Coupling complementary strategy to flexible graph neural network for quick discovery of coformer in diverse co-crystal materials

DTF-diffusion: A 3D equivariant diffusion generation model based on ligand-target information fusion

The goal of drug discovery based on deep learning is to generate drug molecules that bind to a given target protein. Recently, the use of three-dimensional molecular structures has shown superior performance over other two-dimensional structural models. However, most of the current depth generation models are based on ligands, and in the process of molecular generation, the models only learn the independent information of ligands or targets, without considering the complex interaction information of them. In addition, chemical knowledge was not considered in the process of molecular formation, which led to generation unreasonable drug molecular structure. In order to solve above problems, this paper proposes DTF-diffusion, a 3D equivariant diffusion generation model based on ligand-target information fusion. Firstly based on the diffusion model, DTF-diffusion uses multimodal feature fusion module proposed in this paper to fuse the three-dimensional position feature information of ligand molecules and targets, and extract advanced hidden features from ligand atom information and target sequence information. Secondly, this paper designs a chemical rule discrimination module, and learns the real ligand molecular structure and the characteristic information of the generated ligand molecules through the discriminator, and then capture the chemical rules in the drug molecular structure, which effectively improve the rationality of the ligand structure generated by the model. This paper evaluates the generation performance of DTF-diffusion and other baseline methods from multiple perspectives based on the CrossDocket2020 dataset. In the quantitative estimate of drug-likeness index, DTF-diffusion is 3.85 % higher than the existing optimal model, the drug validity index increased by 4.34 %. More generation experiments have proved that DTF-diffusion has excellent performance, indicating that it has a good application prospect in the field of drug molecule generation.

High-throughput encapsulated nanodroplet screening for accelerated co-crystal discovery

Co-crystals are composed of two or more chemically inequivalent molecular species, excluding solvents, generally in a stoichiometric ratio. Co-crystals are particularly important in pharmaceutical development, where a suitable co-crystal can significantly improve the physiochemical and pharmacokinetic properties of an active pharmaceutical ingredient. However, co-crystal discovery remains both practically challenging and resource intensive, requiring the extensive searching of complex experimental space. Herein, we demonstrate a high-throughput (HTP) nanoscale co-crystallisation method for the rapid screening of large areas of co-crystallisation space with minimal sample requirements, based on Encapsulated Nanodroplet Crystallisation (ENaCt). HTP co-crystallisation screening by ENaCt allowed rapid access to all 18 possible binary co-crystal combinations of 3 small molecules and 6 co-formers (A/B), through the use of 3456 individual experiments exploring solvent, encapsulating oil and stoichiometry, including 10 novel binary co-crystal structures elucidated by single crystal X-ray diffraction (SCXRD). Higher-order co-crystal (HOC) discovery, accessing co-crystals containing three or more molecules, is one of the most challenging co-crystal research areas, due to the highly complex experimental landscape that must be navigated. Herein, we further exemplify the power of ENaCt co-crystallisation by application to HOC discovery. HTP ENaCt co-crystallisation screening of three component (A/B/C) and four component (A/B/C/D) combinations gave ready access to both ternary and quaternary HOCs, each containing three or four different molecular species respectively. In total, 13 056 individual ENaCt experiments are presented resulting in 54 co-crystal structures by SCXRD, including 17 novel binary co-crystals, 8 novel ternary co-crystals and 4 novel quaternary co-crystals. ENaCt co-crystallisation is thus demonstrated to be a highly impactful and efficient tool in the search for small molecule co-crystals, through the employment of parallelised HTP nanoscale experimental workflows.

Cocry-pred: A Dynamic Resource Propagation Method for Cocrystal Prediction

Drug cocrystallization is a powerful strategy to enhance drug properties by modifying their physicochemical characteristics without altering their chemical structure. However, the identification of suitable coformers remains a challenging and resource-intensive task. To streamline this process, we developed a novel cocrystal prediction model, Cocry-pred, which utilizes the Network-Based Inference (NBI) algorithm─a dynamic resource propagation method─to recommend coformers for target molecules based on topological data from cocrystal network and molecular substructure information. We evaluated the impact of 13 types of molecular fingerprints and different numbers of propagation rounds on model performance. Additionally, to achieve optimal performance, we introduced three key hyperparameters─α (node weights), β (edge weights) and γ (penalty for high-degree nodes)─to balance the influence of various factors within the composite network. The best performance of Cocry-pred achieved an impressive AUC of 0.885 and an RS of 0.108. To validate the reliability of the model, we employed it to predict potential coformers for Apatinib. Subsequently, seven Apatinib cocrystals were then synthesized experimentally, among which single-crystal structures were obtained for two cocrystals. This advancement highlights the potential of Cocry-pred as a powerful tool, offering significant improvements in efficiency and providing valuable insights for cocrystal screening and design.

Recent Advances of Organic Cocrystals in Emerging Cutting-Edge Properties and Applications

Organic cocrystals, representing one type of new functional materials, have gathered significant interest in various engineering areas. Owing to their diverse stacking modes, rich intermolecular interactions and abundant functional components, the physicochemical properties of organic cocrystals can be tailored to meet different requirements and exhibit novel characteristics. The past few years have witnessed the rapid development of organic cocrystals in both fundamental characteristics and various applications. Beyond the typical properties like ambipolarity, emission tuning ability, ferroelectricity, etc. that are previously well demonstrated, many novel, impressive and cutting-edge properties and applications of cocrystals are also emerged and advanced recently. Especially during the nearest five years, photothermal conversion, room-temperature phosphorescence, thermally activated delay fluorescence, circularly polarized luminescence, organic solid-state lasers, near-infrared sensing, photocatalysis, batteries, and stimuli responses have been reported. In this review, these new properties are carefully summarized. Besides, some neoteric architecture and methodologies, such as host-guest structures and machine learning-based screening, are introduced. Finally, the potential future developments and expectations for organic cocrystals are discussed for further investigations on multiple functions and applications.

CMSSP: A Contrastive Mass Spectra-Structure Pretraining Model for Metabolite Identification

A pivotal challenge in metabolite research is the structural annotation of metabolites from tandem mass spectrometry (MS/MS) data. The integration of artificial intelligence (AI) has revolutionized the interpretation of MS data, facilitating the identification of elusive metabolites within the metabolomics landscape. Innovative methodologies are primarily focusing on transforming MS/MS spectra or molecular structures into a unified modality to enable similarity-based comparison and interpretation. In this work, we present CMSSP, a novel Contrastive Mass Spectra-Structure Pretraining framework designed for metabolite annotation. The primary objective of CMSSP is to establish a representation space that facilitates a direct comparison between MS/MS spectra and molecular structures, transcending the limitations of distinct modalities. The evaluation on two benchmark test sets demonstrates the efficacy of the approach. CMSSP achieved a remarkable enhancement in annotation accuracy, outperforming the state-of-the-art methods by a significant margin. Specifically, it improved the top-1 accuracy by 30% on the CASMI 2017 data set and realized a 16% increase in top-10 accuracy on an independent test set. Moreover, the model displayed superior identification accuracy across all seven chemical categories, showcasing its robustness and versatility. Finally, the MS/MS data of 30 metabolites from Glycyrrhiza glabra were analyzed, achieving top-1 and top-3 accuracies of 86.7 and 100%, respectively. The CMSSP model serves as a potent tool for the dissection and interpretation of intricate MS/MS data, propelling the field toward more accurate and efficient metabolite annotation. This not only augments the analytical capabilities of metabolomics but also paves the way for future discoveries in understanding of complex biological systems.

Interpretable and Physicochemical-Intuitive Deep Learning Approach for the Design of Thermal Resistance of Energetic Compounds

Thermal resistance of energetic materials is critical due to its impact on safety and sustainability. However, developing predictive models remains challenging because of data scarcity and limited insights into quantitative structure-property relationships. In this work, a deep learning framework, named EM-thermo, was proposed to address these challenges. A data set comprising 5029 CHNO compounds, including 976 energetic compounds, was constructed to facilitate this study. EM-thermo employs molecular graphs and direct message-passing neural networks to capture structural features and predict thermal resistance. Using transfer learning, the model achieves an accuracy of approximately 97% for predicting the thermal-resistance property (decomposition temperatures above 573.15 K) in energetic compounds. The involvement of molecular descriptors improved model prediction. These findings suggest that EM-thermo is effective for correlating thermal resistance from the atom and covalent bond level, offering a promising tool for advancing molecular design and discovery in the field of energetic compounds.

