： 10.1186/s13072-023-00510-w

PubMed

Authorship：Last author   Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1007/978-3-031-43412-9_19

Other Link： https://dblp.uni-trier.de/db/conf/pkdd/pkdd2023-1.html#LiY23

Authorship：Corresponding author   Language：English   Publishing type：Research paper (scientific journal)  

GLS1 is an attractive target not only as anticancer agents but also as candidates for various potential pharmaceutical applications such as anti-aging and anti-obesity treatments. We performed docking simulations based on the complex crystal structure of GLS1 and its inhibitor CB-839 and found that compound A bearing a thiadiazole skeleton exhibits GLS1 inhibition. Furthermore, we synthesized 27 thiadiazole derivatives in an effort to obtain a more potent GLS1 inhibitor. Among the synthesized derivatives, 4d showed more potent GLS1 inhibitory activity (IC50 of 46.7 µM) than known GLS1 inhibitor DON and A. Therefore, 4d is a very promising novel GLS1 inhibitor.

DOI： 10.1016/j.bmcl.2023.129438

DOI： 10.1016/j.bmcl.2023.129438

Web of Science

Scopus

PubMed

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)  

Computational de novo drug design is a challenging issue in medicine, and it is desirable to consider all of the relevant information of the biological systems in a disease state. Here, we propose a novel computational method to generate drug candidate molecular structures from patient gene expression profiles via deep learning, which we call DRAGONET. Our model can generate new molecules that are likely to counteract disease-specific gene expression patterns in patients, which is made possible by exploring the latent space constructed by a transformer-based variational autoencoder and integrating the substructures of disease-correlated molecules. We applied DRAGONET to generate drug candidate molecules for gastric cancer, atopic dermatitis, and Alzheimer's disease, and demonstrated that the newly generated molecules were chemically similar to registered drugs for each disease. This approach is applicable to diseases with unknown therapeutic target proteins and will make a significant contribution to the field of precision medicine.

DOI： 10.1002/minf.202300064

DOI： 10.1002/minf.202300064

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

Although an association has been reported between diuretics and myocarditis, it is unclear whether the risk of immune checkpoint inhibitor (ICI)-induced myocarditis is affected by concomitant diuretics. Thus, the aim of this work was to evaluate the impact of concomitant diuretics on ICI-induced myocarditis. This cross-sectional study used disproportionality analysis and a pharmacovigilance database to assess the risk of myocarditis with various diuretics in patients receiving ICIs via the analysis of data entered into the VigiBase database through December 2022. Multiple logistic regression analysis was performed to identify risk factors for myocarditis in patients who received ICIs. A total of 90 611 patients who received ICIs, including 975 cases of myocarditis, were included as the eligible dataset. A disproportionality in myocarditis was observed for loop diuretic use (reporting odds ratio 1.47, 95% confidence interval [CI] 1.02-2.04, P = .03) and thiazide use (reporting odds ratio 1.76, 95% CI 1.20-2.50, P < .01) in patients who received ICIs. The results of the multiple logistic regression analysis showed that the use of thiazides (odds ratio 1.67, 95% CI 1.15-2.34, P < .01) was associated with an increased risk of myocarditis in patients who received ICIs. Our findings may help to predict the risk of myocarditis in patients receiving ICIs.

DOI： 10.1002/ijc.34616

DOI： 10.1002/ijc.34616

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

Mutations in the LMNA gene encoding Lamin A and C (Lamin A/C), major components of the nuclear lamina, cause laminopathies including dilated cardiomyopathy (DCM), but the underlying molecular mechanisms have not been fully elucidated. Here, by leveraging single-cell RNA sequencing (RNA-seq), assay for transposase-accessible chromatin using sequencing (ATAC-seq), protein array, and electron microscopy analysis, we show that insufficient structural maturation of cardiomyocytes owing to trapping of transcription factor TEA domain transcription factor 1 (TEAD1) by mutant Lamin A/C at the nuclear membrane underlies the pathogenesis of Q353R-LMNA-related DCM. Inhibition of the Hippo pathway rescued the dysregulation of cardiac developmental genes by TEAD1 in LMNA mutant cardiomyocytes. Single-cell RNA-seq of cardiac tissues from patients with DCM with the LMNA mutation confirmed the dysregulated expression of TEAD1 target genes. Our results propose an intervention for transcriptional dysregulation as a potential treatment of LMNA-related DCM.

DOI： 10.1126/sciadv.ade7047

DOI： 10.1126/sciadv.ade7047

Web of Science

Scopus

PubMed

Web of Science

Authorship：Last author   Language：English   Publishing type：Research paper (scientific journal)  

In an open pilot trial, six patients with various hereditary forms of spinocerebellar ataxia (SCA) were assigned to topiramate (50 mg/day) for 24 weeks. Four patients completed the protocol without adverse events. Of these four patients, topiramate was effective for three patients. Some patients with SCA could respond to treatment with topiramate.

DOI： 10.1002/ccr3.6980

Web of Science

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

Proton pump inhibitors (PPIs) are potent inhibitors of gastric acid secretion, used as first-line agents in treating peptic ulcers. However, we have previously reported that PPIs may diminish the therapeutic effect of anti-vascular endothelial growth factor (VEGF) drugs in patients with cancer. In this study, we explored the effects of vonoprazan, a novel gastric acid secretion inhibitor used for the treatment of peptic ulcers, on the secretion of VEGF in cancer cells and attempted to propose it as an alternative PPI for cancer chemotherapy. The effects of PPI and vonoprazan on VEGF expression in cancer cells were compared by real-time reverse transcription-polymerase chain reaction and ELISA. The interaction of vonoprazan and PPIs with transcriptional regulators by docking simulation analysis. In various cancer cell lines, including the human colorectal cancer cell line (LS174T), PPI increased VEGF messenger RNA expression and VEGF protein secretion, while this effect was not observed with vonoprazan. Molecular docking simulation analysis showed that vonoprazan had a lower binding affinity for estrogen receptor alpha (ER-α), one of the transcriptional regulators of VEGF, compared to PPI. Although the PPI-induced increase in VEGF expression was counteracted by pharmacological ER-α inhibition, the effect of vonoprazan on VEGF expression was unchanged. Vonoprazan does not affect VEGF expression in cancer cells, which suggests that vonoprazan might be an alternative to PPIs, with no interference with the therapeutic effects of anti-VEGF cancer chemotherapy.

DOI： 10.1002/ddr.22013

Web of Science

Scopus

PubMed

Web of Science

Publisher：Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023  

De novo drug design is a challenging task that involves understanding the principles of chemistry, chemical properties, and the rules that govern molecular interactions. Deep learning-based generative models, such as MolGAN, offer a promising approach for generating new molecules with the desired chemical properties from molecular graphs. Such models often combine a discrete generative adversarial network (GAN) and reinforcement learning (RL) to produce highly valid and novel molecules. However, the severe mode collapse problem leads to low performance. This study aims to alleviate and investigate the effect of multiple factors on mode collapse. We conducted experiments on different sampling methods, training epochs, and datasets of various volumes and evaluated the experimental results using performance metrics such as validity, uniqueness, novelty, and diversity. The experimental results demonstrate that noise sampling distributions, training epochs, and training data volumes affect performance. The experimental results provide a direction for mitigating the mode collapse problem for RL-based discrete GANs.

DOI： 10.1109/BIBM58861.2023.10385948

Scopus

Language：English   Publishing type：Research paper (scientific journal)  

Myasthenia gravis (MG) is a rare but fatal adverse event of immune checkpoint inhibitors (ICIs). We assessed whether patient characteristics differed between those with ICI-related myasthenia gravis and those with idiopathic myasthenia gravis. Reports from the US Food and Drug Administration Adverse Event Reporting System were analyzed. Multivariate analyses were conducted to evaluate the associations between age, sex, and ICI treatment and the reporting rate of myasthenia gravis. Among 5 464 099 cases between 2011 and 2019, 53 447 were treated with ICIs. Myasthenia gravis was reported more often in ICI users. Multiple logistic regression analyses showed that the reporting rate of ICI-related myasthenia gravis did not differ significantly between men and women; however, it was higher in older people than in younger people (adjusted odds ratio, 2.4 [95%CI, 1.84-3.13]). We also investigated useful signs for the early detection of myositis and myocarditis, which are fatal when overlapping with ICI-related myasthenia gravis. Patients with elevated serum creatine kinase or troponin levels were more likely to have concurrent myositis and myocarditis. Unlike idiopathic myasthenia gravis, there was no sex difference in the development of ICI-related myasthenia gravis, which may be more common in older people. Considering the physiological muscle weakness that occurs in the elderly, it may be necessary to monitor ICI-related myasthenia gravis more closely in older people.

DOI： 10.1002/jcph.2187

DOI： 10.1002/jcph.2187

Web of Science

Scopus

PubMed

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

Abstract

Drugs are expected to recover the cell system away from the impaired state to normalcy through disease treatment. However, the understanding of gene regulatory machinery underlying drug activity or disease pathogenesis is far from complete. Here, we perform large-scale regulome analysis for various diseases in terms of gene regulatory machinery. Transcriptome signatures were converted into regulome signatures of transcription factors by integrating publicly available ChIP-seq data. Regulome-based correlations between diseases and their approved drugs were much clearer than the transcriptome-based correlations. For example, an inverse correlation was observed for cancers, whereas a positive correlation was observed for immune system diseases. After demonstrating the usefulness of the regulome-based drug discovery method in terms of accuracy and applicability, we predicted new drugs for nonsmall cell lung cancer and validated the anticancer activity in vitro. The proposed method is useful for understanding disease–disease relationships and drug discovery.

DOI： 10.1038/s41540-022-00255-4

Web of Science

Scopus

PubMed

Other Link： https://www.nature.com/articles/s41540-022-00255-4

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：SPRINGERNATURE  

Genome-wide identification of single-cell transcriptomic responses of drugs in various human cells is a challenging issue in medical and pharmaceutical research. Here we present a computational method, tensor-based imputation of gene-expression data at the single-cell level (TIGERS), which reveals the drug-induced single-cell transcriptomic landscape. With this algorithm, we predict missing drug-induced single-cell gene-expression data with tensor imputation, and identify trajectories of regulated pathways considering intercellular heterogeneity. Tensor imputation outperformed existing imputation methods for data completion, and provided cell-type-specific transcriptomic responses for unobserved drugs. For example, TIGERS correctly predicted the cell-type-specific expression of maker genes for pancreatic islets. Pathway trajectory analysis of the imputed gene-expression profiles of all combinations of drugs and human cells identified single-cell-specific drug activities and pathway trajectories that reflect drug-induced changes in pathway regulation. The proposed method is expected to expand our understanding of the single-cell mechanisms of drugs at the pathway level.

DOI： 10.1038/s43588-022-00352-8

Web of Science

Scopus

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)  

MOTIVATION: Direct cell conversion, direct reprogramming (DR), is an innovative technology that directly converts source cells to target cells without bypassing induced pluripotent stem cells. The use of small compounds (e.g. drugs) for DR can help avoid carcinogenic risk induced by gene transfection; however, experimentally identifying small compounds remains challenging because of combinatorial explosion. RESULTS: In this article, we present a new computational method, COMPRENDRE (combinatorial optimization of pathway regulations for direct reprograming), to elucidate the mechanism of small compound-based DR and predict new combinations of small compounds for DR. We estimated the potential target proteins of DR-inducing small compounds and identified a set of target pathways involving DR. We identified multiple DR-related pathways that have not previously been reported to induce neurons or cardiomyocytes from fibroblasts. To overcome the problem of combinatorial explosion, we developed a variant of a simulated annealing algorithm to identify the best set of compounds that can regulate DR-related pathways. Consequently, the proposed method enabled to predict new DR-inducing candidate combinations with fewer compounds and to successfully reproduce experimentally verified compounds inducing the direct conversion from fibroblasts to neurons or cardiomyocytes. The proposed method is expected to be useful for practical applications in regenerative medicine. AVAILABILITY AND IMPLEMENTATION: The code supporting the current study is available at the http://labo.bio.kyutech.ac.jp/~yamani/comprendre. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DOI： 10.1093/bioinformatics/btac475

Web of Science

Scopus

PubMed

Authorship：Last author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ijcai.org  

DOI： 10.24963/ijcai.2022/539

Other Link： https://dblp.uni-trier.de/db/conf/ijcai/ijcai2022.html#LiYKY22

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)  

MOTIVATION: A critical element of drug development is the identification of therapeutic targets for diseases. However, the depletion of therapeutic targets is a serious problem. RESULTS: In this study, we propose the novel concept of target repositioning, an extension of the concept of drug repositioning, to predict new therapeutic targets for various diseases. Predictions were performed by a trans-disease analysis which integrated genetically perturbed transcriptomic signatures (knockdown of 4345 genes and overexpression of 3114 genes) and disease-specific gene transcriptomic signatures of 79 diseases. The trans-disease method, which takes into account similarities among diseases, enabled us to distinguish the inhibitory from activatory targets and to predict the therapeutic targetability of not only proteins with known target-disease associations but also orphan proteins without known associations. Our proposed method is expected to be useful for understanding the commonality of mechanisms among diseases and for therapeutic target identification in drug discovery. AVAILABILITY AND IMPLEMENTATION: Supplemental information and software are available at the following website [http://labo.bio.kyutech.ac.jp/~yamani/target_repositioning/]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DOI： 10.1093/bioinformatics/btac240

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

[This corrects the article DOI: 10.3389/fendo.2022.825195.].

DOI： 10.3389/fendo.2022.944910

Web of Science

Scopus

PubMed

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)  

The construction of a virtual library (VL) consisting of novel molecules based on structure-activity relationships is crucial for lead optimization in rational drug design. In this study, we propose a novel scaffold-retained structure generator, EMPIRE (Exhaustive Molecular library Production In a scaffold-REtained manner), to create novel molecules in an arbitrary chemical space. By combining a deep learning model-based generator and a building block-based generator, the proposed method efficiently provides a VL consisting of molecules that retain the input scaffold and contain unique arbitrary substructures. The proposed method enables us to construct rational VLs located in unexplored chemical spaces containing molecules with unique skeletons (e.g., bicyclo[1.1.1]pentane and cubane) or elements (e.g., boron and silicon). We expect EMPIRE to contribute to efficient drug design with unique substructures by virtual screening.

DOI： 10.1021/acs.jcim.1c01130

Web of Science

Scopus

PubMed

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Oxford University Press (OUP)  

Abstract

Motivation

Direct reprogramming involves the direct conversion of fully differentiated mature cell types into various other cell types while bypassing an intermediate pluripotent state (e.g., induced pluripotent stem cells). Cell differentiation by direct reprogramming is determined by two types of transcription factors (TFs): pioneer factors (PFs) and cooperative TFs. PFs have the distinct ability to open chromatin aggregations, assemble a collective of cooperative TFs, and activate gene expression. The experimental determination of two types of TFs is extremely difficult and costly.

