Multitask Learning-Based Approaches for Protein Function Prediction
Document Type
Article
Publication Date
1-1-2025
Abstract
Advancements in sequencing technologies have resulted in a massive growth in the number of sequences available. Only a small fraction of the proteins in UniProtKB have been functionally annotated. Understanding the roles and studying the mechanisms of newly discovered proteins is one of the most important biological problems in the post-genomic era. To address the sequence-function gap many computational methods have been developed. This chapter reviews Multitask Learning (MTL)-based approaches for protein function prediction, highlighting its potential to enhance both predictive accuracy and computational efficiency in bioinformatics. MTL utilizes shared representations to leverage common information across related tasks, improving predictive performance. Key findings reveal that MTL improves predictive performance by integrating shared features across related tasks.
Publication Title
Methods in Molecular Biology
Recommended Citation
Bahmani, S.,
Chaudhari, M.,
Carrier, C.,
Garrett, S.,
Pratyush, P.,
&
KC, D.
(2025).
Multitask Learning-Based Approaches for Protein Function Prediction.
Methods in Molecular Biology,
2947, 75-88.
http://doi.org/10.1007/978-1-0716-4662-5_4
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p2/1969