Machine learning-based screening of complex molecules for polymer solar cells

Providing a Photovoltaic Performance Enhancement Relationship from Binary to Ternary Polymer Solar Cells via Machine Learning

Ternary polymer solar cells (PSCs) are currently the simplest and most efficient way to further improve the device performance in PSCs. To find high-performance organic photovoltaic materials, the established connection between the material structure and device performance before fabrication is of great significance. Herein, firstly, a database of the photovoltaic performance in 874 experimental PSCs reported in the literature is established, and three different fingerprint expressions of a molecular structure are explored as input features; the results show that long fingerprints of 2D atom pairs can contain more effective information and improve the accuracy of the models. Through supervised learning, five machine learning (ML) models were trained to build a mapping of the photovoltaic performance improvement relationship from binary to ternary PSCs. The GBDT model had the best predictive ability and generalization. Eighteen key structural features from a non-fullerene acceptor and the third components that affect the device's PCE were screened based on this model, including a nitrile group with lone-pair electron, a halogen atom, an oxygen atom, etc. Interestingly, the structural features for the enhanced device's PCE were essentially increased by the Jsc or FF. More importantly, the reliability of the ML model was further verified by preparing the highly efficient PSCs. Taking the PM6:BTP-eC9:PY-IT ternary PSC as an example, the PCE prediction (18.03%) by the model was in good agreement with the experimental results (17.78%), the relative prediction error was 1.41%, and the relative error between all experimental results and predicted results was less than 5%. These results indicate that ML is a useful tool for exploring the photovoltaic performance improvement of PSCs and accelerating the design and application with highly efficient non-fullerene materials.

Creation of Polymer Datasets with Targeted Backbones for Screening of High-Performance Membranes for Gas Separation

A simple approach was developed to computationally construct a polymer dataset by combining simplified molecular-input line-entry system (SMILES) strings of a targeted polymer backbone and a variety of molecular fragments. This method was used to create 14 polymer datasets by combining seven polymer backbones and molecules from two large molecular datasets (MOSES and QM9). Polymer backbones that were studied include four polydimethylsiloxane (PDMS) based backbones, poly(ethylene oxide) (PEO), poly(allyl glycidyl ether) (PAGE), and polyphosphazene (PPZ). The generated polymer datasets can be used for various cheminformatics tasks, including high-throughput screening for gas permeability and selectivity. This study utilized machine learning (ML) models to screen the polymers for CO2/CH4 and CO2/N2 gas separation using membranes. Several polymers of interest were identified. The results highlight that employing an ML model fitted to polymer selectivities leads to higher accuracy in predicting polymer selectivity compared to using the ratio of predicted permeabilities.

Applied machine learning as a driver for polymeric biomaterials design

Polymers are ubiquitous to almost every aspect of modern society and their use in medical products is similarly pervasive. Despite this, the diversity in commercial polymers used in medicine is stunningly low. Considerable time and resources have been extended over the years towards the development of new polymeric biomaterials which address unmet needs left by the current generation of medical-grade polymers. Machine learning (ML) presents an unprecedented opportunity in this field to bypass the need for trial-and-error synthesis, thus reducing the time and resources invested into new discoveries critical for advancing medical treatments. Current efforts pioneering applied ML in polymer design have employed combinatorial and high throughput experimental design to address data availability concerns. However, the lack of available and standardized characterization of parameters relevant to medicine, including degradation time and biocompatibility, represents a nearly insurmountable obstacle to ML-aided design of biomaterials. Herein, we identify a gap at the intersection of applied ML and biomedical polymer design, highlight current works at this junction more broadly and provide an outlook on challenges and future directions.

Open Macromolecular Genome: Generative Design of Synthetically Accessible Polymers

A grand challenge in polymer science lies in the predictive design of new polymeric materials with targeted functionality. However, de novo design of functional polymers is challenging due to the vast chemical space and an incomplete understanding of structure-property relations. Recent advances in deep generative modeling have facilitated the efficient exploration of molecular design space, but data sparsity in polymer science is a major obstacle hindering progress. In this work, we introduce a vast polymer database known as the Open Macromolecular Genome (OMG), which contains synthesizable polymer chemistries compatible with known polymerization reactions and commercially available reactants selected for synthetic feasibility. The OMG is used in concert with a synthetically aware generative model known as Molecule Chef to identify property-optimized constitutional repeating units, constituent reactants, and reaction pathways of polymers, thereby advancing polymer design into the realm of synthetic relevance. As a proof-of-principle demonstration, we show that polymers with targeted octanol-water solubilities are readily generated together with monomer reactant building blocks and associated polymerization reactions. Suggested reactants are further integrated with Reaxys polymerization data to provide hypothetical reaction conditions (e.g., temperature, catalysts, and solvents). Broadly, the OMG is a polymer design approach capable of enabling data-intensive generative models for synthetic polymer design. Overall, this work represents a significant advance, enabling the property targeted design of synthetic polymers subject to practical synthetic constraints.

Computational Approaches for Organic Semiconductors: From Chemical and Physical Understanding to Predicting New Materials

While a complete understanding of organic semiconductor (OSC) design principles remains elusive, computational methods─ranging from techniques based in classical and quantum mechanics to more recent data-enabled models─can complement experimental observations and provide deep physicochemical insights into OSC structure-processing-property relationships, offering new capabilities for in silico OSC discovery and design. In this Review, we trace the evolution of these computational methods and their application to OSCs, beginning with early quantum-chemical methods to investigate resonance in benzene and building to recent machine-learning (ML) techniques and their application to ever more sophisticated OSC scientific and engineering challenges. Along the way, we highlight the limitations of the methods and how sophisticated physical and mathematical frameworks have been created to overcome those limitations. We illustrate applications of these methods to a range of specific challenges in OSCs derived from π-conjugated polymers and molecules, including predicting charge-carrier transport, modeling chain conformations and bulk morphology, estimating thermomechanical properties, and describing phonons and thermal transport, to name a few. Through these examples, we demonstrate how advances in computational methods accelerate the deployment of OSCsin wide-ranging technologies, such as organic photovoltaics (OPVs), organic light-emitting diodes (OLEDs), organic thermoelectrics, organic batteries, and organic (bio)sensors. We conclude by providing an outlook for the future development of computational techniques to discover and assess the properties of high-performing OSCs with greater accuracy.

Perspectives on development of biomedical polymer materials in artificial intelligence age

Polymer materials are widely used in biomedicine, chemistry and material science, whose traditional preparations are mainly based on experience, intuition and conceptual insight, having been applied to the development of many new materials, but facing great challenges due to the vast design space for biomedical polymers. So far, the best way to solve these problems is to accelerate material design through artificial intelligence, especially machine learning. Herein, this paper will introduce several successful cases, and analyze the latest progress of machine learning in the field of biomedical polymers, then discuss the opportunities of this novel method. In particular, this paper summarizes the material database, open-source determination tools, molecular generation methods and machine learning models that have been used for biopolymer synthesis and property prediction. Overall, machine learning could be more effectively deployed on the material design of biomedical polymers, and it is expected to become an extensive driving force to meet the huge demand for customized designs.

Polymer Informatics at Scale with Multitask Graph Neural Networks

Artificial intelligence-based methods are becoming increasingly effective at screening libraries of polymers down to a selection that is manageable for experimental inquiry. The vast majority of presently adopted approaches for polymer screening rely on handcrafted chemostructural features extracted from polymer repeat units-a burdensome task as polymer libraries, which approximate the polymer chemical search space, progressively grow over time. Here, we demonstrate that directly "machine learning" important features from a polymer repeat unit is a cheap and viable alternative to extracting expensive features by hand. Our approach-based on graph neural networks, multitask learning, and other advanced deep learning techniques-speeds up feature extraction by 1-2 orders of magnitude relative to presently adopted handcrafted methods without compromising model accuracy for a variety of polymer property prediction tasks. We anticipate that our approach, which unlocks the screening of truly massive polymer libraries at scale, will enable more sophisticated and large scale screening technologies in the field of polymer informatics.

Chemistry-Informed Machine Learning for Polymer Electrolyte Discovery

Solid polymer electrolytes (SPEs) have the potential to improve lithium-ion batteries by enhancing safety and enabling higher energy densities. However, SPEs suffer from significantly lower ionic conductivity than liquid and solid ceramic electrolytes, limiting their adoption in functional batteries. To facilitate more rapid discovery of high ionic conductivity SPEs, we developed a chemistry-informed machine learning model that accurately predicts ionic conductivity of SPEs. The model was trained on SPE ionic conductivity data from hundreds of experimental publications. Our chemistry-informed model encodes the Arrhenius equation, which describes temperature activated processes, into the readout layer of a state-of-the-art message passing neural network and has significantly improved accuracy over models that do not encode temperature dependence. Chemically informed readout layers are compatible with deep learning for other property prediction tasks and are especially useful where limited training data are available. Using the trained model, ionic conductivity values were predicted for several thousand candidate SPE formulations, allowing us to identify promising candidate SPEs. We also generated predictions for several different anions in poly(ethylene oxide) and poly(trimethylene carbonate), demonstrating the utility of our model in identifying descriptors for SPE ionic conductivity.

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.

Selected machine learning of HOMO-LUMO gaps with improved data-efficiency

Despite their relevance for organic electronics, quantum machine learning (QML) models of molecular electronic properties, such as HOMO-LUMO-gaps, often struggle to achieve satisfying data-efficiency as measured by decreasing prediction errors for increasing training set sizes. We demonstrate that partitioning training sets into different chemical classes prior to training results in independently trained QML models with overall reduced training data needs. For organic molecules drawn from previously published QM7 and QM9-data-sets we have identified and exploited three relevant classes corresponding to compounds containing either aromatic rings and carbonyl groups, or single unsaturated bonds, or saturated bonds The selected QML models of band-gaps (considered at GW and hybrid DFT levels of theory) reach mean absolute prediction errors of ∼0.1 eV for up to an order of magnitude fewer training molecules than for QML models trained on randomly selected molecules. Comparison to Δ-QML models of band-gaps indicates that selected QML exhibit superior data-efficiency. Our findings suggest that selected QML, e.g. based on simple classifications prior to training, could help to successfully tackle challenging quantum property screening tasks of large libraries with high fidelity and low computational burden.

Machine-Learning-Based Predictions of Polymer and Postconsumer Recycled Polymer Properties: A Comprehensive Review

There has been a tremendous increase in demand for virgin and postconsumer recycled (PCR) polymers due to their wide range of chemical and physical characteristics. Despite the numerous potential benefits of using a data-driven approach to polymer design, major hurdles exist in the development of polymer informatics due to the complicated hierarchical polymer structures. In this review, a brief introduction on virgin polymer structure, PCR polymers, compatibilization of polymers to be recycled, and their characterization using sensor array technologies as well as factors affecting the polymer properties are provided. Machine-learning (ML) algorithms are gaining attention as cost-effective scalable solutions to exploit the physical and chemical structures of polymers. The basic steps for applying ML in polymer science such as fingerprinting, algorithms, open-source databases, representations, and polymer design are detailed in this review. Further, a state-of-the-art review of the prediction of various polymer material properties using ML is reviewed. Finally, we discuss open-ended research questions on ML application to PCR polymers as well as potential challenges in the prediction of their properties using artificial intelligence for more efficient and targeted PCR polymer discovery and development.

Predicting aggregate morphology of sequence-defined macromolecules with recurrent neural networks

Self-assembly of dilute sequence-defined macromolecules is a complex phenomenon in which the local arrangement of chemical moieties can lead to the formation of long-range structure. The dependence of this structure on the sequence necessarily implies that a mapping between the two exists, yet it has been difficult to model so far. Predicting the aggregation behavior of these macromolecules is challenging due to the lack of effective order parameters, a vast design space, inherent variability, and high computational costs associated with currently available simulation techniques. Here, we accurately predict the morphology of aggregates self-assembled from sequence-defined macromolecules using supervised machine learning. We find that regression models with implicit representation learning perform significantly better than those based on engineered features such as k-mer counting, and a recurrent-neural-network-based regressor performs the best out of nine model architectures we tested. Furthermore, we demonstrate the high-throughput screening of monomer sequences using the regression model to identify candidates for self-assembly into selected morphologies. Our strategy is shown to successfully identify multiple suitable sequences in every test we performed, so we hope the insights gained here can be extended to other increasingly complex design scenarios in the future, such as the design of sequences under polydispersity and at varying environmental conditions.

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.

Measurement(s)	excited state energy
Technology Type(s)	quantum chemistry computational method

Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.17076254

Representing individual electronic states for machine learning GW band structures of 2D materials

Choosing optimal representation methods of atomic and electronic structures is essential when machine learning properties of materials. We address the problem of representing quantum states of electrons in a solid for the purpose of machine leaning state-specific electronic properties. Specifically, we construct a fingerprint based on energy decomposed operator matrix elements (ENDOME) and radially decomposed projected density of states (RAD-PDOS), which are both obtainable from a standard density functional theory (DFT) calculation. Using such fingerprints we train a gradient boosting model on a set of 46k G₀W₀ quasiparticle energies. The resulting model predicts the self-energy correction of states in materials not seen by the model with a mean absolute error of 0.14 eV. By including the material’s calculated dielectric constant in the fingerprint the error can be further reduced by 30%, which we find is due to an enhanced ability to learn the correlation/screening part of the self-energy. Our work paves the way for accurate estimates of quasiparticle band structures at the cost of a standard DFT calculation.

The study introduces novel methods for representing electronic states as input to machine learning models, which is used to learn high-fidelity band structures of two-dimensional materials from low- fidelity input.

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.

Actively Searching: Inverse Design of Novel Molecules with Simultaneously Optimized Properties

Combining quantum chemistry characterizations with generative machine learning models has the potential to accelerate molecular discovery. In this paradigm, quantum chemistry acts as a relatively cost-effective oracle for evaluating the properties of particular molecules, while generative models provide a means of sampling chemical space based on learned structure-function relationships. For practical applications, multiple potentially orthogonal properties must be optimized in tandem during a discovery workflow. This carries additional difficulties associated with the specificity of the targets and the ability for the model to reconcile all properties simultaneously. Here, we demonstrate an active learning approach to improve the performance of multi-target generative chemical models. We first demonstrate the effectiveness of a set of baseline models trained on single property prediction tasks in generating novel compounds (i.e., not present in the training data) with various property targets, including both interpolative and extrapolative generation scenarios. For property ranges where accurate targeting proves difficult, the novel compounds suggested by the model are characterized using quantum chemistry and the new molecules closest to expressing the desired properties are fed back into the generative model for additional training. This gradually improves the generative models' understanding of targeted areas of chemical space and shifts the distribution of the generated compounds toward the targeted values. We then demonstrate the effectiveness of this active learning approach in generating compounds with multiple chemical constraints, including vertical ionization potential, electron affinity, and dipole moment targets, and validate the results at the ωB97X-D3/def2-TZVP level. This method requires no modifications to extant generative approaches, but rather utilizes their inherent generative and predictive aspects for self-refinement, and can be applied to situations where any number of properties with varying degrees of correlation must be optimized simultaneously.

Machine Learning-Assisted Development of Organic Solar Cell Materials: Issues, Analyses, and Outlooks

Nonfullerene, a small molecular electron acceptor, has substantially improved the power conversion efficiency of organic photovoltaics (OPVs). However, the large structural freedom of π-conjugated polymers and molecules makes it difficult to explore with limited resources. Machine learning, which is based on rapidly growing artificial intelligence technology, is a high-throughput method to accelerate the speed of material design and process optimization; however, it suffers from limitations in terms of prediction accuracy, interpretability, data collection, and available data (particularly, experimental data). This recognition motivates the present Perspective, which focuses on utilizing the experimental data set for ML to efficiently aid OPV research. This Perspective discusses the trends in ML-OPV publications, the NFA category, and the effects of data size and explanatory variables (fingerprints or Mordred descriptors) on the prediction accuracy and explainability, which broadens the scope of ML and would be useful for the development of next-generation solar cell materials.

Generative Deep Learning for Targeted Compound Design

In the past few years, de novo molecular design has increasingly been using generative models from the emergent field of Deep Learning, proposing novel compounds that are likely to possess desired properties or activities. De novo molecular design finds applications in different fields ranging from drug discovery and materials sciences to biotechnology. A panoply of deep generative models, including architectures as Recurrent Neural Networks, Autoencoders, and Generative Adversarial Networks, can be trained on existing data sets and provide for the generation of novel compounds. Typically, the new compounds follow the same underlying statistical distributions of properties exhibited on the training data set Additionally, different optimization strategies, including transfer learning, Bayesian optimization, reinforcement learning, and conditional generation, can direct the generation process toward desired aims, regarding their biological activities, synthesis processes or chemical features. Given the recent emergence of these technologies and their relevance, this work presents a systematic and critical review on deep generative models and related optimization methods for targeted compound design, and their applications.

Analysis and Prediction of Hydrothermally Synthesized ZnO-Based Dye-Sensitized Solar Cell Properties Using Statistical and Machine-Learning Techniques

Dye-sensitized solar cells (DSSCs) are one of the most versatile and low-cost solar cells. However, DSSCs are prone to low power conversion efficiency (PCE) compared to their counterparts, owing to their different synthesis parameters and process conditions. Therefore, designing efficient DSSCs and identifying the parameters that control the PCE of DSSCs are a critical tasks. We have collected data from hydrothermally synthesized DSSCs in the present work, published from 2005 to 2020. In line with publishing trends in the said period, we evaluate ZnO as a popular photoactive material for DSSC applications. We further analyzed the performance of hydrothermally synthesized ZnO DSSCs using different statistical techniques and provided some significant insights. We further applied the machine-learning technique with a decision tree algorithm to understand and discover the possible set of rules and heuristics that govern the morphology of the hydrothermally grown ZnO. In addition, we also employed supervised and unsupervised machine-learning models using conventional decision trees and classification and regression trees, respectively, to identify the dependence of the PCE of ZnO DSSCs on the different synthesis parameters. The reported work also evidences the PCE predictions of the ZnO DSSCs by using random forest and artificial neural network algorithms. The results substantiate that the random forest and artificial neural network algorithms successfully predict the PCE of the ZnO DSSCs with reasonable accuracy. Thus, we present a novel approach of applying statistical analysis and machine-learning algorithms to understand, discover, and predict the performance of DSSCs. We recommend extending the said know-how to other solar cells to identify rules and heuristics and experimentally realize highly efficient solar cells in shrinking manufacturing windows with a cost-effective approach.

High-throughput virtual screening for organic electronics: a comparative study of alternative strategies

We present a review of the field of high-throughput virtual screening for organic electronics materials focusing on the sequence of methodological choices that determine each virtual screening protocol. These choices are present in all high-throughput virtual screenings and addressing them systematically will lead to optimised workflows and improve their applicability. We consider the range of properties that can be computed and illustrate how their accuracy can be determined depending on the quality and size of the experimental datasets. The approaches to generate candidates for virtual screening are also extremely varied and their relative strengths and weaknesses are discussed. The analysis of high-throughput virtual screening is almost never limited to the identification of top candidates and often new patterns and structure-property relations are the most interesting findings of such searches. The review reveals a very dynamic field constantly adapting to match an evolving landscape of applications, methodologies and datasets.

First-principles materials simulation and design for alkali and alkaline metal ion batteries accelerated by machine learning

The challenge of regeneration of batteries requires a performance improvement in the alkali/alkaline metal ion battery (AMIB) materials, whereas the traditional research paradigm fully based on experiments and theoretical simulations needs massive research and development investment. During the last decade, machine learning (ML) has made breakthroughs in many complex disciplines, which testifies to their high processing speed and ability to capture relationships. Inspired by these achievements, ML has also been introduced to bring a new paradigm for shortening the development of AMIB materials. In this Perspective, the focus will be on how this new ML technology solves the key problems of redox potentials, ionic conductivity and stability parameters in first-principles materials' simulation and design for AMIBs. It is found that ML not only accelerates the property prediction, but also gives physicochemical insights into AMIB materials' design. In addition, the final part of this paper summarizes current achievements and looks forward to the progress of a novel paradigm in direct/inverse design with the increasing number of databases, skills, and ML technologies for AMIBs.

Artificial Intelligence Designer for Highly-Efficient Organic Photovoltaic Materials

Designing efficient organic photovoltaic (OPV) materials purposefully is still challenging and time-consuming. It is of paramount importance in material development to identify basic functional units that play the key roles in material performance and subsequently establish the substructure-property relationship. Herein, we describe an automatic design framework based on an in-house designed La FREMD Fingerprint and machine learning (ML) algorithms for highly efficient OPV donor molecules. The key building blocks are identified, and a library consisting of 18 960 new molecules is generated within this framework. Through investigating the chemical structures of materials with different performance, a guidance on designing efficient OPV materials is proposed. Furthermore, the most promising candidates exhibit a predicted power conversion efficiency (PCE) value of over 15% when combined with acceptor Y6. Density functional theory (DFT) studies show these candidate materials possess exceptional potential for efficient charge carrier transport. The proposed framework demonstrates the ability to design new materials based on the substructure-property relationship built by ML, which provides an alternative methodology for applying ML in new material discovery.

Capture the high-efficiency non-fullerene ternary organic solar cells formula by machine-learning-assisted energy-level alignment optimization

Appropriate energy-level alignment in non-fullerene ternary organic solar cells (OSCs) can enhance the power conversion efficiencies (PCEs), due to the simultaneous improvement in charge generation/transportation and reduction in voltage loss. Seven machine-learning (ML) algorithms were used to build the regression and classification models based on energy-level parameters to predict PCE and capture high-performance material combinations, and random forest showed the best predictive capability. Furthermore, two sets of verification experiments were designed to compare the experimental and predicted results. The outcome elucidated that a deep lowest unoccupied molecular orbital (LUMO) of the non-fullerene acceptors can slightly reduce the open-circuit voltage (V_OC) but significantly improve short-circuit current density (J_SC), and, to a certain extent, the V_OC could be optimized by the slightly up-shifted LUMO of the third component in non-fullerene ternary OSCs. Consequently, random forest can provide an effective global optimization scheme and capture multi-component combinations for high-efficiency ternary OSCs.

•

ML assists in analyzing energy-level alignment of non-fullerene ternary blends

•

Random forest approach provides the best predictive capability

•

The effective global optimization scheme in material selection is provided

Introducing a third component into a binary blend to fabricate the ternary organic solar cells (OSCs) is a common practice to enhance light harvest and reduce energy loss of the photoactive blends, especially the non-fullerene ternary OSCs, which showed thrilling power conversion efficiencies improvement. A proper energy-level alignment in ternary blends, promoting the device charge generation, transport, and extraction, is of importance to maximize the short-circuit current and open-circuit voltage simultaneously. The machine-learning (ML) technique is a powerful tool for processing complex data from previous research to find the underlying mechanisms. In this work, we built regression and classification models, aiming to find the relationship between molecular energy levels and device performances. The results demonstrated that random forest is an effective method to assess the energy-level alignment, providing guidelines for the design of high-performance non-fullerene ternary OSCs.

Data-driven algorithms for inverse design of polymers

The ever-increasing demand for novel polymers with superior properties requires a deeper understanding and exploration of the chemical space. Recently, data-driven approaches to explore the chemical space for polymer design have emerged. Among them, inverse design strategies for designing polymers with specific properties have evolved to be a significant materials informatics platform by learning hidden knowledge from materials data as well as smartly navigating the chemical space in an optimized way. In this review, we first summarize the progress in the representation of polymers, a prerequisite step for the inverse design of polymers. Then, we systematically introduce three data-driven strategies implemented for the inverse design of polymers, i.e., high-throughput virtual screening, global optimization, and generative models. Finally, we discuss the challenges and opportunities of the data-driven strategies as well as optimization algorithms employed in the inverse design of polymers.

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

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

Hydrogen Evolution Prediction for Alternating Conjugated Copolymers Enabled by Machine Learning with Multidimension Fragmentation Descriptors

Hydrogen evolution by alternating conjugated copolymers has attracted much attention in recent years. To study alternating copolymers with data-driven strategies, two types of multidimension fragmentation descriptors (MDFD), structure-based MDFD (SMDFD), and electronic property-based MDFD (EPMDFD), have been developed with machine learning (ML) algorithms for the first time. The superiority of SMDFD-based models has been demonstrated by the highly accurate and universal predictions of electronic properties. Moreover, EPMDFD-based, experimental-parameter-free ML models were developed for the prediction of the hydrogen evolution reaction, displaying excellent accuracy (real-test accuracy = 0.91). The combination of explainable ML approaches and first-principles calculations was employed to explore photocatalytic dynamics, revealing the importance of electron delocalization in the excited state. Virtual designing of high-performance candidates can also be achieved. Our work illustrates the huge potential of ML-based material design in the field of polymeric photocatalysts toward high-performance photocatalysis.

Perspective on integrating machine learning into computational chemistry and materials science

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

Rapid Method for Calculating the Conformationally Averaged Electronic Structure of Conjugated Polymers

We developed a rapid method to calculate the average electronic structure properties of large ensembles of conjugated polymer chains sampling their conformational space. This is achieved by using the localized molecular orbital (MO) method to rapidly compute the MOs and their energies for isolated polymer chains and through using a calibration scheme to further correct the obtained energies by comparison with a few accurate calculations. The method is applied to the study of the density of states and orbital localization characteristics for five polymers. It is shown that all key properties of the individual chain related to the charge mobility can be rationalized in terms of the properties of the constituent monomers, their interaction, and the conformational flexibility of the chain. More specifically we identify the features that lead to greater charge delocalization. Finally, we discuss the prospect of using this method for a computational high-throughput screening of conjugated polymers.

Computational Identification of Novel Families of Nonfullerene Acceptors by Modification of Known Compounds

We considered a database of tens of thousands of known organic semiconductors and identified those compounds with computed electronic properties (orbital energies, excited state energies, and oscillator strengths) that would make them suitable as nonfullerene electron acceptors in organic solar cells. The range of parameters for the desirable acceptors is determined from a set of experimentally characterized high-efficiency nonfullerene acceptors. This search leads to ∼30 lead compounds never considered before for organic photovoltaic applications. We then proceed to modify these compounds to bring their computed solubility in line with that of the best small-molecule nonfullerene acceptors. A further refinement of the search can be based on additional properties like the reorganization energy for chemical reduction. This simple strategy, which relies on a few easily computable parameters and can be expanded to a larger set of molecules, enables the identification of completely new chemical families to be explored experimentally.

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.

A machine-learning-assisted study of the permeability of small drug-like molecules across lipid membranes

Study of the permeability of small organic molecules across lipid membranes plays a significant role in designing potential drugs in the field of drug discovery. Approaches to design promising drug molecules have gone through many stages, from experiment-based trail-and-error approaches, to the well-established avenue of the quantitative structure-activity relationship, and currently to the stage guided by machine learning (ML) and artificial intelligence techniques. In this work, we present a study of the permeability of small drug-like molecules across lipid membranes by two types of ML models, namely the least absolute shrinkage and selection operator (LASSO) and deep neural network (DNN) models. Molecular descriptors and fingerprints are used for featurization of organic molecules. Using molecular descriptors, the LASSO model uncovers that the electro-topological, electrostatic, polarizability, and hydrophobicity/hydrophilicity properties are the most important physical properties to determine the membrane permeability of small drug-like molecules. Additionally, with molecular fingerprints, the LASSO model suggests that certain chemical substructures can significantly affect the permeability of organic molecules, which closely connects to the identified main physical properties. Moreover, the DNN model using molecular fingerprints can help develop a more accurate mapping between molecular structures and their membrane permeability than LASSO models. Our results provide deep understanding of drug-membrane interactions and useful guidance for the inverse molecular design of drug-like molecules. Last but not least, while the current focus is on the permeability of drug-like molecules, the methodology of this work is general and can be applied for other complex physical chemistry problems to gain molecular insights.

Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers

Despite the remarkable progress of machine learning (ML) techniques in chemistry, modeling the optoelectronic properties of long conjugated oligomers and polymers with ML remains challenging due to the difficulty in obtaining sufficient training data. Here, we use transfer learning to address the data scarcity issue by pre-training graph neural networks using data from short oligomers. With only a few hundred training data, we are able to achieve an average error of about 0.1 eV for the excited-state energy of oligothiophenes against time-dependent density functional theory (TDDFT) calculations. We show that the success of our transfer learning approach relies on the relative locality of low-lying electronic excitations in long conjugated oligomers. Finally, we demonstrate the transferability of our approach by modeling the lowest-lying excited-state energies of poly(3-hexylthiophene) in its single-crystal and solution phases using the transfer learning models trained with the data of gas-phase oligothiophenes. The transfer learning predicted excited-state energy distributions agree quantitatively with TDDFT calculations and capture some important qualitative features observed in experimental absorption spectra.

Improving the generative performance of chemical autoencoders through transfer learning

Generative models are a sub-class of machine learning models that are capable of generating new samples with a target set of properties. In chemical and materials applications, these new samples might be drug targets, novel semiconductors, or catalysts constrained to exhibit an application-specific set of properties. Given their potential to yield high-value targets from otherwise intractable design spaces, generative models are currently under intense study with respect to how predictions can be improved through changes in model architecture and data representation. Here we explore the potential of multi-task transfer learning as a complementary approach to improving the validity and property specificity of molecules generated by such models. We have compared baseline generative models trained on a single property prediction task against models trained on additional ancillary prediction tasks and observe a generic positive impact on the validity and specificity of the multi-task models. In particular, we observe that the validity of generated structures is strongly affected by whether or not the models have chemical property data, as opposed to only syntactic structural data, supplied during learning. We demonstrate this effect in both interpolative and extrapolative scenarios (i.e., where the generative targets are poorly represented in training data) for models trained to generate high energy structures and models trained to generated structures with targeted bandgaps within certain ranges. In both instances, the inclusion of additional chemical property data improves the ability of models to generate valid, unique structures with increased property specificity. This approach requires only minor alterations to existing generative models, in many cases leveraging prediction frameworks already native to these models. Additionally, the transfer learning strategy is complementary to ongoing efforts to improve model architectures and data representation and can foreseeably be stacked on top of these developments.

EvoMol: a flexible and interpretable evolutionary algorithm for unbiased de novo molecular generation

The objective of this work is to design a molecular generator capable of exploring known as well as unfamiliar areas of the chemical space. Our method must be flexible to adapt to very different problems. Therefore, it has to be able to work with or without the influence of prior data and knowledge. Moreover, regardless of the success, it should be as interpretable as possible to allow for diagnosis and improvement. We propose here a new open source generation method using an evolutionary algorithm to sequentially build molecular graphs. It is independent of starting data and can generate totally unseen compounds. To be able to search a large part of the chemical space, we define an original set of 7 generic mutations close to the atomic level. Our method achieves excellent performances and even records on the QED, penalised logP, SAscore, CLscore as well as the set of goal-directed functions defined in GuacaMol. To demonstrate its flexibility, we tackle a very different objective issued from the organic molecular materials domain. We show that EvoMol can generate sets of optimised molecules having high energy HOMO or low energy LUMO, starting only from methane. We can also set constraints on a synthesizability score and structural features. Finally, the interpretability of EvoMol allows for the visualisation of its exploration process as a chemically relevant tree.

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.