Enhancing chemistry-intuitive feature learning to improve prediction performance of optical properties

Emitters have been widely applied in versatile fields, dependent on their optical properties. Thus, it is of great importance to explore a quick and accurate prediction method for optical properties. To this end, we have developed a state-of-the-art deep learning (DL) framework by enhancing chemistry-intuitive subgraph and edge learning and coupling this with prior domain knowledge for a classic message passing neural network (MPNN) which can better capture the structural features associated with the optical properties from a limited dataset. Benefiting from technical advantages, our model significantly outperforms eight competitive ML models used in five different optical datasets, achieving the highest accuracy to date in predicting four important optical properties (absorption wavelength, emission wavelength, photoluminescence quantum yield and full width at half-maximum), showcasing its robustness and generalization. More importantly, based on our predicted results, one new deep-blue light-emitting molecule PPI-2TPA was successfully synthesized and characterized, which exhibits close consistency with our predictions, clearly confirming the application potential of our model as a quick and reliable prediction tool for the optical properties of diverse emitters in practice.

Integrative residue-intuitive machine learning and MD Approach to Unveil Allosteric Site and Mechanism for β2AR

Allosteric drugs offer a new avenue for modern drug design. However, the identification of cryptic allosteric sites presents a formidable challenge. Following the allostery nature of residue-driven conformation transition, we propose a state-of-the-art computational pipeline by developing a residue-intuitive hybrid machine learning (RHML) model coupled with molecular dynamics (MD) simulation, through which we can efficiently identify the allosteric site and allosteric modulator as well as reveal their regulation mechanism. For the clinical target β2-adrenoceptor (β2AR), we discover an additional allosteric site located around residues D792.50, F2826.44, N3187.45 and S3197.46 and one putative allosteric modulator ZINC5042. Using Molecular Mechanics/Generalized Born Surface Area (MM/GBSA) and protein structure network (PSN), the allosteric potency and regulation mechanism are probed to further improve identification accuracy. Benefiting from sufficient computational evidence, the experimental assays then validate our predicted allosteric site, negative allosteric potency and regulation pathway, showcasing the effectiveness of the identification pipeline in practice. We expect that it will be applicable to other target proteins.

Cocrystal Prediction of Nifedipine Based on the Graph Neural Network and Molecular Electrostatic Potential Surface

Nifedipine (NIF) is a dihydropyridine calcium channel blocker primarily used to treat conditions such as hypertension and angina. However, its low solubility and low bioavailability limit its effectiveness in clinical practice. Here, we developed a cocrystal prediction model based on Graph Neural Networks (CocrystalGNN) for the screening of cocrystals with NIF. And scoring 50 coformers using CocrystalGNN. To validate the reliability of the model, we used another prediction method, Molecular Electrostatic Potential Surface (MEPS), to verify the prediction results. Subsequently, we performed a second validation using experiments. The results indicate that our model achieved high performance. Ultimately, cocrystals of NIF were successfully obtained and all cocrystals exhibited better solubility and dissolution characteristics compared to the parent drug. This study lays a solid foundation for combining virtual prediction with experimental screening to discover novel water-insoluble drug cocrystals.

AI-enhanced chemical paradigm: From molecular graphs to accurate prediction and mechanism

The development of accurate and interpretable models for predicting reaction constants of organic compounds with hydroxyl radicals is vital for advancing quantitative structure-activity relationships (QSAR) in pollutant degradation. Methods like molecular descriptors, molecular fingerprinting, and group contribution methods have limitations, as traditional machine learning struggles to capture all intramolecular information simultaneously. To address this, we established an integrated graph neural network (GNN) with approximately 12 million learnable parameters. GNN represents atoms as nodes and chemical bonds as edges, thus transforming molecules into a graph structures, effectively capturing microscopic properties while depicting atom connectivity in non-Euclidean space. Our datasets comprise 1401 pollutants to develop an integrated GNN model with Bayesian optimization, the model achieves root mean square errors of 0.165, 0.172, and 0.189 on the training, validation, and test datasets, respectively. Furthermore, we assess molecular structure similarity using molecular fingerprint to enhance the model's applicability. Afterwards, we propose a gradient weight mapping method for model explainability, uncovering the key functional groups in chemical reactions in artificial intelligence perspective, which would boost chemistry through artificial intelligence extreme arithmetic power.

Efficient cocrystal coformer screening based on a Machine learning Strategy: A case study for the preparation of imatinib cocrystal with enhanced physicochemical properties

Cocrystal engineering, which involves the self-assembly of two or more components into a solid-state supramolecular structure through non-covalent interactions, has emerged as a promising approach to tailor the physicochemical properties of active pharmaceutical ingredient (API). Efficient coformer screening for cocrystal remains a challenge. Herein, a prediction strategy based on machine learning algorithms was employed to predict cocrystal formation and seven reliable models with accuracy over 0.890 were successfully constructed. Imatinib was selected as the model drug and the models established were applied to screen 31 potential coformers. Experimental verification results indicated RF-8 is the optimal model among seven models with an accuracy of 0.839. When the seven models were combined for coformer screening of Imatinib, the combinational model achieved an accuracy of 0.903, and eight new solid forms were observed and characterized. Benefiting from intermolecular interactions, the obtained multicomponent crystals displayed enhanced physicochemical properties. Dissolution and solubility experiments showed the prepared multicomponent crystals had higher cumulative dissolution rate and remarkably improved the solubility of imatinib, and IM-MC exhibited comparable solubility to Imatinib mesylate α form. Stability test and cytotoxicity results showed that multicomponent crystals exhibited excellent stability and the drug-drug cocrystal IM-5F exhibited higher cytotoxicity than pure API.

Graph Neural Networks with Multi-features for Predicting Cocrystals using APIs and Coformers Interactions

INTRODUCTION

Active pharmaceutical ingredients (APIs) have gained direct pharmaceutical interest, along with their in vitro properties, and thus utilized as auxiliary solid dosage forms upon FDA guidance and approval on pharmaceutical cocrystals when reacting with coformers, as a potential and attractive route for drug substance development.

METHODS

However, screening and selecting suitable and appropriate coformers that may potentially react with APIs to successfully form cocrystals is a time-consuming, inefficient, economically expensive, and labour-intensive task. In this study, we implemented GNNs to predict the formation of cocrystals using our introduced API-coformers relational graph data. We further compared our work with previous studies that implemented descriptor-based models (e.g., random forest, support vector machine, extreme gradient boosting, and artificial neural networks).

RESULTS

All built graph-based models show compelling performance accuracies (i.e., 91.36, 94.60 and 95. 95% for GCN, GraphSAGE, and RGCN respectively). RGCN demonstrated effectiveness and prevailed among the built graph-based models due to its capability to capture intricate and learn nuanced relationships between entities such as non-ionic and non-covalent interactions or link information between APIs and coformers which are crucial for accurate predictions and representations.

CONCLUSION

These capabilities allows the model to adeptly learn the topological structure inherent in the graph data.

In silico co-crystal design: Assessment of the latest advances

Pharmaceutical co-crystals represent a growing class of crystal forms in the context of pharmaceutical science. They are attractive to pharmaceutical scientists because they significantly expand the number of crystal forms that exist for an active pharmaceutical ingredient and can lead to improvements in physicochemical properties of clinical relevance. At the same time, machine learning is finding its way into all areas of drug discovery and delivers impressive results. In this review, we attempt to provide an overview of machine learning, deep learning and network-based recommendation approaches applied to pharmaceutical co-crystallization. We also present crystal structure prediction as an alternative to machine learning approaches.

Graph Comparison of Molecular Crystals in Band Gap Prediction Using Neural Networks

In material informatics, the representation of the material structure is fundamentally essential to obtaining better prediction results, and graph representation has attracted much attention in recent years. Molecular crystals can be graphically represented in molecular and crystal representations, but a comparison of which representation is more effective has not been examined. In this study, we compared the prediction accuracy between molecular and crystal graphs for band gap prediction. The results showed that the prediction accuracies using crystal graphs were better than those obtained using molecular graphs. While this result is not surprising, error analysis quantitatively evaluated that the error of the crystal graph was 0.4 times that of the molecular graph with moderate correlation. The novelty of this study lies in the comparison of molecular crystal representations and in the quantitative evaluation of the contribution of crystal structures to the band gap.

