{"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/lo-hi-practical-ml-drug-discovery-benchmark-1","title":"Lo-Hi: Practical ML Drug Discovery Benchmark","arxiv_id":"2310.06399","date":"2023-10-10","proceeding":"NeurIPS 2023 11","authors":["Simon Steshin"],"abstract":"Finding new drugs is getting harder and harder. One of the hopes of drug discovery is to use machine learning models to predict molecular properties. That is why models for molecular property prediction are being developed and tested on benchmarks such as MoleculeNet. However, existing benchmarks are unrealistic and are too different from applying the models in practice. We have created a new practical \\emph{Lo-Hi} benchmark consisting of two tasks: Lead Optimization (Lo) and Hit Identification (Hi), corresponding to the real drug discovery process. For the Hi task, we designed a novel molecular splitting algorithm that solves the Balanced Vertex Minimum $k$-Cut problem. We tested state-of-the-art and classic ML models, revealing which works better under practical settings. We analyzed modern benchmarks and showed that they are unrealistic and overoptimistic. Review: https://openreview.net/forum?id=H2Yb28qGLV Lo-Hi benchmark: https://github.com/SteshinSS/lohi_neurips2023 Lo-Hi splitter library: https://github.com/SteshinSS/lohi_splitter","url_abs":"https://arxiv.org/abs/2310.06399v1","url_pdf":"https://arxiv.org/pdf/2310.06399v1.pdf","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":"lo-hi-practical-ml-drug-discovery-benchmark-1","repo_url":"https://github.com/steshinss/lohi_neurips2023","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"lo-hi-practical-ml-drug-discovery-benchmark-1","repo_url":"https://github.com/steshinss/lohi_splitter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}