cs.LGNov 7, 2026

ProtLink: Sequence and Multispecies Graph Context for Protein Interaction Prediction

Authors: Xingyuan Zhang

Organizations: Department of Chemistry, Wu Tsai Neurosciences Institute, Stanford University

Abstract

Predicting protein-protein interactions (PPIs) from sequence alone is difficult, while known interaction networks may provide informative biological context. We introduce ProtLink, a sequence-conditioned graph-learning framework that combines frozen ESM-2 representations with protein interaction topology and orthogroup-mediated connections between species. We compare sequence-only models, GraphSAGE, a homogeneous graph transformer, and a heterogeneous graph transformer (HGT) for human PPI prediction. In an initial edge-level comparison, three-layer multispecies HGT with ESM-2 650M features achieves an average precision (AP) of 0.980 under random negative sampling, compared with 0.951 for the homogeneous transformer; its AP decreases to 0.878 with two-hop-preferred negatives. In controlled three-seed experiments, three-layer full-graph HGT obtains an AP of 0.9701±0.00220.9701\pm0.0022, exceeding an orthogroup-only model (0.9435±0.00940.9435\pm0.0094). The corresponding two-layer comparison shows little additional benefit from non-human PPI edges, consistent with the greater message-passing depth needed to transmit their information. For human proteins excluded from training interactions, multispecies HGT achieves 0.8335±0.00940.8335\pm0.0094 AP versus 0.6482±0.00520.6482\pm0.0052 for a sequence-only pair model. These results identify the value, depth dependence, and limits of evolutionary graph context while distinguishing prediction of held-out edges from generalization to held-out proteins.

Figures & tables

Explore similar work

CardsList
  1. MKGR: Multimodal Knowledge-Graph Representation Learning for Cold-Start Protein-Protein Interaction Prediction

    Jul 2, 2026Wenbo ZhangKG EmbeddingProtein-Protein Interaction Prediction

  2. Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach

    May 11, 2026Ziqi Gao, Chenyi Zi, Zijing Liu +3Prompt LearningGraph Representation Learning

  3. Structure-Guided Adaptive Propagation for Protein-Protein Interaction Site Prediction

    Jun 1, 2026Enqiang Zhu, Yizi Liu, Yilong Luo +3Protein-Protein Interaction PredictionGraph Diffusion