Comprehensive mass spectrometric metabolomic profiling of a chemically diverse collection of plants of the Celastraceae family

Natural products exhibit interesting structural features and significant biological activities. The discovery of new bioactive molecules is a complex process that requires high-quality metabolite profiling data to properly target the isolation of compounds of interest and enable their complete structural characterization. The same metabolite profiling data can also be used to better understand chemotaxonomic links between species. This Data Descriptor details a dataset resulting from the untargeted liquid chromatography-mass spectrometry metabolite profiling of 76 natural extracts of the Celastraceae family. The spectral annotation results and related chemical and taxonomic metadata are shared, along with proposed examples of data reuse. This data can be further studied by researchers exploring the chemical diversity of natural products. This can serve as a reference sample set for deep metabolome investigation of this chemically rich plant family.

Expanding Predictive Capacities in Toxicology: Insights from Hackathon-Enhanced Data and Model Aggregation

In the realm of predictive toxicology for small molecules, the applicability domain of QSAR models is often limited by the coverage of the chemical space in the training set. Consequently, classical models fail to provide reliable predictions for wide classes of molecules. However, the emergence of innovative data collection methods such as intensive hackathons have promise to quickly expand the available chemical space for model construction. Combined with algorithmic refinement methods, these tools can address the challenges of toxicity prediction, enhancing both the robustness and applicability of the corresponding models. This study aimed to investigate the roles of gradient boosting and strategic data aggregation in enhancing the predictivity ability of models for the toxicity of small organic molecules. We focused on evaluating the impact of incorporating fragment features and expanding the chemical space, facilitated by a comprehensive dataset procured in an open hackathon. We used gradient boosting techniques, accounting for critical features such as the structural fragments or functional groups often associated with manifestations of toxicity.

Machine Learning-Driven Classification of Urease Inhibitors Leveraging Physicochemical Properties as Effective Filter Criteria

Urease, a pivotal enzyme in nitrogen metabolism, plays a crucial role in various microorganisms, including the pathogenic Helicobacter pylori. Inhibiting urease activity offers a promising approach to combating infections and associated ailments, such as chronic kidney diseases and gastric cancer. However, identifying potent urease inhibitors remains challenging due to resistance issues that hinder traditional approaches. Recently, machine learning (ML)-based models have demonstrated the ability to predict the bioactivity of molecules rapidly and effectively. In this study, we present ML models designed to predict urease inhibitors by leveraging essential physicochemical properties. The methodological approach involved constructing a dataset of urease inhibitors through an extensive literature search. Subsequently, these inhibitors were characterized based on physicochemical properties calculations. An exploratory data analysis was then conducted to identify and analyze critical features. Ultimately, 252 classification models were trained, utilizing a combination of seven ML algorithms, three attribute selection methods, and six different strategies for categorizing inhibitory activity. The investigation unveiled discernible trends distinguishing urease inhibitors from non-inhibitors. This differentiation enabled the identification of essential features that are crucial for precise classification. Through a comprehensive comparison of ML algorithms, tree-based methods like random forest, decision tree, and XGBoost exhibited superior performance. Additionally, incorporating the "chemical family type" attribute significantly enhanced model accuracy. Strategies involving a gray-zone categorization demonstrated marked improvements in predictive precision. This research underscores the transformative potential of ML in predicting urease inhibitors. The meticulous methodology outlined herein offers actionable insights for developing robust predictive models within biochemical systems.

Enhancing property and activity prediction and interpretation using multiple molecular graph representations with MMGX

Graph Neural Networks (GNNs) excel in compound property and activity prediction, but the choice of molecular graph representations significantly influences model learning and interpretation. While atom-level molecular graphs resemble natural topology, they overlook key substructures or functional groups and their interpretation partially aligns with chemical intuition. Recent research suggests alternative representations using reduced molecular graphs to integrate higher-level chemical information and leverages both representations for model. However, there is a lack of studies about applicability and impact of different molecular graphs on model learning and interpretation. Here, we introduce MMGX (Multiple Molecular Graph eXplainable discovery), investigating the effects of multiple molecular graphs, including Atom, Pharmacophore, JunctionTree, and FunctionalGroup, on model learning and interpretation with various perspectives. Our findings indicate that multiple graphs relatively improve model performance, but in varying degrees depending on datasets. Interpretation from multiple graphs in different views provides more comprehensive features and potential substructures consistent with background knowledge. These results help to understand model decisions and offer valuable insights for subsequent tasks. The concept of multiple molecular graph representations and diverse interpretation perspectives has broad applicability across tasks, architectures, and explanation techniques, enhancing model learning and interpretation for relevant applications in drug discovery.

Probing the chemical 'reactome' with high-throughput experimentation data

High-throughput experimentation (HTE) has the potential to improve our understanding of organic chemistry by systematically interrogating reactivity across diverse chemical spaces. Notable bottlenecks include few publicly available large-scale datasets and the need for facile interpretation of these data's hidden chemical insights. Here we report the development of a high-throughput experimentation analyser, a robust and statistically rigorous framework, which is applicable to any HTE dataset regardless of size, scope or target reaction outcome, which yields interpretable correlations between starting material(s), reagents and outcomes. We improve the HTE data landscape with the disclosure of 39,000+ previously proprietary HTE reactions that cover a breadth of chemistry, including cross-coupling reactions and chiral salt resolutions. The high-throughput experimentation analyser was validated on cross-coupling and hydrogenation datasets, showcasing the elucidation of statistically significant hidden relationships between reaction components and outcomes, as well as highlighting areas of dataset bias and the specific reaction spaces that necessitate further investigation.

Will we ever be able to accurately predict solubility?

Accurate prediction of thermodynamic solubility by machine learning remains a challenge. Recent models often display good performances, but their reliability may be deceiving when used prospectively. This study investigates the origins of these discrepancies, following three directions: a historical perspective, an analysis of the aqueous solubility dataverse and data quality. We investigated over 20 years of published solubility datasets and models, highlighting overlooked datasets and the overlaps between popular sets. We benchmarked recently published models on a novel curated solubility dataset and report poor performances. We also propose a workflow to cure aqueous solubility data aiming at producing useful models for bench chemist. Our results demonstrate that some state-of-the-art models are not ready for public usage because they lack a well-defined applicability domain and overlook historical data sources. We report the impact of factors influencing the utility of the models: interlaboratory standard deviation, ionic state of the solute and data sources. The herein obtained models, and quality-assessed datasets are publicly available.

