A Mixed Quantum Chemistry/Machine Learning Approach for the Fast and Accurate Prediction of Biochemical Redox Potentials and Its Large-Scale Application to 315 000 Redox Reactions

Clinical translation of nanomedicine with integrated digital medicine and machine learning interventions

Nanomaterials based therapeutics transform the ways of disease prevention, diagnosis and treatment with increasing sophistications in nanotechnology at a breakneck pace, but very few could reach to the clinic due to inconsistencies in preclinical studies followed by regulatory hinderances. To tackle this, integrating the nanomedicine discovery with digital medicine provide technologies as tools of specific biological activity measurement. Hence, overcome the redundancies in nanomedicine discovery by the on-site data acquisition and analytics through integrating intelligent sensors and artificial intelligence (AI) or machine learning (ML). Integrated AI/ML wearable sensors directly gather clinically relevant biochemical information from the subject's body and process data for physicians to make right clinical decision(s) in a time and cost-effective way. This review summarizes insights and recommend the infusion of actionable big data computation enabled sensors in burgeoning field of nanomedicine at academia, research institutes, and pharmaceutical industries, with a potential of clinical translation. Furthermore, many blind spots are present in modern clinically relevant computation, one of which could prevent ML-guided low-cost new nanomedicine development from being successfully translated into the clinic was also discussed.

Self-Driving Laboratories for Chemistry and Materials Science

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through the automation of experimental workflows, along with autonomous experimental planning, SDLs hold the potential to greatly accelerate research in chemistry and materials discovery. This review provides an in-depth analysis of the state-of-the-art in SDL technology, its applications across various scientific disciplines, and the potential implications for research and industry. This review additionally provides an overview of the enabling technologies for SDLs, including their hardware, software, and integration with laboratory infrastructure. Most importantly, this review explores the diverse range of scientific domains where SDLs have made significant contributions, from drug discovery and materials science to genomics and chemistry. We provide a comprehensive review of existing real-world examples of SDLs, their different levels of automation, and the challenges and limitations associated with each domain.

First and Second Reductions in an Aprotic Solvent: Comparing Computational and Experimental One-Electron Reduction Potentials for 345 Quinones

Using reference reduction potentials of quinones recently measured relative to the saturated calomel electrode (SCE) in N,N-dimethylformamide (DMF), we benchmark absolute one-electron reduction potentials computed for 345 Q/Q•- and 265 Q•-/Q2- half-reactions using adiabatic electron affinities computed with density functional theory and solvation energies computed with four continuum solvation models: IEF-PCM, C-PCM, COSMO, and SM12. Regression analyses indicate a strong linear correlation between experimental and absolute computed Q/Q•- reduction potentials with Pearson's correlation coefficient (r) between 0.95 and 0.96 and the mean absolute error (MAE) relative to the linear fit between 83.29 and 89.51 mV for different solvation methods when the slope of the regression is constrained to 1. The same analysis for Q•-/Q2- gave a linear regression with r between 0.74 and 0.90 and MAE between 95.87 and 144.53 mV, respectively. The y-intercept values obtained from the linear regressions are in good agreement with the range of absolute reduction potentials reported in the literature for the SCE but reveal several sources of systematic error. The y-intercepts from Q•-/Q2- calculations are lower than those from Q/Q•- by around 320-410 mV for IEF-PCM, C-PCM, and SM12 compared to 210 mV for COSMO. Systematic errors also arise between molecules having different ring sizes (benzoquinones, naphthoquinones, and anthraquinones) and different substituents (titratable vs nontitratable). SCF convergence issues were found to be a source of random error that was slightly reduced by directly optimizing the solute structure in the continuum solvent reaction field. While SM12 MAEs were lower than those of the other solvation models for Q/Q•-, SM12 had larger MAEs for Q•-/Q2- pointing to a larger error when describing multiply charged anions in DMF. Altogether, the results highlight the advantages of, and further need for, testing computational methods using a large experimental data set that is not skewed (e.g., having more titratable than nontitratable substituents on different parent groups or vice versa) to help further distinguish between sources of random and systematic errors in the calculations.

Autonomous generation of single photon emitting materials

The utilization of machine learning in Materials Science underscores the critical importance of the quality and quantity of data in training models effectively. Unlike fields such as image processing and natural language processing, there is limited availability of atomistic datasets, leading to biases in training data. Particularly in the domain of materials discovery, there exists an issue of continuity in atomistic datasets. Experimental data sourced from literature and patents is usually only available for favorable data, resulting in bias in the training dataset. This study focuses on developing a SMILES-based model for generating synthetic datasets of quantum materials using a variational autoencoder. This study centers on the generation of a synthetic dataset of quantum materials specifically for quantum sensing applications, with a focus on two-level quantum molecules that exhibit a dipole blockade. The proposed technique offers an improved sampling algorithm by incorporating newly generated data into the sampling algorithm to create a more normally distributed dataset. Through this technique, the study was able to generate over 1 000 000 candidate quantum materials from a small dataset of only 8000 materials. The generated dataset identified several iodine-containing molecules as promising single photon emitting materials for potential quantum sensing applications.

