首页|Study Findings on Machine Learning Described by a Researcher at University of Ke ntucky (Predicting the Association of Metabolites with Both Pathway Categories a nd Individual Pathways)
Study Findings on Machine Learning Described by a Researcher at University of Ke ntucky (Predicting the Association of Metabolites with Both Pathway Categories a nd Individual Pathways)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on artificial intelligenc e is the subject of a new report. According to news reporting out of Lexington, Kentucky, by NewsRx editors, research stated, “Metabolism is a network of chemic al reactions that sustain cellular life. Parts of this metabolic network are def ined as metabolic pathways containing specific biochemical reactions.” Financial supporters for this research include National Science Foundation; Nati onal Institutes of Health. Our news correspondents obtained a quote from the research from University of Ke ntucky: “Products and reactants of these reactions are called metabolites, which are associated with certain human-defined metabolic pathways. Metabolic knowled gebases, such as the Kyoto Encyclopedia of Gene and Genomes (KEGG) contain metab olites, reactions, and pathway annotations; however, such resources are incomple te due to current limits of metabolic knowledge. To fill in missing metabolite p athway annotations, past machine learning models showed some success at predicti ng the KEGG Level 2 pathway category involvement of metabolites based on their c hemical structure. Here, we present the first machine learning model to predict metabolite association to more granular KEGG Level 3 metabolic pathways. We used a feature and dataset engineering approach to generate over one million metabol ite-pathway entries in the dataset used to train a single binary classifier. Thi s approach produced a mean Matthews correlation coefficient (MCC) of 0.806 ± 0.0 17 SD across 100 cross-validation iterations.”
University of KentuckyLexingtonKentu ckyUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesM achine Learning
NETL
NSTL
