In-Pero: Exploiting Deep Learning Embeddings of Protein Sequences to Predict the Localisation of Peroxisomal Proteins.

M. Anteghini*, V.A.P. Martins dos Santos, E. Saccenti*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Peroxisomes are ubiquitous membrane-bound organelles, and aberrant localisation of peroxisomal proteins contributes to the pathogenesis of several disorders. Many computational methods focus on assigning protein sequences to subcellular compartments, but there are no specific tools tailored for the sub-localisation (matrix vs. membrane) of peroxisome proteins. We present here In-Pero, a new method for predicting protein sub-peroxisomal cellular localisation. In-Pero combines standard machine learning approaches with recently proposed multi-dimensional deep-learning representations of the protein amino-acid sequence. It showed a classification accuracy above 0.9 in predicting peroxisomal matrix and membrane proteins. The method is trained and tested using a double cross-validation approach on a curated data set comprising 160 peroxisomal proteins with experimental evidence for sub-peroxisomal localisation. We further show that the proposed approach can be easily adapted (In-Mito) to the prediction of mitochondrial protein localisation obtaining performances for certain classes of proteins (matrix and inner-membrane) superior to existing tools.
Original languageEnglish
Article number6409
JournalInternational Journal of Molecular Sciences
Volume22
Issue number12
DOIs
Publication statusPublished - 15 Jun 2021

Keywords

  • protein sequence encoding and embedding; machine learning; neural networks; subcellular localisation; sub-peroxisomal localisation; sub-mitochondrial localisation

Fingerprint

Dive into the research topics of 'In-Pero: Exploiting Deep Learning Embeddings of Protein Sequences to Predict the Localisation of Peroxisomal Proteins.'. Together they form a unique fingerprint.

Cite this