首页|Ecole Polytechnique Reports Findings in Machine Learning (Classifying protein ki nase conformations with machine learning)
Ecole Polytechnique Reports Findings in Machine Learning (Classifying protein ki nase conformations with machine learning)
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 from Palaiseau,France,by Ne wsRx journalists,research stated,"Protein kinases are key actors of signaling networks and important drug targets. They cycle between active and inactive conf ormations,distinguished by a few elements within the catalytic domain." The news correspondents obtained a quote from the research from Ecole Polytechni que,"One is the activation loop,whose conserved DFG motif can occupy DFG-in,D FG-out,and some rarer conformations. Annotation and classification of the struc tural kinome are important,as different conformations can be targeted by differ ent inhibitors and activators. Valuable resources exist; however,large-scale ap plications will benefit from increased automation and interpretability of struct ural annotation. Interpretable machine learning models are described for this pu rpose,based on ensembles of decision trees. To train them,a set of catalytic d omain sequences and structures was collected,somewhat larger and more diverse t han existing resources. The structures were clustered based on the DFG conformat ion and manually annotated. They were then used as training input. Two main mode ls were constructed,which distinguished active/inactive and in/out/other DFG co nformations. They considered initially 1692 structural variables,spanning the w hole catalytic domain,then identified (‘learned') a small subset that sufficed for accurate classification. The first model correctly labeled all but 3 of 3289 structures as active or inactive,while the second assigned the correct DFG lab el to all but 17 of 8826 structures. The most potent classifying variables were all related to well-known structural elements in or near the activation loop and their ranking gives insights into the conformational preferences. The models we re used to automatically annotate 3850 kinase structures predicted recently with the Alphafold2 tool,showing that Alphafold2 reproduced the active/inactive but not the DFG-in proportions seen in the Protein Data Bank."
PalaiseauFranceEuropeCyborgsEmer ging TechnologiesEnzymes and CoenzymesKinaseMachine Learning
NETL
NSTL
