Anderson Rodrigues dos Santos

GenPPi 1.5 improves protein interaction prediction by integrating Random Forest with Reduced Interaction Sampling, enhancing performance in low sequence identity scenarios.

This paper develops a fast machine learning method to classify non-classical secreted bacterial proteins with 91% accuracy, outperforming existing methods in speed without sacrificing accuracy.

The paper integrates the Medpipe microservice with Pannotator to enhance genomic annotation with immunological and subcellular location features.

GENPPI creates protein interaction networks from genomes using evolutionary characteristics, distinguishing biovars and species in Corynebacterium pseudotuberculosis.