Prediction of Enzyme Catalysis by Computing Reaction Energy Barriers via Steered QM/MM Molecular Dynamics Simulations and Machine Learning.

The prediction of enzyme activity is one of the main challenges in catalysis. With computer-aided methods, it is possible to simulate the reaction mechanism at the atomic level. However, these methods are usually expensive if they are to be used on a large scale, as they are needed for protein engineering campaigns. To alleviate this situation, machine learning methods can help in the generation of predictive-decision models. Herein, we test different regression algorithms for the prediction of the reaction energy barrier of the rate-limiting step of the hydrolysis of mono-(2-hydroxyethyl)terephthalic acid by the MHETase ofIdeonella sakaiensis. As a training data set, we use steered quantum mechanics/molecular mechanics (QM/MM) molecular dynamics (MD) simulation snapshots and their corresponding pulling work values. We have explored three algorithms together with three chemical representations. As an outcome, our trained models are able to predict pulling works along the steered QM/MM MD simulations with a mean absolute error below 3 kcal mol-1 and a score value above 0.90. More challenging is the prediction of the energy maximum with a single geometry. Whereas the use of the initial snapshot of the QM/MM MD trajectory as input geometry yields a very poor prediction of the reaction energy barrier, the use of an intermediate snapshot of the former trajectory brings the score value above 0.40 with a low mean absolute error (ca. 3 kcal mol-1). Altogether, we have faced in this work some initial challenges of the final goal of getting an efficient workflow for the semiautomatic prediction of enzyme-catalyzed energy barriers and catalytic efficiencies.

Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems.

Machine learning models are poised to make a transformative impact on chemical sciences by dramatically accelerating computational algorithms and amplifying insights available from computational chemistry methods. However, achieving this requires a confluence and coaction of expertise in computer science and physical sciences. This Review is written for new and experienced researchers working at the intersection of both fields. We first provide concise tutorials of computational chemistry and machine learning methods, showing how insights involving both can be achieved. We follow with a critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful (and useful) predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design.

Machine Learning Force Fields.

In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.

Automatic identification of chemical moieties.

In recent years, the prediction of quantum mechanical observables with machine learning methods has become increasingly popular. Message-passing neural networks (MPNNs) solve this task by constructing atomic representations, from which the properties of interest are predicted. Here, we introduce a method to automatically identify chemical moieties (molecular building blocks) from such representations, enabling a variety of applications beyond property prediction, which otherwise rely on expert knowledge. The required representation can either be provided by a pretrained MPNN, or be learned from scratch using only structural information. Beyond the data-driven design of molecular fingerprints, the versatility of our approach is demonstrated by enabling the selection of representative entries in chemical databases, the automatic construction of coarse-grained force fields, as well as the identification of reaction coordinates.

SchNetPack 2.0: A neural network toolbox for atomistic machine learning.

SchNetPack is a versatile neural network toolbox that addresses both the requirements of method development and the application of atomistic machine learning. Version 2.0 comes with an improved data pipeline, modules for equivariant neural networks, and a PyTorch implementation of molecular dynamics. An optional integration with PyTorch Lightning and the Hydra configuration framework powers a flexible command-line interface. This makes SchNetPack 2.0 easily extendable with a custom code and ready for complex training tasks, such as the generation of 3D molecular structures.

Perspective on integrating machine learning into computational chemistry and materials science.

Machine learning (ML) methods are being used in almost every conceivable area of electronic structure theory and molecular simulation. In particular, ML has become firmly established in the construction of high-dimensional interatomic potentials. Not a day goes by without another proof of principle being published on how ML methods can represent and predict quantum mechanical properties-be they observable, such as molecular polarizabilities, or not, such as atomic charges. As ML is becoming pervasive in electronic structure theory and molecular simulation, we provide an overview of how atomistic computational modeling is being transformed by the incorporation of ML approaches. From the perspective of the practitioner in the field, we assess how common workflows to predict structure, dynamics, and spectroscopy are affected by ML. Finally, we discuss how a tighter and lasting integration of ML methods with computational chemistry and materials science can be achieved and what it will mean for research practice, software development, and postgraduate training.

