A Bayesian active learning strategy for sequential experimental design in systems biology.

BackgroundDynamical models used in systems biology involve unknown kinetic parameters. Setting these parameters is a bottleneck in many modeling projects. This motivates the estimation of these parameters from empirical data. However, this estimation problem has its own difficulties, the most important one being strong ill-conditionedness. In this context, optimizing experiments to be conducted in order to better estimate a system¿s parameters provides a promising direction to alleviate the difficulty of the task.ResultsBorrowing ideas from Bayesian experimental design and active learning, we propose a new strategy for optimal experimental design in the context of kinetic parameter estimation in systems biology. We describe algorithmic choices that allow to implement this method in a computationally tractable way and make it fully automatic. Based on simulation, we show that it outperforms alternative baseline strategies, and demonstrate the benefit to consider multiple posterior modes of the likelihood landscape, as opposed to traditional schemes based on local and Gaussian approximations.ConclusionThis analysis demonstrates that our new, fully automatic Bayesian optimal experimental design strategy has the potential to support the design of experiments for kinetic parameter estimation in systems biology.

Drug side-effect prediction based on the integration of chemical and biological spaces.

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.

Identification of chemogenomic features from drug-target interaction networks using interpretable classifiers.

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 process. 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. AVAILABILITY: Softwares are available at the supplemental website. CONTACT: yamanishi@bioreg.kyushu-u.ac.jp SUPPLEMENTARY INFORMATION: Datasets and all results are available at http://cbio.ensmp.fr/~yyamanishi/l1binary/ .

Relating drug-protein interaction network with drug side effects.

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. SUPPLEMENTARY INFORMATION: Datasets and all results are available at http://web.kuicr.kyoto-u.ac.jp/supp/smizutan/target-effect/. AVAILABILITY: Software is available at the above supplementary website. CONTACT: yamanishi@bioreg.kyushu-u.ac.jp, or goto@kuicr.kyoto-u.ac.jp.

A probabilistic model for cell population phenotyping using HCS data.

High Content Screening (HCS) platforms allow screening living cells under a wide range of experimental conditions and give access to a whole panel of cellular responses to a specific treatment. The outcome is a series of cell population images. Within these images, the heterogeneity of cellular response to the same treatment leads to a whole range of observed values for the recorded cellular features. Consequently, it is difficult to compare and interpret experiments. Moreover, the definition of phenotypic classes at a cell population level remains an open question, although this would ease experiments analyses. In the present work, we tackle these two questions. The input of the method is a series of cell population images for which segmentation and cellular phenotype classification has already been performed. We propose a probabilistic model to represent and later compare cell populations. The model is able to fully exploit the HCS-specific information: "dependence structure of population descriptors" and "within-population variability". The experiments we carried out illustrate how our model accounts for this specific information, as well as the fact that the model benefits from considering them. We underline that these features allow richer HCS data analysis than simpler methods based on single cellular feature values averaged over each well. We validate an HCS data analysis method based on control experiments. It accounts for HCS specificities that were not taken into account by previous methods but have a sound biological meaning. Biological validation of previously unknown outputs of the method constitutes a future line of work.

Predicting drug side-effect profiles: a chemical fragment-based approach.

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.

Extracting sets of chemical substructures and protein domains governing drug-target interactions.

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.