首页|Polytechnic University of Tirana Reports Findings in Machine Learning (A compara tive study of supervised and unsupervised machine learning algorithms applied to human microbiome)
Polytechnic University of Tirana Reports Findings in Machine Learning (A compara tive study of supervised and unsupervised machine learning algorithms applied to human microbiome)
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 – New research on Machine Learning is the subject o f a report. According to news reporting out of Tirana, Albania, by NewsRx editor s, research stated, “The human microbiome, consisting of diverse bacterial, fun gal, protozoan and viral species, exerts a profound influence on various physiol ogical processes and disease susceptibility. However, the complexity of microbio me data has presented significant challenges in the analysis and interpretation of these intricate datasets, leading to the development of specialized software that employs machine learning algorithms for these aims.” Our news journalists obtained a quote from the research from the Polytechnic Uni versity of Tirana, “In this paper, we analyze raw data taken from 16S rRNA gene sequencing from three studies, including stool samples from healthy control, pat ients with adenoma, and patients with colorectal cancer. Firstly, we use network -based methods to reduce dimensions of the dataset and consider only the most im portant features. In addition, we employ supervised machine learning algorithms to make prediction. Results show that graph-based techniques reduces dimen-sion from 255 up to 78 features with modularity score 0.73 based on different central ity measures. On the other hand, projection methods (non-negative matrix factori zation and principal component analysis) reduce dimensions to 7 features. Furthe rmore, we apply supervised machine learning algorithms on the most important fea tures obtained from centrality measures and on the ones obtained from projection methods, founding that the evaluation metrics have approximately the same score s when applying the algorithms on the entire dataset, on 78 feature and on 7 fea tures. This study demonstrates the efficacy of graph-based and projection method s in the interpretation for 16S rRNA gene sequencing data.”
NETL
NSTL
