{"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/freed-improving-rl-agents-for-fragment-based","title":"FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproduction","arxiv_id":"2401.09840","date":"2024-01-18","proceeding":null,"authors":["Alexander Telepov","Artem Tsypin","Kuzma Khrabrov","Sergey Yakukhnov","Pavel Strashnov","Petr Zhilyaev","Egor Rumiantsev","Daniel Ezhov","Manvel Avetisian","Olga Popova","Artur Kadurin"],"abstract":"A rational design of new therapeutic drugs aims to find a molecular structure with desired biological functionality, e.g., an ability to activate or suppress a specific protein via binding to it. Molecular docking is a common technique for evaluating protein-molecule interactions. Recently, Reinforcement Learning (RL) has emerged as a promising approach to generating molecules with the docking score (DS) as a reward. In this work, we reproduce, scrutinize and improve the recent RL model for molecule generation called FREED (arXiv:2110.01219). Extensive evaluation of the proposed method reveals several limitations and challenges despite the outstanding results reported for three target proteins. Our contributions include fixing numerous implementation bugs and simplifying the model while increasing its quality, significantly extending experiments, and conducting an accurate comparison with current state-of-the-art methods for protein-conditioned molecule generation. We show that the resulting fixed model is capable of producing molecules with superior docking scores compared to alternative approaches.","url_abs":"https://arxiv.org/abs/2401.09840v1","url_pdf":"https://arxiv.org/pdf/2401.09840v1.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":"freed-improving-rl-agents-for-fragment-based","repo_url":"https://github.com/airi-institute/ffreed","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"molecular-docking","task_name":"Molecular Docking"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.09840","atlas_url":"https://app.syntology.ai/?focus=2401.09840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09840"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ffreed","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":"9955da56a485cdfd","entry":"HSF","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/env/reward.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/env/reward.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9955da56a485cdfd"}},{"code_sha256_prefix":"4542b8f7b6c43580","entry":"ReLU","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/env/reward.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/env/reward.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4542b8f7b6c43580"}},{"code_sha256_prefix":"ba5df7ab771cb02c","entry":"brics_compatible","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/env/utils.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/env/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":"ba5df7ab771cb02c"}},{"code_sha256_prefix":"9910e2fc297f8665","entry":"identity","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/env/reward.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/env/reward.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9910e2fc297f8665"}},{"code_sha256_prefix":"a18ae998f817f851","entry":"lmap","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/utils.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/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":"a18ae998f817f851"}},{"code_sha256_prefix":"7d0881a0d7a421a8","entry":"log_time","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/train/utils.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/train/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":"7d0881a0d7a421a8"}},{"code_sha256_prefix":"b0cf9a70a462ead4","entry":"read_json","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/utils.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/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":"b0cf9a70a462ead4"}},{"code_sha256_prefix":"f93a33caebf99076","entry":"str2strs","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/args.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/args.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f93a33caebf99076"}},{"code_sha256_prefix":"a0e4ddb131be1778","entry":"read_mols","repo":"airi-institute/ffreed","repo_kind":"official","path":"ffreed/utils.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0e4ddb131be1778"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}