RefusalBench shows strict refusal rates fail to rank frontier LLMs correctly on biological safety, with provider effects and partial-compliance patterns that binary metrics miss.
UniProt: the uni- versal protein knowledgebase in 2025
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
Introduces first protein sequence dataset for nine Bangladeshi fish species and a deployable hybrid CNN-Transformer model achieving 79.8% accuracy with strong efficiency advantages over ProtBERT.
OmicsLM integrates continuous omics embeddings into LLMs for multi-sample biological reasoning, matching specialized models on profile tasks while outperforming them and general LLMs on language-guided QA over real expression data.
AMix-2 unifies protein sequences and text in one LLM via shared tokens and block-wise diffusion modeling, introduces the ProteinArena benchmark, and reports competitive performance against task-specific protein models and frontier LLMs.
A new aggregated PROTAC dataset shows potency is more predictable than maximum degradation by ML, with classical methods outperforming a specialized graph neural network.
Introduces TEDBench benchmark and MiAE self-supervised framework that outperforms baselines for large-scale protein fold classification.
2D-ProteinRAG is a dual-dimensional RAG framework that incorporates BLAST workflows plus horizontal attribute alignment and vertical homology denoising to improve protein-text QA on both in-distribution and out-of-distribution cases.
Bucket Masking improves protein fitness prediction by up to 14% over random masking by preferentially masking structurally coupled residue groups on four downstream tasks.
Hyformer jointly models molecule generation and property prediction via alternating attention and joint pre-training, showing synergistic gains in conditional sampling, OOD prediction, and a drug design case for antimicrobial peptides.
citing papers explorer
-
RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts
RefusalBench shows strict refusal rates fail to rank frontier LLMs correctly on biological safety, with provider effects and partial-compliance patterns that binary metrics miss.
-
Protein-Based Fish Species Identification: Dataset, Models, and Insights from Native Bangladeshi Fish
Introduces first protein sequence dataset for nine Bangladeshi fish species and a deployable hybrid CNN-Transformer model achieving 79.8% accuracy with strong efficiency advantages over ProtBERT.
-
OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning
OmicsLM integrates continuous omics embeddings into LLMs for multi-sample biological reasoning, matching specialized models on profile tasks while outperforming them and general LLMs on language-guided QA over real expression data.
-
AMix-2: Establishing Protein as a Native Modality in Large Language Models
AMix-2 unifies protein sequences and text in one LLM via shared tokens and block-wise diffusion modeling, introduces the ProteinArena benchmark, and reports competitive performance against task-specific protein models and frontier LLMs.
-
TACK: A Statistical Evaluation of Degradation Activity on a Novel TArgeting Chimeras Knowledge Dataset
A new aggregated PROTAC dataset shows potency is more predictable than maximum degradation by ML, with classical methods outperforming a specialized graph neural network.
-
Protein Fold Classification at Scale: Benchmarking and Pretraining
Introduces TEDBench benchmark and MiAE self-supervised framework that outperforms baselines for large-scale protein fold classification.
-
Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework
2D-ProteinRAG is a dual-dimensional RAG framework that incorporates BLAST workflows plus horizontal attribute alignment and vertical homology denoising to improve protein-text QA on both in-distribution and out-of-distribution cases.
-
Structure-Aware Masking for Protein Representation Learning
Bucket Masking improves protein fitness prediction by up to 14% over random masking by preferentially masking structurally coupled residue groups on four downstream tasks.
-
Synergistic Benefits of Joint Molecule Generation and Property Prediction
Hyformer jointly models molecule generation and property prediction via alternating attention and joint pre-training, showing synergistic gains in conditional sampling, OOD prediction, and a drug design case for antimicrobial peptides.