{"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/gradual-optimization-learning-for","title":"Gradual Optimization Learning for Conformational Energy Minimization","arxiv_id":"2311.06295","date":"2023-11-05","proceeding":null,"authors":["Artem Tsypin","Leonid Ugadiarov","Kuzma Khrabrov","Alexander Telepov","Egor Rumiantsev","Alexey Skrynnik","Aleksandr I. Panov","Dmitry Vetrov","Elena Tutubalina","Artur Kadurin"],"abstract":"Molecular conformation optimization is crucial to computer-aided drug discovery and materials design. Traditional energy minimization techniques rely on iterative optimization methods that use molecular forces calculated by a physical simulator (oracle) as anti-gradients. However, this is a computationally expensive approach that requires many interactions with a physical simulator. One way to accelerate this procedure is to replace the physical simulator with a neural network. Despite recent progress in neural networks for molecular conformation energy prediction, such models are prone to distribution shift, leading to inaccurate energy minimization. We find that the quality of energy minimization with neural networks can be improved by providing optimization trajectories as additional training data. Still, it takes around $5 \\times 10^5$ additional conformations to match the physical simulator's optimization quality. In this work, we present the Gradual Optimization Learning Framework (GOLF) for energy minimization with neural networks that significantly reduces the required additional data. The framework consists of an efficient data-collecting scheme and an external optimizer. The external optimizer utilizes gradients from the energy prediction model to generate optimization trajectories, and the data-collecting scheme selects additional training data to be processed by the physical simulator. Our results demonstrate that the neural network trained with GOLF performs on par with the oracle on a benchmark of diverse drug-like molecules using $50$x less additional data.","url_abs":"https://arxiv.org/abs/2311.06295v2","url_pdf":"https://arxiv.org/pdf/2311.06295v2.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":"gradual-optimization-learning-for","repo_url":"https://github.com/airi-institute/golf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.06295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06295"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/airi-institute/golf","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9},"by_repo_kind":{"official":{"samples":9,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bb450a928edb1ffa","entry":"aggregate2string","repo":"airi-institute/golf","repo_kind":"official","path":"evaluate_batch_dft.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/evaluate_batch_dft.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb450a928edb1ffa"}},{"code_sha256_prefix":"2e63244f4af8ee6b","entry":"calculate_dft_energy_tcp_client","repo":"airi-institute/golf","repo_kind":"official","path":"env/dft.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/env/dft.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e63244f4af8ee6b"}},{"code_sha256_prefix":"7c532365402d1a64","entry":"get_lr_scheduler","repo":"airi-institute/golf","repo_kind":"official","path":"GOLF/utils.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/GOLF/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c532365402d1a64"}},{"code_sha256_prefix":"d7a78068f73dfc9f","entry":"mean_std","repo":"airi-institute/golf","repo_kind":"official","path":"read_evaluation_metrics.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/read_evaluation_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7a78068f73dfc9f"}},{"code_sha256_prefix":"f2718c3c137d1590","entry":"outliers_fraction","repo":"airi-institute/golf","repo_kind":"official","path":"read_evaluation_metrics.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/read_evaluation_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2718c3c137d1590"}},{"code_sha256_prefix":"892727a56439fd79","entry":"read_metrics","repo":"airi-institute/golf","repo_kind":"official","path":"evaluate_batch_dft.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/evaluate_batch_dft.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"892727a56439fd79"}},{"code_sha256_prefix":"9eae9feb6656ee86","entry":"read_metrics","repo":"airi-institute/golf","repo_kind":"official","path":"read_evaluation_metrics.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/read_evaluation_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9eae9feb6656ee86"}},{"code_sha256_prefix":"6061e72c09ebd282","entry":"recv_one_message","repo":"airi-institute/golf","repo_kind":"official","path":"env/dft.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/env/dft.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6061e72c09ebd282"}},{"code_sha256_prefix":"f33201b615cc0380","entry":"recvall","repo":"airi-institute/golf","repo_kind":"official","path":"env/dft.py","file_url":"https://github.com/airi-institute/golf/blob/HEAD/env/dft.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f33201b615cc0380"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}