{"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/rita-a-study-on-scaling-up-generative-protein","title":"RITA: a Study on Scaling Up Generative Protein Sequence Models","arxiv_id":"2205.05789","date":"2022-05-11","proceeding":null,"authors":["Daniel Hesslow","Niccoló Zanichelli","Pascal Notin","Iacopo Poli","Debora Marks"],"abstract":"In this work we introduce RITA: a suite of autoregressive generative models for protein sequences, with up to 1.2 billion parameters, trained on over 280 million protein sequences belonging to the UniRef-100 database. Such generative models hold the promise of greatly accelerating protein design. We conduct the first systematic study of how capabilities evolve with model size for autoregressive transformers in the protein domain: we evaluate RITA models in next amino acid prediction, zero-shot fitness, and enzyme function prediction, showing benefits from increased scale. We release the RITA models openly, to the benefit of the research community.","url_abs":"https://arxiv.org/abs/2205.05789v2","url_pdf":"https://arxiv.org/pdf/2205.05789v2.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":"rita-a-study-on-scaling-up-generative-protein","repo_url":"https://github.com/lightonai/rita","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rita-a-study-on-scaling-up-generative-protein","repo_url":"https://github.com/oatml-markslab/proteingym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"rita-a-study-on-scaling-up-generative-protein","repo_url":"https://github.com/oatml-markslab/tranception","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"rita-a-study-on-scaling-up-generative-protein","repo_url":"https://github.com/MindCode-4/code-13/tree/main/RITA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"protein-design","task_name":"Protein Design"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.05789","atlas_url":"https://app.syntology.ai/?focus=2205.05789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05789"}},"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/MindCode-4/code-13/tree/main/RITA","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lightonai/rita","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oatml-markslab/proteingym","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oatml-markslab/tranception","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":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":0,"samples":[{"code_sha256_prefix":"2400426b114038c3","entry":"calc_fitness","repo":"lightonai/rita","repo_kind":"official","path":"compute_fitness.py","file_url":"https://github.com/lightonai/rita/blob/HEAD/compute_fitness.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":"2400426b114038c3"}},{"code_sha256_prefix":"e41e1d19bf181625","entry":"get_mutated_sequence","repo":"lightonai/rita","repo_kind":"official","path":"compute_fitness.py","file_url":"https://github.com/lightonai/rita/blob/HEAD/compute_fitness.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":"e41e1d19bf181625"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}