Predicting Energetics Materials' Crystalline Density from Chemical Structure by Machine Learning

Molecular designing of potential environmentally friendly PFAS based on deep learning and generative models

Perfluoroalkyl and polyfluoroalkyl substances (PFAS) are widely used across a spectrum of industrial and consumer goods. Nonetheless, their persistent nature and tendency to accumulate in biological systems pose substantial environmental and health threats. Consequently, striking a balance between maximizing product efficiency and minimizing environmental and health risks by tailoring the molecular structure of PFAS has become a pivotal challenge in the fields of environmental chemistry and sustainable development. To address this issue, a computational workflow was proposed for designing an environmentally friendly PFAS by incorporating deep learning (DL) and molecular generative models. The hybrid DL architecture MolHGT+ based on heterogeneous graph neural network with transformer-like attention was applied to predict the surface tension, bioaccumulation, and hepatotoxicity of the molecules. Through virtual screening of the PFAS master database using MolHGT+, the findings indicate that incorporating the siloxane group and betaine fragment can effectively decrease both the bioaccumulation and hepatotoxicity of PFAS while preserving low surface tension. In addition, molecular generative models were employed to create a structurally diverse pool of novel PFASs with the aforementioned hit molecules serving as the initial template structures. Overall, our study presents a promising AI-driven method for advancing the development of environmentally friendly PFAS.

AI4ACEIP: A Computing Tool to Identify Food Peptides with High Inhibitory Activity for ACE by Merged Molecular Representation and Rich Intrinsic Sequence Information Based on an Ensemble Learning Strategy

Hypertension is a common chronic disorder and a major risk factor for cardiovascular diseases. Angiotensin-converting enzyme (ACE) converts angiotensin I to angiotensin II, causing vasoconstriction and raising blood pressure. Pharmacotherapy is the mainstay of traditional hypertension treatment, leading to various negative side effects. Some food-derived peptides can suppress ACE, named ACEIP with fewer undesirable effects. Therefore, it is crucial to seek strong dietary ACEIP to aid in hypertension treatment. In this article, we propose a new model called AI4ACEIP to identify ACEIP. AI4ACEIP uses a novel two-layer stacked ensemble architecture to predict ACEIP relying on integrated view features derived from sequence, large language models, and molecular-based information. The analysis of feature combinations reveals that four selected integrated feature pairs exhibit enhancing performance for identifying ACEIP. For finding meta models with strong abilities to learn information from integrated feature pairs, PowerShap, a feature selection method, is used to select 40 optimal feature and meta model combinations. Compared with seven state-of-the-art methods on the source and clear benchmark data sets, AI4ACEIP significantly outperformed by 8.47 to 20.65% and 5.49 to 14.42% for Matthew's correlation coefficient. In brief, AI4ACEIP is a reliable model for ACEIP prediction and is freely available at https://github.com/abcair/AI4ACEIP.

Towards the prediction of drug solubility in binary solvent mixtures at various temperatures using machine learning

Drug solubility is an important parameter in the drug development process, yet it is often tedious and challenging to measure, especially for expensive drugs or those available in small quantities. To alleviate these challenges, machine learning (ML) has been applied to predict drug solubility as an alternative approach. However, the majority of existing ML research has focused on the predictions of aqueous solubility and/or solubility at specific temperatures, which restricts the model applicability in pharmaceutical development. To bridge this gap, we compiled a dataset of 27,000 solubility datapoints, including solubility of small molecules measured in a range of binary solvent mixtures under various temperatures. Next, a panel of ML models were trained on this dataset with their hyperparameters tuned using Bayesian optimization. The resulting top-performing models, both gradient boosted decision trees (light gradient boosting machine and extreme gradient boosting), achieved mean absolute errors (MAE) of 0.33 for LogS (S in g/100 g) on the holdout set. These models were further validated through a prospective study, wherein the solubility of four drug molecules were predicted by the models and then validated with in-house solubility experiments. This prospective study demonstrated that the models accurately predicted the solubility of solutes in specific binary solvent mixtures under different temperatures, especially for drugs whose features closely align within the solutes in the dataset (MAE < 0.5 for LogS). To support future research and facilitate advancements in the field, we have made the dataset and code openly available. Scientific contribution Our research advances the state-of-the-art in predicting solubility for small molecules by leveraging ML and a uniquely comprehensive dataset. Unlike existing ML studies that predominantly focus on solubility in aqueous solvents at fixed temperatures, our work enables prediction of drug solubility in a variety of binary solvent mixtures over a broad temperature range, providing practical insights on the modeling of solubility for realistic pharmaceutical applications. These advancements along with the open access dataset and code support significant steps in the drug development process including new molecule discovery, drug analysis and formulation.

