DeepMito: accurate prediction of protein sub-mitochondrial localization using convolutional neural networks

Abstract

Motivation The correct localization of proteins in cell compartments is a key issue for their function. Particularly, mitochondrial proteins are physiologically active in different compartments and their aberrant localization contributes to the pathogenesis of human mitochondrial pathologies. Many computational methods exist to assign protein sequences to subcellular compartments such as nucleus, cytoplasm and organelles. However, a substantial lack of experimental evidence in public sequence databases hampered so far a finer grain discrimination, including also intra-organelle compartments. Results We describe DeepMito, a novel method for predicting protein sub-mitochondrial cellular localization. Taking advantage of powerful deep-learning approaches, such as convolutional neural networks, our method is able to achieve very high prediction performances when discriminating among four different mitochondrial compartments (matrix, outer, inner and intermembrane regions). The method is trained and tested in cross-validation on a newly generated, high-quality dataset comprising 424 mitochondrial proteins with experimental evidence for sub-organelle localizations. We benchmark DeepMito towards the only one recent approach developed for the same task. Results indicate that DeepMito performances are superior. Finally, genomic-scale prediction on a highly-curated dataset of human mitochondrial proteins further confirms the effectiveness of our approach and suggests that DeepMito is a good candidate for genome-scale annotation of mitochondrial protein subcellular localization. Availability and implementation The DeepMito web server as well as all datasets used in this study are available at http://busca.biocomp.unibo.it/deepmito. A standalone version of DeepMito is available on DockerHub at https://hub.docker.com/r/bolognabiocomp/deepmito. DeepMito source code is available on GitHub at https://github.com/BolognaBiocomp/deepmito Supplementary information Supplementary data are available at Bioinformatics online.

Two neuronal peptides encoded from a single transcript regulate mitochondrial complex III inDrosophila

“…Tim8 and Tim13 form a complex in the mitochondrial intermembrane space, where they act as a chaperone to bind and stabilize transmembrane proteins that transit to the inner mitochondrial membrane (CHACINSKA et al 2009). The deep learning algorithm DeepMito (SAVOJARDO et al 2020) predicts that Sloth1 orthologs localize to the mitochondrial inner membrane, and its domain structure is similar to other inner membrane proteins (CHACINSKA et al 2009). Therefore, our results suggest that Sloth1 and Sloth2 localize to mitochondria, likely to the inner membrane.…”

MULocDeep: A deep-learning framework for protein subcellular and suborganellar localization prediction with residue-level interpretation

“…The details of the training process and hyperparameter configuration are introduced in the Methods section. 20 . MULocDeep performed better than DeepMito for every mitochondrial compartment in both datasets (Table 2).…”

“…Most of the methods focus on the prediction of protein localization at the subcellular level. Although there are some predictors for specific suborganelle localizations [19][20][21][22] , a systematic suborganelle localization prediction tool at the whole-cell scale is still missing. Furthermore, protein localization is a multi-label problem; i.e., one protein may be found in several different compartments in a cell.…”

BITS2019: the sixteenth annual meeting of the Italian society of bioinformatics

“…In the research area of proteomics, Savojardo et al presented the work "Large-scale prediction and analysis of protein submitochondrial localisation with DeepMito" [16]. In that work, authors applied their previously developed DeepMito algorithm [17] on large scale data. They performed proteome-wide prediction of submitochondrial localisation on representative proteomes of five species including human, mouse, yeast, fly and Arabidopsis thaliana.…”