Figure 1.

epitope1D workflow with four main stages: (1) Data Collection and Curation, which includes the selection of benchmarks and also the curation of an updated large-scale data set; (2) Feature Engineering, representing the step where all descriptors were calculated; (3) Explainable Machine Learning, in which the supervised machine learning classifiers were analyzed in terms of their predictive power, explainability, and assessed via cross-validation and blind-test approaches; (4) Web Server Interface, where epitope1D is made publicly available as a user-friendly web interface and API.