Meta tags:
description=Official repository for the ProteinGym benchmarks. Contribute to OATML-Markslab/ProteinGym development by creating an account on GitHub.;

Headings (most frequently used words):

uh, oh, proteingym, navigation, saved, searches, to, results, and, files, resources, releases, license, footer, new, search, code, repositories, users, issues, pull, requests, provide, feedback, oatml, markslab, menu, use, filter, your, more, quickly, folders, latest, commit, history, repository, table, of, contents, overview, how, contribute, usage, reproducibility, acknowledgements, reference, links, about, packages, contributors, languages, benchmarks, leaderboard, assays, baselines, notes, topics, stars, watchers, forks,

Text of the page (most frequently used words):
the (114), and (82), for (53), github (41), https (35), protein (34), sequence (34), dms (32), model (31), com (30), all (28), #proteingym (27), #benchmark (24), with (24), zip (23), msa (22), assays (20), single (20), benchmarks (19), are (19), clinical (19), this (18), structure (17), baselines (16), code (15), files (15), you (14), substitutions (14), models (14), scores (13), please (12), prediction (11), marks (11), from (11), performance (11), new (11), indels (11), language (11), security (10), your (10), license (9), file (9), following (9), esm (9), assay (9), 2022 (9), reload (8), fitness (8), neurips (8), zero (8), shot (8), relevant (8), script (8), scripts (8), 2024 (8), nature (8), effects (8), deep (8), was (7), resources (7), version (7), download (7), substitution (7), raw (7), filename (7), view (7), not (6), error (6), 2025 (6), repository (6), design (6), link (6), website (6), notin (6), reference (6), supervised (6), saprot (6), these (6), oatml (6), markslab (6), our (6), scoring (6), proteins (6), learning (6), zhou (6), enterprise (6), that (5), community (5), navigation (5), there (5), while (5), loading (5), page (5), 2023 (5), use (5), available (5), xtrimopglm (5), venusrem (5), mutation (5), protssn (5), gemme (5), poet (5), mulan (5), prosst (5), transformer (5), data (5), run (5), each (5), metrics (5), how (5), across (5), name (5), tan (5), rives (5), variant (5), yang (5), generative (5), 2021 (5), variants (5), search (5), releases (4), readme (4), gal (4), progen3 (4), proteingym_v1 (4), s3f (4), escott (4), using (4), corresponding (4), have (4), would (4), like (4), rsalor (4), aido (4), repo (4), tranception (4), rita (4), proteinmpnn (4), protgpt2 (4), unirep (4), scoring_dms_zero_shot (4), config (4), see (4), requests (4), mutants (4), methods (4), open (4), should (4), function (4), detailed (4), needs (4), also (4), predicted (4), based (4), wang (4), liu (4), verkuil (4), sercu (4), effect (4), mutational (4), sequences (4), more (4), results (4), dms_score (4), actions (4), quality (4), issues (4), support (4), can (3), latest (3), stars (3), mit (3), topics (3), org (3), proceedings (3), paper (3), kollasch (3), frazer (3), dias (3), work (3), under (3), added (3), esm3 (3), teams (3), bib (3), siterm (3), ai4protein (3), vespa (3), progen2 (3), eve (3), repositories (3), merge (3), json (3), various (3), follow (3), steps (3), only (3), which (3), indel (3), source (3), set (3), issue (3), number (3), family (3), aggregated (3), include (3), follows (3), size (3), folds (3), inverse (3), folding (3), unzip (3), song (3), enable (3), biorxiv (3), scaling (3), rao (3), representation (3), liang (3), hong (3), bingxin (3), retrieval (3), icml (3), meier (3), 2019 (3), ingraham (3), variation (3), sander (3), includes (3), depth (3), spearman (3), different (3), mutated (3), environments (3), commit (3), insights (3), pull (3), signed (3), settings (3), another (3), tab (3), window (3), refresh (3), session (3), sign (3), saved (3), documentation (3), feedback (3), grade (3), features (3), copilot (3), platform (3), solutions (3), explore (3), time (2), information (2), manage (2), footer (2), inc (2), other (2), python (2), report (2), forks (2), 450 (2), biology (2), official (2), huggingface (2), pypi (2), zenodo (2), abstract (2), www (2), links (2), large (2), scale (2), curran (2), pascal (2), ritter (2), van (2), niekerk (2), han (2), debora (2), level (2), predictions (2), consider (2), papers (2), team (2), providing (2), integrating (2), their (2), tekpinar (2), prescott (2), foldseek (2), microsoft (2), mif (2), carp (2), dauparas (2), hmmer (2), evmutation (2), combining (2), evolutionary (2), compute (2), acknowledgements (2), performance_substitutions (2), create (2), add (2), step (2), per (2), instructions (2), above (2), usage (2), reproducibility (2), currently (2), into (2), considering (2), wide (2), able (2), same (2), raise (2), label (2), submit (2), two (2), example (2), similar (2), subfolder (2), named (2), well (2), high (2), dataset (2), contribute (2), unzipped (2), before (2), weights (2), msas (2), structures (2), 200mb (2), dms_proteingym_substitutions (2), specific (2), table (2), below (2), used (2), cheng (2), understanding (2), ruffolo (2), madani (2), functional (2), gong (2), zeng (2), tang (2), unified (2), lin (2), thomas (2), hsu (2), million (2), evolution (2), science (2), conservation (2), predicting (2), lab (2), enhanced (2), carbone (2), aware (2), epistatic (2), missense (2), modeling (2), daria (2), encoding (2), zanichelli (2), transformers (2), trancepteve (2), gomez (2), autoregressive (2), arxiv (2), abs (2), unsupervised (2), communications (2), human (2), mutations (2), disease (2), riesselman (2), hopf (2), poelwijk (2), schärfe (2), springer (2), 2017 (2), biotechnology (2), 128 (2), 135 (2), input (2), full (2), folder (2), csv (2), aggregating (2), categories (2), auc (2), setting (2), details (2), provide (2), fit (2), pathogenic (2), benign (2), corresponds (2), experimental (2), higher (2), present (2), they (2), str (2), amino (2), acid (2), position (2), replaced (2), overview (2), setup (2), gitignore (2), reference_files (2), notebooks (2), 219 (2), commits (2), last (2), message (2), menu (2), projects (2), appearance (2), cancel (2), searches (2), business (2), advanced (2), developer (2), customer (2), services (2), devops (2), app (2), perform, action, share, personal, cookies, contact, docs, status, privacy, terms, 2026, shell, tex, html, languages, contributors, packages, apr, pg_v1, watching, watchers, custom, properties, activity, computational, about, preprint, year, volume, paper_files, cac723e5ff29f65e3fcbb0739ae91bee, datasets_and_benchmarks, pdf, url, title, associates, publisher, 64331, 64379, pages, neumann, globerson, saenko, hardt, levine, editor, advances, neural, processing, systems, booktitle, aaron, daniel, lood, paul, steffanie, spinner, rollins, nathan, shaw, ada, orenbuch, rose, weitzman, ruben, jonathan, mafalda, franceschi, dinko, yarin, author, neurips2023_cac723e5, inproceedings, cite, project, found, updates, addition, initial, release, special, thanks, experimentalists, who, developed, performed, built, citing, facilitate, prepared, containing, bibtex, entries, thank, earlier, vespag, genbio, profluent, biomap, research, evolutionaryscale, songlab, cal, cherryml, deepgraphlearning, 3biocompbio, http, gitlab, lcqb, upmc, dfrolova, openproteinai, westlake, repl, steineggerlab, rostlab, lightonai, nferruz, rmrao, eddyrivaslab, salesforce, progen, debbiemarkslab, evcouplings, facebookresearch, hub, docker, elodielaine, chloechsu, labelled, churchlab, codebase, leveraged, focusing, will, adding, adjust, accordingly, path, dms_output_score_folder_subs, update, paths, downloaded, prior, locally, december, training, evaluating, shared, process, proteinnpt, notes, stage, given, provided, requester, but, planning, regularly, ourselves, adoption, suggestions, many, upvotes, reproduce, needed, score, ensure, compared, exactly, everywhere, point, satisfying, conditions, checkpoints, reporting, note, correct, biases, groupings, thus, resulting, arithmetic, average, things, bash, hyperparameters, dependencies, required, properly, included, has, sufficiently, dynamic, range, insufficient, measurements, related, exclude, utr, trna, promoter, etc, publicly, suggest, part, new_assay, criteria, typically, inclusion, indels_raw_clinical, 