Molecular force fields with gradient-domain machine learning (GDML): Comparison and synergies with classical force fields.

Modern machine learning force fields (ML-FF) are able to yield energy and force predictions at the accuracy of high-level ab initio methods, but at a much lower computational cost. On the other hand, classical molecular mechanics force fields (MM-FF) employ fixed functional forms and tend to be less accurate, but considerably faster and transferable between molecules of the same class. In this work, we investigate how both approaches can complement each other. We contrast the ability of ML-FF for reconstructing dynamic and thermodynamic observables to MM-FFs in order to gain a qualitative understanding of the differences between the two approaches. This analysis enables us to modify the generalized AMBER force field by reparametrizing short-range and bonded interactions with more expressive terms to make them more accurate, without sacrificing the key properties that make MM-FFs so successful.

Comparing the accuracy of high-dimensional neural network potentials and the systematic molecular fragmentation method: A benchmark study for all-trans alkanes.

Many approaches, which have been developed to express the potential energy of large systems, exploit the locality of the atomic interactions. A prominent example is the fragmentation methods in which the quantum chemical calculations are carried out for overlapping small fragments of a given molecule that are then combined in a second step to yield the system's total energy. Here we compare the accuracy of the systematic molecular fragmentation approach with the performance of high-dimensional neural network (HDNN) potentials introduced by Behler and Parrinello. HDNN potentials are similar in spirit to the fragmentation approach in that the total energy is constructed as a sum of environment-dependent atomic energies, which are derived indirectly from electronic structure calculations. As a benchmark set, we use all-trans alkanes containing up to eleven carbon atoms at the coupled cluster level of theory. These molecules have been chosen because they allow to extrapolate reliable reference energies for very long chains, enabling an assessment of the energies obtained by both methods for alkanes including up to 10 000 carbon atoms. We find that both methods predict high-quality energies with the HDNN potentials yielding smaller errors with respect to the coupled cluster reference.

Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments.

The GEMS method enables molecular dynamics simulations of large heterogeneous systems at ab initio quality.

Improved motif-scaffolding with SE(3) flow matching.

Protein design often begins with the knowledge of a desired function from a motif which motif-scaffolding aims to construct a functional protein around. Recently, generative models have achieved breakthrough success in designing scaffolds for a range of motifs. However, generated scaffolds tend to lack structural diversity, which can hinder success in wet-lab validation. In this work, we extend FrameFlow, an SE(3) flow matching model for protein backbone generation, to perform motif-scaffolding with two complementary approaches. The first is motif amortization, in which FrameFlow is trained with the motif as input using a data augmentation strategy. The second is motif guidance, which performs scaffolding using an estimate of the conditional score from FrameFlow without additional training. On a benchmark of 24 biologically meaningful motifs, we show our method achieves 2.5 times more designable and unique motif-scaffolds compared to state-of-the-art. Code: https://github.com/microsoft/protein-frame-flow.

Deep learning study of tyrosine reveals that roaming can lead to photodamage.

Amino acids are among the building blocks of life, forming peptides and proteins, and have been carefully 'selected' to prevent harmful reactions caused by light. To prevent photodamage, molecules relax from electronic excited states to the ground state faster than the harmful reactions can occur; however, such photochemistry is not fully understood, in part because theoretical simulations of such systems are extremely expensive-with only smaller chromophores accessible. Here, we study the excited-state dynamics of tyrosine using a method based on deep neural networks that leverages the physics underlying quantum chemical data and combines different levels of theory. We reveal unconventional and dynamically controlled 'roaming' dynamics in excited tyrosine that are beyond chemical intuition and compete with other ultrafast deactivation mechanisms. Our findings suggest that the roaming atoms are radicals that can lead to photodamage, offering a new perspective on the photostability and photodamage of biological systems.

