⚠️ DeepMito Server Maintenance Notice
The DeepMito server will be unavailable due to scheduled maintenance from Tuesday, February 10th, 2026 at 01:00 AM (CET) until Wednesday, February 11th, 2026 at 7:00 PM (CET).
Any jobs submitted before the maintenance window and not completed in time will be permanently lost.
Please submit new jobs starting from Thursday, February 12th, 2026.
We apologize for the inconvenience and thank you for your understanding.
DeepMito
Mitochondrial proteins are physiologically active in different compartments and their aberrant localization contributes to the pathogenesis of human mitochondrial pathologies.
Here we present DeepMito, a novel method for predicting sub-mitochondrial localization and based on a convolutional neural network architecture to extract relevant patterns from primary features. Given an input protein, DeepMito is able to discriminate four different sub-mitochondrial compartments: outer membrane, inner membrane, intermembrane space and mitochondrial matrix.
More details on DeepMito can be found in the following paper:
Savojardo C, Bruciaferri N, Tartari G, Martelli PL, Casadio R. DeepMito: accurate prediction of protein submitochondrial localization using convolutional neural networks. Bioinformatics. 2019 Jun 20.