{"url":"/task/protein-design","name":"Protein Design","slug":"protein-design","description_markdown":"Formally, given the design requirements of users, models are required to generate protein amino acid sequences that align with those requirements.","categories":[{"name":"Medical","url":"/area/medical"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":175,"papers_with_code":74,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/protein-design-on-cath-4-2","slug":"protein-design-on-cath-4-2","dataset":"CATH 4.2","dataset_url":"/dataset/cath-4-2","rows_in_archive":8,"metrics":["Perplexity","Sequence Recovery %(All)"],"first_row_in_archive_order":{"model":"Knowledge-Design","paper_title":"Knowledge-Design: Pushing the Limit of Protein Design via Knowledge Refinement","paper_url":"/paper/knowledge-design-pushing-the-limit-of-protein","paper_date":"2023-05-20","arxiv_id":"2305.15151","code_links":[{"title":"A4Bio/OpenCPD","url":"https://github.com/A4Bio/OpenCPD"}],"syntology":null}},{"leaderboard":"/sota/protein-design-on-cath-4-3","slug":"protein-design-on-cath-4-3","dataset":"CATH 4.3","dataset_url":"/dataset/cath-4-3","rows_in_archive":2,"metrics":["Perplexity","Sequence Recovery %(All)"],"first_row_in_archive_order":{"model":"GVP-large","paper_title":"Knowledge-Design: Pushing the Limit of Protein Design via Knowledge Refinement","paper_url":"/paper/knowledge-design-pushing-the-limit-of-protein","paper_date":"2023-05-20","arxiv_id":"2305.15151","code_links":[{"title":"A4Bio/OpenCPD","url":"https://github.com/A4Bio/OpenCPD"}],"syntology":null}}],"datasets":[{"url":"/dataset/flip","name":"FLIP","full_name":"Fitness Landscape Inference for Proteins","num_papers_in_archive":11},{"url":"/dataset/protein-structures-ingraham","name":"Protein structures Ingraham","full_name":"Dataset of protein backbones and sequences","num_papers_in_archive":2},{"url":"/dataset/cath-4-2","name":"CATH 4.2","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cath-4-3","name":"CATH 4.3","full_name":"","num_papers_in_archive":1},{"url":"/dataset/flip-aav-designed-vs-mutant","name":"FLIP -- AAV, Designed vs mutant","full_name":"adeno-associated virus","num_papers_in_archive":1},{"url":"/dataset/cameo","name":"CAMEO","full_name":"Continuous automated model evaluation","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":74,"tagged_in_all":175,"items":[{"url":"/paper/x-lora-mixture-of-low-rank-adapter-experts-a","title":"X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design","date":"2024-02-11","arxiv_id":"2402.07148","repositories_listed":4,"syntology":null},{"url":"/paper/progen2-exploring-the-boundaries-of-protein","title":"ProGen2: Exploring the Boundaries of Protein Language Models","date":"2022-06-27","arxiv_id":"2206.13517","repositories_listed":4,"syntology":{"n":18,"n_ran":13,"n_unverified":5,"n_pointer_only":2}},{"url":"/paper/rita-a-study-on-scaling-up-generative-protein","title":"RITA: a Study on Scaling Up Generative Protein Sequence Models","date":"2022-05-11","arxiv_id":"2205.05789","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/taxdiff-taxonomic-guided-diffusion-model-for","title":"TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation","date":"2024-02-27","arxiv_id":"2402.17156","repositories_listed":3,"syntology":null},{"url":"/paper/a-text-guided-protein-design-framework","title":"A Text-guided Protein Design Framework","date":"2023-02-09","arxiv_id":"2302.04611","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/geometry-complete-diffusion-for-3d-molecule","title":"Geometry-Complete Diffusion for 3D Molecule Generation and Optimization","date":"2023-02-08","arxiv_id":"2302.04313","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/learning-from-protein-structure-with","title":"Learning from Protein Structure with Geometric Vector Perceptrons","date":"2020-09-03","arxiv_id":"2009.01411","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/improved-motif-scaffolding-with-se-3-flow","title":"Improved motif-scaffolding with SE(3) flow matching","date":"2024-01-08","arxiv_id":"2401.04082","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/fast-protein-backbone-generation-with-se-3","title":"Fast protein backbone generation with SE(3) flow matching","date":"2023-10-08","arxiv_id":"2310.05297","repositories_listed":2,"syntology":null},{"url":"/paper/practical-and-asymptotically-exact-1","title":"Practical and Asymptotically Exact Conditional Sampling in Diffusion Models","date":"2023-06-30","arxiv_id":"2306.17775","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_unverified":6,"n_pointer_only":15}},{"url":"/paper/few-shot-learning-of-accurate-folding","title":"Unsupervisedly