How machine learning can assist the interpretation of ab initio molecular dynamics simulations and conceptual understanding of chemistry

Machine Learning Analysis of Direct Dynamics Trajectory Outcomes for Thermal Deazetization of 2,3-Diazabicyclo[2.2.1]hept-2-ene

Experimentally, the thermal gas-phase deazetization of 2,3-diazabicyclo[2.2.1]hept-2-ene (1) results in the loss of N₂ and the formation of bicyclo products 3 (exo) and 4 (endo) in a nonstatistical ratio, with preference for the exo product. Here, we report unrestricted M06-2X quasiclassical trajectories initialized from the concerted N₂ ejection transition state that were able to replicate the experimental preference to form 3. We found that the 3:4 ratio results from the relative amounts of very fast (ballistic) exotype trajectories versus trajectories that lead to the 1,3-diradical intermediate 2. These quasiclassical trajectories provided a set of transition-state vibrational, velocity, momenta, and geometric features for the machine learning analysis. A selection of popular supervised classification algorithms (e.g., random forest) provided poor prediction of trajectory outcomes based on only transition-state vibrational quanta and energy features. However, these machine learning models provided more accurate predictions using atomic velocities and atomic positions, attaining ∼70% accuracy using initial conditions and between 85 and 95% accuracy at later reaction time steps. This increased accuracy allowed the feature importance analysis to reveal that, at the later-time analysis, the methylene bridge out-of-plane bending is correlated with trajectory outcomes for the formation of either the exo product or toward the diradical intermediate. Possible reasons for the struggle of machine learning algorithms to classify trajectories based on transition-state features is the heavily overlapping feature values, the finite but very large possible vibrational mode combinations, and the possibility of chaos as trajectories propagate. We examined this chaos by comparing a set of nearly identical trajectories that differed by only a very small scaling of the kinetic energies resulting from the transition-state reaction coordinate.

Modern quantum chemistry with [Open]Molcas

MOLCAS/OpenMolcas is an ab initio electronic structure program providing a large set of computational methods from Hartree-Fock and density functional theory to various implementations of multiconfigurational theory. This article provides a comprehensive overview of the main features of the code, specifically reviewing the use of the code in previously reported chemical applications as well as more recent applications including the calculation of magnetic properties from optimized density matrix renormalization group wave functions.

Quantum yields of singlet and triplet chemiexcitation of dimethyl 1,2-dioxetane: ab initio nonadiabatic molecular dynamic simulations

The global nonadiabatic switching on-the-fly trajectory surface hopping simulation at the 8SA-CASSCF quantum level has been performed to estimate the quantum yield of chemiexcitation for the uncatalyzed decomposition reaction of the open-shell biradical trans-3,4-dimethyl-1,2-dioxetane system. The present ab initio nonadiabatic molecular dynamic simulation involving both conical intersection and intersystem crossing is to compute for the first time the population evolution of quantum yields at the four lowest singlet and four lowest triplet states. The simulated results demonstrate not only the stepwise dissociation of O-O and C-C bond breaking, but also confirm the existence of a biradical entropic trap which is responsible for chemiexcitation. The simulated quantum yield of the triplet chemiexcitation ΦT1 = 0.266 ± 0.096 agrees with the experimental value of 0.20 ± 0.04 very well. The present nonadiabatic molecular dynamic simulation of dimethyl 1,2-dioxetanes provides a further advanced understanding and stepping stone for future studies on chemi- and bio-luminescence.

Using Machine Learning to Predict the Dissociation Energy of Organic Carbonyls

Bond dissociation energy (BDE), an indicator of the strength of chemical bonds, exhibits great potential for evaluating and screening high-performance materials and catalysts, which are of critical importance in industrial applications. However, the measurement or computation of BDE via conventional experimental or theoretical methods is usually costly and involved, substantially preventing the BDE from being applied to large-scale and high-throughput studies. Therefore, a potentially more efficient approach for estimating BDE is highly desirable. To this end, we combined first-principles calculations and machine learning techniques, including neural networks and random forest, to explore the inner relationships between carbonyl structure and its BDE. Results show that machine learning can not only effectively reproduce the computed BDEs of carbonyls but also in turn serve as guidance for the rational design of carbonyl structure aimed at optimizing performance.