Molecular generation targeting desired electronic properties via deep generative models

As we seek to discover new functional materials, we need ways to explore the vast chemical space of precursor building blocks, not only generating large numbers of possible building blocks to investigate, but trying to find non-obvious options, that we might not suggest by chemical experience alone. Artificial intelligence techniques provide a possible avenue to generate large numbers of organic building blocks for functional materials, and can even do so from very small initial libraries of known building blocks. Specifically, we demonstrate the application of deep recurrent neural networks for the exploration of the chemical space of building blocks for a test case of donor-acceptor oligomers with specific electronic properties. The recurrent neural network learned how to produce novel donor-acceptor oligomers by trading off between selected atomic substitutions, such as halogenation or methylation, and molecular features such as the oligomer's size. The electronic and structural properties of the generated oligomers can be tuned by sampling from different subsets of the training database, which enabled us to enrich the library of donor-acceptors towards desired properties. We generated approximately 1700 new donor-acceptor oligomers with a recurrent neural network tuned to target oligomers with a HOMO-LUMO gap <2 eV and a dipole moment <2 Debye, which could have potential application in organic photovoltaics.

Machine-Learning-Assisted De Novo Design of Organic Molecules and Polymers: Opportunities and Challenges

Organic molecules and polymers have a broad range of applications in biomedical, chemical, and materials science fields. Traditional design approaches for organic molecules and polymers are mainly experimentally-driven, guided by experience, intuition, and conceptual insights. Though they have been successfully applied to discover many important materials, these methods are facing significant challenges due to the tremendous demand of new materials and vast design space of organic molecules and polymers. Accelerated and inverse materials design is an ideal solution to these challenges. With advancements in high-throughput computation, artificial intelligence (especially machining learning, ML), and the growth of materials databases, ML-assisted materials design is emerging as a promising tool to flourish breakthroughs in many areas of materials science and engineering. To date, using ML-assisted approaches, the quantitative structure property/activity relation for material property prediction can be established more accurately and efficiently. In addition, materials design can be revolutionized and accelerated much faster than ever, through ML-enabled molecular generation and inverse molecular design. In this perspective, we review the recent progresses in ML-guided design of organic molecules and polymers, highlight several successful examples, and examine future opportunities in biomedical, chemical, and materials science fields. We further discuss the relevant challenges to solve in order to fully realize the potential of ML-assisted materials design for organic molecules and polymers. In particular, this study summarizes publicly available materials databases, feature representations for organic molecules, open-source tools for feature generation, methods for molecular generation, and ML models for prediction of material properties, which serve as a tutorial for researchers who have little experience with ML before and want to apply ML for various applications. Last but not least, it draws insights into the current limitations of ML-guided design of organic molecules and polymers. We anticipate that ML-assisted materials design for organic molecules and polymers will be the driving force in the near future, to meet the tremendous demand of new materials with tailored properties in different fields.

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

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

Machine learning-assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials

In the process of finding high-performance materials for organic photovoltaics (OPVs), it is meaningful if one can establish the relationship between chemical structures and photovoltaic properties even before synthesizing them. Here, we first establish a database containing over 1700 donor materials reported in the literature. Through supervised learning, our machine learning (ML) models can build up the structure-property relationship and, thus, implement fast screening of OPV materials. We explore several expressions for molecule structures, i.e., images, ASCII strings, descriptors, and fingerprints, as inputs for various ML algorithms. It is found that fingerprints with length over 1000 bits can obtain high prediction accuracy. The reliability of our approach is further verified by screening 10 newly designed donor materials. Good consistency between model predictions and experimental outcomes is obtained. The result indicates that ML is a powerful tool to prescreen new OPV materials, thus accelerating the development of the OPV field.

Atomistic simulations of bulk heterojunctions to evaluate the structural and packing properties of new predicted donors in OPVs

Organic photovoltaic materials (OPVs), with low cost and structure flexibility, are of great interest and importance for their application in solar cell device development. However, the optimization of new OPV structures and the study of the structure arrangements and packing morphologies when materials are blended takes time and consumes raw materials, thus theoretical models could be of considerable value. In this work, we performed molecular dynamics simulations of present OPVs to understand the morphological packing of the donor-acceptor (DA) phases and DA heterojunction during evaporation and annealing processes, following inter and intramolecular properties like frontier orbitals, π-π stacking, coordination, distances, angles, and aggregation. Our considered donor molecules were selected from already proved experimental studies and also from predicted optimal compounds, designed through high throughput studies. The acceptor molecule employed in all our studied systems was PCBM ([6,6]-phenyl-C61-butyric acid methyl ester). Furthermore, we also analyze the influence of including different lateral aliphatic chains on the structural properties of the resulting DA packing morphologies. Our results can guide the design of new OPVs and subsequent studies applying charge transport and charge separation models.