Signal peptide (SP) is a short peptide located in the N-terminus of proteins. It is essential to target and transfer transmembrane and secreted proteins to correct positions. Compared with traditional experimental methods to identify signal peptides, computational methods are faster and more efficient, which are more practical for analyzing thousands or even millions of protein sequences, especially for metagenomic data. Here we present Unbiased Organism-agnostic Signal Peptide Network (USPNet), a signal peptide classification and cleavage site prediction deep learning method that takes advantage of protein language models. We propose to apply label distribution-aware margin loss to handle data imbalance problems and use evolutionary information of protein to enrich representation and overcome species information dependence.
@article{arxiv.2312.08987,
title = {Unbiased organism-agnostic and highly sensitive signal peptide predictor with deep protein language model},
author = {Junbo Shen and Qinze Yu and Shenyang Chen and Qingxiong Tan and Jingcheng Li and Yu Li},
journal= {arXiv preprint arXiv:2312.08987},
year = {2023}
}