Understanding and modelling the interactions of peptides with membranes: from partitioning to self-assembly

Atomic detail simulations are starting to reveal how flexible polypeptides interact with fluid lipid bilayers. These insights are transforming our understanding of one of the fundamental processes in biology: membrane protein folding and assembly. Advanced molecular dynamics (MD) simulation techniques enable accurate prediction of protein structure, folding pathways and assembly in microsecond-timescales. Such simulations show how membrane-active peptides self-assemble in cell membranes, revealing their binding, folding, insertion, and aggregation, while at the same time providing atomic resolution details of peptide-lipid interactions. Essential to the impact of simulations are experimental approaches that enable calibration and validation of the computational models and techniques. In this review, we summarize the current development of applying unbiased atomic detail MD simulations and the relation to experimental techniques, to study peptide folding and provide our perspective of the field.

Quantum Chemistry in the Age of Machine Learning

As the quantum chemistry (QC) community embraces machine learning (ML), the number of new methods and applications based on the combination of QC and ML is surging. In this Perspective, a view of the current state of affairs in this new and exciting research field is offered, challenges of using machine learning in quantum chemistry applications are described, and potential future developments are outlined. Specifically, examples of how machine learning is used to improve the accuracy and accelerate quantum chemical research are shown. Generalization and classification of existing techniques are provided to ease the navigation in the sea of literature and to guide researchers entering the field. The emphasis of this Perspective is on supervised machine learning.

What Does the Machine Learn? Knowledge Representations of Chemical Reactivity

In a departure from conventional chemical approaches, data-driven models of chemical reactions have recently been shown to be statistically successful using machine learning. These models, however, are largely black box in character and have not provided the kind of chemical insights that historically advanced the field of chemistry. To examine the knowledgebase of machine-learning models-what does the machine learn-this article deconstructs black-box machine-learning models of a diverse chemical reaction data set. Through experimentation with chemical representations and modeling techniques, the analysis provides insights into the nature of how statistical accuracy can arise, even when the model lacks informative physical principles. By peeling back the layers of these complicated models we arrive at a minimal, chemically intuitive model (and no machine learning involved). This model is based on systematic reaction-type classification and Evans-Polanyi relationships within reaction types which are easily visualized and interpreted. Through exploring this simple model, we gain deeper understanding of the data set and uncover a means for expert interactions to improve the model's reliability.

Molecular dynamics based descriptors for predicting supramolecular gelation

Four molecular dynamics-based descriptors were derived able to classify gelator–solvent combinations as a gel, precipitate or clear solution.

Interpretable machine learning as a tool for scientific discovery in chemistry

There has been an upsurge of interest in applying machine learning to chemistry, and impressive predictive accuracies have been achieved, but this has been done without providing any insight into what has been learnt from the training data.

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

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.

Machine learning enables long time scale molecular photodynamics simulations

Photo-induced processes are fundamental in nature but accurate simulations of their dynamics are seriously limited by the cost of the underlying quantum chemical calculations, hampering their application for long time scales. Here we introduce a method based on machine learning to overcome this bottleneck and enable accurate photodynamics on nanosecond time scales, which are otherwise out of reach with contemporary approaches. Instead of expensive quantum chemistry during molecular dynamics simulations, we use deep neural networks to learn the relationship between a molecular geometry and its high-dimensional electronic properties. As an example, the time evolution of the methylenimmonium cation for one nanosecond is used to demonstrate that machine learning algorithms can outperform standard excited-state molecular dynamics approaches in their computational efficiency while delivering the same accuracy.