Inverse design of 3d molecular structures with conditional generative neural networks.

The rational design of molecules with desired properties is a long-standing challenge in chemistry. Generative neural networks have emerged as a powerful approach to sample novel molecules from a learned distribution. Here, we propose a conditional generative neural network for 3d molecular structures with specified chemical and structural properties. This approach is agnostic to chemical bonding and enables targeted sampling of novel molecules from conditional distributions, even in domains where reference calculations are sparse. We demonstrate the utility of our method for inverse design by generating molecules with specified motifs or composition, discovering particularly stable molecules, and jointly targeting multiple electronic properties beyond the training regime.

Machine learning of solvent effects on molecular spectra and reactions.

Fast and accurate simulation of complex chemical systems in environments such as solutions is a long standing challenge in theoretical chemistry. In recent years, machine learning has extended the boundaries of quantum chemistry by providing highly accurate and efficient surrogate models of electronic structure theory, which previously have been out of reach for conventional approaches. Those models have long been restricted to closed molecular systems without accounting for environmental influences, such as external electric and magnetic fields or solvent effects. Here, we introduce the deep neural network FieldSchNet for modeling the interaction of molecules with arbitrary external fields. FieldSchNet offers access to a wealth of molecular response properties, enabling it to simulate a wide range of molecular spectra, such as infrared, Raman and nuclear magnetic resonance. Beyond that, it is able to describe implicit and explicit molecular environments, operating as a polarizable continuum model for solvation or in a quantum mechanics/molecular mechanics setup. We employ FieldSchNet to study the influence of solvent effects on molecular spectra and a Claisen rearrangement reaction. Based on these results, we use FieldSchNet to design an external environment capable of lowering the activation barrier of the rearrangement reaction significantly, demonstrating promising venues for inverse chemical design.

SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects.

Machine-learned force fields combine the accuracy of ab initio methods with the efficiency of conventional force fields. However, current machine-learned force fields typically ignore electronic degrees of freedom, such as the total charge or spin state, and assume chemical locality, which is problematic when molecules have inconsistent electronic states, or when nonlocal effects play a significant role. This work introduces SpookyNet, a deep neural network for constructing machine-learned force fields with explicit treatment of electronic degrees of freedom and nonlocality, modeled via self-attention in a transformer architecture. Chemically meaningful inductive biases and analytical corrections built into the network architecture allow it to properly model physical limits. SpookyNet improves upon the current state-of-the-art (or achieves similar performance) on popular quantum chemistry data sets. Notably, it is able to generalize across chemical and conformational space and can leverage the learned chemical insights, e.g. by predicting unknown spin states, thus helping to close a further important remaining gap for today's machine learning models in quantum chemistry.

Combining SchNet and SHARC: The SchNarc Machine Learning Approach for Excited-State Dynamics.

In recent years, deep learning has become a part of our everyday life and is revolutionizing quantum chemistry as well. In this work, we show how deep learning can be used to advance the research field of photochemistry by learning all important properties-multiple energies, forces, and different couplings-for photodynamics simulations. We simplify such simulations substantially by (i) a phase-free training skipping costly preprocessing of raw quantum chemistry data; (ii) rotationally covariant nonadiabatic couplings, which can either be trained or (iii) alternatively be approximated from only ML potentials, their gradients, and Hessians; and (iv) incorporating spin-orbit couplings. As the deep-learning method, we employ SchNet with its automatically determined representation of molecular structures and extend it for multiple electronic states. In combination with the molecular dynamics program SHARC, our approach termed SchNarc is tested on two polyatomic molecules and paves the way toward efficient photodynamics simulations of complex systems.

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.

Machine learning molecular dynamics for the simulation of infrared spectra.

