{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Nguyen TB"],"funding":["National Health and Medical Research Council of Australia","Medical Research Council","Victorian Government’s Operational Infrastructure Support Program","Wellcome Trust"],"pagination":["bbab512"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC8769910"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["23(1)"],"pubmed_abstract":["Protein-carbohydrate interactions are crucial for many cellular processes but can be challenging to biologically characterise. To improve our understanding and ability to model these molecular interactions, we used a carefully curated set of 370 protein-carbohydrate complexes with experimental structural and biophysical data in order to train and validate a new tool, cutoff scanning matrix (CSM)-carbohydrate, using machine learning algorithms to accurately predict their binding affinity and rank docking poses as a scoring function. Information on both protein and carbohydrate complementarity, in terms of shape and chemistry, was captured using graph-based structural signatures. Across both training and independent test sets, we achieved comparable Pearson's correlations of 0.72 under cross"],"journal":["Briefings in bioinformatics"],"pubmed_title":["CSM-carbohydrate: protein-carbohydrate binding affinity prediction and docking scoring function."],"pmcid":["PMC8769910"],"funding_grant_id":["093167/Z/10/Z","GNT1174405","MR/M026302/1"],"pubmed_authors":["Nguyen TB","Ascher DB","Pires DEV"],"additional_accession":[]},"is_claimable":false,"name":"CSM-carbohydrate: protein-carbohydrate binding affinity prediction and docking scoring function.","description":"Protein-carbohydrate interactions are crucial for many cellular processes but can be challenging to biologically characterise. To improve our understanding and ability to model these molecular interactions, we used a carefully curated set of 370 protein-carbohydrate complexes with experimental structural and biophysical data in order to train and validate a new tool, cutoff scanning matrix (CSM)-carbohydrate, using machine learning algorithms to accurately predict their binding affinity and rank docking poses as a scoring function. Information on both protein and carbohydrate complementarity, in terms of shape and chemistry, was captured using graph-based structural signatures. Across both training and independent test sets, we achieved comparable Pearson's correlations of 0.72 under cross","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Jan","modification":"2026-07-09T12:15:39.13Z","creation":"2025-05-29T21:24:07.464Z"},"accession":"S-EPMC8769910","cross_references":{"pubmed":["34882232"],"doi":["10.1093/bib/bbab512"]}}