Sequence-based data-constraint deep learning framework to predict spider dragline mechanical properties

Abstract We establish a deep-learning framework for describing the mechanical behavior of spider dragline silks to clarify the missing link between the sequence and mechanics of this exceptionally strong and tough biomaterial. The method utilizes sequence and mechanical property data of dragline spider silk as well as enriching descriptors such as residue-level mobility (B-factor) predictions. Our sequence representation captures the relative position, repetitiveness, as well as descriptors of amino acids that serve to physically enrich the model. We obtain high Pearson correlation coefficients (0.76-0.88) for strength, toughness, and other properties, which show that our B-factor based representation outperforms pure sequence-based models or models that use other descriptors. We prove the utility of our framework by identifying influential motifs, and also by demonstrating how the B-factor serves to pinpoint potential mutations that improve strength and toughness, thereby establishing a validated, predictive, and interpretable sequence model for designing sustainable biomaterials with sequence-defined properties.