Switchable Design of Redox-Enhanced Nonaromatic Quinones Enabled by Conjugation Recovery

An innovative switchable design strategy for modulating the electronic structures of quinones is proposed herein, leading to remarkably enhanced intrinsic redox potentials by restoring conjugated but nonaromatic backbone architectures. Computational validation of two fundamental hypotheses confirms the recovery of backbone conjugation and optimal utilization of the inductive effect in switched quinones, which affords significantly improved redox chemistry and overall performance compared to reference quinones. Geometric and electronic analyses provide strong evidence for the restored backbone conjugation and nonaromaticity in the switched quinones, while highlighting the reinforcement of the inductive effect and suppression of the resonance effect. This strategic approach facilitates the development of an exceptional quinone, viz. 2,6-naphthoquinone, with outstanding performance parameters (338.9 mAh g-1 and 912.9 mWh g-1). Furthermore, 2,6-anthraquinone with superior cyclic stability, demonstrates comparable performance (257.4 mAh g-1 and 702.8 mWh g-1). These findings offer valuable insights into the design of organic cathode materials with favorable redox chemistry in secondary batteries.

Density functional theory and machine learning for electrochemical square-scheme prediction: an application to quinone-type molecules relevant to redox flow batteries

Proton-electron transfer (PET) reactions are rather common in chemistry and crucial in energy storage applications. How electrons and protons are involved or which mechanism dominates is strongly molecule and pH dependent. Quantum chemical methods can be used to assess redox potential (Ered.) and acidity constant (pKa) values but the computations are rather time consuming. In this work, supervised machine learning (ML) models are used to predict PET reactions and analyze molecular space. The data for ML have been created by density functional theory (DFT) calculations. Random forest regression models are trained and tested on a dataset that we created. The dataset contains more than 8200 quinone-type organic molecules that each underwent two proton and two electron transfer reactions. Both structural and chemical descriptors are used. The HOMO of the reactant and LUMO of the product participating in the oxidation reaction appeared to be strongly associated with Ered.. Trained models using a SMILES-based structural descriptor can efficiently predict the pKa and Ered. with a mean absolute error of less than 1 and 66 mV, respectively. Good prediction accuracy of R2 > 0.76 and >0.90 was also obtained on the external test set for Ered. and pKa, respectively. This hybrid DFT-ML study can be applied to speed up the screening of quinone-type molecules for energy storage and other applications.

Functional convergence in slow-growing microbial communities arises from thermodynamic constraints

The dynamics of microbial communities is complex, determined by competition for metabolic substrates and cross-feeding of byproducts. Species in the community grow by harvesting energy from chemical reactions that transform substrates to products. In many anoxic environments, these reactions are close to thermodynamic equilibrium and growth is slow. To understand the community structure in these energy-limited environments, we developed a microbial community consumer-resource model incorporating energetic and thermodynamic constraints on an interconnected metabolic network. The central element of the model is product inhibition, meaning that microbial growth may be limited not only by depletion of metabolic substrates but also by accumulation of products. We demonstrate that these additional constraints on microbial growth cause a convergence in the structure and function of the community metabolic network-independent of species composition and biochemical details-providing a possible explanation for convergence of community function despite taxonomic variation observed in many natural and industrial environments. Furthermore, we discovered that the structure of community metabolic network is governed by the thermodynamic principle of maximum free energy dissipation. Our results predict the decrease of functional convergence in faster growing communities, which we validate by analyzing experimental data from anaerobic digesters. Overall, the work demonstrates how universal thermodynamic principles may constrain community metabolism and explain observed functional convergence in microbial communities.

Unlocking the Potential: Predicting Redox Behavior of Organic Molecules, from Linear Fits to Neural Networks

Redox-active organic molecules, i.e., molecules that can relatively easily accept and/or donate electrons, are ubiquitous in biology, chemical synthesis, and electronic and spintronic devices, such as solar cells and rechargeable batteries, etc. Choosing the best candidates from an essentially infinite chemical space for experimental testing in a target application requires efficient screening approaches. In this Review, we discuss modern in silico techniques for predicting reduction and oxidation potentials of organic molecules that go beyond conventional first-principles computations and thermodynamic cycles. Approaches ranging from simple linear fits based on molecular orbital energy approximation and energy difference approximation to advanced regression and neural network machine learning algorithms employing complex descriptors of molecular compositions, geometries, and electronic structures are examined in conjunction with relevant literature examples. We discuss the interplay between ab initio data and machine learning (ML), i.e., whether it is better to base predictions on low-level quantum-chemical results corrected with ML or to bypass first-principles computations entirely and instead rely on elaborate deep learning architectures. Finally, we list currently available data sets of redox-active organic molecules and their experimental and/or computed properties to facilitate the development of screening platforms and rational design of redox-active organic molecules.

The landscape of computational approaches for artificial photosynthesis

Artificial photosynthesis is an attractive strategy for converting solar energy into fuels, largely because the Earth receives enough solar energy in one hour to meet humanity's energy needs for an entire year. However, developing devices for artificial photosynthesis remains difficult and requires computational approaches to guide and assist the interpretation of experiments. In this Perspective, we discuss current and future computational approaches, as well as the challenges of designing and characterizing molecular assemblies that absorb solar light, transfer electrons between interfaces, and catalyze water-splitting and fuel-forming reactions.

Harnessing Data Augmentation and Normalization Preprocessing to Improve the Performance of Chemical Reaction Predictions of Data-Driven Model

As a template-free, data-driven methodology, the molecular transformer model provides an alternative by which to predict the outcome of chemical reactions and design the route of the retrosynthetic plane in the field of organic synthesis and polymer chemistry. However, in consideration of the small datasets of chemical reactions, the data-driven model suffers from the difficulty of low accuracy in the prediction tasks of chemical reactions. In this contribution, we integrate the molecular transformer model with the strategies of data augmentation and normalization preprocessing to accomplish the three tasks of chemical reactions, including the forward predictions of chemical reactions, and single-step retrosynthetic predictions with and without the reaction classes. It is clearly demonstrated that the prediction accuracy of the molecular transformer model can be significantly raised by the use of proposed strategies for the three tasks of chemical reactions. Notably, after the introduction of the 40-level data augmentation and normalization preprocessing, the top-1 accuracy of the forward prediction increases markedly from 71.6% to 84.2% and the top-1 accuracy of the single-step retrosynthetic prediction with additional reaction class increases from 53.2% to 63.4%. Furthermore, it is found that the superior performance of the data-driven model originates from the correction of the grammatical errors of the SMILES strings, especially for the case of the reaction classes with small datasets.

Machine learning for a sustainable energy future

Transitioning from fossil fuels to renewable energy sources is a critical global challenge; it demands advances - at the materials, devices and systems levels - for the efficient harvesting, storage, conversion and management of renewable energy. Energy researchers have begun to incorporate machine learning (ML) techniques to accelerate these advances. In this Perspective, we highlight recent advances in ML-driven energy research, outline current and future challenges, and describe what is required to make the best use of ML techniques. We introduce a set of key performance indicators with which to compare the benefits of different ML-accelerated workflows for energy research. We discuss and evaluate the latest advances in applying ML to the development of energy harvesting (photovoltaics), storage (batteries), conversion (electrocatalysis) and management (smart grids). Finally, we offer an overview of potential research areas in the energy field that stand to benefit further from the application of ML.

Machine Learning for Efficient Prediction of Protein Redox Potential: The Flavoproteins Case

Determining the redox potentials of protein cofactors and how they are influenced by their molecular neighborhoods is essential for basic research and many biotechnological applications, from biosensors and biocatalysis to bioremediation and bioelectronics. The laborious determination of redox potential with current experimental technologies pushes forward the need for computational approaches that can reliably predict it. Although current computational approaches based on quantum and molecular mechanics are accurate, their large computational costs hinder their usage. In this work, we explored the possibility of using more efficient QSPR models based on machine learning (ML) for the prediction of protein redox potential, as an alternative to classical approaches. As a proof of concept, we focused on flavoproteins, one of the most important families of enzymes directly involved in redox processes. To train and test different ML models, we retrieved a dataset of flavoproteins with a known midpoint redox potential (Em) and 3D structure. The features of interest, accounting for both short- and long-range effects of the protein matrix on the flavin cofactor, have been automatically extracted from each protein PDB file. Our best ML model (XGB) has a performance error below 1 kcal/mol (∼36 mV), comparing favorably to more sophisticated computational approaches. We also provided indications on the features that mostly affect the Em value, and when possible, we rationalized them on the basis of previous studies.

Design of Molecules with Low Hole and Electron Reorganization Energy Using DFT Calculations and Bayesian Optimization

Materials exhibiting higher mobility than conventional organic semiconducting materials, such as fullerenes and fused thiophenes, are in high demand for applications in printed electronics. To discover new molecules that might show improved charge mobility, the adaptive design of experiments (DoE) to design molecules with low reorganization energy was performed by combining density functional theory (DFT) methods and machine learning techniques. DFT-calculated values of 165 molecules were used as an initial training dataset for a Gaussian process regression (GPR) model, and five rounds of molecular designs applying the GPR model and validation via DFT calculations were executed. As a result, new molecules whose reorganization energy is smaller than the lowest value in the initial training dataset were successfully discovered.

John PC. Multi-objective goal-directed optimization of de novo stable organic radicals for aqueous redox flow batteries

Advances in the field of goal-directed molecular optimization offer the promise of finding feasible candidates for even the most challenging molecular design applications. One example of a fundamental design challenge is the search for novel stable radical scaffolds for an aqueous redox flow battery that simultaneously satisfy redox requirements at the anode and cathode, as relatively few stable organic radicals are known to exist. To meet this challenge, we develop a new open-source molecular optimization framework based on AlphaZero coupled with a fast, machine-learning-derived surrogate objective trained with nearly 100,000 quantum chemistry simulations. The objective function comprises two graph neural networks: one that predicts adiabatic oxidation and reduction potentials and a second that predicts electron density and local three-dimensional environment, previously shown to be correlated with radical persistence and stability. With no hard-coded knowledge of organic chemistry, the reinforcement learning agent finds molecule candidates that satisfy a precise combination of redox, stability and synthesizability requirements defined at the quantum chemistry level, many of which have reasonable predicted retrosynthetic pathways. The optimized molecules show that alternative stable radical scaffolds may offer a unique profile of stability and redox potentials to enable low-cost symmetric aqueous redox flow batteries.

Machine learning for flow batteries: opportunities and challenges

With increased computational ability of modern computers, the rapid development of mathematical algorithms and the continuous establishment of material databases, artificial intelligence (AI) has shown tremendous potential in chemistry. Machine learning (ML), as one of the most important branches of AI, plays an important role in accelerating the discovery and design of key materials for flow batteries (FBs), and the optimization of FB systems. In this perspective, we first provide a fundamental understanding of the workflow of ML in FBs. Moreover, recent progress on applications of the state-of-art ML in both organic FBs and vanadium FBs are discussed. Finally, the challenges and future directions of ML research in FBs are proposed.

Autonomous design of new chemical reactions using a variational autoencoder

Artificial intelligence based chemistry models are a promising method of exploring chemical reaction design spaces. However, training datasets based on experimental synthesis are typically reported only for the optimal synthesis reactions. This leads to an inherited bias in the model predictions. Therefore, robust datasets that span the entirety of the solution space are necessary to remove inherited bias and permit complete training of the space. In this study, an artificial intelligence model based on a Variational AutoEncoder (VAE) has been developed and investigated to synthetically generate continuous datasets. The approach involves sampling the latent space to generate new chemical reactions. This developed technique is demonstrated by generating over 7,000,000 new reactions from a training dataset containing only 7,000 reactions. The generated reactions include molecular species that are larger and more diverse than the training set.

Emerging Landscape of Computational Modeling in Pharmaceutical Development

Computational chemistry applications have become an integral part of the drug discovery workflow over the past 35 years. However, computational modeling in support of drug development has remained a relatively uncharted territory for a significant part of both academic and industrial communities. This review considers the computational modeling workflows for three key components of drug preclinical and clinical development, namely, process chemistry, analytical research and development, as well as drug product and formulation development. An overview of the computational support for each step of the respective workflows is presented. Additionally, in context of solid form design, special consideration is given to modern physics-based virtual screening methods. This covers rational approaches to polymorph, coformer, counterion, and solvent virtual screening in support of solid form selection and design.

ChemSpaX: exploration of chemical space by automated functionalization of molecular scaffold

Exploration of the local chemical space of molecular scaffolds by post-functionalization (PF) is a promising route to discover novel molecules with desired structure and function. PF with rationally chosen substituents based on known electronic and steric properties is a commonly used experimental and computational strategy in screening, design and optimization of catalytic scaffolds. Automated generation of reasonably accurate geometric representations of post-functionalized molecular scaffolds is highly desirable for data-driven applications. However, automated PF of transition metal (TM) complexes remains challenging. In this work a Python-based workflow, ChemSpaX, that is aimed at automating the PF of a given molecular scaffold with special emphasis on TM complexes, is introduced. In three representative applications of ChemSpaX by comparing with DFT and DFT-B calculations, we show that the generated structures have a reasonable quality for use in computational screening applications. Furthermore, we show that ChemSpaX generated geometries can be used in machine learning applications to accurately predict DFT computed HOMO-LUMO gaps for transition metal complexes. ChemSpaX is open-source and aims to bolster and democratize the efforts of the scientific community towards data-driven chemical discovery.

