首页|Robert Koch Institute Reports Findings in Machine Learning (Interpretable molecu lar encodings and representations for machine learning tasks)
Robert Koch Institute Reports Findings in Machine Learning (Interpretable molecu lar encodings and representations for machine learning tasks)
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 Machine Learning is th e subject of a report. According to news reporting out of Berlin, Germany, by Ne wsRx editors, research stated, "Molecular encodings and their usage in machine l earning models have demonstrated significant breakthroughs in biomedical applica tions, particularly in the classification of peptides and proteins. To this end, we propose a new encoding method: Interpretable Carbon-based Array of Neighborh oods (iCAN)." Our news journalists obtained a quote from the research from Robert Koch Institu te, "Designed to address machine learning models' need for more structured and l ess flexible input, it captures the neighborhoods of carbon atoms in a counting array and improves the utility of the resulting encodings for machine learning m odels. The iCAN method provides interpretable molecular encodings and representa tions, enabling the comparison of molecular neighborhoods, identification of rep eating patterns, and visualization of relevance heat maps for a given data set. When reproducing a large biomedical peptide classification study, it outperforms its predecessor encoding. When extended to proteins, it outperforms a lead stru cture-based encoding on 71% of the data sets. Our method offers in terpretable encodings that can be applied to all organic molecules, including ex otic amino acids, cyclic peptides, and larger proteins, making it highly versati le across various domains and data sets."
BerlinGermanyEuropeCyborgsEmergi ng TechnologiesMachine Learning
NETL
NSTL
