公开(公告)号：EP4439570A1

公开(公告)日：2024-10-02

申请号：EP24153929.5

申请日：2024-01-25

申请人： Tata Consultancy Services Limited

发明人： BUNG, Navneet ,  SRINIVASAN, Rajgopal ,  VANGALA, Sarveswararao ,  KRISHNAN, Sowmya Ramaswamy ,  ROY, Arijit

IPC分类号： G16C20/50 ,  G16C20/30 ,  G16C20/70

CPC分类号： G16C20/50 ,  G16C20/70 ,  G06N3/00 ,  G16C20/30

摘要： The embodiments of present disclosure herein address the inability of existing techniques to fragment both small molecules and substituents of a core scaffold. And it addresses generation of lesser number of unique fragments which hinders application of graph propagation approaches to predict properties from molecular datasets. The method and system for extraction of small molecule fragments and their explanation for drug-like properties. A molecular graph representation is used to train graph convolution network (GCN) models for prediction of various absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. The models developed are compared with an existing atom-level graph model trained using a similar architecture. Further, the explanations obtained from the predictive models are validated based on their relevance to the existing knowledgebase of substructure contributions using matched molecular pairs (MMP) analysis.

公开(公告)号：EP3968333A1

公开(公告)日：2022-03-16

申请号：EP20217644.2

申请日：2020-12-29

申请人： Tata Consultancy Services Limited

发明人： ROY, Arijit ,  Ramaswamy Krishnan, Sowmya ,  BUNG, Navneet ,  BULUSU, Gopalakrishnan

IPC分类号： G16B15/30 ,  G16B40/20

摘要： Conventionally, deep learning-based methods have shown some success in ligand-based drug design. However, these methods face data scarcity problems while designing drugs against novel targets. Embodiments of the present disclosure provide systems and methods that leverage the potential of deep learning and molecular modeling approaches to develop a drug design pipeline, which can be useful for cases where there is limited or no availability of target-specific ligand datasets. Inhibitors of other proteins, structurally similar to the target protein are screened at the active site of the target protein to create an initial target-specific dataset. Transfer learning is implemented to learn features of target-specific dataset and design new chemical entities/molecules using a deep generative model. A deep predictive model is used predict docking scores of newly designed/identified molecules. Both these models are then combined using reinforcement learning to design new chemical entities with optimized docking score.