Bridging the Experiment-Calculation Divide: Machine Learning Corrections to Redox Potential Calculations in Implicit and Explicit Solvent Models

Prediction of redox potentials is essential for catalysis and energy storage. Although density functional theory (DFT) calculations have enabled rapid redox potential predictions for numerous compounds, prominent errors persist compared to experimental measurements. In this work, we develop machine learning (ML) models to reduce the errors of redox potential calculations in both implicit and explicit solvent models. Training and testing of the ML correction models are based on the diverse ROP313 data set with experimental redox potentials measured for organic and organometallic compounds in a variety of solvents. For the implicit solvent approach, our ML models can reduce both the systematic bias and the number of outliers. ML corrected redox potentials also demonstrate less sensitivity to DFT functional choice. For the explicit solvent approach, we significantly reduce the computational costs by embedding the microsolvated cluster in implicit bulk solvent, obtaining converged redox potential results with a smaller solvation shell. This combined implicit-explicit solvent model, together with GPU-accelerated quantum chemistry methods, enabled rapid generation of a large data set of explicit-solvent-calculated redox potentials for 165 organic compounds, allowing detailed investigation of the error sources in explicit solvent redox potential calculations.

De Novo Design of Molecules with Low Hole Reorganization Energy Based on a Quarter-Million Molecule DFT Screen

Materials exhibiting higher mobilities than conventional organic semiconducting materials such as fullerenes and fused thiophenes are in high demand for applications in printed electronics. To discover new molecules in the heteroacene family that might show improved hole mobility, three de novo design methods were applied. Machine learning (ML) models were generated based on previously calculated hole reorganization energies of a quarter million examples of heteroacenes, where the energies were calculated by applying density functional theory (DFT) and a massive cloud computing environment. The three generative methods applied were (1) the continuous space method, where molecular structures are converted into continuous variables by applying the variational autoencoder/decoder technique; (2) the method based on reinforcement learning of SMILES strings (the REINVENT method); and (3) the junction tree variational autoencoder method that directly generates molecular graphs. Among the three methods, the second and third methods succeeded in obtaining chemical structures whose DFT-calculated hole reorganization energy was lower than the lowest energy in the training dataset. This suggests that an extrapolative materials design protocol can be developed by applying generative modeling to a quantitative structure-property relationship (QSPR) utility function.

Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning

Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes.

A Multitask Approach to Learn Molecular Properties

The endeavors to pursue a robust multitask model to resolve intertask correlations have lasted for many years. A multitask deep neural network, as the most widely used multitask framework, however, experiences several issues such as inconsistent performance improvement over the independent model benchmark. The research aims to introduce an alternative framework by using the problem transformation methods. We build our multitask models essentially based on the stacking of a base regressor and classifier, where the multitarget predictions are realized from an additional training stage on the expanded molecular feature space. The model architecture is implemented on the QM9, Alchemy, and Tox21 datasets, by using a variety of baseline machine learning techniques. The resultant multitask performance shows 1 to 10% enhancement of forecasting precision, with the task prediction accuracy being consistently improved over the independent single-target models. The proposed method demonstrates a notable superiority in tackling the intertarget dependence and, moreover, a great potential to simulate a wide range of molecular properties under the transformation framework.

A Computational Protocol Combining DFT and Cheminformatics for Prediction of pH-Dependent Redox Potentials

Discovering new materials for energy storage requires reliable and efficient protocols for predicting key properties of unknown compounds. In the context of the search for new organic electrolytes for redox flow batteries, we present and validate a robust procedure to calculate the redox potentials of organic molecules at any pH value, using widely available quantum chemistry and cheminformatics methods. Using a consistent experimental data set for validation, we explore and compare a few different methods for calculating reaction free energies, the treatment of solvation, and the effect of pH on redox potentials. We find that the B3LYP hybrid functional with the COSMO solvation method, in conjunction with thermal contributions evaluated from BLYP gas-phase harmonic frequencies, yields a good prediction of pH = 0 redox potentials at a moderate computational cost. To predict how the potentials are affected by pH, we propose an improved version of the Alberty-Legendre transform that allows the construction of a more realistic Pourbaix diagram by taking into account how the protonation state changes with pH.

Generative Models for Extrapolation Prediction in Materials Informatics

We report a deep generative model for regression tasks in materials informatics. The model is introduced as a component of a data imputer and predicts more than 20 diverse experimental properties of organic molecules. The imputer is designed to predict material properties by "imagining" the missing data in the database, enabling the use of incomplete material data. Even removing 60% of the data does not diminish the prediction accuracy in a model task. Moreover, the model excels at extrapolation prediction, where target values of the test data are out of the range of the training data. Such an extrapolation has been regarded as an essential technique for exploring novel materials but has hardly been studied to date due to its difficulty. We demonstrate that the prediction performance can be improved by >30% by using the imputer compared with traditional linear regression and boosting models. The benefit becomes especially pronounced with few records for an experimental property (<100 cases) when prediction would be difficult by conventional methods. The presented approach can be used to more efficiently explore functional materials and break through previous performance limits.

