Search

Background: Peru is one of the most biodiverse countries in the world, which is reflected in its wealth of knowledge about medicinal plants. However, there is a lack of information regarding intestinal absorption and the permeability of natural products. The human colon adenocarcinoma cell line (Caco-2) is an in vitro assay used to measure apparent permeability. This study aims to develop a quantitative structure–property relationship (QSPR) model using machine learning algorithms to predict the apparent permeability of the Caco-2 cell in natural products from Peru. Methods: A dataset of 1817 compounds, including experimental log Papp values and molecular descriptors, was utilized. Six QSPR models were constructed: a multiple linear regression (MLR) model, a partial least squares regression (PLS) model, a support vector machine regression (SVM) model, a random forest (RF) model, a gradient boosting machine (GBM) model, and an SVM–RF–GBM model. Results: An evaluation of the testing set revealed that the MLR and PLS models exhibited an RMSE = 0.47 and R2 = 0.63. In contrast, the SVM, RF, and GBM models showcased an RMSE = 0.39–0.40 and R2 = 0.73–0.74. Notably, the SVM–RF–GBM model demonstrated superior performance, with an RMSE = 0.38 and R2 = 0.76. The model predicted log Papp values for 502 natural products falling within the applicability domain, with 68.9% (n = 346) showing high permeability, suggesting the potential for intestinal absorption. Additionally, we categorized the natural products into six metabolic pathways and assessed their drug-likeness. Conclusions: Our results provide insights into the potential intestinal absorption of natural products in Peru, thus facilitating drug development and pharmaceutical discovery efforts. [ABSTRACT FROM AUTHOR]

Molecular descriptors characterize the biological, physical, and chemical properties of molecules and have long been used for understanding molecular interactions and facilitating materials design. Some of the most robust descriptors are derived from geometrical representations of molecules, called 3-dimensional (3D) descriptors. When calculated from molecular dynamics (MD) simulation trajectories, 3D descriptors can also capture the effects of operating conditions such as temperature or pressure. However, extracting 3D descriptors from MD trajectories is non-trivial, which hinders their wide use by researchers developing advanced quantitative-structure-property-relationship models using machine learning. Here, we describe a suite of open-source Python-based post-processing routines, called PyL3dMD, for calculating 3D descriptors from MD simulations. PyL3dMD is compatible with the popular simulation package LAMMPS and enables users to compute more than 2000 3D molecular descriptors from atomic trajectories generated by MD simulations. PyL3dMD is freely available via GitHub and can be easily installed and used as a highly flexible Python package on all major platforms (Windows, Linux, and macOS). A performance benchmark study used descriptors calculated by PyL3dMD to develop a neural network and the results showed that PyL3dMD is fast and efficient in calculating descriptors for large and complex molecular systems with long simulation durations. PyL3dMD facilitates the calculation of 3D molecular descriptors using MD simulations, making it a valuable tool for cheminformatics studies.

We developed a partial least squares regression (PLSR) model based on competitive adaptive reweighted sampling (CARS) to predict the processing factors of 54 pesticides during soybean oil processing. Characteristic variables were selected to improve the performance of the model. Four calculators were used to compute the molecular descriptors used in the model, and the model based on values computed with ChemoPy produced the best results: Rc ​= ​0.94, RMSEc ​= ​0.67, Rp ​= ​0.91, and RMSEp ​= ​0.54 for hot-pressed oil and Rc ​= ​0.93, RMSEc ​= ​0.73, Rp ​= ​0.93, and RMSEp ​= ​0.59 for cold-pressed oil. A rapid and quantitative model of processing factors was established to predict the behaviour and distribution of pesticide residues during food processing. The model was further validated using data from field-grown soybeans; it demonstrated a high correlation coefficient between predicted and measured residue concentrations (Rp ​> ​0.93, RMSEp ​

Abstract Supramolecular chemistry is a fascinating field that explores the interactions between molecules to create higher-order structures. In the case of the supramolecular chain of Fuchsine acid, which is a type of dye molecule, several chemical applications are possible. Fuchsine acid helps to make better medicine carriers that deliver drugs where they’re needed in the body, making treatments more effective and reducing side effects. It also helps create smart materials like sensors and self-fixing plastics, which are useful in electronics, keeping our environment clean, and making new materials. In sensing and detection, the supramolecular chain of Fuchsine acid utilizes as a sensor or detector for specific analyzes. In drug delivery, the supramolecular chains of Fuchsine acid incorporated into drug delivery systems. In recent years, a common method is linking a graph to a chemical structure and using topological descriptors to study it. This technique is becoming increasingly important over time. Topological descriptors gives very useful information while studying the topology of chemical graph. In this paper, we have computed the 3D structure of supramolecular graph of Fuchsine acid. We have computed an explicit expressions of ABC index, GA index, General Randi $$\acute{c}$$ c ´ index, first and second Zagreb index, hyper Zagreb index, H-index and F-index of supramolecular structure of Fushine acid.

Supramolecular chemistry is a fascinating field that explores the interactions between molecules to create higher-order structures. In the case of the supramolecular chain of Fuchsine acid, which is a type of dye molecule, several chemical applications are possible. Fuchsine acid helps to make better medicine carriers that deliver drugs where they’re needed in the body, making treatments more effective and reducing side effects. It also helps create smart materials like sensors and self-fixing plastics, which are useful in electronics, keeping our environment clean, and making new materials. In sensing and detection, the supramolecular chain of Fuchsine acid utilizes as a sensor or detector for specific analyzes. In drug delivery, the supramolecular chains of Fuchsine acid incorporated into drug delivery systems. In recent years, a common method is linking a graph to a chemical structure and using topological descriptors to study it. This technique is becoming increasingly important over time. Topological descriptors gives very useful information while studying the topology of chemical graph. In this paper, we have computed the 3D structure of supramolecular graph of Fuchsine acid. We have computed an explicit expressions of ABC index, GA index, General Randi c ´ index, first and second Zagreb index, hyper Zagreb index, H-index and F-index of supramolecular structure of Fushine acid. [ABSTRACT FROM AUTHOR]

