SyntaLinker: automatic fragment linking with deep conditional transformer neural networks
Yuyao Yang, Shuangjia Zheng, Shimin Su, Chao Zhao, Jun Xu, Hongming Chen
Abstract
ChEMBL database). Conventionally, linking molecular fragments was viewed as connecting substructures that were predefined by empirical rules. In SyntaLinker, however, the rules of linking fragments can be learned implicitly from known chemical structures by recognizing syntactic patterns embedded in SMILES notations. With deep conditional transformer neural networks, SyntaLinker can generate molecular structures based on a given pair of fragments and additional restrictions. Case studies have demonstrated the advantages and usefulness of SyntaLinker in FBDD.
Topics & Concepts
Fragment (logic)TransformerComputer scienceArtificial neural networkArtificial intelligenceDeep neural networksDrug targetDrug discoveryComputational biologyCombinatorial chemistryChemistryEngineeringProgramming languageBiologyBiochemistryElectrical engineeringVoltageComputational Drug Discovery MethodsMachine Learning in Materials ScienceProtein Structure and Dynamics