Prompting AlphaFold2 for Few-Shot Learning of Accurate Folding Landscape and Protein Structure Prediction","date":"2022-08-20","arxiv_id":"2208.09652","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":2}},{"url":"/paper/variational-auto-encoding-of-protein","title":"Variational auto-encoding of protein sequences","date":"2017-12-09","arxiv_id":"1712.03346","repositories_listed":2,"syntology":null},{"url":"/paper/improving-large-language-models-with-concept","title":"Improving large language models with concept-aware fine-tuning","date":"2025-06-09","arxiv_id":"2506.07833","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-sequence-models-for-enhanced","title":"Diffusion Sequence Models for Enhanced Protein Representation and Generation","date":"2025-06-09","arxiv_id":"2506.08293","repositories_listed":1,"syntology":null},{"url":"/paper/cfp-gen-combinatorial-functional-protein","title":"CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models","date":"2025-05-28","arxiv_id":"2505.22869","repositories_listed":1,"syntology":null},{"url":"/paper/psbench-a-large-scale-benchmark-for","title":"PSBench: a large-scale benchmark for estimating the accuracy of protein complex structural models","date":"2025-05-13","arxiv_id":"2505.22674","repositories_listed":1,"syntology":null},{"url":"/paper/scoring-assisted-generative-exploration-for","title":"Scoring-Assisted Generative Exploration for Proteins (SAGE-Prot): A Framework for Multi-Objective Protein Optimization via Iterative Sequence Generation and Evaluation","date":"2025-05-02","arxiv_id":"2505.01277","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/multi-objective-quality-diversity-in","title":"Multi-Objective Quality-Diversity in Unstructured and Unbounded Spaces","date":"2025-03-28","arxiv_id":"2504.03715","repositories_listed":1,"syntology":null},{"url":"/paper/proteina-scaling-flow-based-protein-structure","title":"Proteina: Scaling Flow-based Protein Structure Generative Models","date":"2025-03-02","arxiv_id":"2503.00710","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/reqflow-rectified-quaternion-flow-for","title":"ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation","date":"2025-02-20","arxiv_id":"2502.14637","repositories_listed":1,"syntology":null},{"url":"/paper/motifbench-a-standardized-protein-design","title":"MotifBench: A standardized protein design benchmark for motif-scaffolding problems","date":"2025-02-18","arxiv_id":"2502.12479","repositories_listed":1,"syntology":null},{"url":"/paper/persistent-sheaf-laplacian-analysis-of","title":"Persistent Sheaf Laplacian Analysis of Protein Flexibility","date":"2025-02-12","arxiv_id":"2502.08772","repositories_listed":1,"syntology":null},{"url":"/paper/controllable-protein-sequence-generation-with","title":"Controllable Protein Sequence Generation with LLM Preference Optimization","date":"2025-01-25","arxiv_id":"2501.15007","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-framework-for-inference-time","title":"A General Framework for Inference-time Scaling and Steering of Diffusion Models","date":"2025-01-12","arxiv_id":"2501.06848","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/building-confidence-in-deep-generative","title":"Building Confidence in Deep Generative Protein Design","date":"2024-11-27","arxiv_id":"2411.18568","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/beyond-human-like-processing-large-language","title":"Beyond Human-Like Processing: Large Language Models Perform Equivalently on Forward and Backward Scientific Text","date":"2024-11-17","arxiv_id":"2411.11061","repositories_listed":1,"syntology":null},{"url":"/paper/concept-bottleneck-language-models-for","title":"Concept Bottleneck Language Models For protein design","date":"2024-11-09","arxiv_id":"2411.06090","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/bridge-if-learning-inverse-protein-folding","title":"Bridge-IF: Learning Inverse Protein Folding with Markov Bridges","date":"2024-11-04","arxiv_id":"2411.02120","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/peptide-gpt-generative-design-of-peptides","title":"Peptide-GPT: Generative Design of Peptides using Generative Pre-trained Transformers and Bio-informatic Supervision","date":"2024-10-25","arxiv_id":"2410.19222","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-on-structure","title":"Reinforcement learning on structure-conditioned categorical diffusion for protein inverse folding","date":"2024-10-22","arxiv_id":"2410.17173","repositories_listed":1,"syntology":null}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}