skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: PreDSLpmo: A neural network-based prediction tool for functional annotation of lytic polysaccharide monooxygenases

Abstract

Lytic polysaccharide monooxygenases (LPMOs), a family of copper-dependent oxidative enzymes, boost the degradation of polysaccharides such as cellulose, chitin, and others. While experimental methods are used to validate LPMO function, a computational method that can aid experimental methods and provide fast and accurate classification of sequences into LPMOs and its families would be an important step towards understanding the breadth of contributions these enzymes make in deconstruction of recalcitrant polysaccharides. In this study, we developed a machine learning-based tool called PreDSLpmo that employs two different approaches to functionally classify protein sequences into the major LPMO families (AA9 and AA10). The first approach uses a traditional neural network or multilayer percerptron-based approach, while the second employs bi-directional long short-term memory for sequence classification. Finally, our method shows improvement in predictive power when compared with dbCAN2, an existing HMM-profile-based CAZyme predicting tool, on both validation and independent benchmark set.

Authors:
 [1];  [2];  [3]; ORCiD logo [1]
  1. Jaypee Univ. of Information Technology, Waknaghat (India)
  2. Michigan State Univ., East Lansing, MI (United States)
  3. Univ. of Wisconsin, Madison, WI (United States)
Publication Date:
Research Org.:
Univ. of Wisconsin, Madison, WI (United States). Great Lakes Bioenergy Research Center
Sponsoring Org.:
USDOE Office of Science (SC), Biological and Environmental Research (BER)
OSTI Identifier:
1601231
Grant/Contract Number:  
SC0018409; FC02-07ER64494
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Biotechnology
Additional Journal Information:
Journal Volume: 308; Journal Issue: C; Journal ID: ISSN 0168-1656
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES; Lytic polysaccharide monooxygenases; Machine learning technique; Neural network; Long short-term memory; Proteome

Citation Formats

Srivastava, Pulkit Anupam, Hegg, Eric L., Fox, Brian G., and Yennamalli, Ragothaman M.. PreDSLpmo: A neural network-based prediction tool for functional annotation of lytic polysaccharide monooxygenases. United States: N. p., 2019. Web. https://doi.org/10.1016/j.jbiotec.2019.12.002.
Srivastava, Pulkit Anupam, Hegg, Eric L., Fox, Brian G., & Yennamalli, Ragothaman M.. PreDSLpmo: A neural network-based prediction tool for functional annotation of lytic polysaccharide monooxygenases. United States. https://doi.org/10.1016/j.jbiotec.2019.12.002
Srivastava, Pulkit Anupam, Hegg, Eric L., Fox, Brian G., and Yennamalli, Ragothaman M.. Mon . "PreDSLpmo: A neural network-based prediction tool for functional annotation of lytic polysaccharide monooxygenases". United States. https://doi.org/10.1016/j.jbiotec.2019.12.002. https://www.osti.gov/servlets/purl/1601231.
@article{osti_1601231,
title = {PreDSLpmo: A neural network-based prediction tool for functional annotation of lytic polysaccharide monooxygenases},
author = {Srivastava, Pulkit Anupam and Hegg, Eric L. and Fox, Brian G. and Yennamalli, Ragothaman M.},
abstractNote = {Lytic polysaccharide monooxygenases (LPMOs), a family of copper-dependent oxidative enzymes, boost the degradation of polysaccharides such as cellulose, chitin, and others. While experimental methods are used to validate LPMO function, a computational method that can aid experimental methods and provide fast and accurate classification of sequences into LPMOs and its families would be an important step towards understanding the breadth of contributions these enzymes make in deconstruction of recalcitrant polysaccharides. In this study, we developed a machine learning-based tool called PreDSLpmo that employs two different approaches to functionally classify protein sequences into the major LPMO families (AA9 and AA10). The first approach uses a traditional neural network or multilayer percerptron-based approach, while the second employs bi-directional long short-term memory for sequence classification. Finally, our method shows improvement in predictive power when compared with dbCAN2, an existing HMM-profile-based CAZyme predicting tool, on both validation and independent benchmark set.},
doi = {10.1016/j.jbiotec.2019.12.002},
journal = {Journal of Biotechnology},
number = C,
volume = 308,
place = {United States},
year = {2019},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share: