Protein family classification with partial least squares

Stephen O. Opiyo, Etsuko N. Moriyama

Research output: Contribution to journalArticlepeer-review

20 Scopus citations


The quality of protein function predictions relies on appropriate training of protein classification methods. Performance of these methods can be affected when only a limited number of protein samples are available, which is often the case in divergent protein families. Whereas profile hidden Markov models and PSI-BLAST presented significant performance decrease in such cases, alignment-free partial least-squares classifiers performed consistently better even when used to identify short fragmented sequences.

Original languageEnglish (US)
Pages (from-to)846-853
Number of pages8
JournalJournal of proteome research
Issue number2
StatePublished - Feb 2007


  • Amino acid composition
  • G-protein coupled receptors
  • Partial least square
  • Physico-chemical properties
  • Profile hidden Markov model

ASJC Scopus subject areas

  • General Chemistry
  • Biochemistry


Dive into the research topics of 'Protein family classification with partial least squares'. Together they form a unique fingerprint.

Cite this