Protein Representation Learning

Overview

Protein representation learning studies how to encode amino-acid sequences and three-dimensional structures so models can compare proteins and predict properties such as function, folding, interactions, and mutation effects. Common approaches include protein language models trained with masked-token prediction, geometric and graph encoders of residue contacts, structure-aware masking, and contrastive learning that aligns sequence with structure or function. These representations are tested on tasks such as remote homology, protein fitness, structure prediction, and binding, using both pooled protein embeddings and residue-level features. A central challenge is making representations transferable across proteins and data splits: larger pretrained models can help, but useful information varies by task and layer, and structural or evolutionary features may offer gains with less data or computation.

Latest papers

CardsList

77 papers12 papers in the last four weeks, up 20% on the four weeks before. 0.1% of all new papers.

  1. Match and Correct: A Repeated Computational Motif in Evoformer Layers

    Nov 13, 2026Ishan Khire, Naren Manikandan, Tyler Hayes +1Protein Structure PredictionNeural Representation Geometry

  2. One Mistake, Three Layers: Persistence Rules Under Depth Correlation

    Nov 2, 2026Maryam Rahimimovassagh, Michael Brown, Sanjeda Sara Jennifer +1Hidden-State ProbingProtein Representation Learning

  3. GraphTFactor: A graph-based approach for proteins transcription factor prediction

    Oct 29, 2026Domenico Amato, Salvatore Calderaro, Giosuè Lo Bosco +2Protein Representation Learning

  4. Towards Generalizing Pretrained All-Atom Representations to Unified Binder Design

    Oct 27, 2026Maojiang Su, Jiale Chen, Qijie Zhu +6Protein Binder DesignCross-Modal Representation Transfer

  5. Escaping the Phylogenetic Trap: Persistent Homology Enables Cross-Species Ion Channel Classification via Multimodal Graph Neural Networks

    Oct 21, 2026Arezoo Bybordi, Favour Achimba, Mariam Gelashvili +4OOD GeneralizationProtein Representation Learning

  6. Ensemble-Aware Structural Encoding (EASE): Conditioning Protein Encoders on Peptide Conformational Ensembles

    Oct 20, 2026Ruoyao Zhang, Hongxuan Li, Jie Peng +1Protein Representation LearningMolecular Property Prediction

  7. ProTok: Unified Protein Tokenization via Modular Multi-Codebook Quantization

    Oct 13, 2026Romain Hardy, Xiaoman Zhang, Pranav RajpurkarProtein Representation LearningProtein Language Models

  8. PIT-GCL: Protein Interaction using Topological Graph Contrastive Learning

    Oct 4, 2026Jae Won Choi, Ryoonki Hong, Alan Liang +5Protein-Protein Interaction PredictionProtein Representation Learning

  9. Learning Latent Protein Languages for Autoregressive Generation

    Oct 2, 2026Mahdi Pourmirzaei, Farzaneh Esmaili, Amir Ziashahabi +2Protein Structure GenerationProtein Language Models

  10. StabilityArc: Decoding Protein Sequence Embeddings into Generalizable Stability Landscapes

    Sep 30, 2026Aaron L. Feller, Andrew D. Ellington, Claus O. Wilkeprotein mutation effect predictionTransfer Learning

  11. ORBIT-FMIB: Tracking Order-Resolved Epistatic Information Through ESM-2

    Sep 30, 2026Maryam Rahimimovassagh, Waldemar Karwowski, Ivan Garibay +1Protein Language ModelsProtein Representation Learning

  12. LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling

    Sep 29, 2026Biswajit Banerjee, Claudia Alvarez Carreno, Anton S. PetrovProtein Language ModelsProtein Representation Learning

  13. From Surfaces to Volumes: Registered Geometry for Protein Representation Learning

    Sep 28, 2026Siyuan Chen, Cai Zhou, Jinrui Zhang +8Protein-Protein Interaction Prediction3D Representation Learning

  14. Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy

    Sep 27, 2026Zhe Zhang, Yikai Zhang, Jiangtao Feng +3Protein Representation LearningDiscrete Flow Matching

  15. MT-ProtBERT: Multi-task Learning ProtBERT for Intrinsically Disordered Proteins Classification with Scarce Data

    Sep 21, 2026Jian Sun, Kingshuk Ghosh, Lilianna Houston +1Protein Language ModelsMulti-Task Learning

  16. The microscope is the mask: privileged views and labels from a cryo-ET forward model

    Sep 3, 2026Bogdan Toader, Kiarash Jamali, Tanmay A. M. Bharat +1Protein Representation LearningCryo-Electron Microscopy

  17. Chemical and geometric representation fidelity improves drug--target affinity prediction

    Sep 2, 2026Yixiao Li, Yining Qian, Yefan Chen +5Privacy-Preserving Representation LearningProtein-Ligand Binding Affinity Prediction

  18. Learning Task-Specific Antibody Representations via Function-Aware Masking

    Sep 1, 2026Ayan Goel, Thomas A. Walton, Amirali AghazadehMasked Language ModelingProtein Language Models

  19. Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts

    Aug 31, 2026Jiaxin Tian, Darren An, Jun LiProtein-Ligand Binding Affinity PredictionOOD Generalization

  20. Hyper-Fold: Exploring the Expressive Limit of Sequence-Geometry Learning for Proteins via Hypergraph Modeling

    Aug 29, 2026Yifan Feng, Guanjie Cheng, Shihui Ying +2Protein Function PredictionHypergraph Neural Networks

  21. Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Prediction

    Aug 26, 2026Paulo Yanez Sarmiento, Pia Francesca Rissom, Manuel Pfeuffer +6Protein Language ModelsProtein Representation Learning

  22. Beyond Tokens: Probing Higher-Order Epistasis in Learned Protein Representations

    Aug 24, 2026Maryam Rahimimovassagh, Ivan Garibay, Niloofar YousefiProtein Representation LearningProtein Fitness Prediction

  23. Protein Structure Prediction: From Evolutionary Constraints to Generative Modeling

    Aug 17, 2026Wengan He, Yongsheng Luo, Lihong Jiang +2Protein Structure PredictionProtein Representation Learning