Machine learning has emerged as an invaluable tool in many research areas. In the present work, we harness this power to predict highly accurate molecular infrared spectra with unprecedented computational efficiency. To account for vibrational anharmonic and dynamical effects - typically neglected by conventional quantum chemistry approaches - we base our machine learning strategy on ab initio molecular dynamics simulations. While these simulations are usually extremely time consuming even for small molecules, we overcome these limitations by leveraging the power of a variety of machine learning techniques, not only accelerating simulations by several orders of magnitude, but also greatly extending the size of systems that can be treated. To this end, we develop a molecular dipole moment model based on environment dependent neural network charges and combine it with the neural network potential approach of Behler and Parrinello. Contrary to the prevalent big data philosophy, we are able to obtain very accurate machine learning models for the prediction of infrared spectra based on only a few hundreds of electronic structure reference points. This is made possible through the use of molecular forces during neural network potential training and the introduction of a fully automated sampling scheme. We demonstrate the power of our machine learning approach by applying it to model the infrared spectra of a methanol molecule, n-alkanes containing up to 200 atoms and the protonated alanine tripeptide, which at the same time represents the first application of machine learning techniques to simulate the dynamics of a peptide. In all of these case studies we find an excellent agreement between the infrared spectra predicted via machine learning models and the respective theoretical and experimental spectra.

High-Dimensional Neural Network Potentials for Organic Reactions and an Improved Training Algorithm.

Artificial neural networks (NNs) represent a relatively recent approach for the prediction of molecular potential energies, suitable for simulations of large molecules and long time scales. By using NNs to fit electronic structure data, it is possible to obtain empirical potentials of high accuracy combined with the computational efficiency of conventional force fields. However, as opposed to the latter, changing bonding patterns and unusual coordination geometries can be described due to the underlying flexible functional form of the NNs. One of the most promising approaches in this field is the high-dimensional neural network (HDNN) method, which is especially adapted to the prediction of molecular properties. While HDNNs have been mostly used to model solid state systems and surface interactions, we present here the first application of the HDNN approach to an organic reaction, the Claisen rearrangement of allyl vinyl ether to 4-pentenal. To construct the corresponding HDNN potential, a new training algorithm is introduced. This algorithm is termed "element-decoupled" global extended Kalman filter (ED-GEKF) and is based on the decoupled Kalman filter. Using a metadynamics trajectory computed with density functional theory as reference data, we show that the ED-GEKF exhibits superior performance - both in terms of accuracy and training speed - compared to other variants of the Kalman filter hitherto employed in HDNN training. In addition, the effect of including forces during ED-GEKF training on the resulting potentials was studied.

Loganin and secologanin derived tryptamine-iridoid alkaloids from Palicourea crocea and Palicourea padifolia (Rubiaceae).

During comparative analysis on Palicourea species from Costa Rica, two unusual loganin derived tryptamine-iridoid alkaloids were isolated from an accession of Palicourea crocea. Besides the already known brachycerine (2), palicroceaine (1) features a novel hexacyclic backbone. A second provenance, however, yielded strictosidinic acid (3), belonging to the more common secologanin derived tryptamine-iridoid alkaloids, such as those found in Palicourea padifolia. From this species, strictosidine (4), lyaloside (5) and its derivative (E)-O-(6')-(4″-hydroxy-3″,5″-dimethoxy)-cinnamoyl lyaloside (6) could be isolated. A herbarium specimen-based screening was performed, indicating some degree of regional differentiation in alkaloid content and biosynthetic pathways within the widespread and variable Pal. crocea. It further shows its differentiation from the related strictosidine containing Palicourea croceoides. The occurrence of loganin derived tryptamine-iridoid alkaloids in Pal. crocea, Psychotria brachyceras and Psychotria brachypoda, all putatively unrelated members of the Palicourea s.l. clade, is a noteworthy exception within the genus, otherwise largely characterized by secologanin-derived tryptamine-iridoid alkaloids.