Details

Autor(en) / Beteiligte

• Opiyo, Stephen O
• Moriyama, Etsuko N

Titel

Protein Family Classification with Partial Least Squares

Ist Teil von

• Journal of proteome research, 2007-02, Vol.6 (2), p.846-853

Ort / Verlag

United States: American Chemical Society

Erscheinungsjahr

2007

Quelle

MEDLINE

Beschreibungen/Notizen

• 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. Keywords: partial least square • physico-chemical properties • amino acid composition • profile hidden Markov model • G-protein coupled receptors