mlsanityData to 14 Oct 2026

PiFold: Toward effective and efficient protein inverse folding

arXiv 2209.12643 ↗First posted 22 Sep 2022cs.AI cs.CE cs.LGcited by 83

Not on the map. Why?

Abstract (arXiv)

How can we design protein sequences folding into the desired structures effectively and efficiently? AI methods for structure-based protein design have attracted increasing attention in recent years; however, few methods can simultaneously improve the accuracy and efficiency due to the lack of expressive features and autoregressive sequence decoder. To address these issues, we propose PiFold, which contains a novel residue featurizer and PiGNN layers to generate protein sequences in a one-shot way with improved recovery. Experiments show that PiFold could achieve 51.66% recovery on CATH 4.2, while the inference speed is 70 times faster than the autoregressive competitors. In addition, PiFold achieves 58.72% and 60.42% recovery scores on TS50 and TS500, respectively. We conduct comprehensive ablation studies to reveal the role of different types of protein features and model designs, inspiring further simplification and improvement. The PyTorch code is available at hrefhttps://github.com/A4Bio/PiFoldGitHub.

Key facts. Cited by 83 papers in the map (data through 14 Oct 2026). Builds on 32 of its 72 references that are in the map. First posted on arXiv 22 Sep 2022.

Builds on

32 of 72 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2016Densely Connected Convolutional Networkscited by 6,720
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  9. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  10. 2017Non-Autoregressive Neural Machine Translationcited by 463
  11. 2018Deep Learning on Graphs: A Surveycited by 393
  12. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
20 more
  1. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
  2. 2022SimVP: Simpler yet Better Video Predictioncited by 184
  3. 2022EquiBind: Geometric Deep Learning for Drug Binding Structure Predictioncited by 144
  4. 2022Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learningcited by 86
  5. 2021AutoMix: Unveiling the Power of Mixup for Stronger Classifierscited by 69
  6. 2019Non-Autoregressive Machine Translation with Auxiliary Regularizationcited by 52
  7. 2022AlphaDesign: A graph protein design method and benchmark on AlphaFoldDBcited by 40
  8. 2021Protein sequence design with deep generative modelscited by 35
  9. 2020Deep Learning in Protein Structural Modeling and Designcited by 25
  10. 2021Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Designcited by 23
  11. 2022OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learningcited by 21
  12. 2022Target-aware Molecular Graph Generationcited by 18
  13. 2021Deep Generative Modeling for Protein Designcited by 17
  14. 2022Hyperspherical Consistency Regularizationcited by 16
  15. 2022SemiRetro: Semi-template framework boosts deep retrosynthesis predictioncited by 13
  16. 2022CoSP: Co-supervised pretraining of pocket and ligandcited by 12
  17. 2022HelixFold: An Efficient Implementation of AlphaFold2 using PaddlePaddlecited by 12
  18. 2020Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanismcited by 5
  19. 2022TERMinator: A Neural Framework for Structure-Based Protein Design using Tertiary Repeating Motifscited by 3
  20. 2020Clustering Based on Graph of Density Topologycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 17; 2024: 34; 2025: 18; 2026: 11.

83 papers.

Sort:

By area:

  1. 2024Diffusion Language Models Are Versatile Protein Learnerscited by 98
  2. 2023Structure-informed Language Models Are Protein Designerscited by 68
  3. 2024DPLM-2: A Multimodal Diffusion Protein Language Modelcited by 64
  4. 2024Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactionscited by 46
  5. 2023Graph Denoising Diffusion for Inverse Protein Foldingcited by 44
  6. 2024Full-Atom Peptide Design based on Multi-modal Flow Matchingcited by 34
  7. 2023Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaborationcited by 30
  8. 2023Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Designcited by 30
  9. 2024A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generationcited by 29
  10. 2024A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applicationscited by 28
  11. 2023Learning Subpocket Prototypes for Generalizable Structure-based Drug Designcited by 25
  12. 2024ProteinBench: A Holistic Evaluation of Protein Foundation Modelscited by 25
38 more
  1. 2024FoldToken: Learning Protein Language via Vector Quantization and Beyondcited by 23
  2. 2022Protein Language Models and Structure Prediction: Connection and Progressioncited by 17
  3. 2024Structure Language Models for Protein Conformation Generationcited by 17
  4. 2022Geometry-Complete Perceptron Networks for 3D Molecular Graphscited by 16
  5. 2023A Systematic Study of Joint Representation Learning on Protein Sequences and Structurescited by 15
  6. 2023De novo protein design using geometric vector field networkscited by 14
  7. 2024SurfPro: Functional Protein Design Based on Continuous Surfacecited by 14
  8. 2023Knowledge-Design: Pushing the Limit of Protein Design via Knowledge Refinementcited by 12
  9. 2024Kermut: Composite kernel regression for protein variant effectscited by 12
  10. 2024Endowing Protein Language Models with Structural Knowledgecited by 11
  11. 2023DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraintscited by 10
  12. 2024A Graph is Worth K Words: Euclideanizing Graph using Pure Transformercited by 10
  13. 2024PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Predictioncited by 10
  14. 2025dyAb: Flow Matching for Flexible Antibody Design with AlphaFold-driven Pre-binding Antigencited by 10
  15. 2024UniIF: Unified Molecule Inverse Foldingcited by 9
  16. 2024Bridge-IF: Learning Inverse Protein Folding with Markov Bridgescited by 9
  17. 2024Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extensioncited by 9
  18. 2023RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Designcited by 8
  19. 2023Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designercited by 8
  20. 2024Generative AI for Controllable Protein Sequence Design: A Surveycited by 8
  21. 2024Relation-Aware Equivariant Graph Networks for Epitope-Unknown Antibody Design and Specificity Optimizationcited by 8
  22. 2025All-atom inverse protein folding through discrete flow matchingcited by 8
  23. 2023PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embeddingcited by 7
  24. 2024BEACON: Benchmark for Comprehensive RNA Tasks and Language Modelscited by 7
  25. 2023PDB-Struct: A Comprehensive Benchmark for Structure-based Protein Designcited by 6
  26. 2024Pre-Training Protein Bi-level Representation Through Span Mask Strategy On 3D Protein Chainscited by 6
  27. 2024Reinforcement learning on structure-conditioned categorical diffusion for protein inverse foldingcited by 6
  28. 2025Computational Protein Science in the Era of Large Language Models (LLMs)cited by 6
  29. 2025Improving Protein Sequence Design through Designability Preference Optimizationcited by 6
  30. 2025ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Searchcited by 6
  31. 2025ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learningcited by 6
  32. 2025PRISM: Enhancing Protein Inverse Folding through Fine-Grained Retrieval on Structure-Sequence Multimodal Representationscited by 6
  33. 2023Generative artificial intelligence for de novo protein designcited by 5
  34. 2023Fast non-autoregressive inverse folding with discrete diffusioncited by 5
  35. 2023Progressive Multi-Modality Learning for Inverse Protein Foldingcited by 5
  36. 2024Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networkscited by 5
  37. 2024Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimizationcited by 5
  38. 2024Mask prior-guided denoising diffusion improves inverse protein foldingcited by 5

50 most cited of 83 All 83 (JSON)