Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing...Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing computational methods for preclinical and clinical cancer drug response(CDR)prediction,challenges remain regarding the generalization of new drugs that are unseen in the training set.Herein,we propose a multimodal fusion deep learning(DL)model called drug-target and single-cell language based CDR(DTLCDR)to predict preclinical and clinical CDRs.The model integrates chemical descriptors,molecular graph representations,predicted protein target profiles of drugs,and cell line expression profiles with general knowledge from single cells.Among these features,a well-trained drug-target interaction(DTI)prediction model is used to generate target profiles of drugs,and a pretrained single-cell language model is integrated to provide general genomic knowledge.Comparison experiments on the cell line drug sensitivity dataset demonstrated that DTLCDR exhibited improved generalizability and robustness in predicting unseen drugs compared with previous state-of-the-art baseline methods.Further ablation studies verified the effectiveness of each component of our model,highlighting the significant contribution of target information to generalizability.Subsequently,the ability of DTLCDR to predict novel molecules was validated through in vitro cell experiments,demonstrating its potential for real-world applications.Moreover,DTLCDR was transferred to the clinical datasets,demonstrating satisfactory performance in the clinical data,regardless of whether the drugs were included in the cell line dataset.Overall,our results suggest that the DTLCDR is a promising tool for personalized drug discovery.展开更多
Molecular Generation The molecular generation has emerged as a powerful tool for computer-aided drug design in recent years,as it can explore a large and unknown chemical space and discover novel structures or scaffol...Molecular Generation The molecular generation has emerged as a powerful tool for computer-aided drug design in recent years,as it can explore a large and unknown chemical space and discover novel structures or scaffolds.Furthermore,a candidate compound needs to satisfy multiple criteria,such as target affinity,pharmacokinetics,toxicity,synthetic accessibility,etc.,to pass clinical trials and meet industrial standards.Therefore,multi-objective methods have become a focal point of molecular generation and optimization.Several reviews have been published recently to summarize previous works in molecular generation and categorize them(Table).In this article,we propose a classification scheme based on both the model’s architecture and its practical use,namely,entrenched or plug-in models,especially for multi-objective molecular generation models.We argue that plug-in methods have superior flexibility in both model building and practical use,broader application potential,and higher performance boundaries,and they deserve more attention in the future.展开更多
基金supported by the National Key Research and Development Program of China(Grant No.:2023YFC2605002)the National Key R&D Program of China(Grant No.:2022YFF1203003)+2 种基金Beijing AI Health Cultivation Project,China(Grant No.:Z221100003522022)the National Natural Science Foundation of China(Grant No.:82273772)the Beijing Natural Science Foundation,China(Grant No.:7212152).
文摘Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing computational methods for preclinical and clinical cancer drug response(CDR)prediction,challenges remain regarding the generalization of new drugs that are unseen in the training set.Herein,we propose a multimodal fusion deep learning(DL)model called drug-target and single-cell language based CDR(DTLCDR)to predict preclinical and clinical CDRs.The model integrates chemical descriptors,molecular graph representations,predicted protein target profiles of drugs,and cell line expression profiles with general knowledge from single cells.Among these features,a well-trained drug-target interaction(DTI)prediction model is used to generate target profiles of drugs,and a pretrained single-cell language model is integrated to provide general genomic knowledge.Comparison experiments on the cell line drug sensitivity dataset demonstrated that DTLCDR exhibited improved generalizability and robustness in predicting unseen drugs compared with previous state-of-the-art baseline methods.Further ablation studies verified the effectiveness of each component of our model,highlighting the significant contribution of target information to generalizability.Subsequently,the ability of DTLCDR to predict novel molecules was validated through in vitro cell experiments,demonstrating its potential for real-world applications.Moreover,DTLCDR was transferred to the clinical datasets,demonstrating satisfactory performance in the clinical data,regardless of whether the drugs were included in the cell line dataset.Overall,our results suggest that the DTLCDR is a promising tool for personalized drug discovery.
基金the“AI+Health Collaborative Innovation Cultivation”Project(grant number Z2211-00003522022)the National Key Research and Development Program(grant number 2022YFF1203003)the Peking University Medicine-StoneWise Joint Laboratory Project(grant numbers L202107).
文摘Molecular Generation The molecular generation has emerged as a powerful tool for computer-aided drug design in recent years,as it can explore a large and unknown chemical space and discover novel structures or scaffolds.Furthermore,a candidate compound needs to satisfy multiple criteria,such as target affinity,pharmacokinetics,toxicity,synthetic accessibility,etc.,to pass clinical trials and meet industrial standards.Therefore,multi-objective methods have become a focal point of molecular generation and optimization.Several reviews have been published recently to summarize previous works in molecular generation and categorize them(Table).In this article,we propose a classification scheme based on both the model’s architecture and its practical use,namely,entrenched or plug-in models,especially for multi-objective molecular generation models.We argue that plug-in methods have superior flexibility in both model building and practical use,broader application potential,and higher performance boundaries,and they deserve more attention in the future.
