IMLP, a predictor for internal matrix targeting-like sequences in mitochondrial proteins

Kevin Schneider, David Zimmer, Henrik Nielsen, Johannes M. Herrmann, Timo Mühlhaus*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

24 Downloads (Pure)


Matrix targeting sequences (MTSs) direct proteins from the cytosol into mitochondria. Efficient targeting often relies on internal matrix targeting-like sequences (iMTS-Ls) which share structural features with MTSs. Predicting iMTS-Ls was tedious and required multiple tools and webservices. We present iMLP, a deep learning approach for the prediction of iMTS-Ls in protein sequences. A recurrent neural network has been trained to predict iMTS-L propensity profiles for protein sequences of interest. The iMLP predictor considerably exceeds the speed of existing approaches. Expanding on our previous work on iMTS-L prediction, we now serve an intuitive iMLP webservice available at and a stand-alone command line tool for power user in addition.

Original languageEnglish
JournalBiological Chemistry
Issue number8
Pages (from-to)937-943
Publication statusPublished - 2021

Bibliographical note

Funding Information:
Research funding: This work was funded by the TRR 175 (project D02) and the Landesforschungsschwerpunkt BioComp.


  • Deep learning
  • Mitochondria
  • Protein targeting
  • Recurrent neural network
  • Sequence analysis
  • Webservice


Dive into the research topics of 'IMLP, a predictor for internal matrix targeting-like sequences in mitochondrial proteins'. Together they form a unique fingerprint.

Cite this