VirtuousPocketome: a computational tool for screening protein-ligand complexes to identify similar binding sites

Protein residues within binding pockets play a critical role in determining the range of ligands that can interact with a protein, influencing its structure and function. Identifying structural similarities in proteins offers valuable insights into their function and activation mechanisms, aiding in predicting protein-ligand interactions, anticipating off-target effects, and facilitating the development of therapeutic agents. Numerous computational methods assessing global or local similarity in protein cavities have emerged, but their utilization is impeded by complexity, impractical automation for amino acid pattern searches, and an inability to evaluate the dynamics of scrutinized protein-ligand systems. Here, we present a general, automatic and unbiased computational pipeline, named VirtuousPocketome, aimed at screening huge databases of proteins for similar binding pockets starting from an interested protein-ligand complex. We demonstrate the pipeline's potential by exploring a recently-solved human bitter taste receptor, i.e. the TAS2R46, complexed with strychnine. We pinpointed 145 proteins sharing similar binding sites compared to the analysed bitter taste receptor and the enrichment analysis highlighted the related biological processes, molecular functions and cellular components. This work represents the foundation for future studies aimed at understanding the effective role of tastants outside the gustatory system: this could pave the way towards the rationalization of the diet as a supplement to standard pharmacological treatments and the design of novel tastants-inspired compounds to target other proteins involved in specific diseases or disorders. The proposed pipeline is publicly accessible, can be applied to any protein-ligand complex, and could be expanded to screen any database of protein structures.

Bidirectional generation of structure and properties through a single molecular foundation model

Recent successes of foundation models in artificial intelligence have prompted the emergence of large-scale chemical pre-trained models. Despite the growing interest in large molecular pre-trained models that provide informative representations for downstream tasks, attempts for multimodal pre-training approaches on the molecule domain were limited. To address this, here we present a multimodal molecular pre-trained model that incorporates the modalities of structure and biochemical properties, drawing inspiration from recent advances in multimodal learning techniques. Our proposed model pipeline of data handling and training objectives aligns the structure/property features in a common embedding space, which enables the model to regard bidirectional information between the molecules' structure and properties. These contributions emerge synergistic knowledge, allowing us to tackle both multimodal and unimodal downstream tasks through a single model. Through extensive experiments, we demonstrate that our model has the capabilities to solve various meaningful chemical challenges, including conditional molecule generation, property prediction, molecule classification, and reaction prediction.

Precise atom-to-atom mapping for organic reactions via human-in-the-loop machine learning

Atom-to-atom mapping (AAM) is a task of identifying the position of each atom in the molecules before and after a chemical reaction, which is important for understanding the reaction mechanism. As more machine learning (ML) models were developed for retrosynthesis and reaction outcome prediction recently, the quality of these models is highly dependent on the quality of the AAM in reaction datasets. Although there are algorithms using graph theory or unsupervised learning to label the AAM for reaction datasets, existing methods map the atoms based on substructure alignments instead of chemistry knowledge. Here, we present LocalMapper, an ML model that learns correct AAM from chemist-labeled reactions via human-in-the-loop machine learning. We show that LocalMapper can predict the AAM for 50 K reactions with 98.5% calibrated accuracy by learning from only 2% of the human-labeled reactions from the entire dataset. More importantly, the confident predictions given by LocalMapper, which cover 97% of 50 K reactions, show 100% accuracy for 3,000 randomly sampled reactions. In an out-of-distribution experiment, LocalMapper shows favorable performance over other existing methods. We expect LocalMapper can be used to generate more precise reaction AAM and improve the quality of future ML-based reaction prediction models.

Can Small Molecules Provide Clues on Disease Progression in Cerebrospinal Fluid from Mild Cognitive Impairment and Alzheimer's Disease Patients?

Alzheimer's disease (AD) is a complex and multifactorial neurodegenerative disease, which is currently diagnosed via clinical symptoms and nonspecific biomarkers (such as Aβ1-42, t-Tau, and p-Tau) measured in cerebrospinal fluid (CSF), which alone do not provide sufficient insights into disease progression. In this pilot study, these biomarkers were complemented with small-molecule analysis using non-target high-resolution mass spectrometry coupled with liquid chromatography (LC) on the CSF of three groups: AD, mild cognitive impairment (MCI) due to AD, and a non-demented (ND) control group. An open-source cheminformatics pipeline based on MS-DIAL and patRoon was enhanced using CSF- and AD-specific suspect lists to assist in data interpretation. Chemical Similarity Enrichment Analysis revealed a significant increase of hydroxybutyrates in AD, including 3-hydroxybutanoic acid, which was found at higher levels in AD compared to MCI and ND. Furthermore, a highly sensitive target LC-MS method was used to quantify 35 bile acids (BAs) in the CSF, revealing several statistically significant differences including higher dehydrolithocholic acid levels and decreased conjugated BA levels in AD. This work provides several promising small-molecule hypotheses that could be used to help track the progression of AD in CSF samples.

Chemical Synthesis, Biological Evaluation, and Cheminformatics Analysis of a Group of Chlorinated Diaryl Sulfonamides: Promising Inhibitors of Cholesteryl Ester Transfer Protein

BACKGROUND

Hyperlipidemia is characterized by an abnormally elevated serum cholesterol, triglycerides, or both. The relationship between an elevated level of LDL and cardiovascular diseases is well-established. Cholesteryl ester transfer protein (CETP) is an enzyme that moves cholesterol esters and triglycerides between LDL, VLDL, and HDL. CETP inhibition leads to a reduction in cardiovascular disease by raising HDL and minimizing LDL.

OBJECTIVE

This study synthesized ten meta-chlorinated benzene sulfonamides 6a-6j and explored their structure-activity relationship.

METHODS

The synthesized molecules were characterized using 1H-NMR, 13C-NMR, IR, and HR-MS. Moreover, cheminformatics analyses included pharmacophore mapping, LibDock studies, and cheminformatics characterization using 2-dimensional (2D) molecular descriptors and principal component analysis.

RESULTS

Based on in vitro functional CETP assays, compounds 6e, 6i, and 6j demonstrated the strongest inhibitory activities against CETP, reaching 100% inhibition. The inhibitory activity of compounds 6a-6d and 6f-6h ranged from 47.5% to 96.5% at 10 μM concentration. Pharmacophore mapping results suggested CETP inhibitory action, while the docking scores and calculated binding energies predicted favoring binding at the CETP active site. Best-scoring docking poses predicted critical hydrophobic features corresponding to key interactions with His232 and Cys13. Cheminformatics analysis using 2D molecular descriptors indicated that the synthesized compounds span various physicochemical properties and drug-likeness.