Theoretical advances in understanding and enhancing the thermostability of energetic materials

The quest for thermally stable energetic materials is pivotal in advancing the safety of applications ranging from munitions to aerospace. This perspective delves into the role of theoretical methodologies in interpreting and advancing the thermal stability of energetic materials. Quantum chemical calculations offer an in-depth understanding of the molecular and electronic structure properties of energetic compounds related to thermal stability. It is also essential to incorporate the surrounding interactions and their impact on molecular stability. Ab initio molecular dynamics (AIMD) simulations provide detailed theoretical insights into the reaction pathways and the key intermediates during thermal decomposition in the condensed phase. Analyzing the kinetic barrier of rate-determining steps under various temperature and pressure conditions allows for a comprehensive assessment of thermal stability. Recent advances in machine learning have demonstrated their utility in constructing potential energy surfaces and predicting thermal stability for newly designed energetic materials. The machine learning-assisted high-throughput virtual screening (HTVS) methodology can accelerate the discovery of novel energetic materials with improved properties. As a result, the newly identified and synthesized energetic molecule ICM-104 revealed excellence in performance and thermostability. Theoretical approaches are pivotal in elucidating the mechanisms underlying thermal stability, enabling the prediction and design of enhanced thermal stability for emerging EMs. These insights are instrumental in accelerating the development of novel energetic materials that optimally balance performance and thermal stability.

Recognition of Molecular Structure of Phosphonium Salts from the Visual Appearance of Material with Deep Learning Can Reveal Subtle Homologs

Determining molecular structures is foundational in chemistry and biology. The notion of discerning molecular structures simply from the visual appearance of a material remained almost unthinkable until the advent of machine learning. This paper introduces a pioneering approach bridging the visual appearance of materials (both at the micro- and nanostructural levels) with traditional chemical structure analysis methods. Quaternary phosphonium salts are opted as the model compounds, given their significant roles in diverse chemical and medicinal fields and their ability to form homologs with only minute intermolecular variances. This research results in the successful creation of a neural network model capable of recognizing molecular structures from visual electron microscopy images of the material. The performance of the model is evaluated and related to the chemical nature of the studied chemicals. Additionally, unsupervised domain transfer is tested as a method to use the resulting model on optical microscopy images, as well as test models trained on optical images directly. The robustness of the method is further tested using a complex system of phosphonium salt mixtures. To the best of the authors' knowledge, this study offers the first evidence of the feasibility of discerning nearly indistinguishable molecular structures.

Going beyond the Ordered Bulk: A Perspective on the Use of the Cambridge Structural Database for Predictive Materials Design

When Olga Kennard founded the Cambridge Crystallographic Data Centre in 1965, the Cambridge Structural Database was a pioneering attempt to collect scientific data in a standard format. Since then, it has evolved into an indispensable resource in contemporary molecular materials science, with over 1.25 million structures and comprehensive software tools for searching, visualizing and analyzing the data. In this perspective, we discuss the use of the CSD and CCDC tools to address the multiscale challenge of predictive materials design. We provide an overview of the core capabilities of the CSD and CCDC software and demonstrate their application to a range of materials design problems with recent case studies drawn from topical research areas, focusing in particular on the use of data mining and machine learning techniques. We also identify several challenges that can be addressed with existing capabilities or through new capabilities with varying levels of development effort.

