{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/scorch2-a-generalised-heterogeneous-consensus","title":"SCORCH2: a generalised heterogeneous consensus model for high-enrichment interaction-based virtual screening","arxiv_id":null,"date":"2025-04-05","proceeding":"bioRxiv 2025 4","authors":["Lin Chen","Vincent Blay","Pedro J. Ballester","Douglas R. Houston"],"abstract":"The discovery of effective therapeutics remains a complex, costly, and time-consuming endeavor, characterized\r\nby high failure rates and significant resource investments. A central bottleneck in early-stage drug discovery is\r\nidentifying suitable hit compounds with moderate affinity for known biological targets. Although advancements have\r\nbeen made, current in silico virtual screening methods are subject to limitations, including model overfitting, data\r\nbias, and constrained interpretability in their predictive processes. In this study, we present SCORCH2, a machine\r\nlearning-based framework designed to enhance both the performance and interpretability of virtual screening by\r\nleveraging interaction features. Compared with its predecessor SCORCH, SCORCH2 exhibits superior predictive\r\naccuracy and generalizability across a wide range of biological targets. Importantly, SCORCH2 demonstrates robust\r\nhit identification capabilities on previously unseen targets, indicating strong transferability. These results highlight\r\nthe potential of SCORCH2 as a valuable tool in accelerating drug discovery, offering reliable predictive capabilities\r\nwhile improving the interpretability of virtual screening models.","url_abs":"https://www.biorxiv.org/content/10.1101/2025.03.31.646332v1.article-metrics","url_pdf":"https://www.biorxiv.org/content/10.1101/2025.03.31.646332v1.article-metrics","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"scorch2-a-generalised-heterogeneous-consensus","repo_url":"https://github.com/LinCompbio/SCORCH2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}