Results

In this study, we developed a novel computational method, TRANSDIRE (TRANS-omics-based approach for DIrect REprogramming), to predict the TFs that induce direct reprogramming in various human cell types using multiple omics data. In the algorithm, potential PFs were predicted based on low signal chromatin regions, and the cooperative TFs were predicted through a trans-omics analysis of genomic data (e.g., enhancers), transcriptome data (e.g., gene expression profiles in human cells), epigenome data (e.g., chromatin immunoprecipitation sequencing data), and interactome data. We applied the proposed methods to the reconstruction of TFs that induce direct reprogramming from fibroblasts to six other cell types: hepatocytes, cartilaginous cells, neurons, cardiomyocytes, pancreatic cells, and Paneth cells. We demonstrated that the methods successfully predicted TFs for most cell conversions with high accuracy. Thus, the proposed methods are expected to be useful for various practical applications in regenerative medicine.

Availability

The source code and data are available at the following website: http://figshare.com/s/b653781a5b9e6639972b

DOI： 10.1093/bioinformatics/btac209

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

The GGIP web server (https://protein.b.dendai.ac.jp/GGIP/) provides a web application for GPCR-GPCR interaction pair prediction by a support vector machine. The server accepts two sequences in the FASTA format. It responds with a prediction that the input GPCR sequence pair either interacts or not. GPCRs predicted to interact with the monomers constituting the pair are also shown when query sequences are human GPCRs. The server is simple to use. A pair of amino acid sequences in the FASTA format is pasted into the text area, a PDB ID for a template structure is selected, and then the 'Execute' button is clicked. The server quickly responds with a prediction result. The major advantage of this server is that it employs the GGIP software, which is presently the only method for predicting GPCR-interaction pairs. Our web server is freely available with no login requirement. In this article, we introduce some application examples of GGIP for disease-associated mutation analysis.

DOI： 10.3389/fendo.2022.825195

Web of Science

Scopus

PubMed

Authorship：Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

Abstract

Background

Elucidating the modes of action (MoAs) of drugs and drug candidate compounds is critical for guiding translation from drug discovery to clinical application. Despite the development of several data-driven approaches for predicting chemical–disease associations, the molecular cues that organize the epigenetic landscape of drug responses remain poorly understood.

Results

With the use of a computational method, we attempted to elucidate the epigenetic landscape of drug responses, in terms of transcription factors (TFs), through large-scale ChIP-seq data analyses. In the algorithm, we systematically identified TFs that regulate the expression of chemically induced genes by integrating transcriptome data from chemical induction experiments and almost all publicly available ChIP-seq data (consisting of 13,558 experiments). By relating the resultant chemical–TF associations to a repository of associated proteins for a wide range of diseases, we made a comprehensive prediction of chemical–TF–disease associations, which could then be used to account for drug MoAs. Using this approach, we predicted that: (1) cisplatin promotes the anti-tumor activity of TP53 family members but suppresses the cancer-inducing function of MYCs; (2) inhibition of RELA and E2F1 is pivotal for leflunomide to exhibit antiproliferative activity; and (3) CHD8 mediates valproic acid-induced autism.

Conclusions

Our proposed approach has the potential to elucidate the MoAs for both approved drugs and candidate compounds from an epigenetic perspective, thereby revealing new therapeutic targets, and to guide the discovery of unexpected therapeutic effects, side effects, and novel targets and actions.

DOI： 10.1186/s12859-022-04571-8

Web of Science

Scopus

PubMed

Other Link： https://link.springer.com/article/10.1186/s12859-022-04571-8/fulltext.html

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)  

One of the most challenging tasks in the drug-discovery process is the efficient identification of small molecules with desired phenotypes. In this study, we propose a novel computational method for omics-based de novo drug design, which we call TRIOMPHE (transcriptome-based inference and generation of molecules with desired phenotypes). We investigated the correlation between chemically induced transcriptome profiles (reflecting cellular responses to compound treatment) and genetically perturbed transcriptome profiles (reflecting cellular responses to gene knock-down or gene overexpression of target proteins) in terms of ligand-target interactions. Subsequently, we developed novel machine learning methods to generate the chemical structures of new molecules with desired transcriptome profiles in the framework of a variational autoencoder. The use of desired transcriptome profiles enables the automatic design of molecules that are likely to have bioactivities for target proteins of interest. We showed that our methods can generate chemically valid molecules that are likely to have biological activities on 10 target proteins; moreover, they can outperform previous methods that had the same objective. Our omics-based structure generator is expected to be useful for the de novo design of drugs for a variety of target proteins.

DOI： 10.1021/acs.jcim.1c00967

Web of Science

Scopus

PubMed

Language：English  

Essential tremor (ET) is one of the most common movement disorders. However, there are currently no accepted biomarkers for ET. This report suggested that concentration of plasma glutamic acid, aspartic acid, and taurine could be biomarkers for ET.

DOI： 10.1002/ccr3.4580

Web of Science

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：American Chemical Society (ACS)  

In structure-based virtual screening (SBVS), a binding site on a protein structure is used to search for ligands with favorable nonbonded interactions. Because it is computationally difficult, docking is time-consuming and any docking user will eventually encounter a chemical library that is too big to dock. This problem might arise because there is not enough computing power or because preparing and storing so many three-dimensional (3D) ligands requires too much space. In this study, however, we show that quality regressors can be trained to predict docking scores from molecular fingerprints. Although typical docking has a screening rate of less than one ligand per second on one CPU core, our regressors can predict about 5800 docking scores per second. This approach allows us to focus docking on the portion of a database that is predicted to have docking scores below a user-chosen threshold. Herein, usage examples are shown, where only 25% of a ligand database is docked, without any significant virtual screening performance loss. We call this method "lean-docking". To validate lean-docking, a massive docking campaign using several state-of-the-art docking software packages was undertaken on an unbiased data set, with only wet-lab tested active and inactive molecules. Although regressors allow the screening of a larger chemical space, even at a constant docking power, it is also clear that significant progress in the virtual screening power of docking scores is desirable.

DOI： 10.1021/acs.jcim.0c01452

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

<title>Abstract</title>Heart failure is a heterogeneous disease with multiple risk factors and various pathophysiological types, which makes it difficult to understand the molecular mechanisms involved. In this study, we proposed a trans-omics approach for predicting molecular pathological mechanisms of heart failure and identifying marker genes to distinguish heterogeneous phenotypes, by integrating multiple omics data including single-cell RNA-seq, ChIP-seq, and gene interactome data. We detected a significant increase in the expression level of natriuretic peptide A (<italic>Nppa</italic>), after stress loading with transverse aortic constriction (TAC), and showed that cardiomyocytes with high <italic>Nppa</italic> expression displayed specific gene expression patterns. Multiple NADH ubiquinone complex family, which are associated with the mitochondrial electron transport system, were negatively correlated with <italic>Nppa</italic> expression during the early stages of cardiac hypertrophy. Large-scale ChIP-seq data analysis showed that Nkx2-5 and Gtf2b were transcription factors characteristic of high-<italic>Nppa-</italic>expressing cardiomyocytes. <italic>Nppa</italic> expression levels may, therefore, represent a useful diagnostic marker for heart failure.

DOI： 10.1038/s41598-021-86821-y

Web of Science

Scopus

PubMed

Other Link： http://www.nature.com/articles/s41598-021-86821-y

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Wiley  

Targeting mutated oncogenes is an effective approach for treating cancer. The 4 main driver genes of pancreatic ductal adenocarcinoma (PDAC) are KRAS, TP53, CDKN2A, and SMAD4, collectively called the "big 4" of PDAC, however they remain challenging therapeutic targets. In this study, ArfGAP with SH3 domain, ankyrin repeat and PH domain 2 (ASAP2), one of the ArfGAP family, was identified as a novel driver gene in PDAC. Clinical analysis with PDAC datasets showed that ASAP2 was overexpressed in PDAC cells based on increased DNA copy numbers, and high ASAP2 expression contributed to a poor prognosis in PDAC. The biological roles of ASAP2 were investigated using ASAP2-knockout PDAC cells generated with CRISPR-Cas9 technology or transfected PDAC cells. In vitro and in vivo analyses showed that ASAP2 promoted tumor growth by facilitating cell cycle progression through phosphorylation of epidermal growth factor receptor (EGFR). A repositioned drug targeting the ASAP2 pathway was identified using a bioinformatics approach. The gene perturbation correlation method showed that niclosamide, an antiparasitic drug, suppressed PDAC growth by inhibition of ASAP2 expression. These data show that ASAP2 is a novel druggable driver gene that activates the EGFR signaling pathway. Furthermore, niclosamide was identified as a repositioned therapeutic agent for PDAC possibly targeting ASAP2.

DOI： 10.1111/cas.14858

Web of Science

Scopus

PubMed

Web of Science

Language：English   Publishing type：Research paper (scientific journal)  

In ligand-based virtual screening, high-throughput screening (HTS) data sets can be exploited to train classification models. Such models can be used to prioritize yet untested molecules, from the most likely active (against a protein target of interest) to the least likely active. In this study, a single-parameter ranking method with an Applicability Domain (AD) is proposed. In effect, Kernel Density Estimates (KDE) are revisited to improve their computational efficiency and incorporate an AD. Two modifications are proposed: (i) using vanishing kernels (i.e., kernel functions with a finite support) and (ii) using the Tanimoto distance between molecular fingerprints as a radial basis function. This construction is termed "Vanishing Ranking Kernels" (VRK). Using VRK on 21 HTS assays, it is shown that VRK can compete in performance with a graph convolutional deep neural network. VRK are conceptually simple and fast to train. During training, they require optimizing a single parameter. A trained VRK model usually defines an active AD. Exploiting this AD can significantly increase the screening frequency of a VRK model. Software: https://github.com/UnixJunkie/rankers. Data sets: https://zenodo.org/record/1320776 and https://zenodo.org/record/3540423.

DOI： 10.1021/acs.jcim.9b01075

Web of Science

Scopus

PubMed

Other Link： https://dblp.uni-trier.de/db/journals/jcisd/jcisd60.html#BerengerY20

Language：English   Publishing type：Research paper (scientific journal)  

MOTIVATION: Disease states are distinguished from each other in terms of differing clinical phenotypes, but characteristic molecular features are often common to various diseases. Similarities between diseases can be explained by characteristic gene expression patterns. However, most disease-disease relationships remain uncharacterized. RESULTS: In this study, we proposed a novel approach for network-based characterization of disease-disease relationships in terms of drugs and therapeutic targets. We performed large-scale analyses of omics data and molecular interaction networks for 79 diseases, including adrenoleukodystrophy, leukaemia, Alzheimer's disease, asthma, atopic dermatitis, breast cancer, cystic fibrosis and inflammatory bowel disease. We quantified disease-disease similarities based on proximities of abnormally expressed genes in various molecular networks, and showed that similarities between diseases could be explained by characteristic molecular network topologies. Furthermore, we developed a kernel matrix regression algorithm to predict the commonalities of drugs and therapeutic targets among diseases. Our comprehensive prediction strategy indicated many new associations among phenotypically diverse diseases. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DOI： 10.1093/bioinformatics/btaa439

Web of Science

Scopus

PubMed

Other Link： https://dblp.uni-trier.de/db/journals/bioinformatics/bioinformatics36.html#IidaIY20

Language：English   Publishing type：Research paper (scientific journal)  

BACKGROUND: Predicting of chemical compounds is one of the fundamental tasks in bioinformatics and chemoinformatics, because it contributes to various applications in metabolic engineering and drug discovery. The recent rapid growth of the amount of available data has enabled applications of computational approaches such as statistical modeling and machine learning method. Both a set of chemical interactions and chemical compound structures are represented as graphs, and various graph-based approaches including graph convolutional neural networks have been successfully applied to chemical network prediction. However, there was no efficient method that can consider the two different types of graphs in an end-to-end manner. RESULTS: We give a new formulation of the chemical network prediction problem as a link prediction problem in a graph of graphs (GoG) which can represent the hierarchical structure consisting of compound graphs and an inter-compound graph. We propose a new graph convolutional neural network architecture called dual graph convolutional network that learns compound representations from both the compound graphs and the inter-compound network in an end-to-end manner. CONCLUSIONS: Experiments using four chemical networks with different sparsity levels and degree distributions shows that our dual graph convolution approach achieves high prediction performance in relatively dense networks, while the performance becomes inferior on extremely-sparse networks.

DOI： 10.1186/s12859-020-3378-0

Web of Science

Scopus

PubMed

Other Link： https://dblp.uni-trier.de/db/journals/bmcbi/bmcbi21S.html#HaradaATBTYK20

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Wiley  

Glycans play important roles in cell communication, protein interaction, and immunity, and structural changes in glycans are associated with the regulation of a range of biological pathways involved in disease. However, our understanding of the detailed relationships between specific diseases and glycans is very limited. In this study, we proposed an omics-based method to investigate the correlations between glycans and a wide range of human diseases. We analyzed the gene expression patterns of glycogenes (glycosyltransferases and glycosidases) for 79 different diseases. A biological pathway-based glycogene signature was constructed to identify the alteration in glycan biosynthesis and the associated glycan structures for each disease state. The degradation of N-glycan and keratan sulfate, for example, may promote the growth or metastasis of multiple types of cancer, including endometrial, gastric, and nasopharyngeal. Our results also revealed that commonalities between diseases can be interpreted using glycogene expression patterns, as well as the associated glycan structure patterns at the level of the affected pathway. The proposed method is expected to be useful for understanding the relationships between glycans, glycogenes, and disease and identifying disease-specific glycan biomarkers.

DOI： 10.1002/minf.201900112

Web of Science

Scopus

PubMed

Other Link： https://onlinelibrary.wiley.com/doi/full-xml/10.1002/minf.201900112

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Wiley  

Food proteins work not only as nutrients but also modulators for the physiological functions of the human body. The physiological functions of food proteins are basically regulated by peptides encrypted in food protein sequences (food peptides). In this study, we propose a novel deep learning-based method to predict the health effects of food peptides and elucidate the mode-of-action. In the algorithm, we estimate potential target proteins of food peptides using a multi-task graph convolutional neural network, and predict its health effects using information about therapeutic targets for diseases. We constructed predictive models based on 21,103 peptide-protein interactions involving 10,950 peptides and 2,533 proteins, and applied the models to food peptides (e. g., lactotripeptide, isoleucyltyrosine and sardine peptide) defined in food for specified health use. The models suggested potential effects such as blood-pressure lowering effects, blood glucose level lowering effects, and anti-cancer effects for several food peptides. The interactions of food peptides with target proteins were confirmed by docking simulations.