We used the extreme gradient boosting (XGB) algorithm to predict the experimental solubility of chemical compounds in water and organic solvents and to select significant molecular descriptors. The accuracy of prediction of our forward stepwise top-importance XGB (FSTI-XGB) on curated solubility data sets in terms of RMSE was found to be 0.59–0.76 Log(S) for two water data sets, while for organic solvent data sets it was 0.69–0.79 Log(S) for the Methanol data set, 0.65–0.79 for the Ethanol data set, and 0.62–0.70 Log(S) for the Acetone data set. That was the first step. In the second step, we used uncurated and curated AquaSolDB data sets for applicability domain (AD) tests of Drugbank, PubChem, and COCONUT databases and determined that more than 95% of studied ca. 500,000 compounds were within the AD. In the third step, we applied conformal prediction to obtain narrow prediction intervals and we successfully validated them using test sets' true solubility values. With prediction intervals obtained in the last fourth step, we were able to estimate individual error margins and the accuracy class of the solubility prediction for molecules within the AD of three public databases. All that was possible without the knowledge of experimental database solubilities. We find these four steps novel because usually, solubility-related works only study the first step or the first two steps. [ABSTRACT FROM AUTHOR]

Background: Peru is one of the most biodiverse countries in the world, which is reflected in its wealth of knowledge about medicinal plants. However, there is a lack of information regarding intestinal absorption and the permeability of natural products. The human colon adenocarcinoma cell line (Caco-2) is an in vitro assay used to measure apparent permeability. This study aims to develop a quantitative structure–property relationship (QSPR) model using machine learning algorithms to predict the apparent permeability of the Caco-2 cell in natural products from Peru. Methods: A dataset of 1817 compounds, including experimental log Papp values and molecular descriptors, was utilized. Six QSPR models were constructed: a multiple linear regression (MLR) model, a partial least squares regression (PLS) model, a support vector machine regression (SVM) model, a random forest (RF) model, a gradient boosting machine (GBM) model, and an SVM–RF–GBM model. Results: An evaluation of the testing set revealed that the MLR and PLS models exhibited an RMSE = 0.47 and R2 = 0.63. In contrast, the SVM, RF, and GBM models showcased an RMSE = 0.39–0.40 and R2 = 0.73–0.74. Notably, the SVM–RF–GBM model demonstrated superior performance, with an RMSE = 0.38 and R2 = 0.76. The model predicted log Papp values for 502 natural products falling within the applicability domain, with 68.9% (n = 346) showing high permeability, suggesting the potential for intestinal absorption. Additionally, we categorized the natural products into six metabolic pathways and assessed their drug-likeness. Conclusions: Our results provide insights into the potential intestinal absorption of natural products in Peru, thus facilitating drug development and pharmaceutical discovery efforts.

Abstract Molecular descriptors characterize the biological, physical, and chemical properties of molecules and have long been used for understanding molecular interactions and facilitating materials design. Some of the most robust descriptors are derived from geometrical representations of molecules, called 3-dimensional (3D) descriptors. When calculated from molecular dynamics (MD) simulation trajectories, 3D descriptors can also capture the effects of operating conditions such as temperature or pressure. However, extracting 3D descriptors from MD trajectories is non-trivial, which hinders their wide use by researchers developing advanced quantitative-structure–property-relationship models using machine learning. Here, we describe a suite of open-source Python-based post-processing routines, called PyL3dMD, for calculating 3D descriptors from MD simulations. PyL3dMD is compatible with the popular simulation package LAMMPS and enables users to compute more than 2000 3D molecular descriptors from atomic trajectories generated by MD simulations. PyL3dMD is freely available via GitHub and can be easily installed and used as a highly flexible Python package on all major platforms (Windows, Linux, and macOS). A performance benchmark study used descriptors calculated by PyL3dMD to develop a neural network and the results showed that PyL3dMD is fast and efficient in calculating descriptors for large and complex molecular systems with long simulation durations. PyL3dMD facilitates the calculation of 3D molecular descriptors using MD simulations, making it a valuable tool for cheminformatics studies. Graphical Abstract

Ion mobility-mass spectrometry (IM-MS) is a powerful separation technique providing an additional dimension of separation to support the enhanced separation and characterization of complex components from the tissue metabolome and medicinal herbs. The integration of machine learning (ML) with IM-MS can overcome the barrier to the lack of reference standards, promoting the creation of a large number of proprietary collision cross section (CCS) databases, which help to achieve the rapid, comprehensive, and accurate characterization of the contained chemical components. In this review, advances in CCS prediction using ML in the past 2 decades are summarized. The advantages of ion mobility-mass spectrometers and the commercially available ion mobility technologies with different principles (e.g., time dispersive, confinement and selective release, and space dispersive) are introduced and compared. The general procedures involved in CCS prediction based on ML (acquisition and optimization of the independent and dependent variables, model construction and evaluation, etc.) are highlighted. In addition, quantum chemistry, molecular dynamics, and CCS theoretical calculations are also described. Finally, the applications of CCS prediction in metabolomics, natural products, foods, and the other research fields are reflected. [ABSTRACT FROM AUTHOR]

Solvation Gibbs energy of chemicals is a critical parameter in chemical industry and chemical reactivity. Predicting the solvation Gibbs energies for a large number of solvents and solutes through machine learning techniques is challenging area. In this work, the random forest (RF) algorithm, together with a combined descriptor set from solvents and solutes, was used for developing a quantitative structure–property relationship (QSPR) model for solvation Gibbs energies of 6238 solute/solvent pairs. The optimal RF (ntree = 25, mtry = 10 and nodesize = 5) model was obtained, whose training and test sets, respectively, have determination coefficients of 0.935 and 0.924, and root mean square errors of 2.477 and 2.464 kJ·mol− 1. In predicting the solvation Gibbs energies for a large dataset, the optimal RF model is comparable to other QSPR models reported in the literature. [ABSTRACT FROM AUTHOR]

Oral reference dose (RfD) is a key parameter for deriving the human health ambient water quality criteria (AWQC) for non-carcinogenic substances. In this study, a non-experimental approach was used to calculate the RfD values, which explore the potential correlation between toxicity and physicochemical characteristics and the chemical structure of pesticides. The molecular descriptors of contaminants were calculated using T.E.S.T software from EPA, and a prediction model was developed using a stepwise multiple linear regression (MLR) approaches. Approximately 95% and 85% of the data points differ by less than 10-fold and 5-fold between predicted values and true values, respectively, which improves the efficiency of RfD calculation. The model prediction values have certain reference values in the absence of experimental data, which is beneficial to the advancement of contaminant health risk assessment. In addition, using the prediction model constructed in this manuscript, the RfD values of two pesticide substances in the list of priority pollutants are calculated to derive human health water quality criteria. Furthermore, an initial assessment of the health risk was performed by the quotient value method based on the human health water quality criteria calculated by the prediction model. [ABSTRACT FROM AUTHOR]

