Abstract
Pharmaceutical or phytopharmaceutical molecules rely on the interaction with one or more specific molecular targets to induce their anticipated biological responses. Nonetheless, these compounds are also prone to interact with many other non-intended biological targets, also known as off-targets. Unfortunately, off-target identification is difficult and expensive. Consequently, QSAR models predicting the activity on a target have gained importance in drug discovery or in the de-risking of chemicals. However, a restricted number of targets are well characterized and hold enough data to build such in silico models. A good alternative to individual target evaluations is to use integrative evaluations such as transcriptomics obtained from compound-induced gene expression measurements derived from cell cultures. The advantage of these particular experiments is to capture the consequences of the interaction of compounds on many possible molecular targets and biological pathways, without having any constraints concerning the chemical space. In this work, we assessed the value of a large public dataset of compound-induced transcriptomic data, to predict compound activity on a selection of 69 molecular targets. We compared such descriptors with other QSAR descriptors, namely the Morgan fingerprints (similar to extended-connectivity fingerprints). Depending on the target, active compounds could show similar signatures in one or multiple cell lines, whether these active compounds shared similar or different chemical structures. Random forest models using gene expression signatures were able to perform similarly or better than counterpart models built with Morgan fingerprints for 25% of the target prediction tasks. These performances occurred mostly using signatures produced in cell lines showing similar signatures for active compounds toward the considered target. We show that compound-induced transcriptomic data could represent a great opportunity for target prediction, allowing to overcome the chemical space limitation of QSAR models.
Highlights
Signatures (GESs) of cell line responses to so-called perturbagens (Subramanian et al, 2017)
Gene Expression Signatures (GESs) is represented by an instance, that is a combination of a perturbagen, cell line, concentration and time point, and is composed by the plate-normalized expression z-scores of the whole genome, inferred from 978 landmark genes
We investigated the link between compound structure information (n = 9,035) and their corresponding induced biological responses captured by GESs (n = 39,544) in human tumor cell lines and evaluated the potential of machine learning approaches to infer about molecular targets involved in the compound bioactivity
Summary
Signatures (GESs) of cell line responses to so-called perturbagens (Subramanian et al, 2017). A commonly used technique is to compute descriptors from chemical structures, like the extended-connectivity fingerprints (ECFPs) and use them for prediction, relying on the quantitative structure-activity relationship (QSAR) principle, i.e., molecules sharing a similar structure may share a similar activity profile (Rogers and Hahn, 2010; Cherkasov et al, 2014) Such molecule descriptors show limitations: they do not perform well for all target prediction tasks depending on the quantity and quality of available activity data, prediction is limited to the applicability domain (depending on the training set used), and a small change in chemical structure can lead to a large change in biological response (activity cliffs). A large public CMAP L1000 dataset was released representing more than 300,000 Gene Expression
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