Deep Learning Optical Spectroscopy Based on Experimental Database: Potential Applications to Molecular Design

Accurate and reliable prediction of the optical and photophysical properties of organic compounds is important in various research fields. Here, we developed deep learning (DL) optical spectroscopy using a DL model and experimental database to predict seven optical and photophysical properties of organic compounds, namely, the absorption peak position and bandwidth, extinction coefficient, emission peak position and bandwidth, photoluminescence quantum yield (PLQY), and emission lifetime. Our DL model included the chromophore-solvent interaction to account for the effect of local environments on the optical and photophysical properties of organic compounds and was trained using an experimental database of 30 094 chromophore/solvent combinations. Our DL optical spectroscopy made it possible to reliably and quickly predict the aforementioned properties of organic compounds in solution, gas phase, film, and powder with the root mean squared errors of 26.6 and 28.0 nm for absorption and emission peak positions, 603 and 532 cm-1 for absorption and emission bandwidths, and 0.209, 0.371, and 0.262 for the logarithm of the extinction coefficient, PLQY, and emission lifetime, respectively. Finally, we demonstrated how a blue emitter with desired optical and photophysical properties could be efficiently virtually screened and developed by DL optical spectroscopy. DL optical spectroscopy can be efficiently used for developing chromophores and fluorophores in various research areas.

Quantum Mechanical Methods Predict Accurate Thermodynamics of Biochemical Reactions

Thermodynamics plays a crucial role in regulating the metabolic processes in all living organisms. Accurate determination of biochemical and biophysical properties is important to understand, analyze, and synthetically design such metabolic processes for engineered systems. In this work, we extensively performed first-principles quantum mechanical calculations to assess its accuracy in estimating free energy of biochemical reactions and developed automated quantum-chemistry (QC) pipeline (https://appdev.kbase.us/narrative/45710) for the prediction of thermodynamics parameters of biochemical reactions. We benchmark the QC methods based on density functional theory (DFT) against different basis sets, solvation models, pH, and exchange-correlation functionals using the known thermodynamic properties from the NIST database. Our results show that QC calculations when combined with simple calibration yield a mean absolute error in the range of 1.60-2.27 kcal/mol for different exchange-correlation functionals, which is comparable to the error in the experimental measurements. This accuracy over a diverse set of metabolic reactions is unprecedented and near the benchmark chemical accuracy of 1 kcal/mol that is usually desired from DFT calculations.

A map of mass spectrometry-based in silico fragmentation prediction and compound identification in metabolomics

Metabolomics, the comprehensive study of the metabolome, and lipidomics-the large-scale study of pathways and networks of cellular lipids-are major driving forces in enabling personalized medicine. Complicated and error-prone data analysis still remains a bottleneck, however, especially for identifying novel metabolites. Comparing experimental mass spectra to curated databases containing reference spectra has been the gold standard for identification of compounds, but constructing such databases is a costly and time-demanding task. Many software applications try to circumvent this process by utilizing cutting-edge advances in computational methods-including quantum chemistry and machine learning-and simulate mass spectra by performing theoretical, so called in silico fragmentations of compounds. Other solutions concentrate directly on experimental spectra and try to identify structural properties by investigating reoccurring patterns and the relationships between them. The considerable progress made in the field allows recent approaches to provide valuable clues to expedite annotation of experimental mass spectra. This review sheds light on individual strengths and weaknesses of these tools, and attempts to evaluate them-especially in view of lipidomics, when considering complex mixtures found in biological samples as well as mass spectrometer inter-instrument variability.

High throughput virtual screening of 230 billion molecular solar heat battery candidates

The dihydroazulene/vinylheptafulvene (DHA/VHF) thermocouple is a promising candidate for thermal heat batteries that absorb and store solar energy as chemical energy without the need for insulation. However, in order to be viable the energy storage capacity and lifetime of the high energy form (i.e., the free energy barrier to the back reaction) of the canonical parent compound must be increased significantly to be of practical use. We use semiempirical quantum chemical methods, machine learning, and density functional theory to virtually screen over 230 billion substituted DHA molecules to identify promising candidates. We identify a molecule with a predicted energy density of 0.38 kJ/g, which is significantly larger than the 0.14 kJ/g computed for the parent compound. The free energy barrier to the back reaction is 11 kJ/mol higher than the parent compound, which should correspond to a half-life of about 10 days—4 months. This is considerably longer than the 3–39 h (depending on solvent) observed for the parent compound and sufficiently long for many practical applications. Our paper makes two main important contributions: (1) a novel and generally applicable methodological approach that makes screening of huge libraries for properties involving chemical reactivity with modest computational resources, and (2) a clear demonstration that the storage capacity of the DHA/VHF thermocouple cannot be increased to >0.5 kJ/g by combining simple substituents.

