Biology

Today, as a result of information sharing and rapid sequencing, bioinformatics is deluged with data (“big data”) and faces the daunting multi-dimensional challenges of sequence, structure, expression, and pathway analyses. The explicit understanding of protein secondary structure and beyond can yield great benefit to understanding of human diseases and development of therapeutic drugs and enzymes in the ensuing years. The myriad of machine learning methodologies have their respective relative strengths in various bioinformatics disciplines: hidden Markov model for sequence and profile alignment; support vector machine for protein fold recognition; Bayesian networks and gene regulatory network; and artificial neural networks (ANN) and protein secondary structure prediction