Deciphering functional dark matter: Machine and deep learning-based processing of protein embeddings enables targeted function discoveries
Preprint
Abstract
The ever-expanding catalogue of uncharacterized proteins – the so called functional dark matter - poses a major challenge for biotechnological and biomedical exploitation. Functional assessment of most proteins is hindered by the technical limitations of annotation transfer and by the propagation of erroneous annotations in databases. The common denominator here is the reliance on sequence similarities. However, these become inaccurate below certain thresholds and can diverge even at sequence identities around 70%. To approach this challenge, we implemented a strategy using embeddings generated by protein language models for targeted function discovery (PE-TFD). Datasets of proteins representing target as well as non-target functions were used to train supervised learning models. The resulting ensemble models yielded interpretable prediction scores, enabling the exploration of databases without relying on multiple sequence alignments or structural information. We here tested PE-TFD for the discovery of novel hydrogenases as proof-of-concept, resulting in the novel discovery of 773 [NiFe] and 1,929 [FeFe] hydrogenases that were not detected by established sequence- or profile-based approaches. Structural analyses supported their non-random nature and further revealed a significant number of enzymes lacking prior functional annotation. Our framework therefore enables interpretable function discovery in large-scale datasets and the exploitation of functional dark matter. GraphicalKeywords
Funding Information
- Karlsruhe Institute of Technology and the Helmholtz Society (POF4; 5207.0004.0012)
This publication has 84 references indexed in Scilit:
- Protein Structure Prediction: Challenges, Advances, and the Shift of Research ParadigmsGenomics, Proteomics & Bioinformatics, 2023
- PANTHER: Making genome‐scale phylogenetics accessible to allProtein Science, 2021
- A heterologously-expressed thermostable Pyrococcus furiosus cytoplasmic [NiFe]-hydrogenase I used as the catalyst of H2/air biofuel cellsInternational Journal of Hydrogen Energy, 2021
- Learning from nature: Understanding hydrogenase enzyme using computational approachWIREs Computational Molecular Science, 2019
- [FeFe]- and [NiFe]-hydrogenase diversity, mechanism, and maturationBiochimica et Biophysica Acta (BBA) - Molecular Cell Research, 2015
- Bisecting K-Means Initialization Technique for Protein Sequence Motif IdentificationLecture Notes in Computer Science, 2013
- Structure is three to ten times more conserved than sequence—A study of structural response in protein coresProteins: Structure, Function, and Bioinformatics, 2009
- Beyond the Twilight Zone: Automated prediction of structural properties of proteins by recursive neural networks and remote homology informationProteins: Structure, Function, and Bioinformatics, 2009
- The exchange activities of [Fe] hydrogenase (iron–sulfur-cluster-free hydrogenase) from methanogenic archaea in comparison with the exchange activities of [FeFe] and [NiFe] hydrogenasesJBIC Journal of Biological Inorganic Chemistry, 2007
- Basic Local Alignment Search ToolJournal of Molecular Biology, 1990