{"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/progen-language-modeling-for-protein","title":"ProGen: Language Modeling for Protein Generation","arxiv_id":"2004.03497","date":"2020-03-08","proceeding":null,"authors":["Ali Madani","Bryan McCann","Nikhil Naik","Nitish Shirish Keskar","Namrata Anand","Raphael R. Eguchi","Po-Ssu Huang","Richard Socher"],"abstract":"Generative modeling for protein engineering is key to solving fundamental problems in synthetic biology, medicine, and material science. We pose protein engineering as an unsupervised sequence generation problem in order to leverage the exponentially growing set of proteins that lack costly, structural annotations. We train a 1.2B-parameter language model, ProGen, on ~280M protein sequences conditioned on taxonomic and keyword tags such as molecular function and cellular component. This provides ProGen with an unprecedented range of evolutionary sequence diversity and allows it to generate with fine-grained control as demonstrated by metrics based on primary sequence similarity, secondary structure accuracy, and conformational energy.","url_abs":"https://arxiv.org/abs/2004.03497v1","url_pdf":"https://arxiv.org/pdf/2004.03497v1.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":"progen-language-modeling-for-protein","repo_url":"https://github.com/lucidrains/progen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"progen-language-modeling-for-protein","repo_url":"https://github.com/lucidrains/progen-jax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.03497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03497"}},"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/lucidrains/progen-jax","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/progen","reach":null}],"summary":{"ran_fixture":1,"ran_violates":1,"ran_honours":3,"unverified":9},"by_repo_kind":{"listed":{"samples":14,"ran":5,"repositories":2}},"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":"7088a112a013d3a0","entry":"apply_rotary_pos_emb","repo":"lucidrains/progen","repo_kind":"listed","path":"progen_transformer/progen.py","file_url":"https://github.com/lucidrains/progen/blob/HEAD/progen_transformer/progen.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7088a112a013d3a0"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"progen_transformer/utils.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/progen_transformer/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"c2e3f2e143e65142","entry":"fixed_pos_embedding","repo":"lucidrains/progen","repo_kind":"listed","path":"progen_transformer/progen.py","file_url":"https://github.com/lucidrains/progen/blob/HEAD/progen_transformer/progen.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":"c2e3f2e143e65142"}},{"code_sha256_prefix":"5e2ed23acb71ee11","entry":"noop","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"progen_transformer/utils.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/progen_transformer/utils.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":"5e2ed23acb71ee11"}},{"code_sha256_prefix":"59c0bfea601f828d","entry":"rotate_every_two","repo":"lucidrains/progen","repo_kind":"listed","path":"progen_transformer/progen.py","file_url":"https://github.com/lucidrains/progen/blob/HEAD/progen_transformer/progen.py","link_basis":"first_harvest_node","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":"59c0bfea601f828d"}},{"code_sha256_prefix":"8f3fc2fd28cc770c","entry":"collate_fn","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"progen_transformer/data.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/progen_transformer/data.py","link_basis":"harvester_set","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":"8f3fc2fd28cc770c"}},{"code_sha256_prefix":"82e10e377256f226","entry":"fasta_row_to_sequence_strings","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"generate_data.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/generate_data.py","link_basis":"harvester_set","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":"82e10e377256f226"}},{"code_sha256_prefix":"03563ad6fe313230","entry":"file_get_last_checkpoint","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"progen_transformer/checkpoint.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/progen_transformer/checkpoint.py","link_basis":"harvester_set","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":"03563ad6fe313230"}},{"code_sha256_prefix":"bad2c74c90d94219","entry":"gcs_get_last_checkpoint","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"progen_transformer/checkpoint.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/progen_transformer/checkpoint.py","link_basis":"harvester_set","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":"bad2c74c90d94219"}},{"code_sha256_prefix":"17886a9cb6efdb96","entry":"get_annotations_from_description","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"generate_data.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/generate_data.py","link_basis":"harvester_set","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":"17886a9cb6efdb96"}},{"code_sha256_prefix":"db2d8c3632b26569","entry":"iterator_from_tfrecords_folder","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"progen_transformer/data.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/progen_transformer/data.py","link_basis":"harvester_set","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":"db2d8c3632b26569"}},{"code_sha256_prefix":"0bd02f1529386045","entry":"log","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"progen_transformer/utils.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/progen_transformer/utils.py","link_basis":"harvester_set","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":"0bd02f1529386045"}},{"code_sha256_prefix":"c601205d9879134a","entry":"order_dict_by","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"generate_data.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/generate_data.py","link_basis":"harvester_set","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":"c601205d9879134a"}},{"code_sha256_prefix":"48bc0d4ccdd99810","entry":"parse_fn","repo":"lucidrains/progen-jax","repo_kind":"listed","path":"progen_transformer/data.py","file_url":"https://github.com/lucidrains/progen-jax/blob/HEAD/progen_transformer/data.py","link_basis":"harvester_set","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":"48bc0d4ccdd99810"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}