4mb, substitutions_raw_clinical, 58mb, indels_raw_dms, 450mb, substitutions_raw_dms, 500mb, then, host, preprocessing, cv_folds_indels, 19mb, cv_folds_multiples_substitutions, 81m, multiples, cv_folds_singles_substitutions, 50m, singles, zero_shot_clinical_indels_scores, 7gb, zero_shot_clinical_substitutions_scores, 9gb, clinical_msa_weights, 250mb, clinical_msa_files, 8gb, clinical_proteingym_indels, 8mb, clinical_proteingym_substitutions, 123mb, proteingym_af2_structures, 84mb, dms_msa_weights, redundancy, dms_msa_files, 2gb, multiple, alignments, dms_supervised_indels_scores, 215mb, dms_supervised_substitutions_scores, 3gb, zero_shot_indels_scores, 313mb, zero_shot_substitutions_scores, 4gb, dms_proteingym_indels, 0gb, curl, hms, harvard, edu, proteingym_, template, replacing, desired, want, listed, dbnsfp, manuscript, appendix, clinical_benchmark_notebooks, clinical_subs_processing, ipynb, sun, zou, tao, mahbub, zhuang, xing, mixture, experts, efficient, effective, bhatnagar, jain, beazer, hoffnagle, ching, martyn, nayfach, unlocks, broader, generation, deeper, 649055, chen, geng, bei, dong, 100, billion, parameter, pretrained, deciphering, hayes, akin, sofroniew, oktay, tran, deaton, wiggert, badkundri, shafkat, derry, molina, khan, mishra, kim, bartie, nemeth, candido, simulating, 500, years, sebastian, prillo, wilson, yun, ultrafast, classical, phylogenetic, method, beats, zuobai, zhang, yining, huang, aurelie, lozano, vijil, chenthamarakshan, payel, das, jian, multi, matsvei, tsishyn, pauline, hermans, fabrizio, pucci, marianne, rooman, residue, solvent, accessibility, almost, need, ruilin, banghao, throughput, evaluation, wet, studies, advancing, ismb, eccb, mustafa, laurent, david, henry, alessandra, population, structural, accurately, predicts, medrxiv, mingchen, xinzhu, bozitao, zhong, huiqun, ziyi, wanli, ouyang, pan, quantized, disentangled, attention, frolova, marina, pak, anna, litvin, ilya, sharov, dmitry, ivankov, ivan, oseledets, multimodal, truong, timothy, tristan, bepler, families, jin, chenchen, yuyang, junjie, shan, xibin, fajie, yuan, vocabulary, iclr, lirong, zheng, guisheng, fan, semantical, topological, toward, bioactivity, thermostability, chloe, robert, jason, zeming, brian, hie, tom, adam, lerer, alexander, millions, if1, anishchenko, bennett, bai, ragotte, milles, wicky, courbet, haas, bethel, leung, huddy, pellock, tischer, chan, koepnick, nguyen, kang, sankaran, bera, king, baker, robust, vol, 378, yeh, masked, transfer, fusi, convolutions, competitive, pretraining, agnostic, improved, lmrl, workshop, marchena, hurtado, inference, canny, abbeel, nijkamp, weinstein, naik, exploring, boundaries, 2206, 13517, ferruz, schmidt, höcker, hesslow, poli, study, 2205, 05789, marquet, heinzinger, olenyi, dallago, bernhofer, erckert, rost, embeddings, predict, genetics, 141, 1629, 1647, original, extensions, brandes, goldman, genome, nat, genet, 1512, 1522, goyal, guo, ott, zitnick, fergus, biological, emerge, 250, national, academy, sciences, united, states, america, 118, alley, khimulya, biswas, alquraishi, church, rational, engineering, evo, tuning, min, brock, alignment, laine, karami, simple, fast, global, molecular, 2604, 2619, 2018, genetic, capture, 816, 822, deepsequence, shin, mcmahon, simon, manglik, kruse, wavenet, site, independent, modalities, accessible, via, dedicated, leaderboards, current, leaderboard, performance_substitutions_indels, calculate, bootstrapped, standard, reflect, variance, final, numbers, respect, individual, dives, split, taxa, contained, resp, dms_indels, clinical_substitutions, clinical_indels, counterparts, what, hosted, dms_zero_shot, summary_performance_dms_substitutions_spearman, respectively, dms_substitutions_spearman_uniprot_selection_type_level, dms_substitutions_spearman_uniprot_level, dms_substitutions_spearman_dms_level, taking, mean, those, uniprot, avoid, biasing, towards, several, mse, ndcg, mcc, top, recall, provides, section, created, binarized, target, target_seq, uniprot_id, along, taxon, category, additionally, give, further, contain, particular, dms_score_bin, int, indicates, whether, cutoff, float, measurement, value, column, since, classified, continuous, mutated_sequence, represents, mutant, describes, apply, obtain, a1p, d2n, implies, processed, contains, variables, extensive, scanning, annotated, curated, thorough, comparisons, predictors, regimes, both, divided, consists, characterisation, 217, 525, 300k, 555, contents, items, history, date, folders, tags, branches, main, additional, options, star, fork, must, change, notification, notifications, public, dismiss, alert, switched, accounts, out, resetting, focus, qualifiers, query, filter, quickly, email, address, contacted, read, every, piece, take, very, seriously, syntax, tips, clear, users, jump, pricing, premium, ons, powered, collections, trending, archive, program, accelerator, maintainer, programs, fund, developers, sponsors, partners, trust, center, forum, skills, ebooks, reports, events, webinars, stories, type, software, development, topic, industries, government, manufacturing, financial, healthcare, industry, cases, devsecops, modernization, case, nonprofits, startups, small, medium, enterprises, company, marketplace, changelog, blog, why, stop, leaks, start, secret, protection, secure, build, find, fix, vulnerabilities, application, enforce, changes, review, plan, track, instant, dev, codespaces, automate, any, workflow, workflows, integrate, external, tools, mcp, registry, direct, agents, write, better, creation, toggle, skip, content,

Text of the page (random words):
ences proceedings of the national academy of sciences of the united states of america 118 extensions brandes n goldman g wang c h et al genome wide prediction of disease variant effects with a deep protein language model nat genet 55 1512 1522 2023 esm 1v single sequence meier j rao r verkuil r liu j sercu t rives a 2021 language models enable zero shot prediction of the effects of mutations on protein function neurips vespa single sequence marquet c heinzinger m olenyi t dallago c bernhofer m erckert k rost b 2021 embeddings from protein language models predict conservation and variant effects human genetics 141 1629 1647 rita single sequence hesslow d zanichelli n notin p poli i marks d s 2022 rita a study on scaling up generative protein sequence models arxiv abs 2205 05789 protgpt2 single sequence ferruz n schmidt s höcker b 2022 protgpt2 is a deep unsupervised language model for protein design nature communications 13 progen2 single sequence nijkamp e ruffolo j a weinstein e n naik n madani a 2022 progen2 exploring the boundaries of protein language models arxiv abs 2206 13517 msa transformer msa rao r liu j verkuil r meier j canny j f abbeel p sercu t rives a 2021 msa transformer icml tranception single sequence msa for retrieval notin p dias m frazer j marchena hurtado j gomez a n marks d s gal y 2022 tranception protein fitness prediction with autoregressive transformers and inference time retrieval icml trancepteve msa notin p van niekerk l kollasch a ritter d gal y marks d s 2022 trancepteve combining family specific and family agnostic models of protein sequences for improved fitness prediction neurips lmrl workshop carp single sequence yang k k fusi n lu a x 2022 convolutions are competitive with transformers for protein sequence pretraining mif structure yang k k yeh h zanichelli n 2022 masked inverse folding with sequence transfer for protein representation learning proteinmpnn structure j dauparas i anishchenko n bennett h bai r j ragotte l f milles b i m wicky a courbet r j de haas n bethel p j y leung t f huddy s pellock d tischer f chan b koepnick h nguyen a kang b sankaran a k bera n p king d baker 2022 robust deep learning based protein sequence design using proteinmpnn science vol 378 esm if1 structure chloe hsu robert verkuil jason liu zeming lin brian hie tom sercu adam lerer alexander rives 2022 learning inverse folding from millions of predicted structures icml protssn single sequence structure yang tan bingxin zhou lirong zheng guisheng fan liang hong 2023 semantical and topological protein encoding toward enhanced bioactivity and thermostability saprot single sequence structure jin su chenchen han yuyang zhou junjie shan xibin zhou fajie yuan 2024 saprot protein language modeling with structure aware vocabulary iclr poet msa truong timothy f and tristan bepler poet a generative model of protein families as sequences of sequences neurips mulan single sequence structure daria frolova daria marina a pak anna litvin ilya sharov dmitry n ivankov ivan oseledets 2024 mulan multimodal protein language model for sequence and structure encoding prosst single sequence structure mingchen li yang tan xinzhu ma bozitao zhong huiqun yu ziyi zhou wanli ouyang bingxin zhou pan tan liang hong 2024 prosst protein language modeling with quantized structure and disentangled attention neurips escott msa structure mustafa tekpinar laurent david thomas henry alessandra carbone 2024 prescott a population aware epistatic and structural model accurately predicts missense effect medrxiv venusrem msa structure yang tan ruilin wang banghao wu liang hong bingxin zhou 2024 from high throughput evaluation to wet lab studies advancing mutation effect prediction with a retrieval enhanced model ismb eccb rsalor msa structure matsvei tsishyn pauline hermans fabrizio pucci marianne rooman 2025 residue conservation and solvent accessibility are almost all you need for predicting mutational effects in proteins biorxiv s3f single sequence structure zuobai zhang pascal notin yining huang aurelie c lozano vijil chenthamarakshan debora marks payel das jian tang 2024 multi scale representation learning for protein fitness prediction neurips siterm msa sebastian prillo wilson wu yun song 2024 ultrafast classical phylogenetic method beats large protein language models on variant effect prediction neurips esm3 single sequence structure function hayes t rao r akin h sofroniew n j oktay d lin z verkuil r tran v q deaton j wiggert m badkundri r shafkat i gong j derry a molina r s thomas n khan y a mishra c kim c bartie l j nemeth m hsu p d sercu t candido s rives a 2025 simulating 500 million years of evolution with a language model science esm c single sequence esm team xtrimopglm single sequence chen b cheng x li p geng y gong j li s bei z tan x wang b zeng x liu c zeng a dong y tang j song l 2025 xtrimopglm unified 100 billion parameter pretrained transformer for deciphering the language of proteins nature methods progen3 single sequence bhatnagar a jain s beazer j curran s c hoffnagle a m ching k martyn m nayfach s ruffolo j a madani a 2025 scaling unlocks broader generation and deeper functional understanding of proteins biorxiv 2025 04 15 649055 aido msa structure sun n zou s tao t mahbub s li d zhuang y wang h cheng x song l xing e p 2024 mixture of experts enable efficient and effective protein understanding and design biorxiv for clinical baselines we used dbnsfp 4 4a as detailed in the manuscript appendix and in proteingym clinical_benchmark_notebooks clinical_subs_processing ipynb resources to download and unzip the data use the following template replacing version with the desired version number e g v1 3 and filename with the specific file you want to download as listed in the table below the latest version is v1 3 for example you can download unzip the zero shot predictions for all baselines for all dms substitution assays as follows version v1 3 filename dms_proteingym_substitutions zip curl o filename https marks hms harvard edu proteingym proteingym_ version filename unzip filename rm filename data size unzipped filename dms benchmark substitutions 1 0gb dms_proteingym_substitutions zip dms benchmark indels 200mb dms_proteingym_indels zip zero shot dms model scores substitutions 4 4gb zero_shot_substitutions_scores zip zero shot dms model scores indels 313mb zero_shot_indels_scores zip supervised dms model scores substitutions 3 3gb dms_supervised_substitutions_scores zip supervised dms model scores indels 215mb dms_supervised_indels_scores zip multiple sequence alignments msas for dms assays 5 2gb dms_msa_files zip redundancy based sequence weights for dms assays 200mb dms_msa_weights zip predicted 3d structures from inverse folding models 84mb proteingym_af2_structures zip clinical benchmark substitutions 123mb clinical_proteingym_substitutions zip clinical benchmark indels 2 8mb clinical_proteingym_indels zip clinical msas 17 8gb clinical_msa_files zip clinical msa weights 250mb clinical_msa_weights zip clinical model scores substitutions 0 9gb zero_shot_clinical_substitutions_scores zip clinical model scores indels 0 7gb zero_shot_clinical_indels_scores zip cv folds substitutions singles 50m cv_folds_singles_substitutions zip cv folds substitutions multiples 81m cv_folds_multiples_substitutions zip cv folds indels 19mb cv_folds_indels zip then we also host the raw dms assays before preprocessing data size unzipped link dms benchmark substitutions raw 500mb substitutions_raw_dms zip dms benchmark indels raw 450mb indels_raw_dms zip clinical benchmark substitutions raw 58mb substitutions_raw_clinical zip clinical benchmark indels raw 12 4mb indels_raw_clinical zip how to contribute new assays if you would like to suggest new assays to be part of proteingym please raise an issue on this repository with a new_assay label the criteria we typically consider for inclusion are as follows the corresponding raw dataset needs to be publicly available the assay needs to be protein related ie exclude utr trna promoter etc the dataset needs to have insufficient number of measurements the assay needs to have a sufficiently high dynamic range the assay has to be relevant to fitness prediction new baselines if you would like new baselines to be included in proteingym ie website performance files detailed scoring files please follow the following steps submit a pr to our repo with two things a new subfolder under proteingym baselines named with your new model name this subfolder should include a python scoring script similar to this script as well as all code dependencies required for the scoring script to run properly an example bash script e g under scripts scoring_dms_zero_shot with all relevant hyperparameters for scoring similar to this script raise an issue with a new model label providing instructions on how to download relevant model checkpoints for scoring and reporting the performance of your model on the relevant benchmark using our performance scripts e g for zero shot dms benchmarks please note that our dms performance scripts correct for various biases e g number of assays per protein family and function groupings and thus the resulting aggregated performance is not the same as the arithmetic average across assays at this point we are only considering new baselines satisfying the following conditions the model is able to score all mutants in the relevant benchmark to ensure all models are compared exactly on the same set of mutants everywhere the corresponding model is open source we should be able to reproduce scores if needed at this stage we are only considering requests for which all model scores for all mutants in a given benchmark substitution or indel are provided by the requester but we are planning on regularly scoring new baselines ourselves for methods with wide adoption by the community and or suggestions with many upvotes notes 12 december 2023 the code for training and evaluating supervised models is currently shared in https github com oatml markslab proteinnpt we are in the process of integrating the code into this repo usage and reproducibility if you would like to compute all performance metrics for the various benchmarks please follow the following steps download locally all relevant files as per instructions above see resources update the paths for all files downloaded in the prior step in the config script if adding a new model adjust the config json file accordingly and add the model scores to the relevant path e g dms_output_score_folder_subs if focusing on dms benchmarks run the merge script this will create a single file for each dms assay with scores for all model baselines run the relevant performance script eg scripts scoring_dms_zero_shot performance_substitutions sh acknowledgements our codebase leveraged code from the following repositories to