DOI： 10.1002/minf.201900134

Web of Science

Scopus

PubMed

Other Link： https://onlinelibrary.wiley.com/doi/full-xml/10.1002/minf.201900134

Language：English   Publishing type：Research paper (scientific journal)   Publisher：The Japanese Society of Toxicology  

<p><i>In silico</i> models for predicting chemical-induced side effects have become increasingly important for the development of pharmaceuticals and functional food products. However, existing predictive models have difficulty in estimating the mechanisms of side effects in terms of molecular targets or they do not cover the wide range of pharmacological targets. In the present study, we constructed novel <i>in silico</i> models to predict chemical-induced side effects and estimate the underlying mechanisms with high general versatility by integrating the comprehensive prediction of potential chemical-protein interactions (CPIs) with machine learning. First, the potential CPIs were comprehensively estimated by chemometrics based on the known CPI data (1,179,848 interactions involving 3,905 proteins and 824,143 chemicals). Second, the predictive models for 61 side effects in the cardiovascular system (CVS), gastrointestinal system (GIS), and central nervous system (CNS) were constructed by sparsity-induced classifiers based on the known and potential CPI data. The cross validation experiments showed that the proposed CPI-based models had a higher or comparable performance than the traditional chemical structure-based models. Moreover, our enrichment analysis indicated that the highly weighted proteins derived from predictive models could be involved in the corresponding functions of the side effects. For example, in CVS, the carcinogenesis-related pathways (e.g., prostate cancer, PI3K-Akt signal pathway), which were recently reported to be involved in cardiovascular side effects, were enriched. Therefore, our predictive models are biologically valid and would be useful for predicting side effects and novel potential underlying mechanisms of chemical-induced side effects.</p>

DOI： 10.2131/jts.45.137

Web of Science

Scopus

PubMed

CiNii Research

Publishing type：Research paper (scientific journal)  

DOI： 10.1007/s41019-020-00120-6

Scopus

Web of Science

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Oxford University Press (OUP)  

<title>Abstract</title>
<sec>
<title>Motivation</title>
Genome-wide identification of the transcriptomic responses of human cell lines to drug treatments is a challenging issue in medical and pharmaceutical research. However, drug-induced gene expression profiles are largely unknown and unobserved for all combinations of drugs and human cell lines, which is a serious obstacle in practical applications.


</sec>
<sec>
<title>Results</title>
Here, we developed a novel computational method to predict unknown parts of drug-induced gene expression profiles for various human cell lines and predict new drug therapeutic indications for a wide range of diseases. We proposed a tensor-train weighted optimization (TT-WOPT) algorithm to predict the potential values for unknown parts in tensor-structured gene expression data. Our results revealed that the proposed TT-WOPT algorithm can accurately reconstruct drug-induced gene expression data for a range of human cell lines in the Library of Integrated Network-based Cellular Signatures. The results also revealed that in comparison with the use of original gene expression profiles, the use of imputed gene expression profiles improved the accuracy of drug repositioning. We also performed a comprehensive prediction of drug indications for diseases with gene expression profiles, which suggested many potential drug indications that were not predicted by previous approaches.


</sec>
<sec>
<title>Supplementary information</title>
Supplementary data are available at Bioinformatics online.


</sec>

DOI： 10.1093/bioinformatics/btz313

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

BACKGROUND: Characterization of drug-protein interaction networks with biological features has recently become challenging in recent pharmaceutical science toward a better understanding of polypharmacology. RESULTS: We present a novel method for systematic analyses of the underlying features characteristic of drug-protein interaction networks, which we call "drug-protein interaction signatures" from the integration of large-scale heterogeneous data of drugs and proteins. We develop a new efficient algorithm for extracting informative drug-protein interaction signatures from the integration of large-scale heterogeneous data of drugs and proteins, which is made possible by space-efficient representations for fingerprints of drug-protein pairs and sparsity-induced classifiers. CONCLUSIONS: Our method infers a set of drug-protein interaction signatures consisting of the associations between drug chemical substructures, adverse drug reactions, protein domains, biological pathways, and pathway modules. We argue the these signatures are biologically meaningful and useful for predicting unknown drug-protein interactions and are expected to contribute to rational drug design.

DOI： 10.1186/s12918-019-0691-1

Web of Science

Scopus

PubMed

Other Link： https://dblp.uni-trier.de/db/journals/bmcsb/bmcsb13S.html#TabeiKSY19

Language：English   Publishing type：Research paper (scientific journal)  

BACKGROUND: OCaml is a functional programming language with strong static types, Hindley-Milner type inference and garbage collection. In this article, we share our experience in prototyping chemoinformatics and structural bioinformatics software in OCaml. RESULTS: First, we introduce the language, list entry points for chemoinformaticians who would be interested in OCaml and give code examples. Then, we list some scientific open source software written in OCaml. We also present recent open source libraries useful in chemoinformatics. The parallelization of OCaml programs and their performance is also shown. Finally, tools and methods useful when prototyping scientific software in OCaml are given. CONCLUSIONS: In our experience, OCaml is a programming language of choice for method development in chemoinformatics and structural bioinformatics.

DOI： 10.1186/s13321-019-0332-0

Web of Science

Scopus

PubMed

Other Link： https://dblp.uni-trier.de/db/journals/jcheminf/jcheminf11.html#BerengerZY19

Language：English   Publishing type：Research paper (scientific journal)  

© 2018 Elsevier B.V. Background and objectives: Meta-iodobenzylguanidine (MIBG) myocardial scintigraphy is an effective tool for distinguishing Parkinson&#039;s disease (PD) from other diseases accompanied by parkinsonism. Unlike other Parkinsonian diseases, in PD, MIBG accumulation in the heart tends to decrease. However, previous studies have reported that a decrease in MIBG accumulation also occurs in progressive supranuclear palsy (PSP). Thus, we analyzed the relationship between the degree of MIBG accumulation decrease, clinical symptoms, and brainstem atrophy in PSP. Methods: We retrospectively collected data from patients who underwent MIBG myocardial scintigraphy and compared MIBG indices (heart to mediastinum [H/M] ratio, washout rate) between subjects with PSP and other diseases including PD. In addition, we evaluated the relationship between clinical characteristics, MIBG accumulation, and brainstem atrophy in patients with PSP. Results: Patients with PSP had a significantly lower early H/M ratio compared with multiple system atrophy with predominant parkinsonism (MSA-P) patients, and a control group. In PSP patients there was a correlation between the decrease in delay H/M ratio, atrophy of the pons, and clinical severity as evaluated by Hoehn and Yahr score. Conclusion: Unlike in PD, PSP patients exhibited a mild decrease in MIBG accumulation in MIBG myocardial scintigraphy, which may be related to brainstem atrophy.

DOI： 10.1016/j.jns.2018.10.019

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

In Quantitative Structure-Activity Relationship (QSAR) modeling, one must come up with an activity model but also with an applicability domain for that model. Some existing methods to create an applicability domain are complex, hard to implement, and/or difficult to interpret. Also, they often require the user to select a threshold value, or they embed an empirical constant. In this work, we propose a trivial to interpret and fully automatic Distance-Based Boolean Applicability Domain (DBBAD) algorithm for category QSAR. In retrospective experiments on High Throughput Screening data sets, this applicability domain improves the classification performance and early retrieval of support vector machine and random forest based classifiers, while improving the scaffold diversity among top-ranked active molecules.

DOI： 10.1021/acs.jcim.8b00499

Web of Science

Scopus

PubMed

Other Link： https://dblp.uni-trier.de/db/journals/jcisd/jcisd59.html#BerengerY19

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/ICDM.2019.00166

Scopus

Other Link： https://dblp.uni-trier.de/db/conf/icdm/icdm2019.html#TabeiYP19

Language：English   Publishing type：Part of collection (book)   Publisher：Springer New York  

© Springer Science+Business Media, LLC, part of Springer Nature 2019. Identification of the modes of action of bioactive compounds is an important issue in chemical systems biology. In this chapter we review a recently developed data-driven approach using large-scale chemically induced transcriptome data acquired from the Library of Integrated Network-based Cellular Signatures to elucidate the modes of action of bioactive compounds. First, we present a method for pathway enrichment analyses of regulated genes to reveal biological pathways activated by compounds. Next, we present a method using the pre-knowledge on chemical–protein interactome for predicting potential target proteins, including primary targets and off-targets, with transcriptional similarity. Finally, we present a method based on the target proteins for predicting new therapeutic indications for a variety of diseases. These approaches are expected to be useful for mode-of-action analysis, drug discovery, and drug repositioning.

DOI： 10.1007/978-1-4939-8891-4_11

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：American Chemical Society (ACS)  

© 2018 American Chemical Society. Developing drugs with anticancer activity and low toxic side-effects at low costs is a challenging issue for cancer chemotherapy. In this work, we propose to use molecular pathways as the therapeutic targets and develop a novel computational approach for drug repositioning for cancer treatment. We analyzed chemically induced gene expression data of 1112 drugs on 66 human cell lines and searched for drugs that inactivate pathways involved in the growth of cancer cells (cell cycle) and activate pathways that contribute to the death of cancer cells (e.g., apoptosis and p53 signaling). Finally, we performed a large-scale prediction of potential anticancer effects for all the drugs and experimentally validated the prediction results via three in vitro cellular assays that evaluate cell viability, cytotoxicity, and apoptosis induction. Using this strategy, we successfully identified several potential anticancer drugs. The proposed pathway-based method has great potential to improve drug repositioning research for cancer treatment.

DOI： 10.1021/acs.jmedchem.8b01044

Web of Science

Scopus

PubMed

© 2018, ASEAN Neurological Association. All rights reserved. Objective: Cervical dystonia (CD) is a clinically under-recognized symptom occurring at the later-to end-stages of Parkinson’s disease (PD). The frequency of CD and its influence on prognosis have not been well studied. Here, we conducted an in-depth examination of CD incidence and impact on disease progression in later-stage PD. Methods: We retrospectively reviewed the clinical features of 22 deceased patients with sporadic PD treated at a hospital in Japan from 1983 to 2008. Results: The most common cause of death in PD was pneumonia. CD, in particular retrocollis, was frequent in the later stages of the disease in elderly patients (9/22, 40.9%). Pneumonia incidence increased sharply in the later period with CD. There was a positive trend between CD duration and duration of pergolide use. Conclusion: Analysis revealed that CD increases markedly in late-to end-stage PD, which may be associated with aspiration pneumonia due to dysphagia. Pathological mechanisms underlying CD might be influenced by treatments including dopamine agonists. Prevention of CD may increase quality of life and prolong survival of PD patients.

Scopus

Web of Science

Web of Science

Language：English   Publishing type：Research paper (scientific journal)   Publisher：NATURE PUBLISHING GROUP  

Natural medicines (i.e., herbal medicines, traditional formulas) are useful for treatment of multifactorial and chronic diseases. Here, we present KampoDB (http://wakanmoview.inm.u-toyama.ac.jp/kampo/), a novel platform for the analysis of natural medicines, which provides various useful scientific resources on Japanese traditional formulas Kampo medicines, constituent herbal drugs, constituent compounds, and target proteins of these constituent compounds. Potential target proteins of these constituent compounds were predicted by docking simulations and machine learning methods based on large-scale omics data (e.g., genome, proteome, metabolome, interactome). The current version of KampoDB contains 42 Kampo medicines, 54 crude drugs, 1230 constituent compounds, 460 known target proteins, and 1369 potential target proteins, and has functional annotations for biological pathways and molecular functions. KampoDB is useful for mode-of-action analysis of natural medicines and prediction of new indications for a wide range of diseases.

DOI： 10.1038/s41598-018-29516-1

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Nature Publishing Group  

Genome-wide identification of all target proteins of drug candidate compounds is a challenging issue in drug discovery. Moreover, emerging phenotypic effects, including therapeutic and adverse effects, are heavily dependent on the inhibition or activation of target proteins. Here we propose a novel computational method for predicting inhibitory and activatory targets of drug candidate compounds. Specifically, we integrated chemically-induced and genetically-perturbed gene expression profiles in human cell lines, which avoided dependence on chemical structures of compounds or proteins. Predictive models for individual target proteins were simultaneously constructed by the joint learning algorithm based on transcriptomic changes in global patterns of gene expression profiles following chemical treatments, and following knock-down and over-expression of proteins. This method discriminates between inhibitory and activatory targets and enables accurate identification of therapeutic effects. Herein, we comprehensively predicted drug-target-disease association networks for 1,124 drugs, 829 target proteins, and 365 human diseases, and validated some of these predictions in vitro. The proposed method is expected to facilitate identification of new drug indications and potential adverse effects.

DOI： 10.1038/s41598-017-18315-9

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

© 2018, Springer Science+Business Media, LLC, part of Springer Nature. Identification of drug–target interactions is a crucial process in drug discovery. In this chapter, we present protocols for recent advancements in machine learning methods for predicting drug–target interactions from heterogeneous biological data in a chemogenomic framework, in which prediction is based on the chemical structure data of drug candidate compounds and translated genomic sequence data of target candidate proteins. Most existing methods are based on either linear modeling or kernel modeling. To illustrate linear modeling, we introduce sparsity-induced binary classifiers and sparse canonical correlation analysis. To illustrate kernel modeling, we introduce pairwise kernel-based support vector machines and kernel-based distance learning. Workflows for using these techniques are presented. We also discuss the characteristics of each method and suggest some directions for future research.

DOI： 10.1007/978-1-4939-8639-2_12

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

Most drugs produce their phenotypic effects by interacting with target proteins, and understanding the molecular features that underpin drug-target interactions is crucial when designing a novel drug. In this chapter, we introduce the protocols that have driven recent advances in sparse modeling methods for analyzing drug-target interaction networks within a chemogenomic framework. In this approach, the chemical structures of candidate drug compounds are correlated with the genomic sequences of the candidate target proteins. We demonstrate the use of sparse canonical correspondence analysis and sparsity-induced binary classifiers to extract the underlying molecular features that are most strongly involved in drug-target interactions. We focus on drug chemical substructures and protein domains. Workflows for applying these methods are presented, and an application is described in detail. We consider the characteristics of each method and suggest possible directions for future research.

DOI： 10.1007/978-1-4939-8561-6_13

Web of Science

Scopus

PubMed

Publishing type：Research paper (scientific journal)  

Other Link： https://dblp.uni-trier.de/db/journals/corr/corr1802.html#abs-1802-06382

Web of Science

Language：English   Publisher：CELL PRESS  

DOI： 10.1016/j.bpj.2016.11.1584

Web of Science

Language：English   Publishing type：Research paper (scientific journal)   Publisher：NATURE PUBLISHING GROUP  

The identification of the modes of action of bioactive compounds is a major challenge in chemical systems biology of diseases. Genome-wide expression profiling of transcriptional responses to compound treatment for human cell lines is a promising unbiased approach for the mode-of-action analysis. Here we developed a novel approach to elucidate the modes of action of bioactive compounds in a cell-specific manner using large-scale chemically-induced transcriptome data acquired from the Library of Integrated Network-based Cellular Signatures (LINCS), and analyzed 16,268 compounds and 68 human cell lines. First, we performed pathway enrichment analyses of regulated genes to reveal active pathways among 163 biological pathways. Next, we explored potential target proteins (including primary targets and off-targets) with cell-specific transcriptional similarity using chemical-protein interactome. Finally, we predicted new therapeutic indications for 461 diseases based on the target proteins. We showed the usefulness of the proposed approach in terms of prediction coverage, interpretation, and large-scale applicability, and validated the new prediction results experimentally by an in vitro cellular assay. The approach has a high potential for advancing drug discovery and repositioning.

