{"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/a-text-guided-protein-design-framework","title":"A Text-guided Protein Design Framework","arxiv_id":"2302.04611","date":"2023-02-09","proceeding":null,"authors":["Shengchao Liu","Yanjing Li","Zhuoxinran Li","Anthony Gitter","Yutao Zhu","Jiarui Lu","Zhao Xu","Weili Nie","Arvind Ramanathan","Chaowei Xiao","Jian Tang","Hongyu Guo","Anima Anandkumar"],"abstract":"Current AI-assisted protein design mainly utilizes protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in the text format describing proteins' high-level functionalities. Yet, whether the incorporation of such text data can help protein design tasks has not been explored. To bridge this gap, we propose ProteinDT, a multi-modal framework that leverages textual descriptions for protein design. ProteinDT consists of three subsequent steps: ProteinCLAP which aligns the representation of two modalities, a facilitator that generates the protein representation from the text modality, and a decoder that creates the protein sequences from the representation. To train ProteinDT, we construct a large dataset, SwissProtCLAP, with 441K text and protein pairs. We quantitatively verify the effectiveness of ProteinDT on three challenging tasks: (1) over 90% accuracy for text-guided protein generation; (2) best hit ratio on 12 zero-shot text-guided protein editing tasks; (3) superior performance on four out of six protein property prediction benchmarks.","url_abs":"https://arxiv.org/abs/2302.04611v4","url_pdf":"https://arxiv.org/pdf/2302.04611v4.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":"a-text-guided-protein-design-framework","repo_url":"https://github.com/QizhiPei/Awesome-Biomolecule-Language-Cross-Modeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-text-guided-protein-design-framework","repo_url":"https://github.com/chao1224/proteindt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-text-guided-protein-design-framework","repo_url":"https://github.com/chao1224/chatdrug","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"protein-design","task_name":"Protein Design"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.04611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04611"}},"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/chao1224/proteindt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chao1224/chatdrug","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/QizhiPei/Awesome-Biomolecule-Language-Cross-Modeling","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"b822dd00427403bf","entry":"cycle_index","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b822dd00427403bf"}},{"code_sha256_prefix":"a12be407413bdb91","entry":"do_CL","repo":"chao1224/proteindt","repo_kind":"official","path":"examples/pretrain_step_01_CLAP.py","file_url":"https://github.com/chao1224/proteindt/blob/HEAD/examples/pretrain_step_01_CLAP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a12be407413bdb91"}},{"code_sha256_prefix":"a5cf0741e192b2c8","entry":"inference","repo":"chao1224/proteindt","repo_kind":"official","path":"examples/downstream_Text2Protein/step_02_inference_ProteinDT.py","file_url":"https://github.com/chao1224/proteindt/blob/HEAD/examples/downstream_Text2Protein/step_02_inference_ProteinDT.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":"a5cf0741e192b2c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}