Manan Goel, Rishal Aggarwal, Bhuvanesh Sridharan, Pradeep Kumar Pal, U. Deva Priyakumar
Drug design involves the process of identifying and designing novel molecules that have desirable properties and bind well to a given target receptor. Typically, such molecules are identified by screening large chemical libraries for desirable physicochemical properties and binding strength with the target protein. This traditional approach, however, has severe limitations as exhaustively screening every molecule in known chemical libraries is computationally infeasible. Furthermore, currently available molecular libraries are only a minuscule part of the entire set of possible drug-like molecular structures (drug-like chemical space). In this review, we discuss how the former limitation is addressed by modeling virtual screening as a search space problem and how these endeavors utilize machine learning to reduce the number of required computational experiments to identify top candidates. We follow that up by discussing generative methods that attempt to approximate the entire drug-like chemical space providing us a path to explore beyond the known drug-like chemical space. We place special emphasis on generative models that learn the marginal distributions conditioned on specific properties or receptor structures for efficient sampling of molecules. Through this review, we aim to highlight modern machine learning based methods that try to efficiently enhance our sampling capability beyond conventional screening methods which, in turn, would benefit drug design significantly. Therefore, we also encourage further methods of development that work on such important aspects of drug design.
{"title":"Efficient and enhanced sampling of drug-like chemical space for virtual screening and molecular design using modern machine learning methods","authors":"Manan Goel, Rishal Aggarwal, Bhuvanesh Sridharan, Pradeep Kumar Pal, U. Deva Priyakumar","doi":"10.1002/wcms.1637","DOIUrl":"https://doi.org/10.1002/wcms.1637","url":null,"abstract":"<p>Drug design involves the process of identifying and designing novel molecules that have desirable properties and bind well to a given target receptor. Typically, such molecules are identified by screening large chemical libraries for desirable physicochemical properties and binding strength with the target protein. This traditional approach, however, has severe limitations as exhaustively screening every molecule in known chemical libraries is computationally infeasible. Furthermore, currently available molecular libraries are only a minuscule part of the entire set of possible drug-like molecular structures (drug-like chemical space). In this review, we discuss how the former limitation is addressed by modeling virtual screening as a search space problem and how these endeavors utilize machine learning to reduce the number of required computational experiments to identify top candidates. We follow that up by discussing generative methods that attempt to approximate the entire drug-like chemical space providing us a path to explore beyond the known drug-like chemical space. We place special emphasis on generative models that learn the marginal distributions conditioned on specific properties or receptor structures for efficient sampling of molecules. Through this review, we aim to highlight modern machine learning based methods that try to efficiently enhance our sampling capability beyond conventional screening methods which, in turn, would benefit drug design significantly. Therefore, we also encourage further methods of development that work on such important aspects of drug design.</p><p>This article is categorized under:\u0000 </p>","PeriodicalId":236,"journal":{"name":"Wiley Interdisciplinary Reviews: Computational Molecular Science","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2022-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5894133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The scalable preparation of high-quality and low-cost two-dimensional (2D) materials is critical to achieving their potential applications in various fields. Chemical vapor deposition (CVD) method is considered the most promising method for producing ultrathin 2D materials and has continued to develop in recent years. First-principles calculations have provided important theoretical guidance for the CVD synthesis of 2D materials, and have played an increasingly important role in the field of material synthesis in recent years. In this review, we present recent advances in the growth mechanism of 2D materials, focusing on the theoretical research progress of four typical 2D materials: graphene, hexagonal boron nitride (hBN), transition metal dichalcogenide (TMDC), and phosphorene. Several aspects of the growth process are discussed in detail, including the decomposition of precursors, nucleation, growth kinetics, domain shape, and epitaxial and alignment of 2D crystals. Based on the understanding of these atomic-scale growth processes, strategies toward the wafer-scale growth of continuous and homogeneous 2D thin films are proposed and confirmed by experiments. In the final section, we summarize future challenges and opportunities in the computational studies of the growth mechanism of 2D materials.
{"title":"Synthesis of two-dimensional materials: How computational studies can help?","authors":"Yanqing Guo, Yishan Hu, Qinghong Yuan","doi":"10.1002/wcms.1635","DOIUrl":"https://doi.org/10.1002/wcms.1635","url":null,"abstract":"<p>The scalable preparation of high-quality and low-cost two-dimensional (2D) materials is critical to achieving their potential applications in various fields. Chemical vapor deposition (CVD) method is considered the most promising method for producing ultrathin 2D materials and has continued to develop in recent years. First-principles calculations have provided important theoretical guidance for the CVD synthesis of 2D materials, and have played an increasingly important role in the field of material synthesis in recent years. In this review, we present recent advances in the growth mechanism of 2D materials, focusing on the theoretical research progress of four typical 2D materials: graphene, hexagonal boron nitride (hBN), transition metal dichalcogenide (TMDC), and phosphorene. Several aspects of the growth process are discussed in detail, including the decomposition of precursors, nucleation, growth kinetics, domain shape, and epitaxial and alignment of 2D crystals. Based on the understanding of these atomic-scale growth processes, strategies toward the wafer-scale growth of continuous and homogeneous 2D thin films are proposed and confirmed by experiments. In the final section, we summarize future challenges and opportunities in the computational studies of the growth mechanism of 2D materials.</p><p>This article is categorized under:\u0000 </p>","PeriodicalId":236,"journal":{"name":"Wiley Interdisciplinary Reviews: Computational Molecular Science","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2022-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"6139654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Philippe Schwaller, Alain C. Vaucher, Ruben Laplaza, Charlotte Bunne, Andreas Krause, Clemence Corminboeuf, Teodoro Laino
The cover image is based on the Advanced Review Machine intelligence for chemical reaction space by Philippe Schwaller et al., https://doi.org/10.1002/wcms.1604.