DOI： 10.1038/srep40164

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：WILEY-BLACKWELL  

G Protein-Coupled Receptors (GPCRs) are important pharmaceutical targets. More than 30% of currently marketed pharmaceutical medicines target GPCRs. Numerous studies have reported that GPCRs function not only as monomers but also as homo- or hetero-dimers or higher-order molecular complexes. Many GPCRs exert a wide variety of molecular functions by forming specific combinations of GPCR subtypes. In addition, some GPCRs are reportedly associated with diseases. GPCR oligomerization is now recognized as an important event in various biological phenomena, and many researchers are investigating this subject. We have developed a support vector machine (SVM)-based method to predict interacting pairs for GPCR oligomerization, by integrating the structure and sequence information of GPCRs. The performance of our method was evaluated by the Receiver Operating Characteristic (ROC) curve. The corresponding area under the curve was 0.938. As far as we know, this is the only prediction method for interacting pairs among GPCRs. Our method could accelerate the analyses of these interactions, and contribute to the elucidation of the global structures of the GPCR networks in membranes. Proteins 2016; 84:1224-1233. (c) 2016 Wiley Periodicals, Inc.

DOI： 10.1002/prot.25071

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: Metabolic pathways are an important class of molecular networks consisting of compounds, enzymes and their interactions. The understanding of global metabolic pathways is extremely important for various applications in ecology and pharmacology. However, large parts of metabolic pathways remain unknown, and most organism-specific pathways contain many missing enzymes. Results: In this study we propose a novel method to predict the enzyme orthologs that catalyze the putative reactions to facilitate the de novo reconstruction of metabolic pathways from metabolome-scale compound sets. The algorithm detects the chemical transformation patterns of substrate-product pairs using chemical graph alignments, and constructs a set of enzyme-specific classifiers to simultaneously predict all the enzyme orthologs that could catalyze the putative reactions of the substrate-product pairs in the joint learning framework. The originality of the method lies in its ability to make predictions for thousands of enzyme orthologs simultaneously, as well as its extraction of enzyme-specific chemical transformation patterns of substrate-product pairs. We demonstrate the usefulness of the proposed method by applying it to some ten thousands of metabolic compounds, and analyze the extracted chemical transformation patterns that provide insights into the characteristics and specificities of enzymes. The proposed method will open the door to both primary (central) and secondary metabolism in genomics research, increasing research productivity to tackle a wide variety of environmental and public health matters.

DOI： 10.1093/bioinformatics/btw260

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computing Machinery  

With massive high-dimensional data now commonplace in research and industry, there is a strong and growing demand for more scalable computational techniques for data analysis and knowledge discovery. Key to turning these data into knowledge is the ability to learn statistical models with high interpretability. Current methods for learning statistical models either produce models that are not interpretable or have prohibitive computational costs when applied to massive data. In this paper we address this need by presenting a scalable algorithm for partial least squares regression (PLS), which we call compression-based PLS (cPLS), to learn predictive linear models with a high interpretability from massive high-dimensional data. We propose a novel grammar-compressed representation of data matrices that supports fast row and column access while the data matrix is in a compressed form. The original data matrix is grammarcompressed and then the linear model in PLS is learned on the compressed data matrix, which results in a significant reduction in working space, greatly improving scalability. We experimentally test cPLS on its ability to learn linear models for classification, regression and feature extraction with various massive high-dimensional data, and show that cPLS performs superiorly in terms of prediction accuracy, computational effciency, and interpretability.

DOI： 10.1145/2939672.2939864

Web of Science

Scopus

Language：English   Publishing type：Research paper (scientific journal)   Publisher：BIOMED CENTRAL LTD  

Background: Phenotype-based high-throughput screening is a useful technique for identifying drug candidate compounds that have a desired phenotype. However, the molecular mechanisms of the hit compounds remain unknown, and substantial effort is required to identify the target proteins associated with the phenotype.
Methods: In this study, we propose a new method to predict target proteins of drug candidate compounds based on drug-induced gene expression data in Connectivity Map and a machine learning classification technique, which we call the "transcriptomic approach."
Results: Unlike existing methods such as the chemogenomic approach, the transcriptomic approach enabled the prediction of target proteins without dependence on prior knowledge of compound chemical structures. The prediction accuracy of the chemogenomic approach was highly depended on compounds structure similarities in data sets. In contrast, the prediction accuracy of the transcriptomic approach was maintained at a sufficient level, even for benchmark data consisting of structurally diverse compounds.
Conclusions: The transcriptomic approach reported here is expected to be a useful tool for structure-independent prediction of target proteins for drug candidate compounds.

DOI： 10.1186/s12920-015-0158-1

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：AMER CHEMICAL SOC  

The identification of beneficial drug combinations is a challenging issue in pharmaceutical and clinical research toward combinatorial drug therapy. In the present study, we developed a novel computational method for large-scale prediction of beneficial drug combinations using drug efficacy and target profiles. We designed an informative descriptor for each drug drug pair based on multiple drug profiles representing drug-targeted proteins and Anatomical Therapeutic Chemical Classification System codes. Then, we constructed a predictive model by learning a sparsity-induced classifier based on known drug combinations from the Orange Book and KEGG DRUG databases. Our results show that the proposed method outperforms the previous methods in terms of the accuracy of high-confidence predictions, and the extracted features are biologically meaningful. Finally, we performed a comprehensive prediction of novel drug combinations for 2,639 approved drugs, which predicted 142,988 new potentially beneficial drug drug pairs. We showed several examples of successfully predicted drug combinations for a variety of diseases.

DOI： 10.1021/acs.jcim.5b00444

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：AMER CHEMICAL SOC  

Graph data are becoming increasingly common in machine learning and data mining, and its application field pervades to bioinformatics and cheminformatics. Accordingly, as a method to extract patterns from graph data, graph mining recently has been studied and developed rapidly. Since the number of patterns in graph data is huge, a central issue is how to efficiently collect informative patterns suitable for subsequent tasks such as classification or regression. In this paper, we consider mining discriminative subgraphs from graph data with multiple labels. The resulting task has important applications in cheminformatics, such as finding common functional groups that trigger multiple drug side effects, or identifying ligand functional groups that hit multiple targets. In computational experiments, we first verify the effectiveness of the proposed approach in synthetic data, then we apply it to drug adverse effect prediction problem. In the latter dataset, we compared the proposed method with L1-norm logistic regression in combination with the PubChem/Open Babel fingerprint, in that the proposed method showed superior performance with a much smaller number of subgraph patterns. Software is available from https://github.com/axot/GLP.

DOI： 10.1021/acs.jcim.5b00376

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：AMER CHEMICAL SOC  

Drug repositioning, or the identification of new indications for known drugs, is a useful strategy for drug discovery. In this study, we developed novel computational methods to predict potential drug targets and new drug indications for systematic drug repositioning using large-scale chemical-protein interactome data. We explored the target space of drugs (including primary targets and off-targets) based on chemical structure similarity and phenotypic effect similarity by making optimal use of millions of compound-protein interactions. On the basis of the target profiles of drugs, we constructed statistical models to predict new drug indications for a wide range of diseases with various molecular features. The proposed method outperformed previous methods in terms of interpretability, applicability, and accuracy. Finally, we conducted a comprehensive prediction of the drug-target-disease association network for 8270 drugs and 1401 diseases and showed biologically meaningful examples of newly predicted drug targets and drug indications. The predictive model is useful to understand the mechanisms of the predicted drug indications.

DOI： 10.1021/acs.jcim.5b00330

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: Recent advances in mass spectrometry and related metabolomics technologies have enabled the rapid and comprehensive analysis of numerous metabolites. However, biosynthetic and biodegradation pathways are only known for a small portion of metabolites, with most metabolic pathways remaining uncharacterized.
Results: In this study, we developed a novel method for supervised de novo metabolic pathway reconstruction with an improved graph alignment-based approach in the reaction-filling framework. We proposed a novel chemical graph alignment algorithm, which we called PACHA (Pairwise Chemical Aligner), to detect the regioisomer-sensitive connectivities between the aligned substructures of two compounds. Unlike other existing graph alignment methods, PACHA can efficiently detect only one common subgraph between two compounds. Our results show that the proposed method outperforms previous descriptor-based methods or existing graph alignment-based methods in the enzymatic reaction-likeness prediction for isomer-enriched reactions. It is also useful for reaction annotation that assigns potential reaction characteristics such as EC (Enzyme Commission) numbers and PIERO (Enzymatic Reaction Ontology for Partial Information) terms to substrate-product pairs. Finally, we conducted a comprehensive enzymatic reaction-likeness prediction for all possible uncharacterized compound pairs, suggesting potential metabolic pathways for newly predicted substrate-product pairs.

DOI： 10.1093/bioinformatics/btv224

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：AMER CHEMICAL SOC  

Drug repositioning, or the appslication of known drugs to new indications, is a challenging issue in pharmaceutical science. In this study, we developed a new computational method to predict unknown drug indications for systematic drug repositioning in a framework of supervised network inference. We defined a descriptor for each drug-disease pair based on the phenotypic features of drugs (e.g., medicinal effects and side effects) and various molecular features of diseases (e.g., disease-causing genes, diagnostic markers, disease-related pathways, and environmental factors) and constructed a statistical model to predict new drug-disease associations for a wide range of diseases in the International Classification of Diseases. Our results show that the proposed method outperforms previous methods in terms of accuracy and applicability, and its performance does not depend on drug chemical structure similarity. Finally, we performed a comprehensive prediction of a drug-disease association network consisting of 2349 drugs and 858 diseases and described biologically meaningful examples of newly predicted drug indications for several types of cancers and nonhereditary diseases.

DOI： 10.1021/ci500670q

Web of Science

Scopus

PubMed

J-GLOBAL

Web of Science

Language：English   Publishing type：Research paper (scientific journal)   Publisher：WILEY-V C H VERLAG GMBH  

The identification of drug-target interactions, or interactions between drug candidate compounds and target candidate proteins, is a crucial process in genomic drug discovery. In silico chemogenomic methods are recently recognized as a promising approach for genome-wide scale prediction of drug-target interactions, but the prediction performance depends heavily on the descriptors and similarity measures of drugs and proteins. In this paper, we investigated the performance of various descriptors and similarity measures of drugs and proteins for the drug-target interaction prediction using a chemogenomic approach. We compared the prediction accuracy of 18 chemical descriptors of drugs (e.g., ECFP, FCFP, E-state, CDK, Klekota-Roth, MACCS, PubChem, Dragon, KCF-S, and graph kernels) and 4 descriptors of proteins (e.g., amino acid composition, domain profile, local sequence similarity, and string kernel) on about one hundred thousand drug-target interactions. We examined the combinatorial effects of drug descriptors and protein descriptors using the same benchmark data under several experimental conditions. Large-scale experiments showed that our proposed KCF-S descriptor worked the best in terms of prediction accuracy. The comparative results are expected to be useful for selecting chemical descriptors in various pharmaceutical applications.

DOI： 10.1002/minf.201400066

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

DINIES (drug-target interaction network inference engine based on supervised analysis) is a web server for predicting unknown drug-target interaction networks from various types of biological data (e.g. chemical structures, drug side effects, amino acid sequences and protein domains) in the framework of supervised network inference. The originality of DINIES lies in prediction with state-of-the-art machine learning methods, in the integration of heterogeneous biological data and in compatibility with the KEGG database. The DINIES server accepts any 'profiles' or precalculated similarity matrices (or 'kernels') of drugs and target proteins in tab-delimited file format. When a training data set is submitted to learn a predictive model, users can select either known interaction information in the KEGG DRUG database or their own interaction data. The user can also select an algorithm for supervised network inference, select various parameters in the method and specify weights for heterogeneous data integration. The server can provide integrative analyses with useful components in KEGG, such as biological pathways, functional hierarchy and human diseases.

DOI： 10.1093/nar/gku337

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: Metabolic pathway analysis is crucial not only in metabolic engineering but also in rational drug design. However, the biosynthetic/ biodegradation pathways are known only for a small portion of metabolites, and a vast amount of pathways remain uncharacterized. Therefore, an important challenge in metabolomics is the de novo reconstruction of potential reaction networks on a metabolome-scale.
Results: In this article, we develop a novel method to predict the multistep reaction sequences for de novo reconstruction of metabolic pathways in the reaction-filling framework. We propose a supervised approach to learn what we refer to as 'multistep reaction sequence likeness', i.e. whether a compound-compound pair is possibly converted to each other by a sequence of enzymatic reactions. In the algorithm, we propose a recursive procedure of using step-specific classifiers to predict the intermediate compounds in the multistep reaction sequences, based on chemical substructure fingerprints/ descriptors of compounds. We further demonstrate the usefulness of our proposed method on the prediction of enzymatic reaction networks from a metabolome-scale compound set and discuss characteristic features of the extracted chemical substructure transformation patterns in multistep reaction sequences. Our comprehensively predicted reaction networks help to fill the metabolic gap and to infer new reaction sequences in metabolic pathways.

DOI： 10.1093/bioinformatics/btu265

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publisher：The Biophysical Society of Japan General Incorporated Association  

DOI： 10.2142/biophys.54.S239_6

Language：English   Publishing type：Research paper (scientific journal)   Publisher：BIOMED CENTRAL LTD  

Background: Most phenotypic effects of drugs are involved in the interactions between drugs and their target proteins, however, our knowledge about the molecular mechanism of the drug-target interactions is very limited. One of challenging issues in recent pharmaceutical science is to identify the underlying molecular features which govern drug-target interactions.
Results: In this paper, we make a systematic analysis of the correlation between drug side effects and protein domains, which we call "pharmacogenomic features," based on the drug-target interaction network. We detect drug side effects and protein domains that appear jointly in known drug-target interactions, which is made possible by using classifiers with sparse models. It is shown that the inferred pharmacogenomic features can be used for predicting potential drug-target interactions. We also discuss advantages and limitations of the pharmacogenomic features, compared with the chemogenomic features that are the associations between drug chemical substructures and protein domains.
Conclusion: The inferred side effect-domain association network is expected to be useful for estimating common drug side effects for different protein families and characteristic drug side effects for specific protein domains.

DOI： 10.1186/1752-0509-7-S6-S18

Web of Science

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：BIOMED CENTRAL LTD  

Background: In order to develop hypothesis on unknown metabolic pathways, biochemists frequently rely on literature that uses a free-text format to describe functional groups or substructures. In computational chemistry or cheminformatics, molecules are typically represented by chemical descriptors, i.e., vectors that summarize information on its various properties. However, it is difficult to interpret these chemical descriptors since they are not directly linked to the terminology of functional groups or substructures that the biochemists use.
Methods: In this study, we used KEGG Chemical Function (KCF) format to computationally describe biochemical substructures in seven attributes that resemble biochemists' way of dealing with substructures.
Results: We established KCF-S (KCF-and-Substructures) format as an additional structural information of KCF. Applying KCF-S revealed the specific appearance of substructures from various datasets of molecules that describes the characteristics of the respective datasets. Structure-based clustering of molecules using KCF-S resulted the clusters in which molecular weights and structures were less diverse than those obtained by conventional chemical fingerprints. We further applied KCF-S to find the pairs of molecules that are possibly converted to each other in enzymatic reactions, and KCF-S clearly improved predictive performance than that presented previously.
Conclusions: KCF-S defines biochemical substructures with keeping interpretability, suggesting the potential to apply more studies on chemical bioinformatics. KCF and KCF-S can be automatically converted from Molfile format, enabling to deal with molecules from any data sources.