CONCLUSION

It was found that a chloro moiety at the ortho-position, or a nitro group at the meta and para-positions, improves the CETP inhibitory activity of synthesized analogs. Computational studies suggest the formation of stable ligand-protein complexes between compounds 6a- 6j and CETP.

Difficulty in chirality recognition for Transformer architectures learning chemical structures from string representations

Recent years have seen rapid development of descriptor generation based on representation learning of extremely diverse molecules, especially those that apply natural language processing (NLP) models to SMILES, a literal representation of molecular structure. However, little research has been done on how these models understand chemical structure. To address this black box, we investigated the relationship between the learning progress of SMILES and chemical structure using a representative NLP model, the Transformer. We show that while the Transformer learns partial structures of molecules quickly, it requires extended training to understand overall structures. Consistently, the accuracy of molecular property predictions using descriptors generated from models at different learning steps was similar from the beginning to the end of training. Furthermore, we found that the Transformer requires particularly long training to learn chirality and sometimes stagnates with low performance due to misunderstanding of enantiomers. These findings are expected to deepen the understanding of NLP models in chemistry.

Calculating Pairwise Similarity of Polymer Ensembles via Earth Mover's Distance

Synthetic polymers, in contrast to small molecules and deterministic biomacromolecules, are typically ensembles composed of polymer chains with varying numbers, lengths, sequences, chemistry, and topologies. While numerous approaches exist for measuring pairwise similarity among small molecules and sequence-defined biomacromolecules, accurately determining the pairwise similarity between two polymer ensembles remains challenging. This work proposes the earth mover's distance (EMD) metric to calculate the pairwise similarity score between two polymer ensembles. EMD offers a greater resolution of chemical differences between polymer ensembles than the averaging method and provides a quantitative numeric value representing the pairwise similarity between polymer ensembles in alignment with chemical intuition. The EMD approach for assessing polymer similarity enhances the development of accurate chemical search algorithms within polymer databases and can improve machine learning techniques for polymer design, optimization, and property prediction.

A spectroscopic test suggests that fragment ion structure annotations in MS/MS libraries are frequently incorrect

Modern untargeted mass spectrometry (MS) analyses quickly detect and resolve thousands of molecular compounds. Although features are readily annotated with a molecular formula in high-resolution small-molecule MS applications, the large majority of them remains unidentified in terms of their full molecular structure. Collision-induced dissociation tandem mass spectrometry (CID-MS2) provides a diagnostic molecular fingerprint to resolve the molecular structure through a library search. However, for de novo identifications, one must often rely on in silico generated MS2 spectra as reference. The ability of different in silico algorithms to correctly predict MS2 spectra and thus to retrieve correct molecular structures is a topic of lively debate, for instance in the CASMI contest. Underlying the predicted MS2 spectra are the in silico generated product ion structures, which are normally not used in de novo identification, but which can serve to critically assess the fragmentation algorithms. Here we evaluate in silico generated MSn product ion structures by comparison with structures established experimentally by infrared ion spectroscopy (IRIS). For a set of three dozen product ion structures from five precursor molecules, we find that virtually all fragment ion structure annotations in three major in silico MS2 libraries (HMDB, METLIN, mzCloud) are incorrect and caution the reader against their use for structure annotation of MS/MS ions.

Implementation of FAIR Practices in Computational Metabolomics Workflows-A Case Study

Scientific workflows facilitate the automation of data analysis tasks by integrating various software and tools executed in a particular order. To enable transparency and reusability in workflows, it is essential to implement the FAIR principles. Here, we describe our experiences implementing the FAIR principles for metabolomics workflows using the Metabolome Annotation Workflow (MAW) as a case study. MAW is specified using the Common Workflow Language (CWL), allowing for the subsequent execution of the workflow on different workflow engines. MAW is registered using a CWL description on WorkflowHub. During the submission process on WorkflowHub, a CWL description is used for packaging MAW using the Workflow RO-Crate profile, which includes metadata in Bioschemas. Researchers can use this narrative discussion as a guideline to commence using FAIR practices for their bioinformatics or cheminformatics workflows while incorporating necessary amendments specific to their research area.

An integrated self-optimizing programmable chemical synthesis and reaction engine

Robotic platforms for chemistry are developing rapidly but most systems are not currently able to adapt to changing circumstances in real-time. We present a dynamically programmable system capable of making, optimizing, and discovering new molecules which utilizes seven sensors that continuously monitor the reaction. By developing a dynamic programming language, we demonstrate the 10-fold scale-up of a highly exothermic oxidation reaction, end point detection, as well as detecting critical hardware failures. We also show how the use of in-line spectroscopy such as HPLC, Raman, and NMR can be used for closed-loop optimization of reactions, exemplified using Van Leusen oxazole synthesis, a four-component Ugi condensation and manganese-catalysed epoxidation reactions, as well as two previously unreported reactions, discovered from a selected chemical space, providing up to 50% yield improvement over 25-50 iterations. Finally, we demonstrate an experimental pipeline to explore a trifluoromethylations reaction space, that discovers new molecules.

Synthesis, docking, MD simulation, ADMET, drug likeness, and DFT studies of novel furo[2,3-b]indol-3a-ol as promising Cyclin-dependent kinase 2 inhibitors

A new series of furo[2,3-b]indol-3a-ol derivatives was synthesized to investigate their potential as inhibitors of the Cyclin-dependent kinase 2 (CDK2) enzyme. CDK2 is a serine/threonine protein kinase belonging to a family of kinases involved in the control of the cell cycle. Based on results from clinical studies, it has been shown that overexpression of CDK2 may play a role in the development of cancer. In order to discover highly effective derivatives, a process of in silico screening was carried out. The obtained results revealed that compound 3f. had excellent binding energies. In this study, in silico screening was used to investigate protein-ligand interactions and assess the stability of the most favorable conformation. The methods utilized included molecular docking, density functional theory (DFT) calculations using the B3LYP/6-31++G(d,p) basis set in the gas phase, molecular dynamic (MD) simulation, as well as the evaluation of drug-likeness scores. The pharmacokinetic and drug-likeness properties of the novel furo[2,3-b]indol-3a-ol derivatives suggest that these compounds have the potential to be considered viable candidates for future development as anticancer drugs.

