We developed machine learning supervised approach for protein sequence retrieval and for protein classification in large scale. Our proposed approach provides significantly faster query processing time than commonly used alignment-based algorithms.
Kimothi, Dhananjay and Biyani, Pravesh and Hogan, James M and Soni, Akshay and Kelly, Wayne
Distributed representations for biological sequence analysis
Kimothi, Dhananjay and Soni, Akshay and Biyani, Pravesh and Hogan, James M
arXiv:1608.05949
Learning supervised embeddings for large scale sequence comparisons
Kimothi, Dhananjay and Biyani, Pravesh and Hogan, James M and Soni, Akshay and Kelly, Wayne
journal.pone.0216636
Metric learning on biological sequence embeddings
Kimothi, Dhananjay and Shukla, Ankita and Biyani, Pravesh and Anand, Saket and Hogan, James M
ieee:8227769
Sequence representations and their utility for predicting protein-protein interactions
Kimothi, Dhananjay and Biyani, Pravesh and Hogan, James M
biorXiv:2019.12.31.890699