DOI： 10.1186/1752-0509-7-S6-S2

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：BioMed Central Ltd.  

The identification of compound-protein interactions plays key roles in the drug development toward discovery of new drug leads and new therapeutic protein targets. There is therefore a strong incentive to develop new efficient methods for predicting compound-protein interactions on a genome-wide scale. In this paper we develop a novel chemogenomic method to make a scalable prediction of compound-protein interactions from heterogeneous biological data using minwise hashing. The proposed method mainly consists of two steps: 1) construction of new compact fingerprints for compound-protein pairs by an improved minwise hashing algorithm, and 2) application of a sparsity-induced classifier to the compact fingerprints. We test the proposed method on its ability to make a large-scale prediction of compound-protein interactions from compound substructure fingerprints and protein domain fingerprints, and show superior performance of the proposed method compared with the previous chemogenomic methods in terms of prediction accuracy, computational efficiency, and interpretability of the predictive model. All the previously developed methods are not computationally feasible for the full dataset consisting of about 200 millions of compound-protein pairs. The proposed method is expected to be useful for virtual screening of a huge number of compounds against many protein targets.

DOI： 10.1186/1752-0509-7-S6-S3

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：WILEY-V C H VERLAG GMBH  

Drug effects are mainly caused by the interactions between drug molecules and target proteins including primary targets and off-targets. Understanding of the molecular mechanisms behind overall drugtarget interactions is crucial in the drug design process. In this paper we review recently developed methods to infer chemogenomic features (the underlying associations between drug chemical substructures and protein domains) which are strongly involved in drug-target interaction networks. We show the usefulness of the methods to detect ligand chemical fragments specific for each protein domain and ligand core substructures important for a wide range of protein families. We also discuss how to use the chemogenomic features for predicting unknown drug-target interactions on a large scale.

DOI： 10.1002/minf.201300079

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computing Machinery  

Analyzing functional interactions between small compounds and proteins is indispensable in genomic drug discovery. Since rich information on various compound-protein interactions is available in recent molecular databases, strong demands for making best use of such databases require to invent powerful methods to help us find new functional compoundprotein pairs on a large scale. We present the succinct interval-splitting tree algorithm (SITA) that efficiently performs similarity search in databases for compound-protein pairs with respect to both binary fingerprints and real-valued properties. SITA achieves both time and space efficiency by developing the data structure called interval-splitting trees, which enables to efficiently prune the useless portions of search space, and by incorporating the ideas behind wavelet tree, a succinct data structure to compactly represent trees. We experimentally test SITA on the ability to retrieve similar compound-protein pairs/substrate-product pairs for a query from large databases with over 200 million compoundprotein pairs/substrate-product pairs and show that SITA performs better than other possible approaches.

DOI： 10.1145/2487575.2487637

Scopus

Other Link： http://dblp.uni-trier.de/db/conf/kdd/kdd2013.html#conf/kdd/TabeiKKY13

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: The metabolic pathway is an important biochemical reaction network involving enzymatic reactions among chemical compounds. However, it is assumed that a large number of metabolic pathways remain unknown, and many reactions are still missing even in known pathways. Therefore, the most important challenge in metabolomics is the automated de novo reconstruction of metabolic pathways, which includes the elucidation of previously unknown reactions to bridge the metabolic gaps.
Results: In this article, we develop a novel method to reconstruct metabolic pathways from a large compound set in the reaction-filling framework. We define feature vectors representing the chemical transformation patterns of compound-compound pairs in enzymatic reactions using chemical fingerprints. We apply a sparsity-induced classifier to learn what we refer to as 'enzymatic-reaction likeness', i.e. whether compound pairs are possibly converted to each other by enzymatic reactions. The originality of our method lies in the search for potential reactions among many compounds at a time, in the extraction of reaction-related chemical transformation patterns and in the large-scale applicability owing to the computational efficiency. In the results, we demonstrate the usefulness of our proposed method on the de novo reconstruction of 134 metabolic pathways in Kyoto Encyclopedia of Genes and Genomes (KEGG). Our comprehensively predicted reaction networks of 15 698 compounds enable us to suggest many potential pathways and to increase research productivity in metabolomics.

DOI： 10.1093/bioinformatics/btt244

Web of Science

Scopus

PubMed

J-GLOBAL

Language：Japanese   Publisher：一般社団法人電子情報通信学会  

近年の新薬開発の行き詰まりを打開する方法として、既存薬の作用を徹底的に調べあげ新たに薬効を見つけ出し、本来それが開発された疾患とは別の疾患に対する治療薬として再開発する創薬研究が注目を浴びている。本研究では、薬物に関するケミカルなデータと疾患に関するフェノタイプのデータから潜在的な薬物と疾患の関係を網羅的に予測する機械学習の手法を開発した。教師付き学習のアルゴリズムにスパース統計モデルを導入することで特徴抽出を可能にし、予測された関係に関与している薬物の標的タンパク質と疾患のフェノタイプの組み合わせを同定する点が独自の点である。また抽出された標的タンパク質の生物学的妥当性をPathway Enrichment解析を用いて評価した。本発表ではこれらの結果と、既知のデータから学習して生成したモデルを適用することで得られる新規の薬と疾患の関連解析の結果について紹介する。

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

The identification of orthologous genes in an increasing number of fully sequenced genomes is a challenging issue in recent genome science. Here we present KEGG OC (http://www.genome.jp/tools/oc/), a novel database of ortholog clusters (OCs). The current version of KEGG OC contains 1 176 030 OCs, obtained by clustering 8 357 175 genes in 2112 complete genomes (153 eukaryotes, 1830 bacteria and 129 archaea). The OCs were constructed by applying the quasi-clique-based clustering method to all possible protein coding genes in all complete genomes, based on their amino acid sequence similarities. It is computationally efficient to calculate OCs, which enables to regularly update the contents. KEGG OC has the following two features: (i) It consists of all complete genomes of a wide variety of organisms from three domains of life, and the number of organisms is the largest among the existing databases; and (ii) It is compatible with the KEGG database by sharing the same sets of genes and identifiers, which leads to seamless integration of OCs with useful components in KEGG such as biological pathways, pathway modules, functional hierarchy, diseases and drugs. The KEGG OC resources are accessible via OC Viewer that provides an interactive visualization of OCs at different taxonomic levels.

DOI： 10.1093/nar/gks1239

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)  

The identification of drug-target interactions from heterogeneous biological data is critical in the drug development. In this chapter, we review recently developed in silico chemogenomic approaches to infer unknown drug-target interactions from chemical information of drugs and genomic information of target proteins. We review several kernel-based statistical methods from two different viewpoints: binary classification and dimension reduction. In the results, we demonstrate the usefulness of the methods on the prediction of drug-target interactions from chemical structure data and genomic sequence data. We also discuss the characteristics of each method, and show some perspectives toward future research direction.

DOI： 10.1007/978-1-62703-107-3_9

PubMed

Web of Science

Language：English   Publishing type：Research paper (scientific journal)   Publisher：AMER CHEMICAL SOC  

Drug side-effects, or adverse drug reactions, have become a major public health concern and remain one of the main causes of drug failure and of drug withdrawal once they have reached the market. Therefore, the identification of potential severe side-effects is a challenging issue. In this paper, we develop a new method to predict potential side-effect profiles of drug candidate molecules based on their chemical structures and target protein information on a large scale. We propose several extensions of kernel regression model for multiple responses to deal with heterogeneous data sources. The originality lies in the integration of the chemical space of drug chemical structures and the biological space of drug target proteins in a unified framework. As a result, we demonstrate the usefulness of the proposed method on the simultaneous prediction of 969 side-effects for approved drugs from their chemical substructure and target protein profiles and show that the prediction accuracy consistently improves owing to the proposed regression model and integration of chemical and biological information. We also conduct a comprehensive side-effect prediction for uncharacterized drug molecules stored in DrugBank and confirm interesting predictions using independent information sources. The proposed method is expected to be useful at many stages of the drug development process.

DOI： 10.1021/ci2005548

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: Unexpected drug activities derived from off-targets are usually undesired and harmful; however, they can occasionally be beneficial for different therapeutic indications. There are many uncharacterized drugs whose target proteins (including the primary target and off-targets) remain unknown. The identification of all potential drug targets has become an important issue in drug repositioning to reuse known drugs for new therapeutic indications.
Results: We defined pharmacological similarity for all possible drugs using the US Food and Drug Administration's (FDA's) adverse event reporting system (AERS) and developed a new method to predict unknown drug-target interactions on a large scale from the integration of pharmacological similarity of drugs and genomic sequence similarity of target proteins in the framework of a pharmacogenomic approach. The proposed method was applicable to a large number of drugs and it was useful especially for predicting unknown drug-target interactions that could not be expected from drug chemical structures. We made a comprehensive prediction for potential off-targets of 1874 drugs with known targets and potential target profiles of 2519 drugs without known targets, which suggests many potential drug-target interactions that were not predicted by previous chemogenomic or pharmacogenomic approaches.

DOI： 10.1093/bioinformatics/bts413

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: Drug effects are mainly caused by the interactions between drug molecules and their target proteins including primary targets and off-targets. Identification of the molecular mechanisms behind overall drug-target interactions is crucial in the drug design
Results: We develop a classifier-based approach to identify chemogenomic features (the underlying associations between drug chemical substructures and protein domains) that are involved in drug-target interaction networks. We propose a novel algorithm for extracting informative chemogenomic features by using L-1 regularized classifiers over the tensor product space of possible drug-target pairs. It is shown that the proposed method can extract a very limited number of chemogenomic features without loosing the performance of predicting drug-target interactions and the extracted features are biologically meaningful. The extracted substructure-domain association network enables us to suggest ligand chemical fragments specific for each protein domain and ligand core substructures important for a wide range of protein families.

DOI： 10.1093/bioinformatics/bts412

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: Identifying the emergence and underlying mechanisms of drug side effects is a challenging task in the drug development process. This underscores the importance of system-wide approaches for linking different scales of drug actions; namely drug-protein interactions (molecular scale) and side effects (phenotypic scale) toward side effect prediction for uncharacterized drugs.
Results: We performed a large-scale analysis to extract correlated sets of targeted proteins and side effects, based on the co-occurrence of drugs in protein-binding profiles and side effect profiles, using sparse canonical correlation analysis. The analysis of 658 drugs with the two profiles for 1368 proteins and 1339 side effects led to the extraction of 80 correlated sets. Enrichment analyses using KEGG and Gene Ontology showed that most of the correlated sets were significantly enriched with proteins that are involved in the same biological pathways, even if their molecular functions are different. This allowed for a biologically relevant interpretation regarding the relationship between drug-targeted proteins and side effects. The extracted side effects can be regarded as possible phenotypic outcomes by drugs targeting the proteins that appear in the same correlated set. The proposed method is expected to be useful for predicting potential side effects of new drug candidate compounds based on their protein-binding profiles.

DOI： 10.1093/bioinformatics/bts383

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Gene network inference engine based on supervised analysis (GENIES) is a web server to predict unknown part of gene network from various types of genome-wide data in the framework of supervised network inference. The originality of GENIES lies in the construction of a predictive model using partially known network information and in the integration of heterogeneous data with kernel methods. The GENIES server accepts any 'profiles' of genes or proteins (e.g. gene expression profiles, protein subcellular localization profiles and phylogenetic profiles) or pre-calculated gene-gene similarity matrices (or 'kernels') in the tab-delimited file format. As a training data set to learn a predictive model, the users can choose either known molecular network information in the KEGG PATHWAY database or their own gene network data. The user can also select an algorithm of supervised network inference, choose various parameters in the method, and control the weights of heterogeneous data integration. The server provides the list of newly predicted gene pairs, maps the predicted gene pairs onto the associated pathway diagrams in KEGG PATHWAY and indicates candidate genes for missing enzymes in organism-specific metabolic pathways. GENIES (http://www.genome.jp/tools/genies/) is publicly available as one of the genome analysis tools in GenomeNet.

DOI： 10.1093/nar/gks459

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：HINDAWI LTD  

We consider the problem of network completion, which is to make the minimum amount of modifications to a given network so that the resulting network is most consistent with the observed data. We employ here a certain type of differential equations as gene regulation rules in a genetic network, gene expression time series data as observed data, and deletions and additions of edges as basic modification operations. In addition, we assume that the numbers of deleted and added edges are specified. For this problem, we present a novel method using dynamic programming and least-squares fitting and show that it outputs a network with the minimum sum squared error in polynomial time if the maximum indegree of the network is bounded by a constant. We also perform computational experiments using both artificially generated and real gene expression time series data.

DOI： 10.1100/2012/957620

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：BIOMED CENTRAL LTD  

Background: Drug side-effects, or adverse drug reactions, have become a major public health concern. It is one of the main causes of failure in the process of drug development, and of drug withdrawal once they have reached the market. Therefore, in silico prediction of potential side-effects early in the drug discovery process, before reaching the clinical stages, is of great interest to improve this long and expensive process and to provide new efficient and safe therapies for patients.
Results: In the present work, we propose a new method to predict potential side-effects of drug candidate molecules based on their chemical structures, applicable on large molecular databanks. A unique feature of the proposed method is its ability to extract correlated sets of chemical substructures (or chemical fragments) and side-effects. This is made possible using sparse canonical correlation analysis (SCCA). In the results, we show the usefulness of the proposed method by predicting 1385 side-effects in the SIDER database from the chemical structures of 888 approved drugs. These predictions are performed with simultaneous extraction of correlated ensembles formed by a set of chemical substructures shared by drugs that are likely to have a set of side-effects. We also conduct a comprehensive side-effect prediction for many uncharacterized drug molecules stored in DrugBank, and were able to confirm interesting predictions using independent source of information.
Conclusions: The proposed method is expected to be useful in various stages of the drug development process.

DOI： 10.1186/1471-2105-12-169

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：AMER CHEMICAL SOC  

The identification of rules governing molecular recognition between drug chemical substructures and protein functional sites is a challenging issue at many stages of the drug development process. In this paper we develop a novel method to extract sets of drug chemical substructures and protein domains that govern drug-target interactions on a genome-wide scale. This is made possible using sparse canonical correspondence analysis (SCCA) for analyzing drug substructure profiles and protein domain profiles simultaneously. The method does not depend on the availability of protein 3D structures. From a data set of known drug-target interactions including enzymes, ion channels, G protein-coupled receptors, and nuclear receptors, we extract a set of chemical substructures shared by drugs able to bind to a set of protein domains. These two sets of extracted chemical substructures and protein domains form components that can be further exploited in a drug discovery process. This approach successfully clusters protein domains that may be evolutionary unrelated but that bind a common set of chemical substructures. As shown in several examples, it can also be very helpful for predicting new protein-ligand interactions and addressing the problem of ligand specificity. The proposed method constitutes a contribution to the recent field of chemogenomics that aims to connect the chemical space with the biological space.

DOI： 10.1021/ci100476q

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Part of collection (book)   Publisher：IGI Global  

In silico prediction of compound-protein interactions from heterogeneous biological data is critical in the process of drug development. In this chapter the authors review several supervised machine learning methods to predict unknown compound-protein interactions from chemical structure and genomic sequence information simultaneously. The authors review several kernel-based algorithms from two different viewpoints: binary classification and dimension reduction. In the results, they demonstrate the usefulness of the methods on the prediction of drug-target interactions and ligand-protein interactions from chemical structure data and genomic sequence data. © 2011, IGI Global.

DOI： 10.4018/978-1-61520-911-8.ch016

Web of Science

Scopus

Web of Science

Publisher：Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Methods and Collaborative Techniques  

DOI： 10.4018/978-1-61520-911-8

Scopus

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Pairwise classification has many applications including network prediction, entity resolution, and collaborative filtering. The pairwise kernel has been proposed for those purposes by several research groups independently, and has been used successfully in several fields. In this paper, we propose an efficient alternative which we call a Cartesian kernel. While the existing pairwise kernel (which we refer to as the Kronecker kernel) can be interpreted as the weighted adjacency matrix of the Kronecker product graph of two graphs, the Cartesian kernel can be interpreted as that of the Cartesian graph, which is more sparse than the Kronecker product graph. We discuss the generalization bounds of the two pairwise kernels by using eigenvalue analysis of the kernel matrices. Also, we consider the N-wise extensions of the two pairwise kernels. Experimental results show the Cartesian kernel is much faster than the Kronecker kernel, and at the same time, competitive with the Kronecker kernel in predictive performance.

DOI： 10.1587/transinf.E93.D.2672

Web of Science

Scopus

Other Link： http://dblp.uni-trier.de/db/journals/ieicet/ieicet93d.html#journals/ieicet/KashimaOYT10

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: In silico prediction of drug-target interactions from heterogeneous biological data is critical in the search for drugs and therapeutic targets for known diseases such as cancers. There is therefore a strong incentive to develop new methods capable of detecting these potential drug-target interactions efficiently.
Results: In this article, we investigate the relationship between the chemical space, the pharmacological space and the topology of drug-target interaction networks, and show that drug-target interactions are more correlated with pharmacological effect similarity than with chemical structure similarity. We then develop a new method to predict unknown drug-target interactions from chemical, genomic and pharmacological data on a large scale. The proposed method consists of two steps: (i) prediction of pharmacological effects from chemical structures of given compounds and (ii) inference of unknown drug-target interactions based on the pharmacological effect similarity in the framework of supervised bipartite graph inference. The originality of the proposed method lies in the prediction of potential pharmacological similarity for any drug candidate compounds and in the integration of chemical, genomic and pharmacological data in a unified framework. In the results, we make predictions for four classes of important drug-target interactions involving enzymes, ion channels, GPCRs and nuclear receptors. Our comprehensively predicted drug-target interaction networks enable us to suggest many potential drug-target interactions and to increase research productivity toward genomic drug discovery.
Supplementary information: Datasets and all prediction results are available at http://cbio.ensmp.fr/(similar to)yyamanishi/pharmaco/.
Availability: Softwares are available upon request.
Contact: yoshihiro.yamanishi@ensmp.fr

DOI： 10.1093/bioinformatics/btq176

Web of Science

Scopus

PubMed

J-GLOBAL

Publisher：Genome informatics. International Conference on Genome Informatics  

Signaling pathways are often represented by networks where each node corresponds to a protein and each edge corresponds to a relationship between nodes such as activation, inhibition and binding. However, such signaling pathways in a cell may be affected by genetic and epigenetic alteration. Some edges may be deleted and some edges may be newly added. The current knowledge about known signaling pathways is available on some public databases, but most of the signaling pathways including changes upon the cell state alterations remain largely unknown. In this paper, we develop an integer programming-based method for inferring such changes by using gene expression data. We test our method on its ability to reconstruct the pathway of colorectal cancer in the KEGG database.

DOI： 10.1142/9781848166585_0016

Scopus

Language：English   Publishing type：Research paper (scientific journal)  

Signaling pathways are often represented by networks where each node corresponds to a protein and each edge corresponds to a relationship between nodes such as activation, inhibition and binding. However, such signaling pathways in a cell may be affected by genetic and epigenetic alteration. Some edges may be deleted and some edges may be newly added. The current knowledge about known signaling pathways is available on some public databases, but most of the signaling pathways including changes upon the cell state alterations remain largely unknown. In this paper, we develop an integer programming-based method for inferring such changes by using gene expression data. We test our method on its ability to reconstruct the pathway of colorectal cancer in the KEGG database.

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone.Results: We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconstruction of three metabolic networks of Caenorhabditis elegans, Helicobacter pylori and Saccharomyces cerevisiae, based on gene expression similarities and amino acid sequence similarities. The experimental results proved that the new simultaneous network inference method consistently improves the predictive performance over the individual network inferences, and it also outperforms in accuracy and speed other established methods such as the pairwise support vector machine.

DOI： 10.1093/bioinformatics/btp494

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: In silico prediction of drug-target interactions from heterogeneous biological data is critical in the search for drugs for known diseases. This problem is currently being attacked from many different points of view, a strong indication of its current importance. Precisely, being able to predict new drug-target interactions with both high precision and accuracy is the holy grail, a fundamental requirement for in silico methods to be useful in a biological setting. This, however, remains extremely challenging due to, amongst other things, the rarity of known drug-target interactions.
Results: We propose a novel supervised inference method to predict unknown drug-target interactions, represented as a bipartite graph. We use this method, known as bipartite local models to first predict target proteins of a given drug, then to predict drugs targeting a given protein. This gives two independent predictions for each putative drug-target interaction, which we show can be combined to give a definitive prediction for each interaction. We demonstrate the excellent performance of the proposed method in the prediction of four classes of drug-target interaction networks involving enzymes, ion channels, G protein-coupled receptors (GPCRs) and nuclear receptors in human. This enables us to suggest a number of new potential drug-target interactions.

DOI： 10.1093/bioinformatics/btp433

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: The IUBMB's Enzyme Nomenclature system, commonly known as the Enzyme Commission (EC) numbers, plays key roles in classifying enzymatic reactions and in linking the enzyme genes or proteins to reactions in metabolic pathways. There are numerous reactions known to be present in various pathways but without any official EC numbers, most of which have no hope to be given ones because of the lack of the published articles on enzyme assays.
Results: In this article we propose a new method to predict the potential EC numbers to given reactant pairs (substrates and products) or uncharacterized reactions, and a web-server named E-zyme as an application. This technology is based on our original biochemical transformation pattern which we call an 'RDM pattern', and consists of three steps: (i) graph alignment of a query reactant pair (substrates and products) for computing the query RDM pattern, (ii) multi-layered partial template matching by comparing the query RDM pattern with template patterns related with known EC numbers and (iii) weighted major voting scheme for selecting appropriate EC numbers. As the result, cross-validation experiments show that the proposed method achieves both high coverage and high prediction accuracy at a practical level, and consistently outperforms the previous method.

DOI： 10.1093/bioinformatics/btp223

Web of Science

Scopus

PubMed

J-GLOBAL

Publisher：Advances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference  

We formulate the problem of bipartite graph inference as a supervised learning problem, and propose a new method to solve it from the viewpoint of distance metric learning. The method involves the learning of two mappings of the heterogeneous objects to a unified Euclidean space representing the network topology of the bipartite graph, where the graph is easy to infer. The algorithm can be formulated as an optimization problem in a reproducing kernel Hilbert space. We report encouraging results on the problem of compound-protein interaction network reconstruction from chemical structure data and genomic sequence data.

Scopus

Publishing type：Research paper (international conference proceedings)   Publisher：SIAM  

We propose Link Propagation as a new semi-supervised learning method for link prediction problems, where the task is to predict unknown parts of the network structure by using auxiliary information such as node similarities. Since the proposed method can fill in missing parts of tensors, it is applicable to multi-relational domains, allowing us to handle multiple types of links simultaneously. We also give a novel efficient algorithm for Link Propagation based on an accelerated conjugate gradient method.

DOI： 10.1137/1.9781611972795.94

Scopus

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：SPRINGER-VERLAG BERLIN  

Pairwise classification has many applications including network prediction, entity resolution, and collaborative filtering. The pairwise kernel has been proposed for those purposes by several research groups independently, and become successful in various fields. In this paper, we propose an efficient alternative which we call Cartesian kennel. While the existing pairwise kernel (which we refer to as Kronecker kernel) can be interpreted as the weighted adjacency matrix of the Kronecker product graph of two graphs, the Cartesian kernel can be interpreted as that of the Cartesian graph which is more sparse than the Kronecker product graph. Experimental results show the Cartesian kernel is much faster than the existing pairwise kernel, and at the same time, competitive with the existing pairwise kernel in predictive performance. We discuss the generalization bounds by the two pairwise kernels by using eigenvalue analysis of the kernel matrices.

DOI： 10.1007/978-3-642-01307-2_110

Web of Science

Scopus

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: The identification of interactions between drugs and target proteins is a key area in genomic drug discovery. Therefore, there is a strong incentive to develop new methods capable of detecting these potential drug-target interactions efficiently.
Results: In this article, we characterize four classes of drug-target interaction networks in humans involving enzymes, ion channels, G-protein-coupled receptors (GPCRs) and nuclear receptors, and reveal significant correlations between drug structure similarity, target sequence similarity and the drug-target interaction network topology. We then develop new statistical methods to predict unknown drug-target interaction networks from chemical structure and genomic sequence information simultaneously on a large scale. The originality of the proposed method lies in the formalization of the drug-target interaction inference as a supervised learning problem for a bipartite graph, the lack of need for 3D structure information of the target proteins, and in the integration of chemical and genomic spaces into a unified space that we call &apos;pharmacological space&apos;. In the results, we demonstrate the usefulness of our proposed method for the prediction of the four classes of drug-target interaction networks. Our comprehensively predicted drug-target interaction networks enable us to suggest many potential drug-target interactions and to increase research productivity toward genomic drug discovery.

DOI： 10.1093/bioinformatics/btn162

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

KEGG (http://www.genome.jp/kegg/) is a database of biological systems that integrates genomic, chemical and systemic functional information. KEGG provides a reference knowledge base for linking genomes to life through the process of PATHWAY mapping, which is to map, for example, a genomic or transcriptomic content of genes to KEGG reference pathways to infer systemic behaviors of the cell or the organism. In addition, KEGG provides a reference knowledge base for linking genomes to the environment, such as for the analysis of drug-target relationships, through the process of BRITE mapping. KEGG BRITE is an ontology database representing functional hierarchies of various biological objects, including molecules, cells, organisms, diseases and drugs, as well as relationships among them. KEGG PATHWAY is now supplemented with a new global map of metabolic pathways, which is essentially a combined map of about 120 existing pathway maps. In addition, smaller pathway modules are defined and stored in KEGG MODULE that also contains other functional units and complexes. The KEGG resource is being expanded to suit the needs for practical applications. KEGG DRUG contains all approved drugs in the US and Japan, and KEGG DISEASE is a new database linking disease genes, pathways, drugs and diagnostic markers.

DOI： 10.1093/nar/gkm882

Web of Science

Scopus

PubMed

J-GLOBAL

Publishing type：Research paper (international conference proceedings)   Publisher：Curran Associates, Inc.  

Other Link： http://dblp.uni-trier.de/db/conf/nips/nips2008.html#conf/nips/Yamanishi08

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: Glycans are covalent assemblies of sugar that play crucial roles in many cellular processes. Recently, comprehensive data about the structure and function of glycans have been accumulated, therefore the need for methods and algorithms to analyze these data is growing fast.
Results: This article presents novel methods for classifying glycans and detecting discriminative glycan motifs with support vector machines (SVM). We propose a new class of tree kernels to measure the similarity between glycans. These kernels are based on the comparison of tree substructures, and take into account several glycan features such as the sugar type, the sugar bound type or layer depth. The proposed methods are tested on their ability to classify human glycans into four blood components: leukemia cells, erythrocytes, plasma and serum. They are shown to outperform a previously published method. We also applied a feature selection approach to extract glycan motifs which are characteristic of each blood component. We confirmed that some leukemia-specific glycan motifs detected by our method corresponded to several results in the literature.

DOI： 10.1093/bioinformatics/btm090

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：WILEY  

The metabolic network is an important biological network which consists of enzymes and chemical compounds. However, a large number of metabolic pathways remains unknown, and most organism-specific metabolic pathways contain many missing enzymes. We present a novel method to identify the genes coding for missing enzymes using available genomic and chemical information from bacterial genomes. The proposed method consists of two steps: (a) estimation of the functional association between the genes with respect to chromosomal proximity and evolutionary association, using supervised network inference; and (b) selection of gene candidates for missing enzymes based on the original candidate score and the chemical reaction information encoded in the EC number. We applied the proposed methods to infer the metabolic network for the bacteria Pseudomonas aeruginosa from two genomic datasets: gene position and phylogenetic profiles. Next, we predicted several missing enzyme genes to reconstruct the lysine-degradation pathway in P. aeruginosa using EC number information. As a result, we identified PA0266 as a putative 5-aminovalerate aminotransferase (EC 2.6.1.48) and PA0265 as a putative glutarate semialdehyde dehydrogenase (EC 1.2.1.20). To verify our prediction, we conducted biochemical assays and examined the activity of the products of the predicted genes, PA0265 and PA0266, in a coupled reaction. We observed that the predicted gene products catalyzed the expected reactions; no activity was seen when both gene products were omitted from the reaction.

DOI： 10.1111/j.1742-4658.2007.05763.x

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：WILEY  

Prediction of molecular interaction networks from large-scale datasets in genomics and other ornics experiments is an important task in terms of both developing bioinformatics methods and solving biological problems. We have applied a kernel-based network inference method for extracting functionally related genes to the response of nitrogen deprivation in cyanobacteria Anabaena sp. PCC 7120 integrating three heterogeneous datasets: microarray data, phylogenetic profiles, and gene orders on the chromosome. We obtained 1348 predicted genes that are somehow related to known genes in the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. While this dataset contained previously known genes related to the nitrogen deprivation condition, it also contained additional genes. Thus, we attempted to select any relevant genes using the constraints of Pfam. domains and NtcA-binding sites. We found candidates of nitrogen metabolism-related genes, which are depicted as extensions of existing KEGG pathways. The prediction of functional relationships between proteins rather than functions of individual proteins will thus assist the discovery from the large-scale datasets.

DOI： 10.1002/pmic.200600862

Web of Science

Scopus

PubMed

J-GLOBAL

Web of Science

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：SPRINGER-VERLAG BERLIN  

The mirror tree is a method to predict protein-protein interaction by evaluating the similarity between distance matrices of proteins. It is known, however, that predictions by the mirror tree method include many false positives. We suspected that the information about the evolutionary relationship of source organisms may be the cause of the false positives, because the information is shared by the distance matrices. Therefore, we excluded the information from the distance matrices and evaluated the similarity of the residuals as the intensity of co-evolution. We developed two different methods with a projection operation and partial correlation coefficient. The number of false positives were drastically reduced by our methods.

DOI： 10.1007/978-3-540-73433-8_23

Web of Science

Scopus

Publisher：Genome informatics. International Conference on Genome Informatics  

The prediction of glycan structures from gene expression of glycosyltransferases (GTs) is a challenging new area in computational biology because the biosynthesis of glycan chains is under the control of GT expression. In this paper we developed a new method for predicting glycan structures from gene expression data. There are two main original aspects of the proposed method. First, we proposed to increase the number of predictable glycan structure candidates by estimating missing glycans from a global glycan structure map, which enables us to predict new glycan structures that are not stored in the database. Second, we proposed a more general scoring scheme based on real-valued gene expression intensity rather than converting it into binary information. In the result we applied the proposed method to predicting cancer-specific glycan structures from gene expression profiles for patients of acute lymphocytic leukemia (ALL) and acute myelocytic leukemia (AML). We confirmed that several of the predicted glycan structures successfully correspond to known cancer-specific glycan structures according to the literature, and our method outperforms the previous methods at a statistically significant level.

DOI： 10.1142/9781860949920_0023

Scopus

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IMPERIAL COLLEGE PRESS  

The prediction of glycan structures from gene expression of glycosyltransferases (GTs) is a challenging new area in computational biology because the biosynthesis of glycan chains is under the control of GT expression. In this paper we developed a new method for predicting glycan structures from gene expression data. There are two main original aspects of the proposed method. First, we proposed to increase the number of predictable glycan structure candidates by estimating missing glycans from a global glycan structure map, which enables us to predict new glycan structures that are not stored in the database. Second, we proposed a more general scoring scheme based on real-valued gene expression intensity rather than converting it into binary information. In the result we applied the proposed method to predicting cancer-specific glycan structures from gene expression profiles for patients of acute lymphocytic leukemia (ALL) and acute myelocytic leukemia (AML). We confirmed that several of the predicted glycan structures successfully correspond to known cancer-specific glycan structures according to the literature, and our method outperforms the previous methods at a statistically significant level.

DOI： 10.11234/gi1990.18.237

Web of Science

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: The computational prediction of protein-protein interactions is currently a major issue in bioinformatics. Recently, a variety of co-evolution-based methods have been investigated toward this goal. In this study, we introduced a partial correlation coefficient as a new measure for the degree of co-evolution between proteins, and proposed its use to predict protein-protein interactions.
Results: The accuracy of the prediction by the proposed method was compared with those of the original mirror tree method and the projection method previously developed by our group. We found that the partial correlation coefficient effectively reduces the number of false positives, as compared with other methods, although the number of false negatives increased in the prediction by the partial correlation coefficient.

DOI： 10.1093/bioinformatics/btl419

Web of Science

Scopus

PubMed

J-GLOBAL

Web of Science

Language：English   Publishing type：Research paper (scientific journal)   Publisher：ELSEVIER SCI LTD  

There have been almost no standard methods for conducting computational analyses on glycan structures in comparison to DNA and proteins. In this paper, we present a novel method for extracting functional motifs from glycan structures using the KEGG/GLYCAN database. First, we developed a new similarity measure for comparing glycan structures taking into account the characteristic mechanisms of glycan biosynthesis, and we tested its ability to classify glycans of different blood components in the framework of support vector machines (SVMs), The results show that our method can successfully classify glycans from four types of human blood components: leukemic cells, erythrocyte, serum, and plasma. Next we extracted characteristic functional motifs of glycans considered to be specific to each blood component. We predicted the substruct the alpha-D-Neup5AC-(2--&gt;3)-beta-D-Galp-(1--&gt;4)-D-GlcpNAc as a leukemia specific glycan motif. Based on the fact that the Agrocybe cylindracea galectin (ACG) specifically binds to the same substructure, we conducted an experiment using Cell agglutination assay and confirmed that this fungal lectin specifically recognized human leukemic cells. (C) 2005 Elsevier Ltd. All rights reserved.

DOI： 10.1016/j.carres.2005.07.012

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: The prediction of protein-protein interactions is currently an important issue in bioinformatics. The mirror tree method uses evolutionary information to predict protein-protein interactions. However, it has been recognized that predictions by the mirror tree method lead to many false positives. The incentive of our study was to solve this problem by improving the method of extracting the co-evolutionary information regarding the protein pairs.
Results: We developed a novel method to predict protein-protein interactions from co-evolutionary information in the framework of the mirror tree method. The originality is the use of the projection operator to exclude the information about the phylogenetic relationships among the source organisms from the distance matrix. Each distance matrix was transformed into a vector for the operation. The vector is referred to as a 'phylogenetic vector'. We have proposed three ways to extract the phylogenetic information: (1) using the 16S rRNA from the same source organisms as the proteins under consideration, (2) averaging the phylogenetic vectors and (3) analyzing the principal components of the phylogenetic vectors. We examined the performance of the proposed methods to predict interacting protein pairs from Escherichia coli, using experimentally verified data. Our method was successful, and it drastically reduced the number of false positives in the prediction.

DOI： 10.1093/bioinformatics/bti564

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：AMER ASSOC CANCER RESEARCH  

Purpose: Integration of hepatitis B virus (HBV) DNA into the human genome is one of the most important steps in HBV-related carcinogenesis. This study attempted to find the link between HBV DNA, the adjoining cellular sequence, and altered gene expression in hepatocellular carcinoma (HCC) with integrated HBV DNA.
Experimental Design: We examined 15 cases of HCC infected with HBV by cassette ligation mediated PCR. The human DNA adjacent to the integrated HBV DNA was sequenced. Protein coding sequences were searched for in the human sequence. In five cases with HBV DNA integration, from which good quality RNA was extracted, gene expression was examined by cDNA microarray analysis.
Results: The human DNA sequence successive to integrated HBV DNA was determined in the 15 HCCs. Eight protein-coding regions were involved: ras-responsive element binding protein 1, calmodulin 1, mixed lineage leukemia 2 (MLL-2), FLJ333655, LOC220272, LOC255345, LOC220220, and LOC168991. The MLL2 gene was expressed in three cases with HBV DNA integrated into exon 3 of MLL2 and in one case with HBV DNA integrated into intron 3 of MLL2. Gene expression analysis suggested that two HCCs with HBV integrated into MLL2 had similar patterns of gene expression compared with three HCCs with HBV integrated into other loci of human chromosomes.
Conclusions: HBV DNA was integrated at random sites of human DNA, and the MLL2 gene was one of the targets for integration. Our results suggest that HBV DNA might modulate human genes near integration sites, followed by integration site-specific expression of such genes during hepatocarcinogenesis.

DOI： 10.1158/1078-0432.CCR-04-2055

Web of Science

Scopus

PubMed

J-GLOBAL

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: The metabolic network is an important biological network which relates enzyme proteins and chemical compounds. A large number of metabolic pathways remain unknown nowadays, and many enzymes are missing even in known metabolic pathways. There is, therefore, an incentive to develop methods to reconstruct the unknown parts of the metabolic network and to identify genes coding for missing enzymes.
Results: This paper presents new methods to infer enzyme networks from the integration of multiple genomic data and chemical information, in the framework of supervised graph inference. The originality of the methods is the introduction of chemical compatibility as a constraint for refining the network predicted by the network inference engine. The chemical compatibility between two enzymes is obtained automatically from the information encoded by their Enzyme Commission (EC) numbers. The proposed methods are tested and compared on their ability to infer the enzyme network of the yeast Saccharomyces cerevisiae from four datasets for enzymes with assigned EC numbers: gene expression data, protein localization data, phylogenetic profiles and chemical compatibility information. It is shown that the prediction accuracy of the network reconstruction consistently improves owing to the introduction of chemical constraints, the use of a supervised approach and the weighted integration of multiple datasets. Finally, we conduct a comprehensive prediction of a global enzyme network consisting of all enzyme candidate proteins of the yeast to obtain new biological findings.

DOI： 10.1093/bioinformatics/bti1012

Web of Science

Scopus

PubMed

J-GLOBAL

Publisher：Advances in Neural Information Processing Systems  

We formulate the problem of graph inference where part of the graph is known as a supervised learning problem, and propose an algorithm to solve it. The method involves the learning of a mapping of the vertices to a Euclidean space where the graph is easy to infer, and can be formulated as an optimization problem in a reproducing kernel Hilbert space. We report encouraging results on the problem of metabolic network reconstruction from genomic data.

Scopus

Publishing type：Research paper (scientific journal)  

DOI： 10.1007/BF02789706

Web of Science

Scopus

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: An increasing number of observations support the hypothesis that most biological functions involve the interactions between many proteins, and that the complexity of living systems arises as a result of such interactions. In this context, the problem of inferring a global protein network for a given organism, using all available genomic data about the organism, is quickly becoming one of the main challenges in current computational biology.
Results: This paper presents a new method to infer protein networks from multiple types of genomic data. Based on a variant of kernel canonical correlation analysis, its originality is in the formalization of the protein network inference problem as a supervised learning problem, and in the integration of heterogeneous genomic data within this framework. We present promising results on the prediction of the protein network for the yeast Saccharomyces cerevisiae from four types of widely available data: gene expressions, protein interactions measured by yeast two-hybrid systems, protein localizations in the cell and protein phylogenetic profiles. The method is shown to outperform other unsupervised protein network inference methods. We finally conduct a comprehensive prediction of the protein network for all proteins of the yeast, which enables us to propose protein candidates for missing enzymes in a biosynthesis pathway.

DOI： 10.1093/bioinformatics/bth910

Web of Science

Scopus

PubMed

Publishing type：Research paper (international conference proceedings)  

Other Link： http://dblp.uni-trier.de/db/conf/nips/nips2004.html#conf/nips/VertY04

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Bioinformatics  

Glycans, which are carbohydrate sugar chains attached to some lipids or proteins, have a huge variety of structures and play a key role in cell communication, protein interaction and immunity. The availability of a number of glycan structures stored in the KEGG/GLYCAN database makes it possible for us to conduct a large-scale comparative research of glycans. In this paper, we present a novel approach to compare glycan structures and extract characteristic glycan substructures of certain organisms. In the algorithm we developed a new similarity measure of glycan structures taking into account of several biological aspects of glycan synthesis and glycosyltransferases, and we confirmed the validity of our similarity measure by conducting experiments on its ability to classify glycans between organisms in the framework of a support vector machine. Finally, our method successfully extracted a set of candidates of substructrues which are characteristic to human, rat, mouse, bovine, pig, chicken, yeast, wheat and sycamore, respectively. We confirmed that the characteristic substructures extracted by our method correspond to the substructures which are known as the species-specific sugar chain of γ-glutamyltranspeptidases in the kidney.

DOI： 10.11234/gi1990.15.69

PubMed

J-GLOBAL

Publisher：Genome informatics. International Conference on Genome Informatics  

Glycans, which are carbohydrate sugar chains attached to some lipids or proteins, have a huge variety of structures and play a key role in cell communication, protein interaction and immunity. The availability of a number of glycan structures stored in the KEGG/GLYCAN database makes it possible for us to conduct a large-scale comparative research of glycans. In this paper, we present a novel approach to compare glycan structures and extract characteristic glycan substructures of certain organisms. In the algorithm we developed a new similarity measure of glycan structures taking into account of several biological aspects of glycan synthesis and glycosyltransferases, and we confirmed the validity of our similarity measure by conducting experiments on its ability to classify glycans between organisms in the framework of a support vector machine. Finally, our method successfully extracted a set of candidates of substructrues which are characteristic to human, rat, mouse, bovine, pig, chicken, yeast, wheat and sycamore, respectively. We confirmed that the characteristic substructures extracted by our method correspond to the substructures which are known as the species-specific sugar chain of gamma-glutamyltranspeptidases in the kidney.

Scopus

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OXFORD UNIV PRESS  

Motivation: A major issue in computational biology is the reconstruction of pathways from several genomic datasets, such as expression data, protein interaction data and phylogenetic profiles. As a first step toward this goal, it is important to investigate the amount of correlation which exists between these data.
Method: We present new methods to measure the correlation between several heterogeneous datasets, and to extract sets of genes which share similarities with respect to multiple biological attributes. The originality of our approach is the extension of the concept of correlation for non-vectorial data, which is made possible by the use of generalized kernel canonical correlation analysis (KCCA), and the method we propose to extract groups of genes responsible for the detected correlations. Moreover, two variants of KCCA are proposed when more than two datasets are available.
Result: These methods are successfully tested on their ability to recognize operons in the Escherichia coli genome, from the comparison of three datasets corresponding to functional relationships between genes in metabolic pathways, geometrical relationships along the chromosome, and co-expression relationships as observed by gene expression data.

DOI： 10.1093/bioinformatics/btg1045

Web of Science

Scopus

PubMed

Other Link： http://dblp.uni-trier.de/db/conf/ismb/ismb2003.html#conf/ismb/YamanishiVNK03

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Bioinformatics  

In recent years, the analysis of orthologous genes based on phylogenetic profiles has received popularity in bioinfomatics. We propose a new method to extract organism groups and their hierarchy from phylogenetic profiles using the independent component analysis (ICA). The method involves first finding independent axes in the projected space from the multivariate data matrix representing phylogenetic profiles for a number of orthologous genes. Then the extracted axes are correlated with major organism groups, according to the extent of affiliaion of axes scores for all the genes to specific organisms. The ICA was applied to the phylogenetic profiles created for 2875 orthologs in 77 organisms by using the KEGG/GENES database. The 9 extracted components out of 18 predefined components well represented the organism groups as categorized in KEGG. Furthermore, we performed the cluster analysis and obtained the hierarchy of organism groups.

DOI： 10.11234/gi1990.13.61

PubMed

Publisher：Genome informatics. International Conference on Genome Informatics  

In recent years, the analysis of orthologous genes based on phylogenetic profiles has received popularity in bioinfomatics. We propose a new method to extract organism groups and their hierarchy from phylogenetic profiles using the independent component analysis (ICA). The method involves first finding independent axes in the projected space from the multivariate data matrix representing phylogenetic profiles for a number of orthologous genes. Then the extracted axes are correlated with major organism groups, according to the extent of affiliation of axes scores for all the genes to specific organisms. The ICA was applied to the phylogenetic profiles created for 2,875 orthologs in 77 organisms by using the KEGG/GENES database. The 9 extracted components out of 18 predefined components well represented the organism groups as categorized in KEGG. Furthermore, we performed the cluster analysis and obtained the hierarchy of organism groups.

