The Harvard organic photovoltaic dataset

In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back

Computational chemistry is an indispensable tool for understanding molecules and predicting chemical properties. However, traditional computational methods face significant challenges due to the difficulty of solving the Schrödinger equations and the increasing computational cost with the size of the molecular system. In response, there has been a surge of interest in leveraging artificial intelligence (AI) and machine learning (ML) techniques to in silico experiments. Integrating AI and ML into computational chemistry increases the scalability and speed of the exploration of chemical space. However, challenges remain, particularly regarding the reproducibility and transferability of ML models. This review highlights the evolution of ML in learning from, complementing, or replacing traditional computational chemistry for energy and property predictions. Starting from models trained entirely on numerical data, a journey set forth toward the ideal model incorporating or learning the physical laws of quantum mechanics. This paper also reviews existing computational methods and ML models and their intertwining, outlines a roadmap for future research, and identifies areas for improvement and innovation. Ultimately, the goal is to develop AI architectures capable of predicting accurate and transferable solutions to the Schrödinger equation, thereby revolutionizing in silico experiments within chemistry and materials science.

Creation of a structured solar cell material dataset and performance prediction using large language models

Materials scientists usually collect experimental data to summarize experiences and predict improved materials. However, a crucial issue is how to proficiently utilize unstructured data to update existing structured data, particularly in applied disciplines. This study introduces a new natural language processing (NLP) task called structured information inference (SII) to address this problem. We propose an end-to-end approach to summarize and organize the multi-layered device-level information from the literature into structured data. After comparing different methods, we fine-tuned LLaMA with an F1 score of 87.14% to update an existing perovskite solar cell dataset with articles published since its release, allowing its direct use in subsequent data analysis. Using structured information, we developed regression tasks to predict the electrical performance of solar cells. Our results demonstrate comparable performance to traditional machine-learning methods without feature selection and highlight the potential of large language models for scientific knowledge acquisition and material development.

Accurate Electronic and Optical Properties of Organic Doublet Radicals Using Machine Learned Range-Separated Functionals

Luminescent organic semiconducting doublet-spin radicals are unique and emergent optical materials because their fluorescent quantum yields (Φfl) are not compromised by the spin-flipping intersystem crossing (ISC) into a dark high-spin state. The multiconfigurational nature of these radicals challenges their electronic structure calculations in the framework of single-reference density functional theory (DFT) and introduces room for method improvement. In the present study, we extended our earlier development of ML-ωPBE [J. Phys. Chem. Lett., 2021, 12, 9516-9524], a range-separated hybrid (RSH) exchange-correlation (XC) functional constructed using the stacked ensemble machine learning (SEML) algorithm, from closed-shell organic semiconducting molecules to doublet-spin organic semiconducting radicals. We assessed its performance for a new test set of 64 doublet-spin radicals from five categories while placing all previously compiled 3926 closed-shell molecules in the new training set. Interestingly, ML-ωPBE agrees with the nonempirical OT-ωPBE functional regarding the prediction of the molecule-dependent range-separation parameter (ω), with a small mean absolute error (MAE) of 0.0197 a0-1, but saves the computational cost by 2.46 orders of magnitude. This result demonstrates an outstanding domain adaptation capacity of ML-ωPBE for diverse organic semiconducting species. To further assess the predictive power of ML-ωPBE in experimental observables, we also applied it to evaluate absorption and fluorescence energies (Eabs and Efl) using linear-response time-dependent DFT (TDDFT), and we compared its behavior with nine popular XC functionals. For most radicals, ML-ωPBE reproduces experimental measurements of Eabs and Efl with small MAEs of 0.299 and 0.254 eV, only marginally different from those of OT-ωPBE. Our work illustrates a successful extension of the SEML framework from closed-shell molecules to doublet-spin radicals and will open the venue for calculating optical properties for organic semiconductors using single-reference TDDFT.

COMPAS-2: a dataset of cata-condensed hetero-polycyclic aromatic systems

Polycyclic aromatic systems are highly important to numerous applications, in particular to organic electronics and optoelectronics. High-throughput screening and generative models that can help to identify new molecules to advance these technologies require large amounts of high-quality data, which is expensive to generate. In this report, we present the largest freely available dataset of geometries and properties of cata-condensed poly(hetero)cyclic aromatic molecules calculated to date. Our dataset contains ~500k molecules comprising 11 types of aromatic and antiaromatic building blocks calculated at the GFN1-xTB level and is representative of a highly diverse chemical space. We detail the structure enumeration process and the methods used to provide various electronic properties (including HOMO-LUMO gap, adiabatic ionization potential, and adiabatic electron affinity). Additionally, we benchmark against a ~50k dataset calculated at the CAM-B3LYP-D3BJ/def2-SVP level and develop a fitting scheme to correct the xTB values to higher accuracy. These new datasets represent the second installment in the COMputational database of Polycyclic Aromatic Systems (COMPAS) Project.

