Predicting Flavonoid UGT Regioselectivity

[摘要] Machine learning was applied to a challenging and biologically significant protein classification problem: the prediction of avonoid UGT acceptor regioselectivity from primary sequence. Novel indices characterizing graphical models of residues were proposed and found to be widelydistributed among existing amino acid indices and to cluster residues appropriately. UGT subsequences biochemically linked to regioselectivitywere modeled as sets of index sequences. Several learning techniques incorporating these UGT models were compared with classifications basedon standard sequence alignment scores. These techniques included an application of time series distance functions to protein classification. Timeseries distances defined on the index sequences were used in nearest neighbor and support vector machine classifiers. Additionally, Bayesian neural network classifiers were applied to the index sequences. The experimentsidentified improvements over the nearest neighbor and support vector machineclassifications relying on standard alignment similarity scores, as well asstrong correlations between specific subsequences and regioselectivities.

[学科分类] 生物技术