Dataset Information

Relating Chemical Structure to Cellular Response: An Integrative Analysis of Gene Expression, Bioactivity, and Structural Data Across 11,000 Compounds.

ABSTRACT: A central premise in systems pharmacology is that structurally similar compounds have similar cellular responses; however, this principle often does not hold. One of the most widely used measures of cellular response is gene expression. By integrating gene expression data from Library of Integrated Network-based Cellular Signatures (LINCS) with chemical structure and bioactivity data from PubChem, we performed a large-scale correlation analysis of chemical structures and gene expression profiles of over 11,000 compounds taking into account confounding factors such as biological conditions (e.g., cell line, dose) and bioactivities. We found that structurally similar compounds do indeed yield similar gene expression profiles. There is an ?20% chance that two structurally similar compounds (Tanimoto Coefficient ? 0.85) share significantly similar gene expression profiles. Regardless of structural similarity, two compounds tend to share similar gene expression profiles in a cell line when they are administrated at a higher dose or when the cell line is sensitive to both compounds.

SUBMITTER: Chen B

PROVIDER: S-EPMC4625862 | biostudies-other | 2015 Oct

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Relating Chemical Structure to Cellular Response: An Integrative Analysis of Gene Expression, Bioactivity, and Structural Data Across 11,000 Compounds.

Chen B B Greenside P P Paik H H Sirota M M Hadley D D Butte A J AJ

CPT: pharmacometrics & systems pharmacology 20150929 10

A central premise in systems pharmacology is that structurally similar compounds have similar cellular responses; however, this principle often does not hold. One of the most widely used measures of cellular response is gene expression. By integrating gene expression data from Library of Integrated Network-based Cellular Signatures (LINCS) with chemical structure and bioactivity data from PubChem, we performed a large-scale correlation analysis of chemical structures and gene expression profiles ...[more]

PMID: 26535158

Similar Datasets

Project description:Traditional toxicity testing reliant on animal models is costly and low throughput, posing a significant challenge with the increasing numbers of chemicals that humans are exposed to in the environment. The purpose of this investigation was to build optimal prediction models for various human in vivo/organ-level toxicity end points (extracted from ChemIDPlus) using chemical structure and Tox21 in vitro quantitative high-throughput screening (qHTS) bioactivity assay data. Several supervised machine learning algorithms were applied to model 14 human toxicity end points pertaining to vascular, kidney, ureter and bladder, and liver organ systems. Three metrics were used to evaluate model performance: area under the receiver operating characteristic curve (AUC-ROC), balanced accuracy (BA), and Matthews correlation coefficient (MCC). The top four models, with AUC-ROC values >0.8, were derived for endocrine (0.90 ± 0.00), musculoskeletal (0.88 ± 0.02), peripheral nerve and sensation (0.85 ± 0.01), and brain and coverings (0.83 ± 0.02) toxicities, whereas the best model AUC-ROC values were >0.7 for the remaining 10 toxicities. Model performance was found to be dependent on the specific data set, model type, and feature selection method used. In addition, chemical structure and assay data showed different levels of contribution to the prediction of different toxicity end points. Although in vitro assay data, when combined with chemical structure, slightly improved the predictive accuracy for most end points (11 out of 14), a noteworthy finding was the near equal success of the structure-only models, which do not require Tox21 qHTS screening data, and the relatively poor performance of assay-only models. Thus, the top-performing structure-only models from this study could be applied for hazard screening of large sets of chemicals for potential human toxicity, whereas the largest assay contributions to models (i.e., cellular targets) could be used, along with the top-contributing structural features, to provide insight into toxicity mechanisms.

Project description:BackgroundIn silico analyses are increasingly being used to support mode-of-action investigations; however many such approaches do not utilise the large amounts of inactive data held in chemogenomic repositories. The objective of this work is concerned with the integration of such bioactivity data in the target prediction of orphan compounds to produce the probability of activity and inactivity for a range of targets. To this end, a novel human bioactivity data set was constructed through the assimilation of over 195 million bioactivity data points deposited in the ChEMBL and PubChem repositories, and the subsequent application of a sphere-exclusion selection algorithm to oversample presumed inactive compounds.ResultsA Bernoulli Naïve Bayes algorithm was trained using the data and evaluated using fivefold cross-validation, achieving a mean recall and precision of 67.7 and 63.8 % for active compounds and 99.6 and 99.7 % for inactive compounds, respectively. We show the performances of the models are considerably influenced by the underlying intraclass training similarity, the size of a given class of compounds, and the degree of additional oversampling. The method was also validated using compounds extracted from WOMBAT producing average precision-recall AUC and BEDROC scores of 0.56 and 0.85, respectively. Inactive data points used for this test are based on presumed inactivity, producing an approximated indication of the true extrapolative ability of the models. A distance-based applicability domain analysis was also conducted; indicating an average Tanimoto Coefficient distance of 0.3 or greater between a test and training set can be used to give a global measure of confidence in model predictions. A final comparison to a method trained solely on active data from ChEMBL performed with precision-recall AUC and BEDROC scores of 0.45 and 0.76.ConclusionsThe inclusion of inactive data for model training produces models with superior AUC and improved early recognition capabilities, although the results from internal and external validation of the models show differing performance between the breadth of models. The realised target prediction protocol is available at https://github.com/lhm30/PIDGIN.Graphical abstractThe inclusion of large scale negative training data for in silico target prediction improves the precision and recall AUC and BEDROC scores for target models.

Dataset Information

Relating Chemical Structure to Cellular Response: An Integrative Analysis of Gene Expression, Bioactivity, and Structural Data Across 11,000 Compounds.

Publications

Relating Chemical Structure to Cellular Response: An Integrative Analysis of Gene Expression, Bioactivity, and Structural Data Across 11,000 Compounds.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets