{"total":65,"rows":[{"id":"2206.13517","title":"ProGen2: Exploring the Boundaries of Protein Language Models","created":"2022-06-27","cited_by_count":159,"area":null},{"id":"2401.14656","title":"Scientific Large Language Models: A Survey on Biological & Chemical Domains","created":"2024-01-26","cited_by_count":80,"area":null},{"id":"2301.12040","title":"ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts","created":"2023-01-28","cited_by_count":78,"area":null},{"id":"2302.04611","title":"A Text-guided Protein Design Framework","created":"2023-02-09","cited_by_count":64,"area":null},{"id":"2410.23326","title":"MassSpecGym: A benchmark for the discovery and identification of molecules","created":"2024-10-30","cited_by_count":38,"area":null},{"id":"2306.06156","title":"PoET: A generative model of protein families as sequences-of-sequences","created":"2023-06-09","cited_by_count":29,"area":null},{"id":"2310.03269","title":"InstructProtein: Aligning Human and Protein Language via Knowledge Instruction","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2408.11363","title":"ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding","created":"2024-08-21","cited_by_count":23,"area":null},{"id":"2402.19155","title":"Beyond Language Models: Byte Models are Digital World Simulators","created":"2024-02-29","cited_by_count":22,"area":null},{"id":"2307.00494","title":"Improving Protein Optimization with Smoothed Fitness Landscapes","created":"2023-07-02","cited_by_count":21,"area":null},{"id":"2306.01474","title":"Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning","created":"2023-06-02","cited_by_count":19,"area":null},{"id":"2402.09649","title":"ProtChatGPT: Towards Understanding Proteins with Large Language Models","created":"2024-02-15","cited_by_count":18,"area":null},{"id":"2502.17504","title":"Protein Large Language Models: A Comprehensive Survey","created":"2025-02-21","cited_by_count":18,"area":null},{"id":"2211.16742","title":"Protein Language Models and Structure Prediction: Connection and Progression","created":"2022-11-30","cited_by_count":17,"area":null},{"id":"2212.09925","title":"Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC","created":"2022-12-20","cited_by_count":17,"area":null},{"id":"2310.18515","title":"Learning to design protein-protein interactions with enhanced generalization","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2303.06275","title":"A Systematic Study of Joint Representation Learning on Protein Sequences and Structures","created":"2023-03-11","cited_by_count":15,"area":null},{"id":"2411.04165","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","created":"2024-11-06","cited_by_count":13,"area":null},{"id":"2407.00002","title":"Kermut: Composite kernel regression for protein variant effects","created":"2024-04-09","cited_by_count":12,"area":null},{"id":"2405.10348","title":"Learning to Predict Mutation Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning","created":"2024-05-16","cited_by_count":11,"area":null},{"id":"2412.07763","title":"Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences","created":"2024-12-10","cited_by_count":11,"area":null},{"id":"2403.12995","title":"ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2410.21127","title":"Retrieval-Enhanced Mutation Mastery: Augmenting Zero-Shot Prediction of Protein Language Model","created":"2024-10-28","cited_by_count":7,"area":null},{"id":"2509.07983","title":"Steering Protein Language Models","created":"2025-07-01","cited_by_count":7,"area":null},{"id":"2410.09543","title":"Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2410.19236","title":"SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries","created":"2024-10-25","cited_by_count":4,"area":null},{"id":"2501.19200","title":"A Variational Perspective on Generative Protein Fitness Optimization","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2506.08954","title":"Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2304.08299","title":"Accurate and Definite Mutational Effect Prediction with Lightweight Equivariant Graph Neural Networks","created":"2023-04-13","cited_by_count":3,"area":null},{"id":"2410.08355","title":"Metalic: Meta-Learning In-Context with Protein Language Models","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2601.06214","title":"Dynamics-inspired Structure Hallucination for Protein-protein Interaction Modeling","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2302.03294","title":"Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretability","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2305.03136","title":"Contrastive losses as generalized models of global epistasis","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2306.00872","title":"Is novelty predictable?","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2408.10247","title":"MetaEnzyme: Meta Pan-Enzyme Learning for Task-Adaptive Redesign","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2410.24022","title":"SFM-Protein: Integrative Co-evolutionary Pre-training for Advanced Protein Sequence Representation","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2502.06846","title":"Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2502.07299","title":"Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2603.06740","title":"ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2603.10302","title":"How to make the most of your masked language model for protein engineering","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.14717","title":"Training-Free Generation of Protein Sequences from Small Family Alignments via Stochastic Attention","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2212.03979","title":"Unsupervised language models for disease variant prediction","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2305.01941","title":"Exploring the Protein Sequence Space with Global Generative Models","created":"2023-05-03","cited_by_count":1,"area":null},{"id":"2306.04899","title":"Multi-level Protein Representation Learning for Blind Mutational Effect Prediction","created":"2023-06-08","cited_by_count":1,"area":null},{"id":"2306.12231","title":"Predicting protein variants with equivariant graph neural networks","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2407.06703","title":"HERMES: Holographic Equivariant neuRal network model for Mutational Effect and Stability prediction","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2410.22949","title":"MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2504.16886","title":"Exploring zero-shot structure-based protein fitness prediction","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2507.08920","title":"AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2309.16685","title":"Target-aware Variational Auto-encoders for Ligand Generation with Multimodal Protein Representation Learning","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2310.17415","title":"PETA: Evaluating the Impact of Protein Transfer Learning with Sub-word Tokenization on Downstream Applications","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2408.16245","title":"Large-Scale Multi-omic Biosequence Transformers for Modeling Protein-Nucleic Acid Interactions","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2502.06913","title":"A Simple yet Effective DDG Predictor is An Unsupervised Antibody Optimizer and Explainer","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2503.10655","title":"Language modelling techniques for analysing the impact of human genetic variation","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2506.02052","title":"General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.02212","title":"Leveraging Natural Language Processing to Unravel the Mystery of Life: A Review of NLP Approaches in Genomics, Transcriptomics, and Proteomics","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2507.02624","title":"A Matrix Variational Auto-Encoder for Variant Effect Prediction in Pharmacogenes","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2508.10629","title":"Energy-Based Models for Predicting Mutational Effects on Proteins","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2510.07286","title":"Evolutionary Profiles for Protein Fitness Prediction","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2512.02315","title":"Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2606.18703","title":"Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.22823","title":"Retrieval-Augmented Multimodal Learning for Enzyme-Substrate Interaction Prediction Under Low-Homology Shift","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.06022","title":"EpiBench: Can LLMs Understand Epitopes for Antibody Drug Discovery?","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.28921","title":"PFArena: Benchmarking Language Models for Protein Modification","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.00742","title":"StabilityArc: Decoding Protein Sequence Embeddings into Generalizable Stability Landscapes","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}