Medizinische Universität Graz - Research portal
Navigation/Search
- Researchers
- Institutions
- Projects
- Publications
- Partners
- Sponsors
- Equipment
- Knowhow
- Fields of Research
"Faces" of the day:
Selected Publication:
SHR Neuro Cancer Cardio Lipid Metab Microb
Lu, AX; Lu, AX; Pritišanac, I; Zarin, T; Forman-Kay, JD; Moses, AM.
Discovering molecular features of intrinsically disordered regions by using evolution for contrastive learning.
PLoS Comput Biol. 2022; 18(6): e1010238
Doi: 10.1371/journal.pcbi.1010238
[OPEN ACCESS]
PubMed
FullText
FullText_MUG
- Co-authors Med Uni Graz
- Pritisanac Iva
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- A major challenge to the characterization of intrinsically disordered regions (IDRs), which are widespread in the proteome, but relatively poorly understood, is the identification of molecular features that mediate functions of these regions, such as short motifs, amino acid repeats and physicochemical properties. Here, we introduce a proteome-scale feature discovery approach for IDRs. Our approach, which we call "reverse homology", exploits the principle that important functional features are conserved over evolution. We use this as a contrastive learning signal for deep learning: given a set of homologous IDRs, the neural network has to correctly choose a held-out homolog from another set of IDRs sampled randomly from the proteome. We pair reverse homology with a simple architecture and standard interpretation techniques, and show that the network learns conserved features of IDRs that can be interpreted as motifs, repeats, or bulk features like charge or amino acid propensities. We also show that our model can be used to produce visualizations of what residues and regions are most important to IDR function, generating hypotheses for uncharacterized IDRs. Our results suggest that feature discovery using unsupervised neural networks is a promising avenue to gain systematic insight into poorly understood protein sequences.
- Find related publications in this database (using NLM MeSH Indexing)
- Amino Acid Sequence - administration & dosage
- Evolution, Molecular - administration & dosage
- Intrinsically Disordered Proteins - chemistry
- Protein Conformation - administration & dosage
- Proteome - metabolism