Читать книгу Biomedical Data Mining for Information Retrieval - Группа авторов - Страница 39

AI and ML have come up as great tools for structure prediction but these techniques rely to a great deal on collection of phenotype data, and not genomic data which may be its disadvantage. Genome researchers have learned that much of the variation between individuals is the result of a number of discrete, single-base changes also known as single nucleotide polymorphisms, or SNP’s in the human genome, which affects the phenotype. Application of ML to SNP data can be done in a manner similar to its application to microarray data which can be employed for supervised learning to identify differences in SNP patterns between people who respond well to a particular drug versus those who respond poorly. This can also be used for supervised learning to identify SNP patterns predictive of disease if possible. If the highly predictive SNP’s appear within genes may indicate that these genes may be important for conferring disease resistance or susceptibility, or the proteins they encode may be potential drug targets an important finding for a doctor and a researcher. Constructing models of biological pathways or even an entire cell in silico cell is a goal of systems biology which may be possible using the advanced computational techniques.

Machine learning has revolutionized the field of biology and medicine where researchers have employed machine learning to make gene chips more practical and useful. Data that might have taken years to collect, now takes a week. Biologist are aided greatly by the supervised and unsupervised learning methods that many are using to make sense of the large amount of data now available to them. As a result a rapid increase has occurred in the rate at which biologists are able to understand the molecular processes that underlie and govern the function of biological systems which can be used for a variety of important medical applications such as diagnosis, prognosis, and drug response. As our vast amount of genomic and similar types of data continues to grow, the role of computational techniques, especially machine learning, will grow with it. These algorithms will enable us to handle the task of analyzing this data to yield valuable insight into the biological systems that surround us and the diseases that affect us.