{"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/prottrans-towards-cracking-the-language-of","title":"ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing","arxiv_id":"2007.06225","date":"2020-07-13","proceeding":null,"authors":["Ahmed Elnaggar","Michael Heinzinger","Christian Dallago","Ghalia Rihawi","Yu Wang","Llion Jones","Tom Gibbs","Tamas Feher","Christoph Angerer","Martin Steinegger","Debsindhu Bhowmik","Burkhard Rost"],"abstract":"Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models taken from NLP. These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids. The LMs were trained on the Summit supercomputer using 5616 GPUs and TPU Pod up-to 1024 cores. Dimensionality reduction revealed that the raw protein LM-embeddings from unlabeled data captured some biophysical features of protein sequences. We validated the advantage of using the embeddings as exclusive input for several subsequent tasks. The first was a per-residue prediction of protein secondary structure (3-state accuracy Q3=81%-87%); the second were per-protein predictions of protein sub-cellular localization (ten-state accuracy: Q10=81%) and membrane vs. water-soluble (2-state accuracy Q2=91%). For the per-residue predictions the transfer of the most informative embeddings (ProtT5) for the first time outperformed the state-of-the-art without using evolutionary information thereby bypassing expensive database searches. Taken together, the results implied that protein LMs learned some of the grammar of the language of life. To facilitate future work, we released our models at https://github.com/agemagician/ProtTrans.","url_abs":"https://arxiv.org/abs/2007.06225v3","url_pdf":"https://arxiv.org/pdf/2007.06225v3.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":"prottrans-towards-cracking-the-language-of","repo_url":"https://github.com/agemagician/ProtTrans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"protein-secondary-structure-prediction","task_name":"Protein Secondary Structure Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/protein-secondary-structure-prediction-on-5","task":"Protein Secondary Structure Prediction","dataset":"CASP12","model":"ProtT5-XL-UniRef50","rank_in_archive_order":1,"of":4,"metrics":{"Q3":"0.81","Q8":"0.70"},"uses_additional_data":false},{"leaderboard":"/sota/protein-secondary-structure-prediction-on-5","task":"Protein Secondary Structure Prediction","dataset":"CASP12","model":"ProtT5-XL-BFD","rank_in_archive_order":2,"of":4,"metrics":{"Q3":"0.77","Q8":"0.66"},"uses_additional_data":false},{"leaderboard":"/sota/protein-secondary-structure-prediction-on-5","task":"Protein Secondary Structure Prediction","dataset":"CASP12","model":"ProtBert-BFD","rank_in_archive_order":3,"of":4,"metrics":{"Q3":"0.76","Q8":"0.65"},"uses_additional_data":false},{"leaderboard":"/sota/protein-secondary-structure-prediction-on-1","task":"Protein Secondary Structure Prediction","dataset":"CB513","model":"ProtT5-XL-UniRef50","rank_in_archive_order":3,"of":10,"metrics":{"Q3":"0.86","Q8":"0.74"},"uses_additional_data":false},{"leaderboard":"/sota/protein-secondary-structure-prediction-on-1","task":"Protein Secondary Structure Prediction","dataset":"CB513","model":"ProtT5-XL-BFD","rank_in_archive_order":6,"of":10,"metrics":{"Q3":"0.84","Q8":"0.71"},"uses_additional_data":false},{"leaderboard":"/sota/protein-secondary-structure-prediction-on-1","task":"Protein Secondary Structure Prediction","dataset":"CB513","model":"ProtBert-BFD","rank_in_archive_order":7,"of":10,"metrics":{"Q3":"0.83","Q8":"0.7"},"uses_additional_data":false},{"leaderboard":"/sota/protein-secondary-structure-prediction-on-6","task":"Protein Secondary Structure Prediction","dataset":"TS115","model":"ProtT5-XL-UniRef50","rank_in_archive_order":1,"of":4,"metrics":{"Q3":"0.87","Q8":"0.77"},"uses_additional_data":false},{"leaderboard":"/sota/protein-secondary-structure-prediction-on-6","task":"Protein Secondary Structure Prediction","dataset":"TS115","model":"ProtT5-XL-BFD","rank_in_archive_order":2,"of":4,"metrics":{"Q3":"0.85","Q8":"0.74"},"uses_additional_data":false},{"leaderboard":"/sota/protein-secondary-structure-prediction-on-6","task":"Protein Secondary Structure Prediction","dataset":"TS115","model":"ProtBert-BFD","rank_in_archive_order":3,"of":4,"metrics":{"Q3":"0.84","Q8":"0.73"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.06225","atlas_url":"https://app.syntology.ai/?focus=2007.06225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06225"}},"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/agemagician/ProtTrans","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":"64fbbbd482d64555","entry":"get_T5_model","repo":"agemagician/ProtTrans","repo_kind":"official","path":"Embedding/prott5_embedder.py","file_url":"https://github.com/agemagician/ProtTrans/blob/HEAD/Embedding/prott5_embedder.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":"64fbbbd482d64555"}},{"code_sha256_prefix":"dd492312bc93c287","entry":"get_embeddings","repo":"agemagician/ProtTrans","repo_kind":"official","path":"Embedding/prott5_embedder.py","file_url":"https://github.com/agemagician/ProtTrans/blob/HEAD/Embedding/prott5_embedder.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":"dd492312bc93c287"}},{"code_sha256_prefix":"2a859e94861d79e9","entry":"read_fasta","repo":"agemagician/ProtTrans","repo_kind":"official","path":"Embedding/prott5_embedder.py","file_url":"https://github.com/agemagician/ProtTrans/blob/HEAD/Embedding/prott5_embedder.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":"2a859e94861d79e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}