compute baselines model repo unirep https github com churchlab unirep unirep https github com chloechsu combining evolutionary and assay labelled data eve https github com oatml markslab eve gemme https hub docker com r elodielaine gemme esm https github com facebookresearch esm evmutation https github com debbiemarkslab evcouplings progen2 https github com salesforce progen hmmer https github com eddyrivaslab hmmer msa transformer https github com rmrao msa transformer protgpt2 https huggingface co nferruz protgpt2 proteinmpnn https github com dauparas proteinmpnn rita https github com lightonai rita tranception https github com oatml markslab tranception vespa https github com rostlab vespa carp https github com microsoft protein sequence models mif https github com microsoft protein sequence models foldseek https github com steineggerlab foldseek protssn https github com ai4protein protssn saprot https github com westlake repl saprot poet https github com openproteinai poet mulan https github com dfrolova mulan prosst https github com ai4protein prosst escott http gitlab lcqb upmc fr tekpinar prescott venusrem https github com ai4protein venusrem rsalor https github com 3biocompbio rsalor s3f https github com deepgraphlearning s3f siterm https github com songlab cal cherryml esm3 https github com evolutionaryscale esm xtrimopglm https github com biomap research xtrimopglm progen3 https github com profluent ai progen3 aido https github com genbio ai aido we would like to thank the gemme team for providing model scores on an earlier version of the benchmark proteingym v0 1 and the protssn saprot poet mulan vespag prosst escott venusrem rsalor siterm and aido teams for integrating their model in the proteingym repo special thanks the teams of experimentalists who developed and performed the assays that proteingym is built on if you are using proteingym in your work please consider citing the corresponding papers to facilitate this we have prepared a file assays bib containing the bibtex entries for all these papers releases proteingym_v1 0 initial release proteingym_v1 1 updates to reference file and addition of protssn and saprot baselines proteingym_v1 2 added 8 baselines to the zero shot dms substitutions benchmark eg venusrem s3f escott added all mutation level predictions for all baselines in supervised benchmarks proteingym_v1 3 added 16 baselines to the zero shot dms substitutions benchmark eg esm3 esm c progen3 xtrimopglm license this project is available under the mit license found in the license file in this github repository reference if you use proteingym in your work please cite the following paper inproceedings neurips2023_cac723e5 author notin pascal and kollasch aaron and ritter daniel and van niekerk lood and paul steffanie and spinner han and rollins nathan and shaw ada and orenbuch rose and weitzman ruben and frazer jonathan and dias mafalda and franceschi dinko and gal yarin and marks debora booktitle advances in neural information processing systems editor a oh and t neumann and a globerson and k saenko and m hardt and s levine pages 64331 64379 publisher curran associates inc title proteingym large scale benchmarks for protein fitness prediction and design url https proceedings neurips cc paper_files paper 2023 file cac723e5ff29f65e3fcbb0739ae91bee paper datasets_and_benchmarks pdf volume 36 year 2023 links website https www proteingym org neurips proceedings link to abstract preprint link to abstract zenodo link to zenodo pypi link to pypi huggingface link to hf about official repository for the proteingym benchmarks proteingym org topics benchmark computational biology protein protein design protein fitness resources readme license mit license uh oh there was an error while loading please reload this page activity custom properties stars 450 stars watchers 9 watching forks 58 forks report repository releases 4 pg_v1 3 latest apr 28 2025 3 releases packages 0 uh oh there was an error while loading please reload this page uh oh there was an error while loading please reload this page contributors uh oh there was an error while ...