首页|Michigan State University Reports Findings in Machine Learning (Eliminating the Deadwood: A Machine Learning Model for CCS Knowledge-Based Conformational Focusi ng for Lipids)
Michigan State University Reports Findings in Machine Learning (Eliminating the Deadwood: A Machine Learning Model for CCS Knowledge-Based Conformational Focusi ng for Lipids)
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 East Lansing, Michigan , by NewsRx editors, research stated, “Accurate elucidation of gas-phase chemica l structures using collision cross section (CCS) values obtained from ion-mobili ty mass spectrometry benefits from a synergism between experimental and results. We have shown in recent work that for a molecule of modest size with a proscrib ed conformational space we can successfully capture a conformation(s) that can m atch experimental CCS values.” Our news journalists obtained a quote from the research from Michigan State Univ ersity, “However, for flexible systems such as fatty acids that have many rotata ble bonds and multiple intramolecular London dispersion interactions, it becomes necessary to sample a much greater conformational space. Sampling more conforme rs, however, accrues significant computational cost downstream in optimization s teps involving quantum mechanics. To reduce this computational expense for lipid s, we have developed a novel machine learning (ML) model to facilitate conformer filtering according to the estimated gasphase CCS values. Herein we report tha t the implementation of our CCS knowledge-based approach for conformational samp ling resulted in improved structure prediction agreement with experiment by achi eving favorable average CCS prediction errors of 2% for lipid syst ems in both the validation set and the test set. Moreover, most of the gas-phase candidate conformations obtained by using CCS focusing achieved lower energy-mi nimum geometries than the candidate conformations without focusing. Altogether, the implementation of this ML model into our modeling workflow has proven to be beneficial for both the quality of the results and the turnaround time.”
East LansingMichiganUnited StatesN orth and Central AmericaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