• Development of models for predicting the heat capacity of liquid organic compounds using machine learning. • Introducing a temperature parameter allows the prediction of the liquid heat capacity at different temperatures. • An automatic process for deriving molecular structural features and heat capacity predictions was realized. • SHAP are used to interpret the constructed model and reveal key features. Heat capacity of compounds is an important reference parameter in thermodynamic, chemical processes, energy storage, heat transfer, heat exchange. However, the heat capacity data of most liquid compounds are missing due to the limited availability of data and the complexity of its experimental measurement. Heat capacity prediction models established did not consider temperature influences, or their complex prediction processes restricted their application. In this work, we developed an automated process based on machine learning algorithms to directly predict the liquid heat capacity of compounds from their molecular structure, with broader applicability to different temperature conditions. A dataset including 1253 heat capacity samples of liquid compounds was collected and divided into training set and test set in a 7:3 ratio. Random Forest (RF), Gradient Boosting Regression Tree (GBRT), Multi-Layer Perception (MLP), and Ridge Regression (RR) algorithms were utilized to develop predictive models. Ten-fold cross-validation, combined with the coefficient of determination (R2), was employed to evaluate the model performance. Notably, GBRT performed the best on the test set with an R 2 of 0.973, an AARD% of 5.248, and an MAE of 9.385 J/mol•K demonstrates the high accuracy of the model, and the model was saved and integrated into an automated prediction process. Meanwhile, through the application of the SHAP method, it was discovered that ATS0pe, NumValenceElectrons, and Kappa2 were identified as the most important features. This study introduces an automated approach for predicting the liquid heat capacities of compounds at various temperatures for the researchers in related fields. [ABSTRACT FROM AUTHOR]

The spectral graph theory explores connections between combinatorial features of graphs and algebraic properties of associated matrices. The neighborhood inverse sum indeg ( N I ) index was recently proposed and explored to be a significant molecular descriptor. Our aim is to investigate the N I index from a spectral standpoint, for which a suitable matrix is proposed. The matrix is symmetric since it is generated from the edge connection information of undirected graphs. A novel graph energy is introduced based on the eigenvalues of that matrix. The usefulness of the energy as a molecular structural descriptor is analyzed by investigating predictive potential and isomer discrimination ability. Fundamental mathematical properties of the present spectrum and energy are investigated. The spectrum of the bipartite class of graphs is identified to be symmetric about the origin of the real line. Bounds of the spectral radius and the energy are explained by identifying the respective extremal graphs. [ABSTRACT FROM AUTHOR]

Reproductive toxicity is one of the prominent endpoints in the risk assessment of environmental and industrial chemicals. Due to the complexity of the reproductive system, traditional reproductive toxicity testing in animals, especially guideline multigeneration reproductive toxicity studies, take a long time and are expensive. Therefore, machine learning, as a promising alternative approach, should be considered when evaluating the reproductive toxicity of chemicals. We curated rat multigeneration reproductive toxicity testing data of 275 chemicals from ToxRefDB (Toxicity Reference Database) and developed predictive models using seven machine learning algorithms (decision tree, decision forest, random forest, k-nearest neighbors, support vector machine, linear discriminant analysis, and logistic regression). A consensus model was built based on the seven individual models. An external validation set was curated from the COSMOS database and the literature. The performances of individual and consensus models were evaluated using 500 iterations of 5-fold cross-validations and the external validation data set. The balanced accuracy of the models ranged from 58% to 65% in the 5-fold cross-validations and 45%-61% in the external validations. Prediction confidence analysis was conducted to provide additional information for more appropriate applications of the developed models. The impact of our findings is in increasing confidence in machine learning models. We demonstrate the importance of using consensus models for harnessing the benefits of multiple machine learning models (i.e., using redundant systems to check validity of outcomes). While we continue to build upon the models to better characterize weak toxicants, there is current utility in saving resources by being able to screen out strong reproductive toxicants before investing in vivo testing. The modeling approach (machine learning models) is offered for assessing the rat multigeneration reproductive toxicity of chemicals. Our results suggest that machine learning may be a promising alternative approach to evaluate the potential reproductive toxicity of chemicals. [ABSTRACT FROM AUTHOR]

Virtual screening can significantly save experimental time and costs for early drug discovery. Drug multi-classification can speed up virtual screening and quickly predict the most likely class for a drug. In this study, 1019 drug molecules with actual therapeutic effects are collected from multiple databases and documents, and molecular sets are grouped according to therapeutic effect and mechanism of action. Molecular descriptors and molecular fingerprints are obtained through SMILES to quantify molecular structures. After using the Kennard–Stone method to divide the data set, a better combination can be obtained by comparing the combined results of five classification algorithms and a fusion method. Furthermore, for a specific data set, the model with the best performance is used to predict the validation data set. The test set shows that prediction accuracy can reach 0.862 and kappa coefficient can reach 0.808. The highest classification accuracy of the validation set is 0.873. The more reliable molecular set has been found, which could be used to predict potential attributes of unknown drug compounds and even to discover new use for old drugs. We hope this research can provide a reference for virtual screening of multiple classes of drugs at the same time in the future. [ABSTRACT FROM AUTHOR]

BackgroundHierarchical cluster analysis (HCA) is a widely used classificatory technique in many areas of scientific knowledge. Applications usually yield a dendrogram from an HCA run over a given data set, using a grouping algorithm and a similarity measure. However, even when such parameters are fixed, ties in proximity (i.e. two equidistant clusters from a third one) may produce several different dendrograms, having different possible clustering patterns (different classifications). This situation is usually disregarded and conclusions are based on a single result, leading to questions concerning the permanence of clusters in all the resulting dendrograms; this happens, for example, when using HCA for grouping molecular descriptors to select that less similar ones in QSAR studies.ResultsRepresenting dendrograms in graph theoretical terms allowed us to introduce four measures of cluster frequency in a canonical way, and use them to calculate cluster frequencies over the set of all possible dendrograms, taking all ties in proximity into account. A toy example of well separated clusters was used, as well as a set of 1666 molecular descriptors calculated for a group of molecules having hepatotoxic activity to show how our functions may be used for studying the effect of ties in HCA analysis. Such functions were not restricted to the tie case; the possibility of using them to derive cluster stability measurements on arbitrary sets of dendrograms having the same leaves is discussed, e.g. dendrograms from variations of HCA parameters. It was found that ties occurred frequently, some yielding tens of thousands of dendrograms, even for small data sets.ConclusionsOur approach was able to detect trends in clustering patterns by offering a simple way of measuring their frequency, which is often very low. This would imply, that inferences and models based on descriptor classifications (e.g. QSAR) are likely to be biased, thereby requiring an assessment of their reliability. Moreover, any classification of molecular descriptors is likely to be far from unique. Our results highlight the need for evaluating the effect of ties on clustering patterns before classification results can be used accurately.Graphical abstractFour cluster contrast functions identifying statistically sound clusters within dendrograms considering ties in proximity.

The screening of compounds for ADME-Tox targets plays an important role in drug design. QSPR models can increase the speed of these specific tasks, although the performance of the models highly depends on several factors, such as the applied molecular descriptors. In this study, a detailed comparison of the most popular descriptor groups has been carried out for six main ADME-Tox classification targets: Ames mutagenicity, P-glycoprotein inhibition, hERG inhibition, hepatotoxicity, blood–brain-barrier permeability, and cytochrome P450 2C9 inhibition. The literature-based, medium-sized binary classification datasets (all above 1,000 molecules) were used for the model building by two common algorithms, XGBoost and the RPropMLP neural network. Five molecular representation sets were compared along with their joint applications: Morgan, Atompairs, and MACCS fingerprints, and the traditional 1D and 2D molecular descriptors, as well as 3D molecular descriptors, separately. The statistical evaluation of the model performances was based on 18 different performance parameters. Although all the developed models were close to the usual performance of QSPR models for each specific ADME-Tox target, the results clearly showed the superiority of the traditional 1D, 2D, and 3D descriptors in the case of the XGBoost algorithm. It is worth trying the classical tools in single model building because the use of 2D descriptors can produce even better models for almost every dataset than the combination of all the examined descriptor sets.

The recent discovery of various forms of carbon nanostructures inspired the researchers due to their uses in various fields. Numerous production approaches for carbon nanostructures have been presented; doping, functionalization, chemical modification, and filling have been achieved, and manipulation, characterization and separation of carbon nanostructures are now possible. On the other hand, the flexibility and strength of carbon nanosheets make them potential candidates in controlling further nanoscale structures, which indicates that they have an important role in nanotechnology engineering. Because of their uniform thickness of only around 1 nanometer(nm), and their high mechanical, thermal and chemical stability, such materials are of high concern for a wide range of applications.A topological index or molecular descriptor is a mathematical formulation that can be applied to any graph which models some molecular structure. Based on the molecular descriptor, it is convenient to analyze mathematical values and advance investigation on some physicochemical properties of a molecule. Consequently, it is an effective method in replacing laborious, expensive and time-consuming laboratory experimentations. Molecular descriptors perform an important part in mathematical chemistry, especially during the investigation of Quantitative structure property relationships (QSPRs) and Quantitative structure-activity relationships (QSARs) that provide insight into animate effects based on chemical structures. In this paper, we have computed some novel neighborhood version molecular descriptors for the two carbon nanosheets VC5C7p,q and (HC5C7p,q) and derived formulas for them. Our computed results are surely helpful in understanding the topology of understudy nanosheets. These computed indices have best correlation with acentric factor and entropy, therefore, are effective in QSPRs and QSARs analysis with powerful accuracy.

Ion mobility-mass spectrometry (IM-MS) is a powerful separation technique providing an additional dimension of separation to support the enhanced separation and characterization of complex components from the tissue metabolome and medicinal herbs. The integration of machine learning (ML) with IM-MS can overcome the barrier to the lack of reference standards, promoting the creation of a large number of proprietary collision cross section (CCS) databases, which help to achieve the rapid, comprehensive, and accurate characterization of the contained chemical components. In this review, advances in CCS prediction using ML in the past 2 decades are summarized. The advantages of ion mobility-mass spectrometers and the commercially available ion mobility technologies with different principles (e.g., time dispersive, confinement and selective release, and space dispersive) are introduced and compared. The general procedures involved in CCS prediction based on ML (acquisition and optimization of the independent and dependent variables, model construction and evaluation, etc.) are highlighted. In addition, quantum chemistry, molecular dynamics, and CCS theoretical calculations are also described. Finally, the applications of CCS prediction in metabolomics, natural products, foods, and the other research fields are reflected.

Oral reference dose (RfD) is a key parameter for deriving the human health ambient water quality criteria (AWQC) for non-carcinogenic substances. In this study, a non-experimental approach was used to calculate the RfD values, which explore the potential correlation between toxicity and physicochemical characteristics and the chemical structure of pesticides. The molecular descriptors of contaminants were calculated using T.E.S.T software from EPA, and a prediction model was developed using a stepwise multiple linear regression (MLR) approaches. Approximately 95% and 85% of the data points differ by less than 10-fold and 5-fold between predicted values and true values, respectively, which improves the efficiency of RfD calculation. The model prediction values have certain reference values in the absence of experimental data, which is beneficial to the advancement of contaminant health risk assessment. In addition, using the prediction model constructed in this manuscript, the RfD values of two pesticide substances in the list of priority pollutants are calculated to derive human health water quality criteria. Furthermore, an initial assessment of the health risk was performed by the quotient value method based on the human health water quality criteria calculated by the prediction model.

Semi-empirical calculations were employed to understand the effects of introducing promoters such as molybdenum (Mo) and tungsten (W) on chromium (III) oxide catalyst for the dehydrogenation of propane into propylene. For this purpose, we investigated CrM-oxide (M = Cr, Mo, and W) catalysts. In this study, the Lewis acidity of the catalyst was examined using Lewis acidity parameters (Ac), including ammonia and pyridine adsorption energy. The results obtained from this study of overall acidity across all sites of the catalysts studied reveal Mo-modified catalyst as the one with the least acidity while the W-modified catalyst was found to have shown the highest acidity signifies that the introduction of Mo would reduce acidity while W accelerates it. The finding, therefore, confirms tungsten (W) to be more influential and would be more promising when compared to molybdenum (Mo) due to the better avenue that is offered by W for the promotion of electron exchange and its higher acidity(s). The suitability of some molecular descriptors for acidity prediction as a potential alternative to the current use of adsorption energies of the probes was also reported.