SQM2.20: Semiempirical quantum-mechanical scoring function yields DFT-quality protein-ligand binding affinity predictions in minutes

Accurate estimation of protein-ligand binding affinity is the cornerstone of computer-aided drug design. We present a universal physics-based scoring function, named SQM2.20, addressing key terms of binding free energy using semiempirical quantum-mechanical computational methods. SQM2.20 incorporates the latest methodological advances while remaining computationally efficient even for systems with thousands of atoms. To validate it rigorously, we have compiled and made available the PL-REX benchmark dataset consisting of high-resolution crystal structures and reliable experimental affinities for ten diverse protein targets. Comparative assessments demonstrate that SQM2.20 outperforms other scoring methods and reaches a level of accuracy similar to much more expensive DFT calculations. In the PL-REX dataset, it achieves excellent correlation with experimental data (average R2 = 0.69) and exhibits consistent performance across all targets. In contrast to DFT, SQM2.20 provides affinity predictions in minutes, making it suitable for practical applications in hit identification or lead optimization.

Valorization potential of Egyptian mango kernel waste product as analyzed via GC/MS metabolites profiling from different cultivars and geographical origins

Increasing attention has been given to mango (Mangifera indica) fruits owing to their characteristic taste, and rich nutritional value. Mango kernels are typically discarded as a major waste product in mango industry, though of potential economic value. The present study aims to outline the first comparison of different mango kernel cvs. originated from different localities alongside Egypt, e.g., Sharqia, Suez, Ismailia, and Giza. Gas chromatography-mass spectroscopy (GC-MS) post silylation analysis revealed that sugars were the major class being detected at 3.5-290.9 µg/mg, with some kernels originating from Sharqia province being the richest amongst other cvs. In consistency with sugar results, sugar alcohols predominated in Sharqia cvs. at 1.3-38.1 µg/mg represented by ribitol, iditol, pinitol, and myo-inositol. No major variation was observed in the fatty acids profile either based on cv. type or localities, with butyl caprylate as a major component in most cvs. identified for the first time in mango. Regarding phenolics, Sedeeq cv. represented the highest level at 18.3 µg/mg and showing distinct variation among cvs. posing phenolics as better classification markers than sugars. Multivariate data analyses (MVA) confirmed that the premium cvs "Aweis and Fons" were less enriched in sugars, i.e., fructose, talose, and glucose compared to the other cvs. Moreover, MVA of Zabdeya cv. collected from three localities revealed clear segregation to be chemically distinct. Sharqia originated mango kernels were rich in sugars (e.g., glucose and fructose), whilst sarcosine esters predominated in other origins.

Exploring the combinatorial explosion of amine-acid reaction space via graph editing

Amines and carboxylic acids are abundant chemical feedstocks that are nearly exclusively united via the amide coupling reaction. The disproportionate use of the amide coupling leaves a large section of unexplored reaction space between amines and acids: two of the most common chemical building blocks. Herein we conduct a thorough exploration of amine-acid reaction space via systematic enumeration of reactions involving a simple amine-carboxylic acid pair. This approach to chemical space exploration investigates the coarse and fine modulation of physicochemical properties and molecular shapes. With the invention of reaction methods becoming increasingly automated and bringing conceptual reactions into reality, our map provides an entirely new axis of chemical space exploration for rational property design.

Reverse metabolomics for the discovery of chemical structures from humans

Determining the structure and phenotypic context of molecules detected in untargeted metabolomics experiments remains challenging. Here we present reverse metabolomics as a discovery strategy, whereby tandem mass spectrometry spectra acquired from newly synthesized compounds are searched for in public metabolomics datasets to uncover phenotypic associations. To demonstrate the concept, we broadly synthesized and explored multiple classes of metabolites in humans, including N-acyl amides, fatty acid esters of hydroxy fatty acids, bile acid esters and conjugated bile acids. Using repository-scale analysis1,2, we discovered that some conjugated bile acids are associated with inflammatory bowel disease (IBD). Validation using four distinct human IBD cohorts showed that cholic acids conjugated to Glu, Ile/Leu, Phe, Thr, Trp or Tyr are increased in Crohn's disease. Several of these compounds and related structures affected pathways associated with IBD, such as interferon-γ production in CD4+ T cells3 and agonism of the pregnane X receptor4. Culture of bacteria belonging to the Bifidobacterium, Clostridium and Enterococcus genera produced these bile amidates. Because searching repositories with tandem mass spectrometry spectra has only recently become possible, this reverse metabolomics approach can now be used as a general strategy to discover other molecules from human and animal ecosystems.

Gas adsorption meets deep learning: voxelizing the potential energy surface of metal-organic frameworks

Intrinsic properties of metal-organic frameworks (MOFs), such as their ultra porosity and high surface area, deem them promising solutions for problems involving gas adsorption. Nevertheless, due to their combinatorial nature, a huge number of structures is feasible which renders cumbersome the selection of the best candidates with traditional techniques. Recently, machine learning approaches have emerged as efficient tools to deal with this challenge, by allowing researchers to rapidly screen large databases of MOFs via predictive models. The performance of the latter is tightly tied to the mathematical representation of a material, thus necessitating the use of informative descriptors. In this work, a generalized framework to predict gaseous adsorption properties is presented, using as one and only descriptor the capstone of chemical information: the potential energy surface (PES). In order to be machine understandable, the PES is voxelized and subsequently a 3D convolutional neural network (CNN) is exploited to process this 3D energy image. As a proof of concept, the proposed pipeline is applied on predicting [Formula: see text] uptake in MOFs. The resulting model outperforms a conventional model built with geometric descriptors and requires two orders of magnitude less training data to reach a given level of performance. Moreover, the transferability of the approach to different host-guest systems is demonstrated, examining [Formula: see text] uptake in COFs. The generic character of the proposed methodology, inherited from the PES, renders it applicable to fields other than reticular chemistry.

Paving the road towards automated homogeneous catalyst design

In the past decade, computational tools have become integral to catalyst design. They continue to offer significant support to experimental organic synthesis and catalysis researchers aiming for optimal reaction outcomes. More recently, data-driven approaches utilizing machine learning have garnered considerable attention for their expansive capabilities. This Perspective provides an overview of diverse initiatives in the realm of computational catalyst design and introduces our automated tools tailored for high-throughput in silico exploration of the chemical space. While valuable insights are gained through methods for high-throughput in silico exploration and analysis of chemical space, their degree of automation and modularity are key. We argue that the integration of data-driven, automated and modular workflows is key to enhancing homogeneous catalyst design on an unprecedented scale, contributing to the advancement of catalysis research.

Advanced chemometric methods for simultaneous quantitation of caffeine, codeine, paracetamol, and p-aminophenol in their quaternary mixture

Two different multivariate techniques have been applied for the quantitative analysis of caffeine, codeine, paracetamol and p-aminophenol (PAP) in quaternary mixture, namely, Partial Least Squares (PLS-1) and Artificial Neural Networks (ANN). For suitable analysis, a calibration set of 25 mixtures with various ratios of the drugs and PAP impurity were established using a 4-factor 5-level experimental design. The most meaningful wavelengths for the chemometric models were chosen using Genetic Algorithm (GA) as a variable selection technique. By using an independent validation set, the validity of the proposed methods was evaluated. A comparative study was established between the three multivariate models (PLS-1, GA-PLS and GA-ANN). The comparison between the various models revealed that the GA-ANN model was superior at resolving the highly overlapped spectra of this quaternary combination. The drugs were successfully quantified in their pharmaceutical dosage form utilizing the GA-ANN models.

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

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

A database of thermally activated delayed fluorescent molecules auto-generated from scientific literature with ChemDataExtractor

A database of thermally activated delayed fluorescent (TADF) molecules was automatically generated from the scientific literature. It consists of 25,482 data records with an overall precision of 82%. Among these, 5,349 records have chemical names in the form of SMILES strings which are represented with 91% accuracy; these are grouped in a subsidiary database. Each data record contains one of the following four properties: maximum emission wavelength (λEM), photoluminescence quantum yield (PLQY), singlet-triplet energy splitting (ΔEST), and delayed lifetime (τD). The databases were created through text mining using ChemDataExtractor, a chemistry-aware natural-language-processing toolkit, which has been adapted for TADF research. The text-mined corpus consisted of 2,733 papers from the Royal Society of Chemistry and Elsevier. To the best of our knowledge, these databases are the first databases that have been auto-generated for TADF molecules from existing publications. The databases have been publicly released for experimental and computational applications in the TADF research field.

Predictive Minisci late stage functionalization with transfer learning

Structural diversification of lead molecules is a key component of drug discovery to explore chemical space. Late-stage functionalizations (LSFs) are versatile methodologies capable of installing functional handles on richly decorated intermediates to deliver numerous diverse products in a single reaction. Predicting the regioselectivity of LSF is still an open challenge in the field. Numerous efforts from chemoinformatics and machine learning (ML) groups have made strides in this area. However, it is arduous to isolate and characterize the multitude of LSF products generated, limiting available data and hindering pure ML approaches. We report the development of an approach that combines a message passing neural network and 13C NMR-based transfer learning to predict the atom-wise probabilities of functionalization for Minisci and P450-based functionalizations. We validated our model both retrospectively and with a series of prospective experiments, showing that it accurately predicts the outcomes of Minisci-type and P450 transformations and outperforms the well-established Fukui-based reactivity indices and other machine learning reactivity-based algorithms.

MolOptimizer: A Molecular Optimization Toolkit for Fragment-Based Drug Design

MolOptimizer is a user-friendly computational toolkit designed to streamline the hit-to-lead optimization process in drug discovery. MolOptimizer extracts features and trains machine learning models using a user-provided, labeled, and small-molecule dataset to accurately predict the binding values of new small molecules that share similar scaffolds with the target in focus. Hosted on the Azure web-based server, MolOptimizer emerges as a vital resource, accelerating the discovery and development of novel drug candidates with improved binding properties.

StackER: a novel SMILES-based stacked approach for the accelerated and efficient discovery of ERα and ERβ antagonists

The role of estrogen receptors (ERs) in breast cancer is of great importance in both clinical practice and scientific exploration. However, around 15-30% of those affected do not see benefits from the usual treatments owing to the innate resistance mechanisms, while 30-40% will gain resistance through treatments. In order to address this problem and facilitate community-wide efforts, machine learning (ML)-based approaches are considered one of the most cost-effective and large-scale identification methods. Herein, we propose a new SMILES-based stacked approach, termed StackER, for the accelerated and efficient identification of ERα and ERβ inhibitors. In StackER, we first established an up-to-date dataset consisting of 1,996 and 1,207 compounds for ERα and ERβ, respectively. Using the up-to-date dataset, StackER explored a wide range of different SMILES-based feature descriptors and ML algorithms in order to generate probabilistic features (PFs). Finally, the selected PFs derived from the two-step feature selection strategy were used for the development of an efficient stacked model. Both cross-validation and independent tests showed that StackER surpassed several conventional ML classifiers and the existing method in precisely predicting ERα and ERβ inhibitors. Remarkably, StackER achieved MCC values of 0.829-0.847 and 0.712-0.786 in terms of the cross-validation and independent tests, respectively, which were 5.92-8.29 and 1.59-3.45% higher than the existing method. In addition, StackER was applied to determine useful features for being ERα and ERβ inhibitors and identify FDA-approved drugs as potential ERα inhibitors in efforts to facilitate drug repurposing. This innovative stacked method is anticipated to facilitate community-wide efforts in efficiently narrowing down ER inhibitor screening.

Unveiling the Potent Antiviral and Antioxidant Activities of an Aqueous Extract from Caesalpinia mimosoides Lamk: Cheminformatics and Molecular Docking Approaches

Our group previously demonstrated that Caesalpinia mimosoides Lamk exhibits many profound biological properties, including anticancer, antibacterial, and antioxidant activities. However, its antiviral activity has not yet been investigated. Here, the aqueous extract of C. mimosoides was prepared from the aerial parts (leaves, stalks, and trunks) to see whether it exerts anti-influenza (H1N1) effects and to reduce the organic solvents consumed during extraction, making it a desirable approach for the large-scale production for medical uses. Our plant extract was quantified to contain 7 g of gallic acid (GA) per 100 g of a dry sample, as determined using HPLC analysis. It also exerts potent antioxidant activities comparable to those of authentic GA. According to untargeted metabolomics (UPLC-ESI(-)-QTOF-MS/MS) with the aid of cheminformatics tools (MetFrag (version 2.1), SIRIUS (version 5.8.3), CSI:FingerID (version 4.8), and CANOPUS), the major metabolite was best annotated as "gallic acid", phenolics (e.g., quinic acid, shikimic acid, and protocatechuic acid), sugar derivatives, and dicarboxylic acids were deduced from this plant species for the first time. The aqueous plant extract efficiently inhibited an influenza A (H1N1) virus infection of MDCK cells with an IC50 of 5.14 µg/mL. Of equal importance, hemolytic activity was absent for this plant extract, signifying its applicability as a safe antiviral agent. Molecular docking suggested that GA interacts with conserved residues (e.g., Arg152 and Asp151) located in the catalytic inner shell of the viral neuraminidase (NA), sharing the same pocket as those of anti-neuraminidase drugs, such as laninamivir and oseltamivir. Additionally, other metabolites were also found to potentially interact with the active site and the hydrophobic 430-cavity of the viral surface protein, suggesting a possibly synergistic effect of various phytochemicals. Therefore, the C. mimosoides aqueous extract may be a good candidate for coping with increasing influenza virus resistance to existing antivirals.

A peptide derived from interleukin-10 exhibits potential anticancer activity and can facilitate cell targeting of gold nanoparticles loaded with anticancer therapeutics

Human interleukin-10 (IL-10) is an immunosuppressive and anti-inflammatory cytokine, and its expression is upregulated in tumor tissues and serum samples of patients with various cancers. Because of its immunosuppressive nature, IL-10 has also been suggested to be a factor leading to tumor cells' evasion of immune surveillance and clearance by the host immune system. In this study, we refined a peptide with 20 amino acids, named NK20a, derived from the binding region of IL-10 on the basis of in silico analysis of the complex structure of IL-10 with IL-10Ra, the ligand binding subunit of the IL-10 receptor. The binding ability of the peptide was confirmed through in vitro biophysical biolayer interferometry and cellular experiments. The IL-10 inhibitory peptide exerted anticancer effects on lymphoma B cells and could abolish the suppression effect of IL-10 on macrophages. NK20a was also conjugated with gold nanoparticles to target the chemotherapeutic 5-fluorouracil (5-FU)-loaded nanoparticles to enhance the anticancer efficacy of 5-FU against the breast cancer cell line BT-474. Our study demonstrated that NK20a designed in silico with improved binding affinity to the IL-10 receptor can be used as a tool in developing anticancer strategies.

Morpho-chemical characterization of individual ancient starches retrieved on ground stone tools from Palaeolithic sites in the Pontic steppe

Despite the extensive literature on the retrieval of digestible starches from archaeological contexts, there are still significant concerns regarding their genuine origin and durability. Here, we propose a multi-analytical strategy to identify the authenticity of ancient starches retrieved from macrolithic tools excavated at Upper Paleolithic sites in the Pontic steppe. This strategy integrates the morphological discrimination of starches through optical microscopy and scanning electron microscopy with single starch chemo-profiling using Fourier transform infrared imaging and microscopy. We obtained evidence of aging and biomineralization in the use-related starches from Palaeolithic sites, providing a methodology to establish their ancient origin, assess their preservation status, and attempt their identification. The pivotal application of this multidisciplinar approach demonstrates that the macrolithic tools, from which starches were dislodged, were used for food-processing across the Pontic Steppe around 40,000 years ago during the earliest colonization of Eurasia by Homo sapiens.

Modelling local and general quantum mechanical properties with attention-based pooling

Atom-centred neural networks represent the state-of-the-art for approximating the quantum chemical properties of molecules, such as internal energies. While the design of machine learning architectures that respect chemical principles has continued to advance, the final atom pooling operation that is necessary to convert from atomic to molecular representations in most models remains relatively undeveloped. The most common choices, sum and average pooling, compute molecular representations that are naturally a good fit for many physical properties, while satisfying properties such as permutation invariance which are desirable from a geometric deep learning perspective. However, there are growing concerns that such simplistic functions might have limited representational power, while also being suboptimal for physical properties that are highly localised or intensive. Based on recent advances in graph representation learning, we investigate the use of a learnable pooling function that leverages an attention mechanism to model interactions between atom representations. The proposed pooling operation is a drop-in replacement requiring no changes to any of the other architectural components. Using SchNet and DimeNet++ as starting models, we demonstrate consistent uplifts in performance compared to sum and mean pooling and a recent physics-aware pooling operation designed specifically for orbital energies, on several datasets, properties, and levels of theory, with up to 85% improvements depending on the specific task.

Identifying opportunities for late-stage C-H alkylation with high-throughput experimentation and in silico reaction screening

Enhancing the properties of advanced drug candidates is aided by the direct incorporation of specific chemical groups, avoiding the need to construct the entire compound from the ground up. Nevertheless, their chemical intricacy often poses challenges in predicting reactivity for C-H activation reactions and planning their synthesis. We adopted a reaction screening approach that combines high-throughput experimentation (HTE) at a nanomolar scale with computational graph neural networks (GNNs). This approach aims to identify suitable substrates for late-stage C-H alkylation using Minisci-type chemistry. GNNs were trained using experimentally generated reactions derived from in-house HTE and literature data. These trained models were then used to predict, in a forward-looking manner, the coupling of 3180 advanced heterocyclic building blocks with a diverse set of sp3-rich carboxylic acids. This predictive approach aimed to explore the substrate landscape for Minisci-type alkylations. Promising candidates were chosen, their production was scaled up, and they were subsequently isolated and characterized. This process led to the creation of 30 novel, functionally modified molecules that hold potential for further refinement. These results positively advocate the application of HTE-based machine learning to virtual reaction screening.

On-tissue dataset-dependent MALDI-TIMS-MS2 bioimaging

Trapped ion mobility spectrometry (TIMS) adds an additional separation dimension to mass spectrometry (MS) imaging, however, the lack of fragmentation spectra (MS2) impedes confident compound annotation in spatial metabolomics. Here, we describe spatial ion mobility-scheduled exhaustive fragmentation (SIMSEF), a dataset-dependent acquisition strategy that augments TIMS-MS imaging datasets with MS2 spectra. The fragmentation experiments are systematically distributed across the sample and scheduled for multiple collision energies per precursor ion. Extendable data processing and evaluation workflows are implemented into the open source software MZmine. The workflow and annotation capabilities are demonstrated on rat brain tissue thin sections, measured by matrix-assisted laser desorption/ionisation (MALDI)-TIMS-MS, where SIMSEF enables on-tissue compound annotation through spectral library matching and rule-based lipid annotation within MZmine and maps the (un)known chemical space by molecular networking. The SIMSEF algorithm and data analysis pipelines are open source and modular to provide a community resource.

Variational autoencoder-based chemical latent space for large molecular structures with 3D complexity

The structural diversity of chemical libraries, which are systematic collections of compounds that have potential to bind to biomolecules, can be represented by chemical latent space. A chemical latent space is a projection of a compound structure into a mathematical space based on several molecular features, and it can express structural diversity within a compound library in order to explore a broader chemical space and generate novel compound structures for drug candidates. In this study, we developed a deep-learning method, called NP-VAE (Natural Product-oriented Variational Autoencoder), based on variational autoencoder for managing hard-to-analyze datasets from DrugBank and large molecular structures such as natural compounds with chirality, an essential factor in the 3D complexity of compounds. NP-VAE was successful in constructing the chemical latent space from large-sized compounds that were unable to be handled in existing methods, achieving higher reconstruction accuracy, and demonstrating stable performance as a generative model across various indices. Furthermore, by exploring the acquired latent space, we succeeded in comprehensively analyzing a compound library containing natural compounds and generating novel compound structures with optimized functions.

Deep learning workflow for the inverse design of molecules with specific optoelectronic properties

The inverse design of novel molecules with a desirable optoelectronic property requires consideration of the vast chemical spaces associated with varying chemical composition and molecular size. First principles-based property predictions have become increasingly helpful for assisting the selection of promising candidate chemical species for subsequent experimental validation. However, a brute-force computational screening of the entire chemical space is decidedly impossible. To alleviate the computational burden and accelerate rational molecular design, we here present an iterative deep learning workflow that combines (i) the density-functional tight-binding method for dynamic generation of property training data, (ii) a graph convolutional neural network surrogate model for rapid and reliable predictions of chemical and physical properties, and (iii) a masked language model. As proof of principle, we employ our workflow in the iterative generation of novel molecules with a target energy gap between the highest occupied molecular orbital (HOMO) and the lowest unoccupied molecular orbital (LUMO).

Developing a class of dual atom materials for multifunctional catalytic reactions

Dual atom catalysts, bridging single atom and metal/alloy nanoparticle catalysts, offer more opportunities to enhance the kinetics and multifunctional performance of oxygen reduction/evolution and hydrogen evolution reactions. However, the rational design of efficient multifunctional dual atom catalysts remains a blind area and is challenging. In this study, we achieved controllable regulation from Co nanoparticles to CoN4 single atoms to Co2N5 dual atoms using an atomization and sintering strategy via an N-stripping and thermal-migrating process. More importantly, this strategy could be extended to the fabrication of 22 distinct dual atom catalysts. In particular, the Co2N5 dual atom with tailored spin states could achieve ideally balanced adsorption/desorption of intermediates, thus realizing superior multifunctional activity. In addition, it endows Zn-air batteries with long-term stability for 800 h, allows water splitting to continuously operate for 1000 h, and can enable solar-powered water splitting systems with uninterrupted large-scale hydrogen production throughout day and night. This universal and scalable strategy provides opportunities for the controlled design of efficient multifunctional dual atom catalysts in energy conversion technologies.

MultiXC-QM9: Large dataset of molecular and reaction energies from multi-level quantum chemical methods

Well curated extensive datasets have helped spur intense molecular machine learning (ML) method development activities over the last few years, encouraging nonchemists to be part of the effort as well. QM9 dataset is one of the benchmark databases for small molecules with molecular energies based on B3LYP functional. G4MP2 based energies of these molecules were published later. To enable a wide variety of ML tasks like transfer learning, delta learning, multitask learning, etc. with QM9 molecules, in this article, we introduce a new dataset with QM9 molecule energies estimated with 76 different DFT functionals and three different basis sets (228 energy numbers for each molecule). We additionally enumerated all possible A ↔ B monomolecular interconversions within the QM9 dataset and provided the reaction energies based on these 76 functionals, and basis sets. Lastly, we also provide the bond changes for all the 162 million reactions with the dataset to enable structure- and bond-based reaction energy prediction tools based on ML.

In vitro and in silico prediction of antibacterial interaction between essential oils via graph embedding approach

Essential oils contain a variety of volatile metabolites, and are expected to be utilized in wide fields such as antimicrobials, insect repellents and herbicides. However, it is difficult to foresee the effect of oil combinations because hundreds of compounds can be involved in synergistic and antagonistic interactions. In this research, it was developed and evaluated a machine learning method to classify types of (synergistic/antagonistic/no) antibacterial interaction between essential oils. Graph embedding was employed to capture structural features of the interaction network from literature data, and was found to improve in silico predicting performances to classify synergistic interactions. Furthermore, in vitro antibacterial assay against a standard strain of Staphylococcus aureus revealed that four essential oil pairs (Origanum compactum-Trachyspermum ammi, Cymbopogon citratus-Thujopsis dolabrata, Cinnamomum verum-Cymbopogon citratus and Trachyspermum ammi-Zingiber officinale) exhibited synergistic interaction as predicted. These results indicate that graph embedding approach can efficiently find synergistic interactions between antibacterial essential oils.

Extracting medicinal chemistry intuition via preference machine learning

The lead optimization process in drug discovery campaigns is an arduous endeavour where the input of many medicinal chemists is weighed in order to reach a desired molecular property profile. Building the expertise to successfully drive such projects collaboratively is a very time-consuming process that typically spans many years within a chemist's career. In this work we aim to replicate this process by applying artificial intelligence learning-to-rank techniques on feedback that was obtained from 35 chemists at Novartis over the course of several months. We exemplify the usefulness of the learned proxies in routine tasks such as compound prioritization, motif rationalization, and biased de novo drug design. Annotated response data is provided, and developed models and code made available through a permissive open-source license.

Artificial Intelligence/Machine Learning-Driven Small Molecule Repurposing via Off-Target Prediction and Transcriptomics

The process of discovering small molecule drugs involves screening numerous compounds and optimizing the most promising ones, both in vitro and in vivo. However, approximately 90% of these optimized candidates fail during trials due to unexpected toxicity or insufficient efficacy. Current concepts with respect to drug-protein interactions suggest that each small molecule interacts with an average of 6-11 targets. This implies that approved drugs and even discontinued compounds could be repurposed by leveraging their interactions with unintended targets. Therefore, we developed a computational repurposing framework for small molecules, which combines artificial intelligence/machine learning (AI/ML)-based and chemical similarity-based target prediction methods with cross-species transcriptomics information. This repurposing methodology incorporates eight distinct target prediction methods, including three machine learning methods. By using multiple orthogonal methods for a "dataset" composed of 2766 FDA-approved drugs targeting multiple therapeutic target classes, we identified 27,371 off-target interactions involving 2013 protein targets (i.e., an average of around 10 interactions per drug). Relative to the drugs in the dataset, we identified 150,620 structurally similar compounds. The highest number of predicted interactions were for drugs targeting G protein-coupled receptors (GPCRs), enzymes, and kinases with 10,648, 4081, and 3678 interactions, respectively. Notably, 17,283 (63%) of the off-target interactions have been confirmed in vitro. Approximately 4000 interactions had an IC50 of <100 nM for 1105 FDA-approved drugs and 1661 interactions had an IC50 of <10 nM for 696 FDA-approved drugs. Together, the confirmation of numerous predicted interactions and the exploration of tissue-specific expression patterns in human and animal tissues offer insights into potential drug repurposing for new therapeutic applications.

Rationalizing general limitations in assessing and comparing methods for compound potency prediction

Compound potency predictions play a major role in computational drug discovery. Predictive methods are typically evaluated and compared in benchmark calculations that are widely applied. Previous studies have revealed intrinsic limitations of potency prediction benchmarks including very similar performance of increasingly complex machine learning methods and simple controls and narrow error margins separating machine learning from randomized predictions. However, origins of these limitations are currently unknown. We have carried out an in-depth analysis of potential reasons leading to artificial outcomes of potency predictions using different methods. Potency predictions on activity classes typically used in benchmark settings were found to be determined by compounds with intermediate potency close to median values of the compound data sets. The potency of these compounds was consistently predicted with high accuracy, without the need for learning, which dominated the results of benchmark calculations, regardless of the activity classes used. Taken together, our findings provide a clear rationale for general limitations of compound potency benchmark predictions and a basis for the design of alternative test systems for methodological comparisons.

The maximal and current accuracy of rigorous protein-ligand binding free energy calculations

Computational techniques can speed up the identification of hits and accelerate the development of candidate molecules for drug discovery. Among techniques for predicting relative binding affinities, the most consistently accurate is free energy perturbation (FEP), a class of rigorous physics-based methods. However, uncertainty remains about how accurate FEP is and can ever be. Here, we present what we believe to be the largest publicly available dataset of proteins and congeneric series of small molecules, and assess the accuracy of the leading FEP workflow. To ascertain the limit of achievable accuracy, we also survey the reproducibility of experimental relative affinity measurements. We find a wide variability in experimental accuracy and a correspondence between binding and functional assays. When careful preparation of protein and ligand structures is undertaken, FEP can achieve accuracy comparable to experimental reproducibility. Throughout, we highlight reliable protocols that can help maximize the accuracy of FEP in prospective studies.

Limitations of representation learning in small molecule property prediction

Machine learning is a powerful tool for the study and design of molecules. Here the authors comment a recent publication in Nature Communications which highlights the challenges of different molecular representations for data-driven property predictions.

A systematic study of key elements underlying molecular property prediction

Artificial intelligence (AI) has been widely applied in drug discovery with a major task as molecular property prediction. Despite booming techniques in molecular representation learning, key elements underlying molecular property prediction remain largely unexplored, which impedes further advancements in this field. Herein, we conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets, a suite of opioids-related datasets and two additional activity datasets from the literature. To investigate the predictive power in low-data and high-data space, a series of descriptors datasets of varying sizes are also assembled to evaluate the models. In total, we have trained 62,820 models, including 50,220 models on fixed representations, 4200 models on SMILES sequences and 8400 models on molecular graphs. Based on extensive experimentation and rigorous comparison, we show that representation learning models exhibit limited performance in molecular property prediction in most datasets. Besides, multiple key elements underlying molecular property prediction can affect the evaluation results. Furthermore, we show that activity cliffs can significantly impact model prediction. Finally, we explore into potential causes why representation learning models can fail and show that dataset size is essential for representation learning models to excel.

Entropy analysis of nickel(II) porphyrins network via curve fitting techniques

Nickel(II) porphyrins typically adopt a square planar coordination geometry, with the nickel atom located at the center of the porphyrin ring and the coordinating atoms arranged in a square plane. The additional atoms or groups coordinated to the nickel atom in nickel(II) porphyrins are called ligands. Porphyrins have been investigated as potential agents for imaging and treating cancer due to their ability to selectively bind to tumor cells and be used as sensors for a variety of analytes. Nickel(II) porphyrins are relatively stable compounds, with high thermal and chemical stability. They can be stored in a solid state or in solution without significant degradation. In this study, we compute several connectivity indices, such as general Randi'c, hyper Zagreb, and redefined Zagreb indices, based on the degrees of vertices of the chemical graph of nickel porphyrins. Then, we compute the entropy and heat of formation NiP production, among other physical parameters. Using MATLAB, we fit curves between various indices and the thermodynamic properties parameters, notably the heat of formation and entropy, using various linearity- and non-linearity-based approaches. The method's effectiveness is evaluated using [Formula: see text], the sum of squared errors, and root mean square error. We also provide visual representations of these indexes. These mathematical frameworks might offer a mechanism to investigate the thermodynamical characteristics of NiP's chemical structure under various circumstances, which will help us understand the connection between system dimensions and these metrics.

Drawing a materials map with an autoencoder for lithium ionic conductors

Efforts to optimize known materials and enhance their performance are ongoing, driven by the advancements resulting from the discovery of novel functional materials. Traditionally, the search for and optimization of functional materials has relied on the experience and intuition of specialized researchers. However, materials informatics (MI), which integrates materials data and machine learning, has frequently been used to realize systematic and efficient materials exploration without depending on manual tasks. Nonetheless, the discovery of new materials using MI remains challenging. In this study, we propose a method for the discovery of materials outside the scope of existing databases by combining MI with the experience and intuition of researchers. Specifically, we designed a two-dimensional map that plots known materials data based on their composition and structure, facilitating researchers' intuitive search for new materials. The materials map was implemented using an autoencoder-based neural network. We focused on the conductivity of 708 lithium oxide materials and considered the correlation with migration energy (ME), an index of lithium-ion conductivity. The distribution of existing data reflected in the materials map can contribute to the development of new lithium-ion conductive materials by enhancing the experience and intuition of material researchers.

Retrosynthesis prediction with an interpretable deep-learning framework based on molecular assembly tasks

Automating retrosynthesis with artificial intelligence expedites organic chemistry research in digital laboratories. However, most existing deep-learning approaches are hard to explain, like a "black box" with few insights. Here, we propose RetroExplainer, formulizing the retrosynthesis task into a molecular assembly process, containing several retrosynthetic actions guided by deep learning. To guarantee a robust performance of our model, we propose three units: a multi-sense and multi-scale Graph Transformer, structure-aware contrastive learning, and dynamic adaptive multi-task learning. The results on 12 large-scale benchmark datasets demonstrate the effectiveness of RetroExplainer, which outperforms the state-of-the-art single-step retrosynthesis approaches. In addition, the molecular assembly process renders our model with good interpretability, allowing for transparent decision-making and quantitative attribution. When extended to multi-step retrosynthesis planning, RetroExplainer has identified 101 pathways, in which 86.9% of the single reactions correspond to those already reported in the literature. As a result, RetroExplainer is expected to offer valuable insights for reliable, high-throughput, and high-quality organic synthesis in drug development.