Rethinking peptide developability with sequence-only models: interpretable screening of microplastic-binding peptides...

Designing peptides for microplastic targeting is intrinsically multi-objective: sequence motifs that promote adsorption to hydrophobic polymers frequently elevate developability risks, including hemolysis, non-specific adsorption, and poor aqueous solubility. In this paper, we show that accurate developability screening can be achieved from sequence alone by focusing on the readout that converts token-level foundation model representations into peptide-level decisions. We introduce gated query pooling (GQP), a lightweight, backbone-agnostic evidence-selection head that learns a small set of query vectors to extract complementary signals from protein language model embeddings and gates them adaptively per peptide. With a consistent evaluation protocol and identical splits for all methods, GQP with sequence-only backbones reaches 91.09%, 86.30%, and 75.56% accuracy on hemolysis, non-fouling, and solubility, respectively, outperforming representative sequence-only and AlphaFold-augmented Multi-Peptide baselines. Beyond predictive accuracy, attention diagnostics and controlled counterfactual substitutions enable residue-level, testable design rules that connect model outputs to actionable sequence edits. Finally, integrating these developability constraints with PepBD-derived affinity scores for polyethylene, polypropylene, and polyethylene terephthalate supports scalable multi-objective prioritization of microplastic-binding candidates and reveals non-fouling as a dominant feasibility bottleneck, with coarse-grained molecular dynamics triage providing complementary physical evidence supporting the plausibility of the PepBD-prioritized selections.