Abstract Computer-aided research on the relationship between molecular structures of natural compounds (NC) and their biological activities have been carried out extensively because the molecular structures of new drug candidates are usually analogous to or derived from the molecular structures of NC. In order to express the relationship physically realistically using a computer, it is essential to have a molecular descriptor set that can adequately represent the characteristics of the molecular structures belonging to the NC’s chemical space. Although several topological descriptors have been developed to describe the physical, chemical, and biological properties of organic molecules, especially synthetic compounds, and have been widely used for drug discovery researches, these descriptors have limitations in expressing NC-specific molecular structures. To overcome this, we developed a novel molecular fingerprint, called Natural Compound Molecular Fingerprints (NC-MFP), for explaining NC structures related to biological activities and for applying the same for the natural product (NP)-based drug development. NC-MFP was developed to reflect the structural characteristics of NCs and the commonly used NP classification system. NC-MFP is a scaffold-based molecular fingerprint method comprising scaffolds, scaffold-fragment connection points (SFCP), and fragments. The scaffolds of the NC-MFP have a hierarchical structure. In this study, we introduce 16 structural classes of NPs in the Dictionary of Natural Product database (DNP), and the hierarchical scaffolds of each class were calculated using the Bemis and Murko (BM) method. The scaffold library in NC-MFP comprises 676 scaffolds. To compare how well the NC-MFP represents the structural features of NCs compared to the molecular fingerprints that have been widely used for organic molecular representation, two kinds of binary classification tasks were performed. Task I is a binary classification of the NCs in commercially available library DB into a NC or synthetic compound. Task II is classifying whether NCs with inhibitory activity in seven biological target proteins are active or inactive. Two tasks were developed with some molecular fingerprints, including NC-MFP, using the 1-nearest neighbor (1-NN) method. The performance of task I showed that NC-MFP is a practical molecular fingerprint to classify NC structures from the data set compared with other molecular fingerprints. Performance of task II with NC-MFP outperformed compared with other molecular fingerprints, suggesting that the NC-MFP is useful to explain NC structures related to biological activities. In conclusion, NC-MFP is a robust molecular fingerprint in classifying NC structures and explaining the biological activities of NC structures. Therefore, we suggest NC-MFP as a potent molecular descriptor of the virtual screening of NC for natural product-based drug development.

Artificial intelligence (AI) based drug design has demonstrated great potential to fundamentally change the pharmaceutical industries. Currently, a key issue in AI-based drug design is efficient transferable molecular descriptors or fingerprints. Here, we present hypergraph-based molecular topological representation, hypergraph-based (weighted) persistent cohomology (HPC/HWPC) and HPC/HWPC-based molecular fingerprints for machine learning models in drug design. Molecular structures and their atomic interactions are highly complicated and pose great challenges for efficient mathematical representations. We develop the first hypergraph-based topological framework to characterize detailed molecular structures and interactions at atomic level. Inspired by the elegant path complex model, hypergraph-based embedded homology and persistent homology have been proposed recently. Based on them, we construct HPC/HWPC, and use them to generate molecular descriptors for learning models in protein–ligand binding affinity prediction, one of the key step in drug design. Our models are tested on three most commonly-used databases, including PDBbind-v2007, PDBbind-v2013 and PDBbind-v2016, and outperform all existing machine learning models with traditional molecular descriptors. Our HPC/HWPC models have demonstrated great potential in AI-based drug design. [ABSTRACT FROM AUTHOR]

The spectral graph theory explores connections between combinatorial features of graphs and algebraic properties of associated matrices. The neighborhood inverse sum indeg (NI) index was recently proposed and explored to be a significant molecular descriptor. Our aim is to investigate the NI index from a spectral standpoint, for which a suitable matrix is proposed. The matrix is symmetric since it is generated from the edge connection information of undirected graphs. A novel graph energy is introduced based on the eigenvalues of that matrix. The usefulness of the energy as a molecular structural descriptor is analyzed by investigating predictive potential and isomer discrimination ability. Fundamental mathematical properties of the present spectrum and energy are investigated. The spectrum of the bipartite class of graphs is identified to be symmetric about the origin of the real line. Bounds of the spectral radius and the energy are explained by identifying the respective extremal graphs.

The variable sum exdeg index of a graph G is defined as SEIa(G) = u2V (G) dG(u)adG(u), where a 6= 1 is a positive real number, dG(u) is the degree of a vertex u 2 V (G). In this paper, we characterize the graphs with the extremum variable sum exdeg index among all the graphs having a fixed number of vertices and cut edges, for every a > 1. [ABSTRACT FROM AUTHOR]

The Sanskruti index of a graph G is defined as S(G)=∑uv∈E(G)sG(u)sG(v)sG(u)+sG(v)−23,$$\begin{align*}S(G)=\sum_{uv\in{}E(G)}{\left(\frac{s_G(u)s_G(v)}{s_G(u)+s_G(v)-2}\right)}^3, \end{align*}$$where sG(u) is the sum of the degrees of the neighbors of a vertex u in G. Let Pn, Cn, Sn and Sn + e be the path, cycle, star and star plus an edge of n vertices, respectively. The Sanskruti index of a molecular graph of a compounds can model the bioactivity of compounds, has a strong correlation with entropy of octane isomers and its prediction power is higher than many existing topological descriptors.

Virtual screening can significantly save experimental time and costs for early drug discovery. Drug multi-classification can speed up virtual screening and quickly predict the most likely class for a drug. In this study, 1019 drug molecules with actual therapeutic effects are collected from multiple databases and documents, and molecular sets are grouped according to therapeutic effect and mechanism of action. Molecular descriptors and molecular fingerprints are obtained through SMILES to quantify molecular structures. After using the Kennard–Stone method to divide the data set, a better combination can be obtained by comparing the combined results of five classification algorithms and a fusion method. Furthermore, for a specific data set, the model with the best performance is used to predict the validation data set. The test set shows that prediction accuracy can reach 0.862 and kappa coefficient can reach 0.808. The highest classification accuracy of the validation set is 0.873. The more reliable molecular set has been found, which could be used to predict potential attributes of unknown drug compounds and even to discover new use for old drugs. We hope this research can provide a reference for virtual screening of multiple classes of drugs at the same time in the future.

Abstract Molecular descriptors are widely employed to present molecular characteristics in cheminformatics. Various molecular-descriptor-calculation software programs have been developed. However, users of those programs must contend with several issues, including software bugs, insufficient update frequencies, and software licensing constraints. To address these issues, we propose Mordred, a developed descriptor-calculation software application that can calculate more than 1800 two- and three-dimensional descriptors. It is freely available via GitHub. Mordred can be easily installed and used in the command line interface, as a web application, or as a high-flexibility Python package on all major platforms (Windows, Linux, and macOS). Performance benchmark results show that Mordred is at least twice as fast as the well-known PaDEL-Descriptor and it can calculate descriptors for large molecules, which cannot be accomplished by other software. Owing to its good performance, convenience, number of descriptors, and a lax licensing constraint, Mordred is a promising choice of molecular descriptor calculation software that can be utilized for cheminformatics studies, such as those on quantitative structure–property relationships.

The blood-brain barrier (BBB) controls the entry of chemicals from the blood to the brain. Since brain drugs need to penetrate the BBB, rapid and reliable prediction of BBB penetration (BBBP) is helpful for drug development. In this study, free-form and in-blood-form datasets were prepared by modifying the original BBBP dataset, and the effects of the data modification were investigated. For each dataset, molecular descriptors were generated and used for BBBP prediction by machine learning (ML). For ML, the dataset was split into training, validation, and test data by the scaffold split algorithm MoleculeNet used. This creates an unbalanced split and makes the prediction difficult; however, we decided to use that algorithm to evaluate the predictive performance for unknown compounds dissimilar to existing ones. The highest prediction score was obtained by the random forest model using 212 descriptors from the free-form dataset, and this score was higher than the existing best score using the same split algorithm without using any external database. Furthermore, using a deep neural network, a comparable result was obtained with only 11 descriptors from the free-form dataset, and the resulting descriptors suggested the importance of recognizing the glucose-like characteristics in BBBP prediction.

Successful drug administration to the central nervous system requires accurate adjustment of the drugs’ molecular properties. Therefore, structure-derived descriptors of potential brain therapeutic agents are essential for an early evaluation of pharmacokinetics during drug development. The collision cross section (CCS) of molecules was recently introduced as a novel measurable parameter to describe blood-brain barrier (BBB) permeation. This descriptor combines molecular information about mass, structure, volume, branching and flexibility. As these chemical properties are known to influence cerebral pharmacokinetics, CCS determination of new drug candidates may provide important additional spatial information to support existing models of BBB penetration of drugs. Besides measuring CCS, calculation is also possible; but however, the reliability of computed CCS values for an evaluation of BBB permeation has not yet been fully investigated. In this work, prediction tools based on machine learning were used to compute CCS values of a large number of compounds listed in drug libraries as negative or positive with respect to brain penetration (BBB+ and BBB− compounds). Statistical evaluation of computed CCS and several other descriptors could prove the high value of CCS. Further, CCS-deduced maximum molecular size of BBB+ drugs matched the dimensions of BBB pores. A threshold for transcellular penetration and possible permeation through pore-like openings of cellular tight-junctions is suggested. In sum, CCS evaluation with modern in silico tools shows high potential for its use in the drug development process.

Semi-empirical calculations were employed to understand the effects of introducing promoters such as molybdenum (Mo) and tungsten (W) on chromium (III) oxide catalyst for the dehydrogenation of propane into propylene. For this purpose, we investigated CrM-oxide (M = Cr, Mo, and W) catalysts. In this study, the Lewis acidity of the catalyst was examined using Lewis acidity parameters (Ac), including ammonia and pyridine adsorption energy. The results obtained from this study of overall acidity across all sites of the catalysts studied reveal Mo-modified catalyst as the one with the least acidity while the W-modified catalyst was found to have shown the highest acidity signifies that the introduction of Mo would reduce acidity while W accelerates it. The finding, therefore, confirms tungsten (W) to be more influential and would be more promising when compared to molybdenum (Mo) due to the better avenue that is offered by W for the promotion of electron exchange and its higher acidity(s). The suitability of some molecular descriptors for acidity prediction as a potential alternative to the current use of adsorption energies of the probes was also reported. [ABSTRACT FROM AUTHOR]

Computer-aided research on the relationship between molecular structures of natural compounds (NC) and their biological activities have been carried out extensively because the molecular structures of new drug candidates are usually analogous to or derived from the molecular structures of NC. In order to express the relationship physically realistically using a computer, it is essential to have a molecular descriptor set that can adequately represent the characteristics of the molecular structures belonging to the NC's chemical space. Although several topological descriptors have been developed to describe the physical, chemical, and biological properties of organic molecules, especially synthetic compounds, and have been widely used for drug discovery researches, these descriptors have limitations in expressing NC-specific molecular structures. To overcome this, we developed a novel molecular fingerprint, called Natural Compound Molecular Fingerprints (NC-MFP), for explaining NC structures related to biological activities and for applying the same for the natural product (NP)-based drug development. NC-MFP was developed to reflect the structural characteristics of NCs and the commonly used NP classification system. NC-MFP is a scaffold-based molecular fingerprint method comprising scaffolds, scaffold-fragment connection points (SFCP), and fragments. The scaffolds of the NC-MFP have a hierarchical structure. In this study, we introduce 16 structural classes of NPs in the Dictionary of Natural Product database (DNP), and the hierarchical scaffolds of each class were calculated using the Bemis and Murko (BM) method. The scaffold library in NC-MFP comprises 676 scaffolds. To compare how well the NC-MFP represents the structural features of NCs compared to the molecular fingerprints that have been widely used for organic molecular representation, two kinds of binary classification tasks were performed. Task I is a binary classification of the NCs in commercially available library DB into a NC or synthetic compound. Task II is classifying whether NCs with inhibitory activity in seven biological target proteins are active or inactive. Two tasks were developed with some molecular fingerprints, including NC-MFP, using the 1-nearest neighbor (1-NN) method. The performance of task I showed that NC-MFP is a practical molecular fingerprint to classify NC structures from the data set compared with other molecular fingerprints. Performance of task II with NC-MFP outperformed compared with other molecular fingerprints, suggesting that the NC-MFP is useful to explain NC structures related to biological activities. In conclusion, NC-MFP is a robust molecular fingerprint in classifying NC structures and explaining the biological activities of NC structures. Therefore, we suggest NC-MFP as a potent molecular descriptor of the virtual screening of NC for natural product-based drug development. [ABSTRACT FROM AUTHOR]

The rising demand from consumer goods and pharmaceutical industry is driving a fast expansion of newly developed chemicals. The conventional toxicity testing of unknown chemicals is expensive, time-consuming, and raises ethical concerns. The quantitative structure–property relationship (QSPR) is an efficient computational method because it saves time, resources, and animal experimentation. Advances in machine learning have improved chemical analysis in QSPR studies, but the real-world application of machine learning-based QSPR studies was limited by the unexplainable 'black box' feature of the machine learnings. In this study, multi-encoder structure-to-toxicity (S2T)-transformer based QSPR model was developed to estimate the properties of polychlorinated biphenyls (PCBs) and endocrine disrupting chemicals (EDCs). Simplified molecular input line entry systems (SMILES) and molecular descriptors calculated by the Dragon 6 software, were simultaneously considered as input of QSPR model. Furthermore, an attention-based framework is proposed to describe the relationship between the molecular structure and toxicity of hazardous chemicals. The S2T-transformer model achieved the highest R2 scores of 0.918, 0.856, and 0.907 for logarithm of octanol-water partition coefficient (Log K OW), octanol-air partition coefficient (Log K OA), and bioconcentration factor (Log BCF) estimation of PCBs, respectively. Moreover, the attention weights were able to properly interpret the lateral (meta , para) chlorination associated with PCBs toxicity and environmental impact. [Display omitted] • Explainable attention-based QSPR model estimates the properties of PCBs and EDCs. • Attention-based prediction reduces 38% errors for octanol-air partition coefficient. • S2T-Transformer shows 65.5% higher performance than SMILES-based models. • Attention analysis identifies PCBs structures that contribute chemical toxicity. [ABSTRACT FROM AUTHOR]

The continuously increased production of various chemicals and their release into environments have raised potential negative effects on ecological health. However, traditional labor-intensive assessment methods cannot effectively and rapidly evaluate these hazards, especially for chronic risk. In this study, machine learning (ML) was employed to construct quantitative structure-activity relationship (QSAR) models, enabling the prediction of chronic toxicity to aquatic organisms by leveraging the molecular characteristics of pollutants, namely, the molecular descriptors, fingerprints, and graphs. The limited dataset size hindered the notable advantages of the graph attention network (GAT) model for the molecular graphs. Considering computational efficiency and performance (R2 = 0.78; RMSE = 0.77), XGBoost (XGB) was used for reliable QSAR-ML models predicting chronic toxicity using small- or medium-sized tabular data and the molecular descriptors. Further kernel density estimation analysis confirmed the high accuracy of the model for pollutant concentrations ranging from 10−3 to 102 mg/L, effectively aligning with most environmental scenarios. Model interpretation showed SlogP and exposure duration as the primary influential factors. SlogP, representing the distribution coefficient of a molecule between lipophilic and hydrophilic environments, had a negative effect on the toxicity outcomes. Additionally, the exposure duration played a crucial role in determining the chronic toxicity. Finally, the chronic toxicity data of bisphenol A validated the robustness and reliability of the model established in this research. Our study provided a robust and feasible methodology for chronic ecological risk evaluation of various types of pollutants and could facilitate and increase the use of ML applications in environmental fields. [Display omitted] • ML model integrated molecular features for pioneering chronic risk assessment. • XGBoost was used for developing a robust ML model in chronic ecotoxicity. • Sample size limited the molecular graph model's advantages. • The developed model was applicable to most environmental scenarios. • SLogP and exposure duration were identified as the primary influential factors. [ABSTRACT FROM AUTHOR]

Molecular descriptors reflecting structural information on hydrophobicity, reactivity, polarizability, hydrogen bond and charged groups, were used to predict the toxicity (pLC 50) of chemicals towards Daphnia magna with global quantitative structure–activity/toxicity relationship (QSAR/QSTR) models. A sufficiently large dataset including 1517 chemical toxicity to Daphnia magna was divided into a training set (758 pLC 50) and a test set (759 pLC 50). By applying random forest algorithm, two classification models, Class Model A and Class Model B were developed, having prediction accuracy, sensitivity and specificity above 85% for Class 1 (with pLC 50 ≤ 4.48) and Class 2 (with pLC 50 > 4.48). The Class Model A was based on nine molecular descriptors and RF parameters of nodesize = 1, ntree = 80 and mtry = 2, and yielded accuracy of 92.3% (training set), 85.6% (test set) and 88.9% (total data set). Class Model B was based on ten descriptors and parameters, nodesize = 1, ntree = 90 and mtry = 2, produced accuracy of 88.3% (training set), 86.8% (test set) and 87.5% (total data set). The two classification models were satisfactory compared with other classification model reported in the literature, although classification models in this work dealt with more samples. Thus, the two classification models with a larger applicability domain provided efficient tools for assessing chemical aquatic toxicity towards Daphnia magna. • Increasing molecular hydrophobicity causes high toxicity pLC 50 to Daphnia magna. • Compounds with charged groups have strong polarity and lower toxicity pLC 50. • Introducing phosphorus-sulfur double bonds increases molecular reactivity and toxicity. • These molecules prone to forming hydrogen bonds have lower toxicity pLC 50. [ABSTRACT FROM AUTHOR]

Malaria remains by far one of the most threatening and dangerous illnesses caused by the plasmodium falciparum parasite. Chloroquine (CQ) and first-line artemisinin-based combination treatment (ACT) have long been the drug of choice for the treatment and controlling of malaria; however, the emergence of CQ-resistant and artemisinin resistance parasites is now present in most areas where malaria is endemic. In this work, we developed five machine learning models to predict antimalarial bioactivities of a drug against plasmodium falciparum from the features (i.e., molecular descriptors values) obtained from PaDEL software from SMILES of compounds and compare the machine learning models by experiments with our collected data of 4794 instances. As a consequence, we found that three models amongst the five, namely artificial neural network (ANN), extreme gradient boost (XGB), and random forest (RF), outperform the others in terms of accuracy while observing that, using roughly a quarter of the promising descriptors picked by the feature selection algorithm, the five models achieved equivalent and comparable performance. Nevertheless, the contribution of all molecular descriptors in the models was investigated through the comparison of their rank values by the feature selection algorithm and found that the most potent and relevant descriptors which come from the ‘Autocorrelation’ module contributed more while the ‘Atom type electrotopological state’ contributed the least to the model.