HMM-GDAN: Hybrid multi-view and multi-scale graph duplex-attention networks for drug response prediction in cancer

Precision medicine is devoted to discovering personalized therapy for complex and difficult diseases like cancer. Many machine learning approaches have been developed for drug response prediction towards precision medicine. Notwithstanding, genetic profiles based multi-view graph learning schemes have not yet been explored for drug response prediction in previous works. Furthermore, multi-scale latent feature fusion is not considered sufficiently in the existing frameworks of graph neural networks (GNNs). Previous works on drug response prediction mainly depend on sequence data or single-view graph data. In this paper, we propose to construct multi-view graph by means of multi-omics data and STRING protein-protein association data, and develop a new architecture of GNNs for drug response prediction in cancer. Specifically, we propose hybrid multi-view and multi-scale graph duplex-attention networks (HMM-GDAN), in which both multi-view self-attention mechanism and view-level attention mechanism are devised to capture the complementary information of views and emphasize on the importance of each view collaboratively, and rich multi-scale features are constructed and integrated to further form high-level representations for better prediction. Experiments on GDSC2 dataset verify the superiority of the proposed HMM-GDAN when compared with state-of-the-art baselines. The effectiveness of multi-view and multi-scale strategies is demonstrated by the ablation study.

Recent Advances in Co-Former Screening and Formation Prediction of Multicomponent Solid Forms of Low Molecular Weight Drugs

Multicomponent solid forms of low molecular weight drugs, such as co-crystals, salts, and co-amorphous systems, are a result of the combination of an active pharmaceutical ingredient (API) with a pharmaceutically acceptable co-former. These solid forms can enhance the physicochemical and pharmacokinetic properties of APIs, making them increasingly interesting and important in recent decades. Nevertheless, predicting the formation of API multicomponent solid forms in the early stages of formulation development can be challenging, as it often requires significant time and resources. To address this, empirical and computational methods have been developed to help screen for potential co-formers more efficiently and accurately, thus reducing the number of laboratory experiments needed. This review provides a comprehensive overview of current screening and prediction methods for the formation of API multicomponent solid forms, covering both crystalline states (co-crystals and salts) and amorphous forms (co-amorphous). Furthermore, it discusses recent advances and emerging trends in prediction methods, with a particular focus on artificial intelligence.

Pharmaceutical Cocrystal Discovery via 3D-SMINBR: A New Network Recommendation Tool Augmented by 3D Molecular Conformations

Cocrystals have significant potential in various fields such as chemistry, material, and medicine. For instance, pharmaceutical cocrystals have the ability to address issues associated with physicochemical and biopharmaceutical properties. However, it can be challenging to find proper coformers to form cocrystals with drugs of interest. Herein, a new in silico tool called 3D substructure-molecular-interaction network-based recommendation (3D-SMINBR) has been developed to address this problem. This tool first integrated 3D molecular conformations with a weighted network-based recommendation model to prioritize potential coformers for target drugs. In cross-validation, the performance of 3D-SMINBR surpassed the 2D substructure-based predictive model SMINBR in our previous study. Additionally, the generalization capability of 3D-SMINBR was confirmed by testing on unseen cocrystal data. The practicality of this tool was further demonstrated by case studies on cocrystal screening of armillarisin A (Arm) and isoimperatorin (iIM). The obtained Arm-piperazine and iIM-salicylamide cocrystals present improved solubility and dissolution rate compared to their parent drugs. Overall, 3D-SMINBR augmented by 3D molecular conformations would be a useful network-based tool for cocrystal discovery. A free web server for 3D-SMINBR can be freely accessed at http://lmmd.ecust.edu.cn/netcorecsys/.

Exploring the Supramolecular Interactions and Thermal Stability of Dapsone:Bipyridine Cocrystals by Combining Computational Chemistry with Experimentation

The application of computational screening methodologies based on H-bond propensity scores, molecular complementarity, molecular electrostatic potentials, and crystal structure prediction has guided the discovery of novel cocrystals of dapsone and bipyridine (DDS:BIPY). The experimental screen, which included mechanochemical and slurry experiments as well as the contact preparation, resulted in four cocrystals, including the previously known DDS:4,4'-BIPY (2:1, CC₄₄-B) cocrystal. To understand the factors governing the formation of the DDS:2,2'-BIPY polymorphs (1:1, CC₂₂-A and CC₂₂-B) and the two DDS:4,4'-BIPY cocrystal stoichiometries (1:1 and 2:1), different experimental conditions (such as the influence of solvent, grinding/stirring time, etc.) were tested and compared with the virtual screening results. The computationally generated (1:1) crystal energy landscapes had the experimental cocrystals as the lowest energy structures, although distinct cocrystal packings were observed for the similar coformers. H-bonding scores and molecular electrostatic potential maps correctly indicated cocrystallization of DDS and the BIPY isomers, with a higher likelihood for 4,4'-BIPY. The molecular conformation influenced the molecular complementarity results, predicting no cocrystallization for 2,2'-BIPY with DDS. The crystal structures of CC₂₂-A and CC₄₄-A were solved from powder X-ray diffraction data. All four cocrystals were fully characterized by a range of analytical techniques, including powder X-ray diffraction, infrared spectroscopy, hot-stage microscopy, thermogravimetric analysis, and differential scanning calorimetry. The two DDS:2,2'-BIPY polymorphs are enantiotropically related, with form B being the stable polymorph at room temperature (RT) and form A being the higher temperature form. Form B is metastable but kinetically stable at RT. The two DDS:4,4'-BIPY cocrystals are stable at room conditions; however, at higher temperatures, CC₄₄-A transforms to CC₄₄-B. The cocrystal formation enthalpy order, derived from the lattice energies, was calculated as follows: CC₄₄-B > CC₄₄-A > CC₂₂-A.

Predicting the Melting Point of Energetic Molecules Using a Learnable Graph Neural Fingerprint Model

Melting point prediction for organic molecules has drawn widespread attention from both academic and industrial communities. In this work, a learnable graph neural fingerprint (GNF) was employed to develop a melting point prediction model using a dataset of over 90,000 organic molecules. The GNF model exhibited a significant advantage, with a mean absolute error (MAE) of 25.0 K, when compared to other featurization methods. Furthermore, by integrating prior knowledge through a customized descriptor set (i.e., CDS) into GNF, the accuracy of the resulting model, GNF_CDS, improved to 24.7 K, surpassing the performance of previously reported models for a wide range of structurally diverse organic compounds. Moreover, the generalizability of the GNF_CDS model was significantly improved with a decreased MAE of 17 K for an independent dataset containing melt-castable energetic molecules. This work clearly demonstrates that prior knowledge is still beneficial for modeling molecular properties despite the powerful learning capability of graph neural networks, especially in specific fields where chemical data are lacking.

Virtual Screening, Structural Analysis, and Formation Thermodynamics of Carbamazepine Cocrystals

In this study, the existing set of carbamazepine (CBZ) cocrystals was extended through the successful combination of the drug with the positional isomers of acetamidobenzoic acid. The structural and energetic features of the CBZ cocrystals with 3- and 4-acetamidobenzoic acids were elucidated via single-crystal X-ray diffraction followed by QTAIMC analysis. The ability of three fundamentally different virtual screening methods to predict the correct cocrystallization outcome for CBZ was assessed based on the new experimental results obtained in this study and data available in the literature. It was found that the hydrogen bond propensity model performed the worst in distinguishing positive and negative results of CBZ cocrystallization experiments with 87 coformers, attaining an accuracy value lower than random guessing. The method that utilizes molecular electrostatic potential maps and the machine learning approach named CCGNet exhibited comparable results in terms of prediction metrics, albeit the latter resulted in superior specificity and overall accuracy while requiring no time-consuming DFT computations. In addition, formation thermodynamic parameters for the newly obtained CBZ cocrystals with 3- and 4-acetamidobenzoic acids were evaluated using temperature dependences of the cocrystallization Gibbs energy. The cocrystallization reactions between CBZ and the selected coformers were found to be enthalpy-driven, with entropy terms being statistically different from zero. The observed difference in dissolution behavior of the cocrystals in aqueous media was thought to be caused by variations in their thermodynamic stability.

General Graph Neural Network-Based Model To Accurately Predict Cocrystal Density and Insight from Data Quality and Feature Representation

Cocrystal engineering as an effective way to modify solid-state properties has inspired great interest from diverse material fields while cocrystal density is an important property closely correlated with the material function. In order to accurately predict the cocrystal density, we develop a graph neural network (GNN)-based deep learning framework by considering three key factors of machine learning (data quality, feature presentation, and model architecture). The result shows that different stoichiometric ratios of molecules in cocrystals can significantly influence the prediction performances, highlighting the importance of data quality. In addition, the feature complementary is not suitable for augmenting the molecular graph representation in the cocrystal density prediction, suggesting that the complementary strategy needs to consider whether extra features can sufficiently supplement the lacked information in the original representation. Based on these results, 4144 cocrystals with 1:1 stoichiometry ratio are selected as the dataset, supplemented by the data augmentation of exchanging a pair of coformers. The molecular graph is determined to learn feature representation to train the GNN-based model. Global attention is introduced to further optimize the feature space and identify important atoms to realize the interpretability of the model. Benefited from the advantages, our model significantly outperforms three competitive models and exhibits high prediction accuracy for unseen cocrystals, showcasing its robustness and generality. Overall, our work not only provides a general cocrystal density prediction tool for experimental investigations but also provides useful guidelines for the machine learning application. All source codes are freely available at https://github.com/Xiao-Gua00/CCPGraph.

