Deep learning for computational chemistry

By Garrett B. Goh, Nathan Oken Hodas, Abhinav Vishnu. 2017

739 citations recorded by the source corpus.

The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on multilayer neural networks. Within the last few years, we have seen the transformative impact of deep learning in many domains, particularly in speech recognition and computer vision, to the extent that the majority of expert practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties that distinguish them from traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including quantitative structure activity relationship, virtual screening, protein structure prediction, quantum chemistry, materials design, and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non‐neural networks state‐of‐the‐art models across disparate research topics, and deep neural network‐based models often exceeded the “glass ceiling” expectations of their respective tasks. Coupled with the maturity of GPU‐accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a valuable tool for computational chemistry. © 2017 Wiley Periodicals, Inc.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, background): “[19]) explored the effects of jointly modeling far more targets than the Merck challenge [301,302], with Ramsundar et al.”
Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction (2017, methodology): “he accuracy of the resulting model. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. arXiv:1712.02734v1 [stat.ML] 7 Dec 2017 With the growth of chemical data [6], it may be desirable to fully leverage representation learning of deep neural networks, which wi”
Computational Protein Design with Deep Learning Neural Networks (2018, background): “56 In many cases it shows better performance than other machine learning methods.”
Deep convolutional neural networks for eigenvalue problems in mechanics (2018, methodology): “…networks from conventional networks, which have made them highly successful in various engineering and science ﬁelds [39, 40, 41, 42, 43, 44, 45] : the use of convolution operation, the implementation of the Rectiﬁed Linear (ReLU) activation function, and a representation-invariance…”
Computer-Aided Diagnostic System for Early Detection of Acute Renal Transplant Rejection Using Diffusion-Weighted MRI (2019, positive): “Compared to classical shallow models, recent advances in deep learning of ANNs [40]–[42] provide more accurate classification ability by: (i) automated dimensionality”
Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond (2021, methodology): “chemistry [62] to games [152], deep models could be used to solve many prob-”
Artificial intelligence to deep learning: machine intelligence approach for drug discovery (2021, background): “In general, there are two important types of VS that are structure-based VS (SBVS) and ligand-based VS (LBVS) [159, 160].”
Deep learning in bioinformatics: introduction, application, and perspective in big data era (2019, background): “Considering its application in material design [97] and quantum chemistry [135], people also believe deep learning will become a valuable tool in computational chemistry [42].”
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns (2019, methodology): “Other interesting reviews covering theoretical aspects (Goh et al., 2017), available descriptors and datasets, and also comparing model performances (Wu et al., 2017) have been published.”
Deep Learning in Pharmacogenomics: From Gene Regulation to Patient Stratification (2018, background): “Deep learning applications in drug discovery and repurposing are starting to emerge, and already show high potential in many tasks including virtual screening, ADME/Tox properties prediction, novel drug-target interactions prediction [8, 28-32].”
QSAR-Based Virtual Screening: Advances and Applications in Drug Discovery (2018, background): “…modeling has grown, diversiﬁed, and evolved to the modeling and virtual screening (VS) of very large data sets comprising thousands of diverse chemical structures and using a wide variety of machine learning techniques (Cherkasov et al., 2014; Mitchell, 2014; Ekins et al., 2015; Goh et al., 2017).”
Partial success in closing the gap between human and machine vision (2021, methodology): “CLIP CLIP is special: trained on 400M images 6 (more data) with joint language-image supervision (novel objective) and a vision transformer backbone (non-standard architecture), it scores close to humans across all of our metrics presented in Figure 1; most strikingly in terms of error consistency…”