Functional Site Discovery From Incomplete Training Data: A Case Study With Nucleic Acid–Binding Proteins

Wang, Wenchuan and Langlois, Robert and Langlois, Marina and Genchev, Georgi Z. and Wang, Xiaolei and Lu, Hui (2019) Functional Site Discovery From Incomplete Training Data: A Case Study With Nucleic Acid–Binding Proteins. Frontiers in Genetics, 10. ISSN 1664-8021

[thumbnail of pubmed-zip/versions/2/package-entries/fgene-10-00729.pdf] Text
pubmed-zip/versions/2/package-entries/fgene-10-00729.pdf - Published Version

Download (2MB)

Abstract

Function annotation efforts provide a foundation to our understanding of cellular processes and the functioning of the living cell. This motivates high-throughput computational methods to characterize new protein members of a particular function. Research work has focused on discriminative machine-learning methods, which promise to make efficient, de novo predictions of protein function. Furthermore, available function annotation exists predominantly for individual proteins rather than residues of which only a subset is necessary for the conveyance of a particular function. This limits discriminative approaches to predicting functions for which there is sufficient residue-level annotation, e.g., identification of DNA-binding proteins or where an excellent global representation can be divined. Complete understanding of the various functions of proteins requires discovery and functional annotation at the residue level. Herein, we cast this problem into the setting of multiple-instance learning, which only requires knowledge of the protein’s function yet identifies functionally relevant residues and need not rely on homology. We developed a new multiple-instance leaning algorithm derived from AdaBoost and benchmarked this algorithm against two well-studied protein function prediction tasks: annotating proteins that bind DNA and RNA. This algorithm outperforms certain previous approaches in annotating protein function while identifying functionally relevant residues involved in binding both DNA and RNA, and on one protein-DNA benchmark, it achieves near perfect classification.

Item Type: Article
Subjects: STM Open Press > Medical Science
Depositing User: Unnamed user with email support@stmopenpress.com
Date Deposited: 02 Feb 2023 11:54
Last Modified: 30 Jul 2024 06:34
URI: http://journal.submissionpages.com/id/eprint/260

Actions (login required)

View Item
View Item