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.

Biomarkers discovery for endometrial cancer: A graph convolutional sample network method

BACKGROUND

Endometrial carcinoma is the sixth most common cancer in women worldwide. Importantly, endometrial cancer is among the few types of cancers with patient mortality that is still increasing, which indicates that the improvement in its diagnosis and treatment is still urgent. Moreover, biomarker discovery is essential for precise classification and prognostic prediction of endometrial cancer.

METHODS

A novel graph convolutional sample network method was used to identify and validate biomarkers for the classification of endometrial cancer. The sample networks were first constructed for each sample, and the gene pairs with high frequencies were identified to construct a subtype-specific network. Putative biomarkers were then screened using the highest degrees in the subtype-specific network. Finally, simplified sample networks are constructed using the biomarkers for the graph convolutional network (GCN) training and prediction.

RESULTS

Putative biomarkers (23) were identified using the novel bioinformatics model. These biomarkers were then rationalised with functional analyses and were found to be correlated to disease survival with network entropy characterisation. These biomarkers will be helpful in future investigations of the molecular mechanisms and therapeutic targets of endometrial cancers.

CONCLUSIONS

A novel bioinformatics model combining sample network construction with GCN modelling is proposed and validated for biomarker discovery in endometrial cancer. The model can be generalized and applied to biomarker discovery in other complex diseases.

Cocrystal Prediction of Bexarotene by Graph Convolution Network and Bioavailability Improvement

Bexarotene (BEX) was approved by the FDA in 1999 for the treatment of cutaneous T-cell lymphoma (CTCL). The poor aqueous solubility causes the low bioavailability of the drug and thereby limits the clinical application. In this study, we developed a GCN-based deep learning model (CocrystalGCN) for in-silico screening of the cocrystals of BEX. The results show that our model obtained high performance relative to baseline models. The top 30 of 109 coformer candidates were scored by CocrystalGCN and then validated experimentally. Finally, cocrystals of BEX-pyrazine, BEX-2,5-dimethylpyrazine, BEX-methyl isonicotinate, and BEX-ethyl isonicotinate were successfully obtained. The crystal structures were determined by single-crystal X-ray diffraction. Powder X-ray diffraction, differential scanning calorimetry, and thermogravimetric analysis were utilized to characterize these multi-component forms. All cocrystals present superior solubility and dissolution over the parent drug. The pharmacokinetic studies show that the plasma exposures (AUC0-8h) of BEX-pyrazine and BEX-2,5-dimethylpyrazine are 1.7 and 1.8 times that of the commercially available BEX powder, respectively. This work sets a good example for integrating virtual prediction and experimental screening to discover the new cocrystals of water-insoluble drugs.

Spectral Encoder to Extract the Features of Near-Infrared Spectra for Multivariate Calibration

An autoencoder architecture was adopted for near-infrared (NIR) spectral analysis by extracting the common features in the spectra. Three autoencoder-based networks with different purposes were constructed. First, a spectral encoder was established by training the network with a set of spectra as the input. The features of the spectra can be encoded by the nodes in the bottleneck layer, which in turn can be used to build a sparse and robust model. Second, taking the spectra of one instrument as the input and that of another instrument as the reference output, the common features in both spectra can be obtained in the bottleneck layer. Therefore, in the prediction step, the spectral features of the second can be predicted by taking the reverse of the decoder as the encoder. Furthermore, transfer learning was used to build the model for the spectra of more instruments by fine-tuning the trained network. NIR datasets of plant, wheat, and pharmaceutical tablets measured on multiple instruments were used to test the method. The multi-linear regression (MLR) model with the encoded features was found to have a similar or slightly better performance in prediction compared with the partial least-squares (PLS) model.

Emerging Landscape of Computational Modeling in Pharmaceutical Development

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