toxCSM: comprehensive prediction of small molecule toxicity profiles

Abstract

Drug discovery is a lengthy, costly and high-risk endeavour that is further convoluted by high attrition rates in later development stages. Toxicity has been one of the main causes of failure during clinical trials, increasing drug development time and costs. To facilitate early identification and optimisation of toxicity profiles, several computational tools emerged aiming at improving success rates by timely pre-screening drug candidates. Despite these efforts, there is an increasing demand for platforms capable of assessing both environmental as well as human-based toxicity properties at large scale. Here, we present toxCSM, a comprehensive computational platform for the study and optimisation of toxicity profiles of small molecules. toxCSM leverages on the well-established concepts of graph-based signatures, molecular descriptors and similarity scores to develop 36 models for predicting a range of toxicity properties, which can assist in developing safer drugs and agrochemicals. toxCSM achieved an Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) of up to 0.99 and Pearson’s correlation coefficients of up to 0.94 on 10-fold cross-validation, with comparable performance on blind test sets, outperforming all alternative methods. toxCSM is freely available as a user-friendly web server and API at http://biosig.lab.uq.edu.au/toxcsm.

kinCSM: Using graph‐based signatures to predict small molecule CDK2 inhibitors

“…Users can identify CDK2 inhibitors, predict CDK2 pK i and possible binding modes by providing a single molecule or a list of molecules as SMILES strings (Figure 5 ). Moreover, users can also predict the toxicity profiles via toxCSM, 32 and selectivity profiles via SwissTarget 33 by clicking on the links on the result page to further prioritize safer, less toxic, and more selective CDK2 inhibitors for clinical usage.…”

“…Results are presented in a table, including predictions on CDK2 inhibitor (Yes or No), CDK2 pK i , binding modes based on different binary classifiers, and final decisions. Users also have the choice to show molecule depiction and properties via visualization controls, as well as redirecting to toxicity and selectivity predictions by toxCSM 32 and SwissTarget, 33 respectively…”

“…To address this Results are presented in a table, including predictions on CDK2 inhibitor (Yes or No), CDK2 pK i , binding modes based on different binary classifiers, and final decisions. Users also have the choice to show molecule depiction and properties via visualization controls, as well as redirecting to toxicity and selectivity predictions by toxCSM 32 and SwissTarget, 33 respectively problem, in our work, the datasets were split into lowredundancy training (70%) and blind test (30%). We ensured the molecules in the training and blind test sets have similar label distribution but are in different similarity clusters.…”

Engineering G protein‐coupled receptors for stabilization

“…The atom pharmacophores are characteristics belonging to eight possible classes: hydrophobic, positive, negative, hydrogen acceptor, hydrogen donor, aromatic, sulfur, and neutral. These signatures have shown to be an effective and efficient method to model protein residue environment, its geometry and physicochemical properties, information that has been used to predict the effects of mutations on protein stability and affinity to its partners (Myung, Pires, & Ascher, 2020 ; Myung, Rodrigues, et al, 2020 ; Nguyen et al, 2021 ; Pires et al, 2014 , 2016 ; Pires & Ascher, 2016 , 2017 ; Rodrigues et al, 2019 , 2021a ; 2021b , 2024 ; Rodrigues & Ascher, 2022 , 2023 ; Ryu et al, 2023 ), pharmacodynamic and pharmacokinetics (Al‐Jarf et al, 2021 ; de Sa et al, 2022 ; Iftkhar et al, 2022 ; Morozov et al, 2023 ; Pires et al, 2015 , 2022 ; Pires & Ascher, 2020 ; Rodrigues et al, 2021c , 2022 ; Velloso et al, 2021 ), and identify drug resistance (Hawkey et al, 2018 ; Karmakar et al, 2018 , 2019 , 2020 ; Portelli et al, 2020 ; Portelli, Heaton, & Ascher, 2023 ; Zhan et al, 2021 ; Zhou et al, 2021 ) and disease mutations (Jessen‐Howard et al, 2023 ; Karmakar et al, 2022 ; Lai et al, 2021 ; Portelli et al, 2021 ; Portelli, Albanaz, et al, 2023 ).…”

CSM-Toxin: A Web-Server for Predicting Protein Toxicity

“…While significant effort has been invested into the prediction and optimisation of peptides and proteins, the assessment of toxicity typically relies on expensive and time-consuming in-vivo assays late in the development process. Comparatively, we have seen that the introduction of rules and predictive algorithms to assess small molecule toxicities has helped to significantly reduce clinical trial failures [ 2 , 3 , 4 , 5 ].…”