AnnoPRO: a strategy for protein function annotation based on multi-scale protein representation and a hybrid deep learning of dual-path encoding

Abstract

Protein function annotation has been one of the longstanding issues in biological sciences, and various computational methods have been developed. However, the existing methods suffer from a serious long-tail problem, with a large number of GO families containing few annotated proteins. Herein, an innovative strategy named AnnoPRO was therefore constructed by enabling sequence-based multi-scale protein representation, dual-path protein encoding using pre-training, and function annotation by long short-term memory-based decoding. A variety of case studies based on different benchmarks were conducted, which confirmed the superior performance of AnnoPRO among available methods. Source code and models have been made freely available at: https://github.com/idrblab/AnnoPRO and https://zenodo.org/records/10012272

Predicting Antimicrobial Peptides Using ESMFold-Predicted Structures and ESM-2-Based Amino Acid Features with Graph Deep Learning

“…We will include the MSA-free HelixFold-Single method to predict 3D peptide structures as another alternative to ESMFold . Additionally, it will be added new strategies to build the graph-based representations, such as the use of contact maps predicted by the ESM-2 models, the use of distance functions other than the Euclidean distance, the use of the criteria implemented in the Graphein library, among others . In this way, it can be analyzed if topologically different graphs could be built to improve the performance of GDL-based models.…”