tmQM Dataset-Quantum Geometries and Properties of 86k Transition Metal Complexes

We report the transition metal quantum mechanics (tmQM) data set, which contains the geometries and properties of a large transition metal-organic compound space. tmQM comprises 86,665 mononuclear complexes extracted from the Cambridge Structural Database, including Werner, bioinorganic, and organometallic complexes based on a large variety of organic ligands and 30 transition metals (the 3d, 4d, and 5d from groups 3 to 12). All complexes are closed-shell, with a formal charge in the range {+1, 0, -1}e. The tmQM data set provides the Cartesian coordinates of all metal complexes optimized at the GFN2-xTB level, and their molecular size, stoichiometry, and metal node degree. The quantum properties were computed at the DFT(TPSSh-D3BJ/def2-SVP) level and include the electronic and dispersion energies, highest occupied molecular orbital (HOMO) and lowest unoccupied molecular orbital (LUMO) energies, HOMO/LUMO gap, dipole moment, and natural charge of the metal center; GFN2-xTB polarizabilities are also provided. Pairwise representations showed the low correlation between these properties, providing nearly continuous maps with unusual regions of the chemical space, for example, complexes combining large polarizabilities with wide HOMO/LUMO gaps and complexes combining low-energy HOMO orbitals with electron-rich metal centers. The tmQM data set can be exploited in the data-driven discovery of new metal complexes, including predictive models based on machine learning. These models may have a strong impact on the fields in which transition metal chemistry plays a key role, for example, catalysis, organic synthesis, and materials science. tmQM is an open data set that can be downloaded free of charge from https://github.com/bbskjelstad/tmqm.

Comparison of computational chemistry methods for the discovery of quinone-based electroactive compounds for energy storage

High-throughput computational screening (HTCS) is a powerful approach for the rational and time-efficient design of electroactive compounds. The effectiveness of HTCS is dependent on accuracy and speed at which the performance descriptors can be estimated for possibly millions of candidate compounds. Here, a systematic evaluation of computational methods, including force field (FF), semi-empirical quantum mechanics (SEQM), density functional based tight binding (DFTB), and density functional theory (DFT), is performed on the basis of their accuracy in predicting the redox potentials of redox-active organic compounds. Geometry optimizations at low-level theories followed by single point energy (SPE) DFT calculations that include an implicit solvation model are found to offer equipollent accuracy as the high-level DFT methods, albeit at significantly lower computational costs. Effects of implicit solvation on molecular geometries and SPEs, and their overall effects on the prediction accuracy of redox potentials are analyzed in view of computational cost versus prediction accuracy, which outlines the best choice of methods corresponding to a desired level of accuracy. The modular computational approach is applicable for accelerating the virtual studies on functional quinones and the respective discovery of candidate compounds for energy storage.

Recent advances in constraint and machine learning-based metabolic modeling by leveraging stoichiometric balances, thermodynamic feasibility and kinetic law formalisms

Understanding the governing principles behind organisms' metabolism and growth underpins their effective deployment as bioproduction chassis. A central objective of metabolic modeling is predicting how metabolism and growth are affected by both external environmental factors and internal genotypic perturbations. The fundamental concepts of reaction stoichiometry, thermodynamics, and mass action kinetics have emerged as the foundational principles of many modeling frameworks designed to describe how and why organisms allocate resources towards both growth and bioproduction. This review focuses on the latest algorithmic advancements that have integrated these foundational principles into increasingly sophisticated quantitative frameworks.

Machine-Learning Guided Quantum Chemical and Molecular Dynamics Calculations to Design Novel Hole-Conducting Organic Materials

Materials exhibiting higher mobilities than conventional organic semiconducting materials such as fullerenes and fused thiophenes are in high demand for applications such as printed electronics, organic solar cells, and image sensors. In order to discover new molecules that might show improved charge mobility, combined density functional theory (DFT) and molecular dynamics (MD) calculations were performed, guided by predictions from machine learning (ML). A ML model was constructed based on 32 values of theoretically calculated hole mobilities for thiophene derivatives, benzodifuran derivatives, a carbazole derivative and a perylene diimide derivative with the maximum value of 10^-1.96 cm²/(V s). Sequential learning, also known as active learning, was applied to select compounds on which to perform DFT/MD calculation of hole mobility to simultaneously improve the mobility surrogate model and identify high mobility compounds. By performing 60 cycles of sequential learning with 165 DFT/MD calculations, a molecule having a fused thioacene structure with its calculated hole mobility of 10^-1.86 cm²/(V s) was identified. This values is higher than the maximum value of mobility in the initial training data set, showing that an extrapolative discovery could be made with the sequential learning.

