Generating and screening de novo compounds against given targets using ultrafast deep learning models as core components

Zhang, Haiping1; Saravanan, Konda Mani2; Yang, Yang3; Wei, Yanjie4; Yi, Pan; Zhang, John Z. H.5

2022-06-01

10.1093/bib/bbac226

BRIEFINGS IN BIOINFORMATICS   Impact Factor & Quartile

1467-5463

1477-4054

Deep learning is an artificial intelligence technique in which models express geometric transformations over multiple levels. This method has shown great promise in various fields, including drug development. The availability of public structure databases prompted the researchers to use generative artificial intelligence models to narrow down their search of the chemical space, a novel approach to chemogenomics and de novo drug development. In this study, we developed a strategy that combined an accelerated LSTM_Chem (long short-term memory for de novo compounds generation), dense fully convolutional neural network (DFCNN), and docking to generate a large number of de novo small molecular chemical compounds for given targets. To demonstrate its efficacy and applicability, six important targets that account for various human disorders were used as test examples. Moreover, using the M protease as a proof-of-concept example, we find that iteratively training with previously selected candidates can significantly increase the chance of obtaining novel compounds with higher and higher predicted binding affinities. In addition, we also check the potential benefit of obtaining reliable final de novo compounds with the help of MD simulation and metadynamics simulation. The generation of de novo compounds and the discovery of binders against various targets proposed here would be a practical and effective approach. Assessing the efficacy of these top de novo compounds with biochemical studies is promising to promote related drug development.

generative model drug discovery deep learning virtual screening drug targets

SCI

English

Others

National Science Foundation of China[62106253,21933010,"U1813203"] ; National Key Research and Development Program of China[2018YFB0204403] ; Shenzhen KQTD Project[KQTD20200820113106007] ; Research Funding of Shenzhen[JCYJ20200109114818703] ; Strategic Priority CAS Project[XDB38000000] ; Shenzhen Basic Research Fund["JCYJ20180507182818013","JCYJ20170413093358429"]

Biochemistry & Molecular Biology ; Mathematical & Computational Biology

Biochemical Research Methods ; Mathematical & Computational Biology

WOS:000813284900001

OXFORD UNIV PRESS

COMPUTER SCIENCE

Web of Science

1.Chinese Acad Sci, Shenzhen Inst Adv Technol SAIT, Beijing, Peoples R China
2.Bharath Inst Higher Educ & Res, Beijing, Peoples R China
3.Southern Univ Sci & Technol, Peoples Hosp 3, Affiliated Hosp 2, Shenzhen, Peoples R China
4.Ctr High Perform Computing SIAT, Computation Biol & Bioinformat, Beijing, Peoples R China
5.SIAT, Computat Biol & Drug Discovery, Beijing, Peoples R China

Zhang, Haiping,Saravanan, Konda Mani,Yang, Yang,et al. Generating and screening de novo compounds against given targets using ultrafast deep learning models as core components[J]. BRIEFINGS IN BIOINFORMATICS,2022.

Zhang, Haiping,Saravanan, Konda Mani,Yang, Yang,Wei, Yanjie,Yi, Pan,&Zhang, John Z. H..(2022).Generating and screening de novo compounds against given targets using ultrafast deep learning models as core components.BRIEFINGS IN BIOINFORMATICS.

Zhang, Haiping,et al."Generating and screening de novo compounds against given targets using ultrafast deep learning models as core components".BRIEFINGS IN BIOINFORMATICS (2022).