Rescalli, S. | Search bioRxiv

bioRxiv2026

Residue-level predictions of the protein-protein interactions of the hepatitis B virus core and envelope proteins

We here predicted the interactions between the capsid (Cp) and envelope proteins (S/M/LHBs) of the hepatitis B virus using a recently established mutation-driven deep-learning model, as well as coevolution signatures that serve as markers of physical interactions and/or functional relationships. The sequence-based analyses reveal putative protein-protein interaction (PPI) hotspots in proteins, and identify abundant coevolved residues within and across proteins. We analyze the results with a focus on the intermolecular interactions between Cp and the large envelope protein LHBs, especially its disordered preS domain. We compare the predicted PPI interface sites to previous evidence on PPIs, derived from mutational analyses described in the literature. We equally integrate experimental NMR data that provide a rationale for the previous observation that spike-binding peptides inhibit core-envelope interactions. Our work sheds new light on the molecular mechanisms at play on HBV envelopment, and provides starting points for the experimental investigation of these interactions using structural and molecular virology approaches.

biophysics↗

bioRxiv2026

X-PAIR: an ultrafast multitask framework for proteome-scale reconstruction of PPI networks and partner-specific interfaces from sequence

Protein-protein interaction prediction and residue-level interface localisation are biologically intertwined but usually treated as separate computational problems. Here we present X-PAIR, a sequence-based multitask deep learning framework that jointly predicts whether two proteins interact and identifies their partner-specific interface residues. By combining protein language-model representations with lightweight cross-attention, X-PAIR requires neither structural templates nor multiple-sequence alignments. Across leakage-controlled benchmarks, it outperforms existing methods in both tasks, with substantial gains in interface localisation. Multitask learning preserves single-task performance while returning both outputs at near-single-task cost, enabling one million protein pairs to be analysed in under two hours--approximately 500-fold faster for interface prediction and 20-fold faster for PPI prediction than current approaches--thereby enabling proteome-scale analysis. Cross-species analyses reveal distinct evolutionary dependencies: interaction prediction benefits from multispecies training, whereas interface localisation remains robust across taxonomic scales. X-PAIR thus links proteome-scale interaction discovery to the residue-level determinants of partner-specific molecular recognition.

bioinformatics↗