MolPackL: Quantification and Interpretation of Intermolecular Interactions Driven by Molecular Packing

In organic optoelectronic devices, the properties of the aggregated organic materials depend not only on individual molecules or monomers but also significantly on their packing modes. Different from their inorganic counterparts linked by explicit covalent bonds, organic solids exhibit intricate and numerous intermolecular interactions (IMIs). Due to the intrinsic complexity and disorder of IMIs, identifying and understanding them is a formidable challenge in experimental, theoretical, and data-driven approaches. In this work, we constructed an innovative algorithm framework, Molecular Packing Learning (MolPackL), which can accurately quantify elusive IMIs using contact density histograms (CDHs) and efficiently extract intermolecular features for further property prediction of organic solids. It performs satisfactorily in training predictive models of IMI-related properties in molecular crystals. Particularly, the band gap predictive model based on MolPackL achieved the best-reported performance, with an MAE of 0.20 eV and an impressive R2 of 0.92. Class activation mapping (CAM) visually demonstrates MolPackL's accurate identification of effective interaction sites as the molecular packing changes. What is more, the elemental importance analysis verified that the superior score benefits from MolPackL's ability to comprehensively consider multiple influencing factors of IMIs. In summary, MolPackL provides a new framework for quantitative assessment and understanding of the effect of IMIs. The development of MolPackL marks a significant advancement in establishing predictive models of molecular aggregates, deepening the comprehension of IMIs on the material properties. Given the superior performance, we believe that MolPackL will also become a powerful tool in the design of high-performance organic optoelectronic materials.

High precision deep-learning model combined with high-throughput screening to discover fused [5,5] biheterocyclic energetic materials with excellent comprehensive properties

Finding novel energetic materials with good comprehensive performance has always been challenging because of the low efficiency in conventional trial and error experimental procedure. In this paper, we established a deep learning model with high prediction accuracy using embedded features in Directed Message Passing Neural Networks. The model combined with high-throughput screening was shown to facilitate rapid discovery of fused [5,5] biheterocyclic energetic materials with high energy and excellent thermal stability. Density Functional Theory (DFT) calculations proved that the performances of the targeting molecules are consistent with the predicted results from the deep learning model. Furthermore, 6,7-trinitro-3H-pyrrolo[1,2-b][1,2,4]triazo-5-amine with both good detonation properties and thermal stability was screened out, whose crystal structure and intermolecular interactions were also analyzed.

Development and uniqueness test of highly selective atomic topological indices based on the number of attached hydrogen atoms

On the basis of the atomic graph-theoretical index - aEAID (atomic Extended Adjacency matrix IDentification) and molecular adjacent topological index - ATID (Adjacent Topological IDentification) suggested by one of the authors (Zhang Q), a highly selective atomic topological index - aATID (atomic Adjacent Topological IDentification) index was suggested to identify the equivalent atoms in this study. The aATID index of an atom was derived from the number of the attached hydrogen atoms of the atom but omitting bond types. In this case, the suggested index can be used to identify equivalent atoms in chemistry but perhaps not equivalent in the molecular graph. To test the uniqueness of aATID indices, the virtual atomic data sets were derived from alkanes containing 15-20 carbon atoms and the isomers of Octogen, as well as a real data set was derived from the NCI database. Only four pairs of atoms from alkanes containing 20 carbons can't be discriminated by aATID, that is, four pairs of degenerates were found for this data set. To solve this problem, the aATID index was modified by introducing distance factors between atoms, and the 2-aATID index was suggested. Its uniqueness was examined by 5,939,902 atoms derived from alkanes containing 20 carbons and further 16,166,984 atoms from alkanes of 21 carbons, and no degenerates were found. In addition, another large real data set of 16,650,688 atoms derived from the PubChem database was also used to test the uniqueness of both aATID and 2-aATID. As a result, each atom was successfully discriminated by any of the two indices. Finally, the suggested aATID index was applied to the identification of duplicate atoms as data pretreatment for QSPR (Quantitative Structure-Property Relationships) studies.

Transfer learning for a foundational chemistry model

Data-driven chemistry has garnered much interest concurrent with improvements in hardware and the development of new machine learning models. However, obtaining sufficiently large, accurate datasets of a desired chemical outcome for data-driven chemistry remains a challenge. The community has made significant efforts to democratize and curate available information for more facile machine learning applications, but the limiting factor is usually the laborious nature of generating large-scale data. Transfer learning has been noted in certain applications to alleviate some of the data burden, but this protocol is typically carried out on a case-by-case basis, with the transfer learning task expertly chosen to fit the finetuning. Herein, I develop a machine learning framework capable of accurate chemistry-relevant prediction amid general sources of low data. First, a chemical "foundational model" is trained using a dataset of ∼1 million experimental organic crystal structures. A task specific module is then stacked atop this foundational model and subjected to finetuning. This approach achieves state-of-the-art performance on a diverse set of tasks: toxicity prediction, yield prediction, and odor prediction.

Predicting the enthalpy of formation of energetic molecules via conventional machine learning and GNN

Machine learning (ML) provides a promising method for efficiently and accurately predicting molecular properties. Using ML models to predict the enthalpy of formation of energetic molecules helps in fast screening of potential high-energy molecules, thereby accelerating the design of energetic materials. A persistent challenge is to determine the optimal featurization methods for molecular representation and use an appropriate ML model. Thus, in our study, we evaluate various featurization methods (CDS, ECFP, SOAP, GNF) and ML models (RF, MLP, GCN, MPNN), dividing them into two groups: conventional ML models and GNN models, to predict the enthalpy of formation of potential high-energy molecules. Our results demonstrate that CDS and SOAP have advantages over the ECFP, while the GNFs in GCN and MPNN models perform better. Furthermore, the MPNN model performs best among all models with a root mean square error (RMSE) as low as 8.42 kcal mol-1, surpassing even the best performing CDS-MLP model in conventional ML models. Overall, this study provides a benchmark for ML in predicting enthalpy of formation and emphasizes the tremendous potential of GNN in property prediction.

Estimation and Prediction of the Polymers' Physical Characteristics Using the Machine Learning Models

This article investigates the utility of machine learning (ML) methods for predicting and analyzing the diverse physical characteristics of polymers. Leveraging a rich dataset of polymers' characteristics, the study encompasses an extensive range of polymer properties, spanning compressive and tensile strength to thermal and electrical behaviors. Using various regression methods like Ensemble, Tree-based, Regularization, and Distance-based, the research undergoes thorough evaluation using the most common quality metrics. As a result of a series of experimental studies on the selection of effective model parameters, those that provide a high-quality solution to the stated problem were found. The best results were achieved by Random Forest with the highest R2 scores of 0.71, 0.73, and 0.88 for glass transition, thermal decomposition, and melting temperatures, respectively. The outcomes are intricately compared, providing valuable insights into the efficiency of distinct ML approaches in predicting polymer properties. Unknown values for each characteristic were predicted, and a method validation was performed by training on the predicted values, comparing the results with the specified variance values of each characteristic. The research not only advances our comprehension of polymer physics but also contributes to informed model selection and optimization for materials science applications.

Machine Learning-Assisted Low-Dimensional Electrocatalysts Design for Hydrogen Evolution Reaction

Efficient electrocatalysts are crucial for hydrogen generation from electrolyzing water. Nevertheless, the conventional "trial and error" method for producing advanced electrocatalysts is not only cost-ineffective but also time-consuming and labor-intensive. Fortunately, the advancement of machine learning brings new opportunities for electrocatalysts discovery and design. By analyzing experimental and theoretical data, machine learning can effectively predict their hydrogen evolution reaction (HER) performance. This review summarizes recent developments in machine learning for low-dimensional electrocatalysts, including zero-dimension nanoparticles and nanoclusters, one-dimensional nanotubes and nanowires, two-dimensional nanosheets, as well as other electrocatalysts. In particular, the effects of descriptors and algorithms on screening low-dimensional electrocatalysts and investigating their HER performance are highlighted. Finally, the future directions and perspectives for machine learning in electrocatalysis are discussed, emphasizing the potential for machine learning to accelerate electrocatalyst discovery, optimize their performance, and provide new insights into electrocatalytic mechanisms. Overall, this work offers an in-depth understanding of the current state of machine learning in electrocatalysis and its potential for future research.

Force field-inspired transformer network assisted crystal density prediction for energetic materials

Machine learning has great potential in predicting chemical information with greater precision than traditional methods. Graph neural networks (GNNs) have become increasingly popular in recent years, as they can automatically learn the features of the molecule from the graph, significantly reducing the time needed to find and build molecular descriptors. However, the application of machine learning to energetic materials property prediction is still in the initial stage due to insufficient data. In this work, we first curated a dataset of 12,072 compounds containing CHON elements, which are traditionally regarded as main composition elements of energetic materials, from the Cambridge Structural Database, then we implemented a refinement to our force field-inspired neural network (FFiNet), through the adoption of a Transformer encoder, resulting in force field-inspired Transformer network (FFiTrNet). After the improvement, our model outperforms other machine learning-based and GNNs-based models and shows its powerful predictive capabilities especially for high-density materials. Our model also shows its capability in predicting the crystal density of potential energetic materials dataset (i.e. Huang & Massa dataset), which will be helpful in practical high-throughput screening of energetic materials.

Quantitative Prediction of Inorganic Nanomaterial Cellular Toxicity via Machine Learning

Organic chemistry has seen colossal progress due to machine learning (ML). However, the translation of artificial intelligence (AI) into materials science is challenging, where biological behavior prediction becomes even more complicated. Nanotoxicity is a critical parameter that describes their interaction with the living organisms screened in every bio-related research. To prevent excessive experiments, such properties have to be pre-evaluated. Several existing ML models partially fulfill the gap by predicting whether a nanomaterial is toxic or not. Yet, this binary categorization neglects the concentration dependencies crucial for experimental scientists. Here, an ML-based approach is proposed to the quantitative prediction of inorganic nanomaterial cytotoxicity achieving the precision expressed by 10-fold cross-validation (CV) Q²  = 0.86 with the root mean squared error (RMSE) of 12.2% obtained by the correlation-based feature selection and grid search-based model hyperparameters optimization. To provide further model flexibility, quantitative atom property-based nanomaterial descriptors are introduced allowing the model to extrapolate on unseen samples. Feature importance is calculated to find an interpretable model with optimal decision-making. These findings allow experimental scientists to perform primary in silico candidate screening and minimize the number of excessive, labor-intensive experiments enabling the rapid development of nanomaterials for medicinal purposes.

Prediction and Construction of Energetic Materials Based on Machine Learning Methods

Energetic materials (EMs) are the core materials of weapons and equipment. Achieving precise molecular design and efficient green synthesis of EMs has long been one of the primary concerns of researchers around the world. Traditionally, advanced materials were discovered through a trial-and-error processes, which required long research and development (R&D) cycles and high costs. In recent years, the machine learning (ML) method has matured into a tool that compliments and aids experimental studies for predicting and designing advanced EMs. This paper reviews the critical process of ML methods to discover and predict EMs, including data preparation, feature extraction, model construction, and model performance evaluation. The main ideas and basic steps of applying ML methods are analyzed and outlined. The state-of-the-art research about ML applications in property prediction and inverse material design of EMs is further summarized. Finally, the existing challenges and the strategies for coping with challenges in the further applications of the ML methods are proposed.

Building Chemical Property Models for Energetic Materials from Small Datasets Using a Transfer Learning Approach

For many experimentally measured chemical properties that cannot be directly computed from first-principles, the existing physics-based models do not extrapolate well to out-of-sample molecules, and experimental datasets themselves are too small for traditional machine learning (ML) approaches. To overcome these limitations, we apply a transfer learning approach, whereby we simultaneously train a multi-target regression model on a small number of molecules with experimentally measured values and a large number of molecules with related computed properties. We demonstrate this methodology on predicting the experimentally measured impact sensitivity of energetic crystals, finding that both characteristics of the computed dataset and model architecture are important to prediction accuracy of the small experimental dataset. Our directed-message passing neural network (D-MPNN) ML model using transfer learning outperforms direct-ML and physics-based models on a diverse test set, and the new methods described here are widely applicable to modeling many other structure-property relationships.

Representing Polymers as Periodic Graphs with Learned Descriptors for Accurate Polymer Property Predictions

Accurately predicting new polymers' properties with machine learning models apriori to synthesis has potential to significantly accelerate new polymers' discovery and development. However, accurately and efficiently capturing polymers' complex, periodic structures in machine learning models remains a grand challenge for the polymer cheminformatics community. Specifically, there has yet to be an ideal solution for the problems of how to capture the periodicity of polymers, as well as how to optimally develop polymer descriptors without requiring human-based feature design. In this work, we tackle these problems by utilizing a periodic polymer graph representation that accounts for polymers' periodicity and coupling it with a message-passing neural network that leverages the power of graph deep learning to automatically learn chemically relevant polymer descriptors. Remarkably, this approach achieves state-of-the-art performance on 8 out of 10 distinct polymer property prediction tasks. These results highlight the advancement in predictive capability that is possible through learning descriptors that are specifically optimized for capturing the unique chemical structure of polymers.

Machine-Learning-Guided Identification of Coordination Polymer Ligands for Crystallizing Separation of Cs/Sr

Separation of Cs/Sr is one of many coordination-chemistry-centered processes in the grand scheme of spent nuclear fuel reprocessing, a critical link for a sustainable nuclear energy industry. To deploy a crystallizing Cs/Sr separation technology, we planned to systematically screen and identify candidate ligands that can efficiently and selectively bind to Sr2+ and form coordination polymers. Therefore, we mined the Cambridge Structural Database for characteristic structural information and developed a machine-learning-guided methodology for ligand evaluation. The optimized machine-learning model, correlating the molecular structures of the ligands with the predicted coordinative properties, generated a ranking list of potential compounds for Cs/Sr selective crystallization. The Sr2+ sequestration capability and selectivity over Cs+ of the promising ligands identified (squaric acid and chloranilic acid) were subsequently confirmed experimentally, with commendable performances, corroborating the artificial-intelligence-guided strategy.

Crystal structures

A personal view is offered on various solved and open problems related to crystal structures: the present state of reconstructing the crystal electron density from X-ray diffraction data; characterization of atomic and molecular motion from a combination of atomic displacement parameters and quantum chemical calculations; Bragg diffraction and diffuse scattering: twins, but different; models of real (as opposed to ideal) crystal structures from diffuse scattering; exploiting unexplored neighbourhoods of crystallography to mathematics, physics and chemistry.

Decoding hexanitrobenzene (HNB) and 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) as two distinctive energetic nitrobenzene compounds by machine learning

Energetic materials (EMs) are a group of special energy materials, and it is generally full of safety risks and generally costs much to create new EMs. Thus, machine learning (ML)-aided discovery becomes highly desired for EMs, as ML is good at risk and cost reduction. This work decodes hexanitrobenzene (HNB) and 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) as two distinctive energetic nitrobenzene compounds by ML, in combination with theoretical calculations. Based on a series of highly accurate models of density, heat of formation, bond dissociation energy and molecular flatness, the ML predictions show that HNB is the most energetic among ∼370 000 000 single benzene ring-containing compounds, while TATB possesses a moderate energy content and very high safety, as determined experimentally. This work exhibits the significant power of ML and presents an instructive procedure for using it in the field of EMs. The ML-aided design and highly efficient synthesis and fabrication combined strategy is expected to accelerate the discovery of new EMs.