Dataset Information

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

ABSTRACT: Biologics are one of the most rapidly expanding classes of therapeutics, but can be associated with a range of toxic properties. In small-molecule drug development, early identification of potential toxicity led to a significant reduction in clinical trial failures, however we currently lack robust qualitative rules or predictive tools for peptide- and protein-based biologics. To address this, we have manually curated the largest set of high-quality experimental data on peptide and protein toxicities, and developed CSM-Toxin, a novel in-silico protein toxicity classifier, which relies solely on the protein primary sequence. Our approach encodes the protein sequence information using a deep learning natural languages model to understand "biological" language, where residues are treated as words and protein sequences as sentences. The CSM-Toxin was able to accurately identify peptides and proteins with potential toxicity, achieving an MCC of up to 0.66 across both cross-validation and multiple non-redundant blind tests, outperforming other methods and highlighting the robust and generalisable performance of our model. We strongly believe the CSM-Toxin will serve as a valuable platform to minimise potential toxicity in the biologic development pipeline. Our method is freely available as an easy-to-use webserver.

SUBMITTER: Morozov V

PROVIDER: S-EPMC9966851 | biostudies-literature | 2023 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Morozov Vladimir V Rodrigues Carlos H M CHM Ascher David B DB

Pharmaceutics 20230128 2

Biologics are one of the most rapidly expanding classes of therapeutics, but can be associated with a range of toxic properties. In small-molecule drug development, early identification of potential toxicity led to a significant reduction in clinical trial failures, however we currently lack robust qualitative rules or predictive tools for peptide- and protein-based biologics. To address this, we have manually curated the largest set of high-quality experimental data on peptide and protein toxic ...[more]

PMID: 36839752

Similar Datasets

Project description:BackgroundThe emergence of drug resistant tuberculosis poses a serious concern globally and researchers are in rigorous search for new drugs to fight against these dreadful bacteria. Recently, the bacterial GlmU protein, involved in peptidoglycan, lipopolysaccharide and techoic acid synthesis, has been identified as an important drug target. A unique C-terminal disordered tail, essential for survival and the absence of gene in host makes GlmU a suitable target for inhibitor design.ResultsThis study describes the models developed for predicting inhibitory activity (IC50) of chemical compounds against GlmU protein using QSAR and docking techniques. These models were trained on 84 diverse compounds (GlmU inhibitors) taken from PubChem BioAssay (AID 1376). These inhibitors were docked in the active site of the C-terminal domain of GlmU protein (2OI6) using the AutoDock. A QSAR model was developed using docking energies as descriptors and achieved maximum correlation of 0.35/0.12 (r/r2) between actual and predicted pIC50. Secondly, QSAR models were developed using molecular descriptors calculated using various software packages and achieved maximum correlation of 0.77/0.60 (r/r2). Finally, hybrid models were developed using various types of descriptors and achieved high correlation of 0.83/0.70 (r/r2) between predicted and actual pIC50. It was observed that some molecular descriptors used in this study had high correlation with pIC50. We screened chemical libraries using models developed in this study and predicted 40 potential GlmU inhibitors. These inhibitors could be used to develop drugs against Mycobacterium tuberculosis.ConclusionThese results demonstrate that docking energies can be used as descriptors for developing QSAR models. The current work suggests that docking energies based descriptors could be used along with commonly used molecular descriptors for predicting inhibitory activity (IC50) of molecules against GlmU. Based on this study an open source platform, http://crdd.osdd.net/raghava/gdoq, has been developed for predicting inhibitors GlmU.

Project description:BACKGROUND: Machine learning-based methods have been proven to be powerful in developing new fold recognition tools. In our previous work [Zhang, Kochhar and Grigorov (2005) Protein Science, 14: 431-444], a machine learning-based method called DescFold was established by using Support Vector Machines (SVMs) to combine the following four descriptors: a profile-sequence-alignment-based descriptor using Psi-blast e-values and bit scores, a sequence-profile-alignment-based descriptor using Rps-blast e-values and bit scores, a descriptor based on secondary structure element alignment (SSEA), and a descriptor based on the occurrence of PROSITE functional motifs. In this work, we focus on the improvement of DescFold by incorporating more powerful descriptors and setting up a user-friendly web server. RESULTS: In seeking more powerful descriptors, the profile-profile alignment score generated from the COMPASS algorithm was first considered as a new descriptor (i.e., PPA). When considering a profile-profile alignment between two proteins in the context of fold recognition, one protein is regarded as a template (i.e., its 3D structure is known). Instead of a sequence profile derived from a Psi-blast search, a structure-seeded profile for the template protein was generated by searching its structural neighbors with the assistance of the TM-align structural alignment algorithm. Moreover, the COMPASS algorithm was used again to derive a profile-structural-profile-alignment-based descriptor (i.e., PSPA). We trained and tested the new DescFold in a total of 1,835 highly diverse proteins extracted from the SCOP 1.73 version. When the PPA and PSPA descriptors were introduced, the new DescFold boosts the performance of fold recognition substantially. Using the SCOP_1.73_40% dataset as the fold library, the DescFold web server based on the trained SVM models was further constructed. To provide a large-scale test for the new DescFold, a stringent test set of 1,866 proteins were selected from the SCOP 1.75 version. At a less than 5% false positive rate control, the new DescFold is able to correctly recognize structural homologs at the fold level for nearly 46% test proteins. Additionally, we also benchmarked the DescFold method against several well-established fold recognition algorithms through the LiveBench targets and Lindahl dataset. CONCLUSIONS: The new DescFold method was intensively benchmarked to have very competitive performance compared with some well-established fold recognition methods, suggesting that it can serve as a useful tool to assist in template-based protein structure prediction. The DescFold server is freely accessible at http://202.112.170.199/DescFold/index.html.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets