# Phage-host interaction prediction

2 related articles

Subscribe to updates

bioRxiv Nov 5, 2026
BacLLM folds UniProt annotation knowledge into a protein language model, so sequence-only input can call resistance genes and rank phage candidates
BacLLM injects semantic representations of UniProt annotations, encoded by a large language model, into an ESM-2 sequence encoder through cross-modal contrastive learning, so inference reads amino acid sequences alone. Across six resistance-prediction benchmarks, BacLLM (4B) beat Ankh, ESM-2, ProteinBERT and ProTrek in mean F1 under both logistic regression and an RBF-kernel support vector machine; on the SHV-1 β-lactamase P0AD64 it recovered six of eight experimentally supported resistance-attenuating sites among the top 65 ranked positions, while ESM-2 recovered none. The text branch is removed after training, so these gains come from sequence input, not annotation input.
BacLLM injects semantic representations of UniProt annotations, encoded by a large language model, into an ESM-2 sequence encoder through cross-modal contrastive learning, so inference reads amino acid sequences alone. Across six resistance-prediction benchmarks, BacLLM (4B) beat Ankh, ESM-2, ProteinBERT and ProTrek in mean F1 under both logistic regression and an RBF-kernel support vector machine; on the SHV-1 β-lactamase P0AD64 it recovered six of eight experimentally supported resistance-attenuating sites among the top 65 ranked positions, while ESM-2 recovered none. The text branch is removed after training, so these gains come from sequence input, not annotation input.
BacLLM Protein Language Model Antimicrobial resistance Contrastive Learning Phage-host interaction prediction
bioRxiv Oct 11, 2026
Phage matching stops relying on one embedding: routing by query novelty lifts both-unseen AUPRC from 0.036 to 0.671
Phage therapy needs a matching phage for each clinical bacterial isolate, and conventional experimental screening is slow and labor-intensive. PhageHost-GNN encodes phage receptor-binding proteins and bacterial K-locus proteins as sequence, structure and genomic-context embeddings, feeds them to a graph neural network, and automatically selects the embedding model best suited to how novel a query strain is relative to the training set. On the Spain-derived Beamud2023 data, with both hosts and phages unseen, the routed model reached an AUPRC of 0.671, while fixed-embedding models stayed at or below 0.036.
Phage therapy needs a matching phage for each clinical bacterial isolate, and conventional experimental screening is slow and labor-intensive. PhageHost-GNN encodes phage receptor-binding proteins and bacterial K-locus proteins as sequence, structure and genomic-context embeddings, feeds them to a graph neural network, and automatically selects the embedding model best suited to how novel a query strain is relative to the training set. On the Spain-derived Beamud2023 data, with both hosts and phages unseen, the routed model reached an AUPRC of 0.671, while fixed-embedding models stayed at or below 0.036.
Shenzhen University Southern University of Science and Technology
Biffon Manyura Momanyi（First author）Lu Fan（Corresponding author）
PhageHost-GNN Phage-host interaction prediction Graph Neural Network Protein Language Model Fine-tuning

You’re all caught up

BacLLM folds UniProt annotation knowledge into a protein language model, so sequence-only input can call resistance genes and rank phage candidates

Phage matching stops relying on one embedding: routing by query novelty lifts both-unseen AUPRC from 0.036 to 0.671