{"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/mol-instructions-a-large-scale-biomolecular","title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","arxiv_id":"2306.08018","date":"2023-06-13","proceeding":null,"authors":["Yin Fang","Xiaozhuan Liang","Ningyu Zhang","Kangwei Liu","Rui Huang","Zhuo Chen","Xiaohui Fan","Huajun Chen"],"abstract":"Large Language Models (LLMs), with their remarkable task-handling capabilities and innovative outputs, have catalyzed significant advancements across a spectrum of fields. However, their proficiency within specialized domains such as biomolecular studies remains limited. To address this challenge, we introduce Mol-Instructions, a comprehensive instruction dataset designed for the biomolecular domain. Mol-Instructions encompasses three key components: molecule-oriented instructions, protein-oriented instructions, and biomolecular text instructions. Each component aims to improve the understanding and prediction capabilities of LLMs concerning biomolecular features and behaviors. Through extensive instruction tuning experiments on LLMs, we demonstrate the effectiveness of Mol-Instructions in enhancing large models' performance in the intricate realm of biomolecular studies, thus fostering progress in the biomolecular research community. Mol-Instructions is publicly available for ongoing research and will undergo regular updates to enhance its applicability.","url_abs":"https://arxiv.org/abs/2306.08018v5","url_pdf":"https://arxiv.org/pdf/2306.08018v5.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":"mol-instructions-a-large-scale-biomolecular","repo_url":"https://github.com/zjunlp/mol-instructions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"catalytic-activity-prediction","task_name":"Catalytic activity prediction"},{"task_slug":"chemical-entity-recognition","task_name":"Chemical Entity Recognition"},{"task_slug":"chemical-disease-interaction-extraction","task_name":"Chemical-Disease Interaction Extraction"},{"task_slug":"chemical-protein-interaction-extraction","task_name":"Chemical-Protein Interaction Extraction"},{"task_slug":"description-guided-molecule-generation","task_name":"Description-guided molecule generation"},{"task_slug":"domain-motif-prediction","task_name":"Domain/Motif Prediction"},{"task_slug":"forward-reaction-prediction","task_name":"Forward reaction prediction"},{"task_slug":"functional-description-generation","task_name":"Functional Description Generation"},{"task_slug":"molecular-description-generation","task_name":"Molecular description generation"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"protein-design","task_name":"Protein Design"},{"task_slug":"protein-function-prediction","task_name":"Protein Function Prediction"},{"task_slug":"reagent-prediction","task_name":"Reagent Prediction"},{"task_slug":"retrosynthesis","task_name":"Retrosynthesis"},{"task_slug":"true-or-false-question-answering","task_name":"True or False Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.08018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08018"}},"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/zjunlp/mol-instructions","reach":null}],"summary":{"ran_honours":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"e54b96edfadaf179","entry":"calculate_accuracy","repo":"zjunlp/mol-instructions","repo_kind":"official","path":"evaluation/biotext/chemical_disease_interaction_extraction.py","file_url":"https://github.com/zjunlp/mol-instructions/blob/HEAD/evaluation/biotext/chemical_disease_interaction_extraction.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e54b96edfadaf179"}},{"code_sha256_prefix":"ed2b06461d8b098d","entry":"calculate_f1_score","repo":"zjunlp/mol-instructions","repo_kind":"official","path":"evaluation/biotext/chemical_disease_interaction_extraction.py","file_url":"https://github.com/zjunlp/mol-instructions/blob/HEAD/evaluation/biotext/chemical_disease_interaction_extraction.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed2b06461d8b098d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}