CLC-Pred 2.0: A Freely Available Web Application for In Silico Prediction of Human Cell Line Cytotoxicity and Molecular Mechanisms of Action for Druglike Compounds

Abstract

In vitro cell-line cytotoxicity is widely used in the experimental studies of potential antineoplastic agents and evaluation of safety in drug discovery. In silico estimation of cytotoxicity against hundreds of tumor cell lines and dozens of normal cell lines considerably reduces the time and costs of drug development and the assessment of new pharmaceutical agent perspectives. In 2018, we developed the first freely available web application (CLC-Pred) for the qualitative prediction of cytotoxicity against 278 tumor and 27 normal cell lines based on structural formulas of 59,882 compounds. Here, we present a new version of this web application: CLC-Pred 2.0. It also employs the PASS (Prediction of Activity Spectra for Substance) approach based on substructural atom centric MNA descriptors and a Bayesian algorithm. CLC-Pred 2.0 provides three types of qualitative prediction: (1) cytotoxicity against 391 tumor and 47 normal human cell lines based on ChEMBL and PubChem data (128,545 structures) with a mean accuracy of prediction (AUC), calculated by the leave-one-out (LOO CV) and the 20-fold cross-validation (20F CV) procedures, of 0.925 and 0.923, respectively; (2) cytotoxicity against an NCI60 tumor cell-line panel based on the Developmental Therapeutics Program’s NCI60 data (22,726 structures) with different thresholds of IG50 data (100, 10 and 1 nM) and a mean accuracy of prediction from 0.870 to 0.945 (LOO CV) and from 0.869 to 0.942 (20F CV), respectively; (3) 2170 molecular mechanisms of actions based on ChEMBL and PubChem data (656,011 structures) with a mean accuracy of prediction 0.979 (LOO CV) and 0.978 (20F CV). Therefore, CLC-Pred 2.0 is a significant extension of the capabilities of the initial web application.

Angiotensin-converting enzyme inhibitors for ovarian cancer? — a new adjuvant option or a silent trap

“…We found that all ACE-Is could actually be active against the variety of ovarian cancer cells. The responsive models identified in our simulation included: A2780cisR (cisplatin-resistant ovarian carcinoma), A2780S (ovarian endometrioid adenocarcinoma), SK-OV3, OVCAR-3, OVCAR-4, OVCAR-5, OVCAR-8, IGROV1, NCI/ADR-RES and PA-1 at GI 50 threshold of 1nM and 10 nM [ 23 ]. The compounds with the highest probability of being cytotoxic were demonstrated in Table 1 .…”

“…The output yielded P a and P i values for each cell line, which corresponded to “probability of being active” and “probability of being inactive”, respectively. If the inequality P a > P i was fulfilled, the compound was considered more likely to belong to the subclass of active compounds than inactive ones, based on the similarity of chemical structure [ 23 ].…”

Exploring SureChEMBL from a drug discovery perspective

“…A large number of compound-centric biological databases have been established in the past decades [27][28][29] . These databases have served various purposes in drug discovery, from identifying the bioactivity of unknown compounds 30,31 to the prediction of mechanisms of action 32,33 , or simply for the virtual screening of drug candidates 34,35 . While previous research by Joerg Ohms (2022) explored the coverage of patent documents in relation to chemicals in two patent databases (SureChEMBL and Patentscope), the scope of this study was limited to manually comparing a set of chemicals between PubChem Substance and patent compounds 36 .…”

Medicinal chemistry lens on patent data in SureChEMBL

“…A large number of compounds-centric biology databases have been established in the past decades [38][39][40][41]. These databases have served various purposes in drug discovery, from identifying the bioactivity of unknown compounds [42,43] to the prediction of mechanism-of-action (MoA) [44,45] or simply for the virtual screening of drug candidates [46,47]. While previous research by Joerg Ohms (2021) explored the coverage of patent documents in relation to chemicals across patent databases, the author was restricted to comparing the compound coverage between PubChem and patent compounds [48].…”