Deciphering tip-enhanced Raman imaging of carbon nanotubes with deep learning neural networks

Recent release of open-source machine learning libraries presents opportunities to unify machine learning with nanoscale research, thus improving effectiveness of research methods and characterization protocols. This paper outlines and demonstrates the effectiveness of such a synergy with artificial neural networks to provide for an accelerated and enhanced characterization of individual carbon nanotubes deposited over a surface. Our algorithms provide a rapid diagnosis and analysis of tip-enhanced Raman spectroscopy mappings and the results show an improved spectral assignment of spectral features and spatial contrast of the collected images. Using several examples, we demonstrate the robustness and versatility of our deep learning neural network models. We highlight the use of machine learning and data science in tandem with tip-enhanced Raman spectroscopy technique enables a fast and accurate understanding of experimental data, thus leading to a powerful and comprehensive imaging analysis applied to spectroscopic measurements.

Electronic Structure Modeling of Metal-Organic Frameworks

Owing to their molecular building blocks, yet highly crystalline nature, metal-organic frameworks (MOFs) sit at the interface between molecule and material. Their diverse structures and compositions enable them to be useful materials as catalysts in heterogeneous reactions, electrical conductors in energy storage and transfer applications, chromophores in photoenabled chemical transformations, and beyond. In all cases, density functional theory (DFT) and higher-level methods for electronic structure determination provide valuable quantitative information about the electronic properties that underpin the functions of these frameworks. However, there are only two general modeling approaches in conventional electronic structure software packages: those that treat materials as extended, periodic solids, and those that treat materials as discrete molecules. Each approach has features and benefits; both have been widely employed to understand the emergent chemistry that arises from the formation of the metal-organic interface. This Review canvases these approaches to date, with emphasis placed on the application of electronic structure theory to explore reactivity and electron transfer using periodic, molecular, and embedded models. This includes (i) computational chemistry considerations such as how functional, k-grid, and other model variables are selected to enable insights into MOF properties, (ii) extended solid models that treat MOFs as materials rather than molecules, (iii) the mechanics of cluster extraction and subsequent chemistry enabled by these molecular models, (iv) catalytic studies using both solids and clusters thereof, and (v) embedded, mixed-method approaches, which simulate a fraction of the material using one level of theory and the remainder of the material using another dissimilar theoretical implementation.

Thermodynamic Favorability of End Products of Anaerobic Glucose Metabolism

The eQuilibrator component contribution method allows calculation of the overall Gibbs energy changes for conversion of glucose to a wide range of final products in the absence of other oxidants. Values are presented for all possible combinations of products with up to three carbons and selected others. The most negative Gibbs energy change is for the formation of graphite and water (-499 kJ mol-1) followed by CH4 and CO2 (-430 kJ mol-1), the observed final products of anaerobic digestion. Other favored products (with various combinations having Gibbs energy changes between -300 and -367 kJ mol-1) are short-chain alkanes, fatty acids, dicarboxylic acids, and even hexane and benzene. The most familiar products, lactate and ethanol + CO2, are less favored (Gibbs energy changes of -206 and -265 kJ mol-1 respectively). The values presented offer an interesting perspective on observed metabolism and its evolutionary origins as well as on cells engineered for biotechnological purposes.

Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex

Homogeneous catalysis using transition metal complexes is ubiquitously used for organic synthesis, as well as technologically relevant in applications such as water splitting and CO2 reduction. The key steps underlying homogeneous catalysis require a specific combination of electronic and steric effects from the ligands bound to the metal center. Finding the optimal combination of ligands is a challenging task due to the exceedingly large number of possibilities and the non-trivial ligand-ligand interactions. The classic example of Vaska's complex, trans-[Ir(PPh3)2(CO)(Cl)], illustrates this scenario. The ligands of this species activate iridium for the oxidative addition of hydrogen, yielding the dihydride cis-[Ir(H)2(PPh3)2(CO)(Cl)] complex. Despite the simplicity of this system, thousands of derivatives can be formulated for the activation of H2, with a limited number of ligands belonging to the same general categories found in the original complex. In this work, we show how DFT and machine learning (ML) methods can be combined to enable the prediction of reactivity within large chemical spaces containing thousands of complexes. In a space of 2574 species derived from Vaska's complex, data from DFT calculations are used to train and test ML models that predict the H2-activation barrier. In contrast to experiments and calculations requiring several days to be completed, the ML models were trained and used on a laptop on a time-scale of minutes. As a first approach, we combined Bayesian-optimized artificial neural networks (ANN) with features derived from autocorrelation and deltametric functions. The resulting ANNs achieved high accuracies, with mean absolute errors (MAE) between 1 and 2 kcal mol-1, depending on the size of the training set. By using a Gaussian process (GP) model trained with a set of selected features, including fingerprints, accuracy was further enhanced. Remarkably, this GP model minimized the MAE below 1 kcal mol-1, by using only 20% or less of the data available for training. The gradient boosting (GB) method was also used to assess the relevance of the features, which was used for both feature selection and model interpretation purposes. Features accounting for chemical composition, atom size and electronegativity were found to be the most determinant in the predictions. Further, the ligand fragments with the strongest influence on the H2-activation barrier were identified.