Scopus

Authorship：Last author,　Corresponding author   Language：English   Publishing type：Article, review, commentary, editorial, etc. (scientific journal)   Publisher：SPRINGERNATURE  

We developed a computational method to reveal the drug-induced single-cell transcriptomic landscape. This algorithm enabled us to impute unknown drug-induced single-cell gene expression profiles using tensor imputation, predict cell type-specific drug efficacy, detect cell-type-specific marker genes, and identify the trajectories of regulated biological pathways while considering intercellular heterogeneity.

DOI： 10.1038/s43588-022-00353-7

Web of Science

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)   Publisher：(一社)日本医療情報学会  

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)   Publisher：(NPO)日本肺癌学会  

J-GLOBAL

Language：English   Publishing type：Research paper, summary (national, other academic conference)   Publisher：(一社)日本癌学会  

Language：English   Publishing type：Research paper, summary (national, other academic conference)   Publisher：(一社)日本癌学会  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)   Publisher：(一社)和漢医薬学会  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)  

CiNii Books

J-GLOBAL

Authorship：Lead author,　Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)   Publisher：(一社)日本内分泌学会  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (scientific journal)  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Authorship：Lead author,　Last author,　Corresponding author   Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (scientific journal)   Publisher：科学評論社  

CiNii Books

Authorship：Lead author,　Last author,　Corresponding author   Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (scientific journal)  

J-GLOBAL

Authorship：Lead author,　Last author,　Corresponding author   Language：Japanese   Publisher：一般社団法人 日本臨床薬理学会  

医薬品開発において、化合物とタンパク質の結合親和性を定量的に評価することは非常に重要であり、ドッキングシミュレーションと機械学習は重要な役割を果たす。ドッキングシミュレーションには実験的に決定されたタンパク質の立体構造情報が必要であるが、現在立体構造データが利用可能なタンパク質はヒトゲノムにコードされている全タンパク質の一部に過ぎない。近年、AI技術の進歩とともにタンパク質立体構造の予測技術が大幅に向上してきている。なかでもニューラルネットワーク技術を取り入れたAlphaFold v2.0(以下AlphaFold2)は、X線結晶構造解析など実験的に決定したタンパク質立体構造と遜色ない精度を持つ。本研究では、AlphaFold2を活用してヒトゲノムにコードされている全タンパク質の立体構造情報に基づき、医薬品化合物の薬効や副作用予測を行う手法を提案する。まずAlphaFold2で予測したヒト全タンパク質（約20,000タンパク質配列）の立体構造データをAlphaFold Protein Structure Databaseより取得した。医薬品化合物に対してヒト全タンパク質立体構造とのドッキングシミュレーションを行い、それらの結合親和性プロファイルを作成し、様々な疾患に対する薬効や副作用を予測する機械学習モデルを構築した。提案手法は高性能の予測だけではなく、薬効や副作用の作用機序の考察を可能にした。提案手法は、医薬品開発に有用であることが期待できる。

DOI： 10.50993/jsptsuppl.43.0_3-c-s41-2

J-GLOBAL

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (scientific journal)  

J-GLOBAL

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Authorship：Lead author,　Last author,　Corresponding author   Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (scientific journal)  

J-GLOBAL

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Authorship：Lead author,　Last author,　Corresponding author   Language：English   Publishing type：Research paper, summary (national, other academic conference)  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：English   Publisher：(一社)日本癌学会  

Language：Japanese   Publisher：(一社)日本神経学会  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：(一社)日本糖尿病学会  

Language：Japanese   Publisher：(公社)日本薬学会  

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：Japanese Pharmacological Society  

Modification of disease-elicited gene expression is one of the core aspects in numerous drugs’ modes of action. To predict drug–disease associations, transcriptomics-based approaches with pathway analysis, graph theory and supervised machine learning-based calculation were developed. However, the pharmacological mechanism employed by drugs remain largely unknown.

In this study, we focused on transcription factors (TFs) that integratively regulate differentially expressed genes (DEGs) in response to drug treatment. In particular, TF enrichment analysis (TFEA) was performed for each chemical to identify TFs with enriched binding for DEGs by combining the chemically perturbed transcriptome data (CTD) and TF-binding database ChIP-Atlas. Performance evaluation with area under the ROC curve (AUC) suggests the reliability of TFEA in drug target discovery (global AUC = 0.66). Furthermore, we successfully identified the key factors that link drugs to diseases or side effects by utilizing protein-disease database DisGeNET (global AUC = 0.68). This approach is with high confidence because it is fully based on actual experiments of given transcriptome data and public ChIP-seq data. In the pharmaceutical field, TFEA is useful to shed light on compounds failed to be approved by identifying TFs primarily involved in the modes of action, together with the factors associated with potential side effects. Approved drugs including agents composed of unidentified ingredients such as traditional herbal medicines can also be re-examined for novel targets and actions, thus beneficial to drug repositioning research.

DOI： 10.1254/jpssuppl.94.0_1-y-e3-4

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：(株)中外医学社  

J-GLOBAL

Language：Japanese   Publisher：(一社)日本神経学会  

Language：English   Publisher：(一社)日本癌学会  

Language：Japanese  

J-GLOBAL

Language：Japanese  

CiNii Books

J-GLOBAL

Other Link： https://search.jamas.or.jp/link/ui/2020333305

Language：Japanese   Publisher：技術情報協会  

CiNii Books

J-GLOBAL

Language：Japanese   Publisher：北隆館  

CiNii Books

Other Link： https://search.jamas.or.jp/link/ui/2020231859

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

Language：English   Publisher：(一社)日本癌学会  

Language：Japanese   Publisher：(一社)和漢医薬学会  

J-GLOBAL

Language：Japanese   Publisher：医歯薬出版  

医薬品開発の低迷を打開する戦略として、既存薬の新しい効能を発見し、本来とは別の疾患に対する治療薬として新薬開発を行うドラッグリポジショニング(DR)が注目されている。近年の生命医科学や創薬科学では疾患、薬物、低分子化合物、遺伝子、蛋白質、代謝産物などに関する大量のオミックスデータが得られるようになり、このようなビッグデータのDRへの有効活用が期待されている。本稿では、さまざまな医薬ビッグデータと機械学習(AI基盤技術)を用いてDRを行うインシリコ(in silico)手法を解説する。とくに、分子プロファイルの比較、疾患の分子機序類似性、ポリファーマコロジー、パスウェイ制御の観点から、疾患に対する治療薬候補を網羅的かつ体系的に予測する手法とその応用例を紹介する。(著者抄録)

CiNii Books

J-GLOBAL

Other Link： https://search.jamas.or.jp/link/ui/2019144389

Language：Japanese   Publisher：(一財)バイオインダストリー協会  

J-GLOBAL

Language：English   Publisher：(一社)日本循環器学会  

J-GLOBAL

Language：Japanese   Publisher：公益社団法人 日本化学会  

近年の生命医科学では，遺伝子，タンパク質，化合物，薬物，疾患に関するビッグデータが得られるようになってきた。ビッグデータ解析から新しい医学的発見や新薬開発につなげる研究が期待されている。本稿では，様々な医薬データを機械学習（人工知能の基盤技術）で有効活用した疾患研究や創薬応用を紹介する。特に，既存薬物から新規効能を発見するドラッグリポジショニングに基づく創薬への応用を解説する。

DOI： 10.20665/kakyoshi.67.2_66

CiNii Books

J-GLOBAL

Language：Japanese   Publisher：小峰工業出版  

CiNii Books

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

Language：Japanese   Publisher：北隆館  

効率的な創薬戦略として、既存薬の新しい効能を発見し、本来とは別の疾患に対する治療薬として開発するドラッグリポジショニングが注目されている。近年の生命医科学では、疾患、薬物、遺伝子、タンパク質、代謝産物に関する大量のオミックスデータが得られるようになり、このようなビッグデータのドラッグリポジショニングへの有効活用が期待されている。本稿では、様々な医薬ビッグデータと機械学習(AI基盤技術)を用いてドラッグリポジショニングを行うインシリコ手法を紹介する。(著者抄録)

CiNii Books

J-GLOBAL

Other Link： https://search.jamas.or.jp/link/ui/2019124444

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：日本計算機統計学会  

DOI： 10.20551/jscstaikai.32.0_76

J-GLOBAL

Language：Japanese   Publisher：公益社団法人 日本薬剤学会  

DOI： 10.14843/jpstj.78.77

J-GLOBAL

Language：Japanese   Publisher：三井住友海上福祉財団  

CiNii Books

J-GLOBAL

Language：Japanese   Publisher：公益社団法人 日本化学会・情報化学部会  

DOI： 10.11546/cicsj.36.42

Language：Japanese  

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

Language：Japanese  

CiNii Books

J-GLOBAL

Language：Japanese  

CiNii Books

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

CiNii Books

J-GLOBAL

Language：Japanese   Publisher：社団法人人工知能学会  

DOI： 10.11517/jjsai.30.2_224

CiNii Books

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：一般社団法人電子情報通信学会  

近年の新薬開発の行き詰まりを打開する方法として、既存薬の作用を徹底的に調べあげ新たに薬効を見つけ出し、本来それが開発された疾患とは別の疾患に対する治療薬として再開発する創薬研究が注目を浴びている。本研究では、薬物に関するケミカルなデータと疾患に関するフェノタイプのデータから潜在的な薬物と疾患の関係を網羅的に予測する機械学習の手法を開発した。教師付き学習のアルゴリズムにスパース統計モデルを導入することで特徴抽出を可能にし、予測された関係に関与している薬物の標的タンパク質と疾患のフェノタイプの組み合わせを同定する点が独自の点である。また抽出された標的タンパク質の生物学的妥当性をPathway Enrichment解析を用いて評価した。本発表ではこれらの結果と、既知のデータから学習して生成したモデルを適用することで得られる新規の薬と疾患の関連解析の結果について紹介する。

CiNii Books

Language：Japanese  

CiNii Books

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：Division of Chemical Information and Computer Sciences The Chemical Society of Japan  

DOI： 10.11546/cicsj.31.26

J-GLOBAL

Language：Japanese   Publisher：Division of Chemical Information and Computer Sciences The Chemical Society of Japan  

DOI： 10.11546/cicsj.31.25

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：日本プロテオーム学会（日本ヒトプロテオーム機構）  

DOI： 10.14889/jhupo.2012.0.86.0

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：情報処理学会  

CiNii Books

Language：Japanese   Publisher：電子情報通信学会  

Language：Japanese   Publisher：電子情報通信学会  

Language：Japanese   Publisher：Information Processing Society of Japan (IPSJ)  

The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone. We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconst...

Language：Japanese   Publisher：情報処理学会  

従来、生体ネットワークの予測は、遺伝子発現などの個々の生物種のもつ情報をもとに、種別に行われてきた。これに対し、本研究では 「リンク伝搬法」 と名付けた半教師つき学習法によって、複数の生物種のネットワークを同時に予測する方法を提案する。各生物種のもつ情報として遺伝子発現の類似度を、生物種間をまたぐ情報としてアミノ酸配列の類似度を用いて、C. elegans、H. pylori および S. cerevisiae のネットワークの同時予測を行い、ペアワイズ SVM などの既存手法を精度と速度の両面において上回ることを示す。The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone. We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconstruction of three metabolic networks of C. elegans, H. pylori, and S. cerevisiae, based on gene expression similarities and amino acid sequence similarities. The experimental results proved that the new simultaneous network inference method consistently improves the predictive performance over the individual network inferences, and it also outperforms in accuracy and speed other established methods such as the pairwise support vector machine.

CiNii Books

J-GLOBAL

Language：Japanese   Publisher：人工知能学会  

CiNii Books

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：日本植物生理学会  

Prediction of molecular interaction networks from large-scale datasets in genomics and other omics experiments is an important task in terms of both developing bioinformatics methods and solving biological problems. We have applied a kernel-based network inference method for extracting functionally related genes to the response of nitrogen deprivation in cyanobacteria &lt;i&gt;Anabaena&lt;/i&gt; PCC7120 integrating three heterogeneous datasets: microarray, phylogenetic profiles, and gene orders on the chromosome. We obtained 1348 predicted genes that are somehow related to known genes in KEGG PATHWAY. While this dataset contained previously known genes related to the nitrogen deprivation response, it also contained unknown genes. Moreover, we attempted to select any relevant genes using the constraints of Pfam domains and NtcA binding sites. We found candidates of nitrogen metabolism-related genes, which are depicted as extensions of existing KEGG PATHWAYs. We showed promising results suggesting that our approach will be helpful in designing experiments in the post-genome era.

DOI： 10.14841/jspp.2007.0.558.0

J-GLOBAL

Language：Japanese   Publisher：一般社団法人日本生物物理学会  

A distance matrix is a set of genetic distances between all possible pairs of proteins under consideration, and is used to construct a phylogenetic tree by the distance matrix method. Pazos and Valencia (2001) have developed a method to predict protein-protein interaction by evaluating the similarity of the distance matrices, under the assumption that the phylogenetic trees of interacting proteins resemble each other through co-evolution. It is known, however, that the prediction includes many false positives. We postulated that the cause of the false positives is the background similarity of the phylogenetic relationship of the source organisms. We have developed a method to exclude such information from the distance matrices with a projection operator. The number of false positives was drastically reduced from the prediction by evaluating the similarity between the residuals after the projection operation.

DOI： 10.2142/biophys.47.004

CiNii Books

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

CiNii Books

J-GLOBAL

Language：Japanese   Publisher：統計数理研究所  

要旨あり予測と発見研究詳解

CiNii Books

Language：Japanese  

DOI： 10.20632/vso.80.4_254

CiNii Books

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：統計数理研究所  

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：日本行動計量学会  

CiNii Books

Language：Japanese  

J-GLOBAL

Language：Japanese  

CiNii Books

Language：Japanese   Publisher：日本計算機統計学会  

DOI： 10.20551/jscswabun.15.1_93_1

CiNii Books

Language：Japanese   Publisher：日本計算機統計学会  

DOI： 10.20551/jscswabun.15.2_325

CiNii Books

Language：Japanese   Publisher：日本計算機統計学会  

DOI： 10.20551/jscswabun.15.1_102_1

CiNii Books

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：日本行動計量学会  

CiNii Books

Language：Japanese  

DOI： 10.20551/jscstaikai.16.0_122

CiNii Books

J-GLOBAL

Event date： 2024.3

Language：Japanese   Presentation type：Oral presentation (invited, special)  

Venue：名古屋   Country：Japan  

Event date： 2024.3

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：新潟   Country：Japan  

Event date： 2024.3

Language：Japanese   Presentation type：Oral presentation (invited, special)  

Venue：東京   Country：Japan  

Event date： 2024.3

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：新潟   Country：Japan  

Event date： 2024.3

Language：Japanese   Presentation type：Oral presentation (invited, special)  

Country：Japan  

Event date： 2024.3