首页|Research from Yale University Reveals New Findings on Machine Learning (Site-spe cific template generative approach for retrosynthetic planning)
Research from Yale University Reveals New Findings on Machine Learning (Site-spe cific template generative approach for retrosynthetic planning)
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 from Yale Universi ty by NewsRx journalists, research stated, "Retrosynthesis, the strategy of devi sing laboratory pathways by working backwards from the target compound, is cruci al yet chAllenging." Our news editors obtained a quote from the research from Yale University: "Enhan cing retrosynthetic efficiency requires overcoming the vast complexity of chemic al space, the limited known interconversions between molecules, and the chAlleng es posed by limited experimental datasets. This study introduces generative mach ine learning methods for retrosynthetic planning. The approach features three in novations: generating reaction templates instead of reactants or synthons to cre ate novel chemical transformations, Allowing user selection of specific bonds to change for human-influenced synthesis, and employing a conditional kernel-elast ic autoencoder (CKAE) to measure the similarity between generated and known reac tions for chemical viability insights. These features form a coherent retrosynth etic framework, validated experimentAlly by designing a 3-step synthetic pathway for a chAllenging smAll molecule, demonstrating a significant improvement over previous 5-9 step approaches."
NETL
NSTL
