Unsupervised protein embeddings outperform hand-crafted sequence and structure features at predicting molecular function.
Bioinformatics
; 37(2): 162-170, 2021 04 19.
Article
in En
| MEDLINE
| ID: mdl-32797179
ABSTRACT
MOTIVATION Protein function prediction is a difficult bioinformatics problem. Many recent methods use deep neural networks to learn complex sequence representations and predict function from these. Deep supervised models require a lot of labeled training data which are not available for this task. However, a very large amount of protein sequences without functional labels is available. RESULTS:
We applied an existing deep sequence model that had been pretrained in an unsupervised setting on the supervised task of protein molecular function prediction. We found that this complex feature representation is effective for this task, outperforming hand-crafted features such as one-hot encoding of amino acids, k-mer counts, secondary structure and backbone angles. Also, it partly negates the need for complex prediction models, as a two-layer perceptron was enough to achieve competitive performance in the third Critical Assessment of Functional Annotation benchmark. We also show that combining this sequence representation with protein 3D structure information does not lead to performance improvement, hinting that 3D structure is also potentially learned during the unsupervised pretraining. AVAILABILITY AND IMPLEMENTATION Implementations of all used models can be found at https//github.com/stamakro/GCN-for-Structure-and-Function. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Full text:
1
Database:
MEDLINE
Main subject:
Software
/
Proteins
Type of study:
Prognostic_studies
/
Risk_factors_studies
Language:
En
Journal:
Bioinformatics
Journal subject:
INFORMATICA MEDICA
Year:
2021
Type:
Article
Affiliation country:
Spain