Data mining and library generation to search electron-rich and electron-deficient building blocks for the designing of polymers for photoacoustic imaging

Photoacoustic imaging is a good method for biological imaging, for this purpose, materials with strong near infrared (NIR) absorbance are required. In the present study, machine learning models are used to predict the light absorption behavior of polymers. Molecular descriptors are utilized to train a variety of machine learning models. Building blocks are searched from chemical databases, as well as new building blocks are designed using chemical library enumeration method. The Breaking Retrosynthetically Interesting Chemical Substructures (BRICS) method is employed for the creation of 10,000 novel polymers. These polymers are designed based on the input of searched and selected building blocks. To enhance the process, the optimal machine learning model is utilized to predict the UV/visible absorption maxima of the newly designed polymers. Concurrently, chemical similarity analysis is also performed on the selected polymers, and synthetic accessibility of selected polymers is calculated. In summary, the polymers are all easy to synthesize, increasing their potential for practical applications.

Accurate prediction of global-density-dependent range-separation parameters based on machine learning

In this work, we develop an accurate and efficient XGBoost machine learning model for predicting the global-density-dependent range-separation parameter, ωGDD, for long-range corrected functional (LRC)-ωPBE. This ωGDDML model has been built using a wide range of systems (11 466 complexes, ten different elements, and up to 139 heavy atoms) with fingerprints for the local atomic environment and histograms of distances for the long-range atomic correlation for mapping the quantum mechanical range-separation values. The promising performance on the testing set with 7046 complexes shows a mean absolute error of 0.001 117 a0-1 and only five systems (0.07%) with an absolute error larger than 0.01 a0-1, which indicates the good transferability of our ωGDDML model. In addition, the only required input to obtain ωGDDML is the Cartesian coordinates without electronic structure calculations, thereby enabling rapid predictions. LRC-ωPBE(ωGDDML) is used to predict polarizabilities for a series of oligomers, where polarizabilities are sensitive to the asymptotic density decay and are crucial in a variety of applications, including the calculations of dispersion corrections and refractive index, and surpasses the performance of all other popular density functionals except for the non-tuned LRC-ωPBE. Finally, LRC-ωPBE (ωGDDML) combined with (extended) symmetry-adapted perturbation theory is used in calculating noncovalent interactions to further show that the traditional ab initio system-specific tuning procedure can be bypassed. The present study not only provides an accurate and efficient way to determine the range-separation parameter for LRC-ωPBE but also shows the synergistic benefits of fusing the power of physically inspired density functional LRC-ωPBE and the data-driven ωGDDML model.

AI-accelerated protein-ligand docking for SARS-CoV-2 is 100-fold faster with no significant change in detection

Protein-ligand docking is a computational method for identifying drug leads. The method is capable of narrowing a vast library of compounds down to a tractable size for downstream simulation or experimental testing and is widely used in drug discovery. While there has been progress in accelerating scoring of compounds with artificial intelligence, few works have bridged these successes back to the virtual screening community in terms of utility and forward-looking development. We demonstrate the power of high-speed ML models by scoring 1 billion molecules in under a day (50 k predictions per GPU seconds). We showcase a workflow for docking utilizing surrogate AI-based models as a pre-filter to a standard docking workflow. Our workflow is ten times faster at screening a library of compounds than the standard technique, with an error rate less than 0.01% of detecting the underlying best scoring 0.1% of compounds. Our analysis of the speedup explains that another order of magnitude speedup must come from model accuracy rather than computing speed. In order to drive another order of magnitude of acceleration, we share a benchmark dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million "in-stock" molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. We believe this is strong evidence for the community to begin focusing on improving the accuracy of surrogate models to improve the ability to screen massive compound libraries 100 × or even 1000 × faster than current techniques and reduce missing top hits. The technique outlined aims to be a fast drop-in replacement for docking for screening billion-scale molecular libraries.

Electronic, redox, and optical property prediction of organic π-conjugated molecules through a hierarchy of machine learning approaches

Accelerating the development of π-conjugated molecules for applications such as energy generation and storage, catalysis, sensing, pharmaceuticals, and (semi)conducting technologies requires rapid and accurate evaluation of the electronic, redox, or optical properties. While high-throughput computational screening has proven to be a tremendous aid in this regard, machine learning (ML) and other data-driven methods can further enable orders of magnitude reduction in time while at the same time providing dramatic increases in the chemical space that is explored. However, the lack of benchmark datasets containing the electronic, redox, and optical properties that characterize the diverse, known chemical space of organic π-conjugated molecules limits ML model development. Here, we present a curated dataset containing 25k molecules with density functional theory (DFT) and time-dependent DFT (TDDFT) evaluated properties that include frontier molecular orbitals, ionization energies, relaxation energies, and low-lying optical excitation energies. Using the dataset, we train a hierarchy of ML models, ranging from classical models such as ridge regression to sophisticated graph neural networks, with molecular SMILES representation as input. We observe that graph neural networks augmented with contextual information allow for significantly better predictions across a wide array of properties. Our best-performing models also provide an uncertainty quantification for the predictions. To democratize access to the data and trained models, an interactive web platform has been developed and deployed.

Renewed Prospects for Organic Photovoltaics

Organic photovoltaics (OPVs) have progressed steadily through three stages of photoactive materials development: (i) use of poly(3-hexylthiophene) and fullerene-based acceptors (FAs) for optimizing bulk heterojunctions; (ii) development of new donors to better match with FAs; (iii) development of non-fullerene acceptors (NFAs). The development and application of NFAs with an A-D-A configuration (where A = acceptor and D = donor) has enabled devices to have efficient charge generation and small energy losses (E_loss < 0.6 eV), resulting in substantially higher power conversion efficiencies (PCEs) than FA-based devices. The discovery of Y6-type acceptors (Y6 = 2,2'-((2Z,2'Z)-((12,13-bis(2-ethylhexyl)-3,9-diundecyl-12,13-dihydro-[1,2,5]-thiadiazolo[3,4-e]-thieno[2″,3″:4',5']thieno-[2',3':4,5]pyrrolo-[3,2-g]thieno-[2',3':4,5]thieno-[3,2-b]indole-2,10-diyl)bis(methanylylidene))bis(5,6-difluoro-3-oxo-2,3-dihydro-1H-indene-2,1-diylidene))dimalononitrile) with an A-DA' D-A configuration has further propelled the PCEs to go beyond 15% due to smaller E_loss values (∼0.5 eV) and higher external quantum efficiencies. Subsequently, the PCEs of Y6-series single-junction devices have increased to >19% and may soon approach 20%. This review provides an update of recent progress of OPV in the following aspects: developments of novel NFAs and donors, understanding of the structure-property relationships and underlying mechanisms of state-of-the-art OPVs, and tasks underpinning the commercialization of OPVs, such as device stability, module development, potential applications, and high-throughput manufacturing. Finally, an outlook and prospects section summarizes the remaining challenges for the further development of OPV technology.

Limitations of machine learning models when predicting compounds with completely new chemistries: possible improvements applied to the discovery of new non-fullerene acceptors

We try to determine if machine learning (ML) methods, applied to the discovery of new materials on the basis of existing data sets, have the power to predict completely new classes of compounds (extrapolating) or perform well only when interpolating between known materials. We introduce the leave-one-group-out cross-validation, in which the ML model is trained to explicitly perform extrapolations of unseen chemical families. This approach can be used across materials science and chemistry problems to improve the added value of ML predictions, instead of using extrapolative ML models that were trained with a regular cross-validation. We consider as a case study the problem of the discovery of non-fullerene acceptors because novel classes of acceptors are naturally classified into distinct chemical families. We show that conventional ML methods are not useful in practice when attempting to predict the efficiency of a completely novel class of materials. The approach proposed in this work increases the accuracy of the predictions to enable at least the categorization of materials with a performance above and below the median value.

Organic materials repurposing, a data set for theoretical predictions of new applications for existing compounds

We present a data set of 48182 organic semiconductors, constituted of molecules that were prepared with a documented synthetic pathway and are stable in solid state. We based our search on the Cambridge Structural Database, from which we selected semiconductors with a computational funnel procedure. For each entry we provide a set of electronic properties relevant for organic materials research, and the electronic wavefunction for further calculations and/or analyses. This data set has low bias because it was not built from a set of materials designed for organic electronics, and thus it provides an excellent starting point in the search of new applications for known materials, with a great potential for novel physical insight. The data set contains molecules used as benchmarks in many fields of organic materials research, allowing to test the reliability of computational screenings for the desired application, "rediscovering" well-known molecules. This is demonstrated by a series of different applications in the field of organic materials, confirming the potential for the repurposing of known organic molecules.

Review on Y6-Based Semiconductor Materials and Their Future Development via Machine Learning

Non-fullerene acceptors are promising to achieve high efficiency in organic solar cells (OSCs). Y6-based acceptors, one group of new n-type semiconductors, have triggered tremendous attention when they reported a power-conversion efficiency (PCE) of 15.7% in 2019. After that, scientists are trying to improve the efficiency in different aspects including choosing new donors, tuning Y6 structures, and device engineering. In this review, we first summarize the properties of Y6 materials and the seven critical methods modifying the Y6 structure to improve the PCEs developed in the latest three years as well as the basic principles and parameters of OSCs. Finally, the authors would share perspectives on possibilities, necessities, challenges, and potential applications for designing multifunctional organic device with desired performances via machine learning.

Data-driven modeling of S0 → S1 excitation energy in the BODIPY chemical space: High-throughput computation, quantum machine learning, and inverse design

Derivatives of BODIPY are popular fluorophores due to their synthetic feasibility, structural rigidity, high quantum yield, and tunable spectroscopic properties. While the characteristic absorption maximum of BODIPY is at 2.5 eV, combinations of functional groups and substitution sites can shift the peak position by ±1 eV. Time-dependent long-range corrected hybrid density functional methods can model the lowest excitation energies offering a semi-quantitative precision of ±0.3 eV. Alas, the chemical space of BODIPYs stemming from combinatorial introduction of-even a few dozen-substituents is too large for brute-force high-throughput modeling. To navigate this vast space, we select 77 412 molecules and train a kernel-based quantum machine learning model providing <2% hold-out error. Further reuse of the results presented here to navigate the entire BODIPY universe comprising over 253 giga (253 × 10⁹) molecules is demonstrated by inverse-designing candidates with desired target excitation energies.

CRNNTL: Convolutional Recurrent Neural Network and Transfer Learning for QSAR Modeling in Organic Drug and Material Discovery

Molecular latent representations, derived from autoencoders (AEs), have been widely used for drug or material discovery over the past couple of years. In particular, a variety of machine learning methods based on latent representations have shown excellent performance on quantitative structure–activity relationship (QSAR) modeling. However, the sequence feature of them has not been considered in most cases. In addition, data scarcity is still the main obstacle for deep learning strategies, especially for bioactivity datasets. In this study, we propose the convolutional recurrent neural network and transfer learning (CRNNTL) method inspired by the applications of polyphonic sound detection and electrocardiogram classification. Our model takes advantage of both convolutional and recurrent neural networks for feature extraction, as well as the data augmentation method. According to QSAR modeling on 27 datasets, CRNNTL can outperform or compete with state-of-art methods in both drug and material properties. In addition, the performances on one isomers-based dataset indicate that its excellent performance results from the improved ability in global feature extraction when the ability of the local one is maintained. Then, the transfer learning results show that CRNNTL can overcome data scarcity when choosing relative source datasets. Finally, the high versatility of our model is shown by using different latent representations as inputs from other types of AEs.

Stacked Ensemble Machine Learning for Range-Separation Parameters

Density functional theory-based high-throughput materials and drug discovery has achieved tremendous success in recent decades, but its power on organic semiconducting molecules suffered catastrophically from the self-interaction error until the nonempirical but expensive optimally tuned range-separated hybrid (OT-RSH) functionals were developed. An OT-RSH transitions from a short-range (semi)local functional to a long-range Hartree-Fock exchange at a distance characterized by a molecule-specific range-separation parameter (ω). Herein, we propose a stacked ensemble machine learning model that provides an accelerated alternative of OT-RSH based on system-dependent structural and electronic configurations. We trained ML-ωPBE, the first functional in our series, using a database of 1970 molecules with sufficient structural and functional diversity, and assessed its accuracy and efficiency using another 1956 molecules. Compared with nonempirical OT-ωPBE, ML-ωPBE reaches a mean absolute error of 0.00504a₀^-1 for optimal ω's, reduces the computational cost by 2.66 orders of magnitude, and achieves comparable predictive power in optical properties.

Predicting Power Conversion Efficiency of Organic Photovoltaics: Models and Data Analysis

In this paper, the ability of three selected machine learning neural and baseline models in predicting the power conversion efficiency (PCE) of organic photovoltaics (OPVs) using molecular structure information as an input is assessed. The bidirectional long short-term memory (gFSI/BiLSTM), attentive fingerprints (attentive FP), and simple graph neural networks (simple GNN) as well as baseline support vector regression (SVR), random forests (RF), and high-dimensional model representation (HDMR) methods are trained to both the large and computational Harvard clean energy project database (CEPDB) and the much smaller experimental Harvard organic photovoltaic 15 dataset (HOPV15). It was found that the neural-based models generally performed better on the computational dataset with the attentive FP model reaching a state-of-the-art performance with the test set mean squared error of 0.071. The experimental dataset proved much harder to fit, with all of the models exhibiting a rather poor performance. Contrary to the computational dataset, the baseline models were found to perform better than the neural models. To improve the ability of machine learning models to predict PCEs for OPVs, either better computational results that correlate well with experiments or more experimental data at well-controlled conditions are likely required.

Molecular excited states through a machine learning lens

Theoretical simulations of electronic excitations and associated processes in molecules are indispensable for fundamental research and technological innovations. However, such simulations are notoriously challenging to perform with quantum mechanical methods. Advances in machine learning open many new avenues for assisting molecular excited-state simulations. In this Review, we track such progress, assess the current state of the art and highlight the critical issues to solve in the future. We overview a broad range of machine learning applications in excited-state research, which include the prediction of molecular properties, improvements of quantum mechanical methods for the calculations of excited-state properties and the search for new materials. Machine learning approaches can help us understand hidden factors that influence photo-processes, leading to a better control of such processes and new rules for the design of materials for optoelectronic applications.

Accelerating organic solar cell material's discovery: high-throughput screening and big data

The discovery of novel high-performing materials such as non-fullerene acceptors and low band gap donor polymers underlines the steady increase of record efficiencies in organic solar cells witnessed during the past years. Nowadays, the resulting catalogue of organic photovoltaic materials is becoming unaffordably vast to be evaluated following classical experimentation methodologies: their requirements in terms of human workforce time and resources are prohibitively high, which slows momentum to the evolution of the organic photovoltaic technology. As a result, high-throughput experimental and computational methodologies are fostered to leverage their inherently high exploratory paces and accelerate novel materials discovery. In this review, we present some of the computational (pre)screening approaches performed prior to experimentation to select the most promising molecular candidates from the available materials libraries or, alternatively, generate molecules beyond human intuition. Then, we outline the main high-throuhgput experimental screening and characterization approaches with application in organic solar cells, namely those based on lateral parametric gradients (measuring-intensive) and on automated device prototyping (fabrication-intensive). In both cases, experimental datasets are generated at unbeatable paces, which notably enhance big data readiness. Herein, machine-learning algorithms find a rewarding application niche to retrieve quantitative structure-activity relationships and extract molecular design rationale, which are expected to keep the material's discovery pace up in organic photovoltaics.

Transfer Learned Designer Polymers For Organic Solar Cells

Organic photovoltaic (OPV) materials have been examined extensively over the past two decades for solar cell applications because of the potential for device flexibility, low-temperature solution processability, and negligible environmental impact. However, discovery of new candidate OPV materials, especially polymer-based electron donors, that demonstrate notable power conversion efficiencies (PCEs), is nontrivial and time-intensive exercise given the extensive set of possible chemistries. Recent progress in machine learning accelerated materials discovery has facilitated to address this challenge, with molecular line representations, such as Simplified Molecular-Input Line-Entry Systems (SMILES), gaining popularity as molecular fingerprints describing the donor chemical structures. Here, we employ a transfer learning based recurrent neural (LSTM) model, which harnesses the SMILES molecular fingerprints as an input to generate novel designer chemistries for OPV devices. The generative model, perfected on a small focused OPV data set, predicts new polymer repeat units with potentially high PCE. Calculations of the similarity coefficient between the known and the generated polymers corroborate the accuracy of the model predictability as a function of the underlying chemical specificity. The data-enabled framework is sufficiently generic for use in accelerated machine learned materials discovery for various chemistries and applications, mining the hitherto available experimental and computational data.

Quantum Deep Field: Data-Driven Wave Function, Electron Density Generation, and Atomization Energy Prediction and Extrapolation with Machine Learning

Deep neural networks (DNNs) have been used to successfully predict molecular properties calculated based on the Kohn-Sham density functional theory (KS-DFT). Although this prediction is fast and accurate, we believe that a DNN model for KS-DFT must not only predict the properties but also provide the electron density of a molecule. This Letter presents the quantum deep field (QDF), which provides the electron density with an unsupervised but end-to-end physics-informed modeling by learning the atomization energy on a large-scale dataset. QDF performed well at atomization energy prediction, generated valid electron density, and demonstrated extrapolation.

Designing and understanding light-harvesting devices with machine learning

Understanding the fundamental processes of light-harvesting is crucial to the development of clean energy materials and devices. Biological organisms have evolved complex metabolic mechanisms to efficiently convert sunlight into chemical energy. Unraveling the secrets of this conversion has inspired the design of clean energy technologies, including solar cells and photocatalytic water splitting. Describing the emergence of macroscopic properties from microscopic processes poses the challenge to bridge length and time scales of several orders of magnitude. Machine learning experiences increased popularity as a tool to bridge the gap between multi-level theoretical models and Edisonian trial-and-error approaches. Machine learning offers opportunities to gain detailed scientific insights into the underlying principles governing light-harvesting phenomena and can accelerate the fabrication of light-harvesting devices.

Autonomous Discovery in the Chemical Sciences Part II: Outlook

This two-part Review examines how automation has contributed to different aspects of discovery in the chemical sciences. In this second part, we reflect on a selection of exemplary studies. It is increasingly important to articulate what the role of automation and computation has been in the scientific process and how that has or has not accelerated discovery. One can argue that even the best automated systems have yet to "discover" despite being incredibly useful as laboratory assistants. We must carefully consider how they have been and can be applied to future problems of chemical discovery in order to effectively design and interact with future autonomous platforms. The majority of this Review defines a large set of open research directions, including improving our ability to work with complex data, build empirical models, automate both physical and computational experiments for validation, select experiments, and evaluate whether we are making progress towards the ultimate goal of autonomous discovery. Addressing these practical and methodological challenges will greatly advance the extent to which autonomous systems can make meaningful discoveries.

Simulation vs. Understanding: A Tension, in Quantum Chemistry and Beyond. Part B. The March of Simulation, for Better or Worse

In the second part of this Essay, we leave philosophy, and begin by describing Roald's being trashed by simulation. This leads us to a general sketch of artificial intelligence (AI), Searle's Chinese room, and Strevens' account of what a go-playing program knows. Back to our terrain-we ask "Quantum Chemistry, † ca. 2020?" Then we move to examples of Big Data, machine learning and neural networks in action, first in chemistry and then affecting social matters, trivial to scary. We argue that moral decisions are hardly to be left to a computer. And that posited causes, even if recognized as provisional, represent a much deeper level of understanding than correlations. At this point, we try to pull the reader up, giving voice to the opposing view of an optimistic, limitless future. But we don't do justice to that view-how could we, older mammals on the way to extinction that we are? We try. But then we return to fuss, questioning the ascetic dimension of scientists, their romance with black boxes. And argue for a science of many tongues.

Powerful, transferable representations for molecules through intelligent task selection in deep multitask networks

We develop and test a framework for selecting appropriate chemical datasets to create molecular representations tailored for specific tasks.

Comparative dataset of experimental and computational attributes of UV/vis absorption spectra

The ability to auto-generate databases of optical properties holds great prospects in data-driven materials discovery for optoelectronic applications. We present a cognate set of experimental and computational data that describes key features of optical absorption spectra. This includes an auto-generated database of 18,309 records of experimentally determined UV/vis absorption maxima, λ_max, and associated extinction coefficients, ϵ, where present. This database was produced using the text-mining toolkit, ChemDataExtractor, on 402,034 scientific documents. High-throughput electronic-structure calculations using fast (simplified Tamm-Dancoff approach) and traditional (time-dependent) density functional theory were executed to predict λ_max and oscillation strengths, f (related to ϵ) for a subset of validated compounds. Paired quantities of these computational and experimental data show strong correlations in λ_max, f and ϵ, laying the path for reliable in silico calculations of additional optical properties. The total dataset of 8,488 unique compounds and a subset of 5,380 compounds with experimental and computational data, are available in MongoDB, CSV and JSON formats. These can be queried using Python, R, Java, and MATLAB, for data-driven optoelectronic materials discovery.

Measurement(s)	ultraviolet–visible spectrum • absorption wavelength • extinction coefficient
Technology Type(s)	digital curation

Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.10304897

Virtual Excited State Reference for the Discovery of Electronic Materials Database: An Open-Access Resource for Ground and Excited State Properties of Organic Molecules

This letter announces the Virtual Excited State Reference for the Discovery of Electronic Materials Database (VERDE materials DB), the first database to include downloadable excited-state structures (S₀, S₁, T₁) and photophysical properties. VERDE materials DB is searchable, open-access via www.verdedb.org , and focused on light-responsive π-conjugated organic molecules with applications in green chemistry, organic solar cells, and organic redox flow batteries. It includes results of our active and past virtual screening studies; to date, more than 13 000 density functional theory (DFT) calculations have been performed on 1 500 molecules to obtain frontier molecular orbitals and photophysical properties, including excitation energies, dipole moments, and redox potentials. To improve community access, we have made VERDE materials DB available via an integration with the Materials Data Facility. We are leveraging VERDE materials DB to train machine learning algorithms to identify new materials and structure-property relationships between molecular ground- and excited-states. We present a case-study involving photoaffinity labels, including predictions of new diazirine-based photoaffinity labels anticipated to have high photostabilities.

A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification

Deep neural networks have been increasingly used in various chemical fields. In the nature of a data-driven approach, their performance strongly depends on data used in training. Therefore, models developed in data-deficient situations can cause highly uncertain predictions, leading to vulnerable decision making. Here, we show that Bayesian inference enables more reliable prediction with quantitative uncertainty analysis. Decomposition of the predictive uncertainty into model- and data-driven uncertainties allows us to elucidate the source of errors for further improvements. For molecular applications, we devised a Bayesian graph convolutional network (GCN) and evaluated its performance for molecular property predictions. Our study on the classification problem of bio-activity and toxicity shows that the confidence of prediction can be quantified in terms of the predictive uncertainty, leading to more accurate virtual screening of drug candidates than standard GCNs. The result of log P prediction illustrates that data noise affects the data-driven uncertainty more significantly than the model-driven one. Based on this finding, we could identify artefacts that arose from quantum mechanical calculations in the Harvard Clean Energy Project dataset. Consequently, the Bayesian GCN is critical for molecular applications under data-deficient conditions.

A deep neural network model for packing density predictions and its application in the study of 1.5 million organic molecules

Computational pipeline for the accelerated discovery of organic materials with high refractive index via high-throughput screening and machine learning.

The process of developing new compounds and materials is increasingly driven by computational modeling and simulation, which allow us to characterize candidates before pursuing them in the laboratory. One of the non-trivial properties of interest for organic materials is their packing in the bulk, which is highly dependent on their molecular structure. By controlling the latter, we can realize materials with a desired density (as well as other target properties). Molecular dynamics simulations are a popular and reasonably accurate way to compute the bulk density of molecules, however, since these calculations are computationally intensive, they are not a practically viable option for high-throughput screening studies that assess material candidates on a massive scale. In this work, we employ machine learning to develop a data-derived prediction model that is an alternative to physics-based simulations, and we utilize it for the hyperscreening of 1.5 million small organic molecules as well as to gain insights into the relationship between structural makeup and packing density. We also use this study to analyze the learning curve of the employed neural network approach and gain empirical data on the dependence of model performance and training data size, which will inform future investigations.

Energy refinement and analysis of structures in the QM9 database via a highly accurate quantum chemical method

A wide variety of data-driven approaches have been introduced in the field of quantum chemistry. To extend the applicable range and improve the prediction power of those approaches, highly accurate quantum chemical benchmarks that cover extremely large chemical spaces are required. Here, we report ~134 k quantum chemical calculations performed with G4MP2, the fourth generation of the G-n series in which second-order perturbation theory is employed. A single composite method calculation executes several low-level calculations to reproduce the results of high-level ab initio calculations with the aim of saving computational costs. Therefore, our database reports the results of the various methods (e.g., density functional theory, Hartree-Fock, Møller-Plesset perturbation theory, and coupled-cluster theory). Additionally, we examined the structure information of both the QM9 and the revised databases via chemical graph analysis. Our database can be applied to refine and improve the quality of data-driven quantum chemical prediction. Furthermore, we reported the raw outputs of all calculations performed in this work for other potential applications.

Message-passing neural networks for high-throughput polymer screening

Machine learning methods have shown promise in predicting molecular properties, and given sufficient training data, machine learning approaches can enable rapid high-throughput virtual screening of large libraries of compounds. Graph-based neural network architectures have emerged in recent years as the most successful approach for predictions based on molecular structure and have consistently achieved the best performance on benchmark quantum chemical datasets. However, these models have typically required optimized 3D structural information for the molecule to achieve the highest accuracy. These 3D geometries are costly to compute for high levels of theory, limiting the applicability and practicality of machine learning methods in high-throughput screening applications. In this study, we present a new database of candidate molecules for organic photovoltaic applications, comprising approximately 91 000 unique chemical structures. Compared to existing datasets, this dataset contains substantially larger molecules (up to 200 atoms) as well as extrapolated properties for long polymer chains. We show that message-passing neural networks trained with and without 3D structural information for these molecules achieve similar accuracy, comparable to state-of-the-art methods on existing benchmark datasets. These results therefore emphasize that for larger molecules with practical applications, near-optimal prediction results can be obtained without using optimized 3D geometry as an input. We further show that learned molecular representations can be leveraged to reduce the training data required to transfer predictions to a new density functional theory functional.

Toward Design of Novel Materials for Organic Electronics

Materials for organic electronics are presently used in prominent applications, such as displays in mobile devices, while being intensely researched for other purposes, such as organic photovoltaics, large-area devices, and thin-film transistors. Many of the challenges to improve and optimize these applications are material related and there is a nearly infinite chemical space that needs to be explored to identify the most suitable material candidates. Established experimental approaches struggle with the size and complexity of this chemical space. Herein, the development of simulation methods is addressed, with a particular emphasis on predictive multiscale protocols, to complement experimental research in the identification of novel materials and illustrate the potential of these methods with a few prominent recent applications. Finally, the potential of machine learning and methods based on artificial intelligence is discussed to further accelerate the search for new materials.

Virtual Screening of Conjugated Polymers for Organic Photovoltaic Devices Using Support Vector Machines and Ensemble Learning

Herein, we report virtual screening of potential semiconductor polymers for high-performance organic photovoltaic (OPV) devices using various machine learning algorithms. We particularly focus on support vector machine (SVM) and ensemble learning approaches. We found that the power conversion efficiencies of the device prepared with the polymer candidates can be predicted with their structure fingerprints as the only inputs. In other words, no preliminary knowledge about material properties was required. Additionally, the predictive performance could be further improved by “blending” the results of the SVM and random forest models. The resulting ensemble learning algorithm might open up a new opportunity for more precise, high-throughput virtual screening of conjugated polymers for OPV devices.

Benchmarking DFT approaches for the calculation of polarizability inputs for refractive index predictions in organic polymers

In a previous study, we introduced a new computational protocol to accurately predict the index of refraction (RI) of organic polymers using a combination of first-principles and data modeling. This protocol is based on the Lorentz-Lorenz equation and involves the calculation of static polarizabilities and number densities of oligomer sequences, which are extrapolated to the polymer limit. We chose to compute the polarizabilities within the density functional theory (DFT) framework using the PBE0/def2-TZVP-D3 model chemistry. While this ad hoc choice proved remarkably successful, it is also relatively expensive from a computational perspective. It represents the bottleneck step in the overall RI modeling protocol, thus limiting its utility for virtual high-throughput screening studies, in which efficiency is essential. For polymers that exhibit late-onset extensivity, the employed linear extrapolation scheme can require demanding calculations on long-oligomer sequences, thus becoming another bottleneck. In the work presented here, we benchmark DFT model chemistries to identify approaches that optimize the balance between accuracy and efficiency for this application domain. We compare results for conjugated and non-conjugated polymers, augment our original extrapolation approach with a non-linear option, analyze how the polarizability errors propagate into the RI predictions, and offer guidance for method selection.

Computer-Aided Screening of Conjugated Polymers for Organic Solar Cell: Classification by Random Forest

Owing to the diverse chemical structures, organic photovoltaic (OPV) applications with a bulk heterojunction framework have greatly evolved over the last two decades, which has produced numerous organic semiconductors exhibiting improved power conversion efficiencies (PCEs). Despite the recent fast progress in materials informatics and data science, data-driven molecular design of OPV materials remains challenging. We report a screening of conjugated molecules for polymer-fullerene OPV applications by supervised learning methods (artificial neural network (ANN) and random forest (RF)). Approximately 1000 experimental parameters including PCE, molecular weight, and electronic properties are manually collected from the literature and subjected to machine learning with digitized chemical structures. Contrary to the low correlation coefficient in ANN, RF yields an acceptable accuracy, which is twice that of random classification. We demonstrate the application of RF screening for the design, synthesis, and characterization of a conjugated polymer, which facilitates a rapid development of optoelectronic materials.

The Alexandria library, a quantum-chemical database of molecular properties for force field development

Data quality as well as library size are crucial issues for force field development. In order to predict molecular properties in a large chemical space, the foundation to build force fields on needs to encompass a large variety of chemical compounds. The tabulated molecular physicochemical properties also need to be accurate. Due to the limited transparency in data used for development of existing force fields it is hard to establish data quality and reusability is low. This paper presents the Alexandria library as an open and freely accessible database of optimized molecular geometries, frequencies, electrostatic moments up to the hexadecupole, electrostatic potential, polarizabilities, and thermochemistry, obtained from quantum chemistry calculations for 2704 compounds. Values are tabulated and where available compared to experimental data. This library can assist systematic development and training of empirical force fields for a broad range of molecules.

The dye-sensitized solar cell database

BACKGROUND

Dye-sensitized solar cells (DSSCs) have garnered a lot of attention in recent years. The solar energy to power conversion efficiency of a DSSC is influenced by various components of the cell such as the dye, electrolyte, electrodes and additives among others leading to varying experimental configurations. A large number of metal-based and metal-free dye sensitizers have now been reported and tools using such data to indicate new directions for design and development are on the rise.

DESCRIPTION

DSSCDB, the first of its kind dye-sensitized solar cell database, aims to provide users with up-to-date information from publications on the molecular structures of the dyes, experimental details and reported measurements (efficiencies and spectral properties) and thereby facilitate a comprehensive and critical evaluation of the data. Currently, the DSSCDB contains over 4000 experimental observations spanning multiple dye classes such as triphenylamines, carbazoles, coumarins, phenothiazines, ruthenium and porphyrins.

CONCLUSION

The DSSCDB offers a web-based, comprehensive source of property data for dye sensitized solar cells. Access to the database is available through the following URL: www.dyedb.com .

Theoretical investigation of the use of nanocages with an adsorbed halogen atom as anode materials in metal-ion batteries

The applicability of C₄₄, B₂₂N₂₂, Ge₄₄, and Al₂₂P₂₂ nanocages, as well as variants of those nanocages with an adsorbed halogen atom, as high-performance anode materials in Li-ion, Na-ion, and K-ion batteries was investigated theoretically via density functional theory. The results obtained indicate that, among the nanocages with no adsorbed halogen atom, Al₂₂P₂₂ would be the best candidate for a novel anode material for use in metal-ion batteries. Calculations also suggest that K-ion batteries which utilize these nanocages as anode materials would give better performance and would yield higher cell voltages than the corresponding Li-ion and Na-ion batteries with nanocage-based anodes. Also, the results for the nanocages with an adsorbed halogen atom imply that employing them as anode materials would lead to higher cell voltages and better metal-ion battery performance than if the nanocages with no adsorbed halogen atom were to be used as anode materials instead. Results further implied that nanocages with an adsorbed F atom would give higher cell voltages and better battery performance than nanocages with an adsorbed Cl or Br atom. We were ultimately able to conclude that a K-ion battery that utilized Al₂₁P₂₂ with an adsorbed F atom as its anode material would afford the best metal-ion battery performance; we therefore propose this as a novel highly efficient metal-ion battery. Graphical abstract The results of a theoretical investigation indicated that Al₂₂P₂₂ is a better candidate for a high-performance anode material in metal-ion batteries than Ge₄₄ is. Calculations also showed that K-ion batteries with nanocage-based anodes would produce higher cell voltages and perform better than the equivalent Li-ion and Na-ion batteries with nanocage-based anodes, and that anodes based on nanocages with an adsorbed F atom would perform better than anodes based on nanocages with an adsorbed Cl or Br atom.