Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns

Abstract

Computational Chemistry is currently a synergistic assembly between ab initio calculations, simulation, machine learning (ML) and optimization strategies for describing, solving and predicting chemical data and related phenomena. These include accelerated literature searches, analysis and prediction of physical and quantum chemical properties, transition states, chemical structures, chemical reactions, and also new catalysts and drug candidates. The generalization of scalability to larger chemical problems, rather than specialization, is now the main principle for transforming chemical tasks in multiple fronts, for which systematic and cost-effective solutions have benefited from ML approaches, including those based on deep learning (e.g. quantum chemistry, molecular screening, synthetic route design, catalysis, drug discovery). The latter class of ML algorithms is capable of combining raw input into layers of intermediate features, enabling bench-to-bytes designs with the potential to transform several chemical domains. In this review, the most exciting developments concerning the use of ML in a range of different chemical scenarios are described. A range of different chemical problems and respective rationalization, that have hitherto been inaccessible due to the lack of suitable analysis tools, is thus detailed, evidencing the breadth of potential applications of these emerging multidimensional approaches. Focus is given to the models, algorithms and methods proposed to facilitate research on compound design and synthesis, materials design, prediction of binding, molecular activity, and soft matter behavior. The information produced by pairing Chemistry and ML, through data-driven analyses, neural network predictions and monitoring of chemical systems, allows (i) prompting the ability to understand the complexity of chemical data, (ii) streamlining and designing experiments, (ii) discovering new molecular targets and materials, and also (iv) planning or rethinking forthcoming chemical challenges. In fact, optimization engulfs all these tasks directly.

Learning Chemistry: Exploring the Suitability of Machine Learning for the Task of Structure-based Chemical Ontology Classification

“…For these classical approaches, relevant features need to be specified in advance. With recent advances in algorithms, data availability and computational processing capability, multi-layer artificial neural networks, which are able to learn features directly from raw data, have begun to be used in chemistry applications [8][9][10].…”

Rosetta Custom Score Functions Accurately Predict ΔΔG of Mutations at Protein-Protein Interfaces Using Machine Learning

“…31 Although this CSF contains no additional energy terms or metrics, one can also easily introduce a variety of bioinformatics terms to further strengthen these models. Additionally, even more complex machine learning methods such as Extreme Gradient Boosted Random Forrest Regressions (XGBoost) or neural networks (NNs) 32 may be employed to further improve ΔΔG prediction. Finally, we hope to extend the SRS2020 model beyond the prediction of interfacial ΔΔG and use it to design protein-protein interfaces as well as peptides or peptidomimetics targeting such interfaces.…”

Interpretable machine learning as a tool for scientific discovery in chemistry

“…There are many examples of where ML has been applied within chemistry, 10 including the design of crystalline structures, 11 planning retrosynthesis routes, 12 and reaction optimisation. 13 Here, we will briefly look at two; namely, drug discovery and quantum chemistry.…”