The eigenvalues of the characteristic polynomial of a graph are sensitive to its symmetry-related characteristics. Within this study, we have examined three eigenvalue–based molecular descriptors. These topological molecular descriptors, among others, are gathering information on the symmetry of a molecular graph. Furthermore, they are being ordinarily employed for predicting physico–chemical properties and/or biological activities of molecules. It has been shown that these indices describe well molecular features that are depending on fine structural details. Therefore, revealing the impact of structural details on the values of the eigenvalue–based topological indices should give a hunch how physico–chemical properties depend on them as well. Here, an effect of a ring in a molecule on the values of the graph energy, Estrada index and the resolvent energy of a graph is examined.

We used the extreme gradient boosting (XGB) algorithm to predict the experimental solubility of chemical compounds in water and organic solvents and to select significant molecular descriptors. The accuracy of prediction of our forward stepwise top-importance XGB (FSTI-XGB) on curated solubility data sets in terms of RMSE was found to be 0.59-0.76 Log(S) for two water data sets, while for organic solvent data sets it was 0.69-0.79 Log(S) for the Methanol data set, 0.65-0.79 for the Ethanol data set, and 0.62-0.70 Log(S) for the Acetone data set. That was the first step. In the second step, we used uncurated and curated AquaSolDB data sets for applicability domain (AD) tests of Drugbank, PubChem, and COCONUT databases and determined that more than 95% of studied ca. 500,000 compounds were within the AD. In the third step, we applied conformal prediction to obtain narrow prediction intervals and we successfully validated them using test sets' true solubility values. With prediction intervals obtained in the last fourth step, we were able to estimate individual error margins and the accuracy class of the solubility prediction for molecules within the AD of three public databases. All that was possible without the knowledge of experimental database solubilities. We find these four steps novel because usually, solubility-related works only study the first step or the first two steps.

Quantitative structure--activity relationships and quantitative structure--property relationships have proved their usefulness for predicting toxicities of drug molecules regarding their biological activities. In silico toxicity prediction techniques are essential for reducing testing on rodents (in vivo) and for a less time-consuming and more cost-efficient alternative for the identification of toxic effects at an early stage of drug development. The authors aim to build a prediction model for better assessment of toxicity to quickly and efficiently test whether certain chemical compounds have the potential to disrupt the processes in the human body that may adversely affect human health. Here, we have proposed a computational method (in silico) for the toxicity prediction of small drug molecules using their various physicochemical properties (molecular descriptors) that can bind to the aryl hydrocarbon receptor. Pharmaceutical data exploration laboratory software is used for extracting the features of drug molecules. The dataset of the aryl hydrocarbon receptor contains 9008 drug molecules, where 1063 are active and 7945 are inactive, and each drug molecule contains 1444 features. It is a novel prediction model based on ensemble learning that can efficiently classify active (binding) and inactive (nonbinding) compounds of the dataset. In our proposed ensemble model, we primarily performed feature selection using the Boruta library in R, after which we resolved the class imbalance problem itself by ensemble learning where we divided the dataset into seven data frames, which have approximately equal numbers of active and inactive drug molecules. An ensemble model based upon the votes of seven random forest models is proposed, which gives an accuracy of 93.76%. K-fold cross-validation is conducted to measure the consistency of the model. Finally, the validity of the proposed ensemble model for some drug molecules of acquired immune deficiency syndrome therapy and androgen receptor has been proved. [ABSTRACT FROM AUTHOR]

Comparing fragment based molecular fingerprints of drug-like molecules is one of the most robust and frequently used approaches in computer-assisted drug discovery. Molprint2D, a popular atom environment (AE) descriptor, yielded the best enrichment of active compounds across a diverse set of targets in a recent large-scale study. We present here BCL::Mol2D descriptors that outperformed Molprint2D on nine PubChem datasets spanning a wide range of protein classes. Because BCL::Mol2D records the number of AEs from a universal AE library, a novel aspect of BCL::Mol2D over the Molprint2D is its reversibility. This property enables decomposition of prediction from machine learning models to particular molecular substructures. Artificial neural networks with dropout, when trained on BCL::Mol2D descriptors outperform those trained on Molprint2D descriptors by up to 26% in logAUC metric. When combined with the Reduced Short Range descriptor set, our previously published set of descriptors optimized for QSARs, BCL::Mol2D yields a modest improvement. Finally, we demonstrate how the reversibility of BCL::Mol2D enables visualization of a 'pharmacophore map' that could guide lead optimization for serine/threonine kinase 33 inhibitors. [ABSTRACT FROM AUTHOR]

The infinite dilution activity coefficient (γ∞) is a crucial thermodynamic property that provides a measure of the affinity between the solute and the solvent. In this work, three deep learning models (deep neural network, convolution neural network, and convolution deep neural network) were proposed to predict the γ∞ for ionic liquid-solute systems. 52 ionic liquids and 114 organic solutes (7783 data points in total) contained in the γ∞ database over the temperature from 293.15 to 428.15 K were collected to construct the model. Molecular descriptor was generated using the RDKit. The Bayesian optimization algorithm was employed to determine the parameters for each model, and the stability of the model was increased by 10-fold cross validation. Finally, the method of SHapley Additive exPlanations was employed to explain our proposed model. The coefficient of determination, mean absolute error, mean square error, root mean square error, error, sum of squared error, relative root mean square error and the Wilcoxon signed-rank test were used to assess the model. The results indicated that the experimental values were in satisfactory agreement with the values predicted for convolution deep neural network. These predictive models can be used to predict the γ∞ for ionic liquid-solute systems to solve problems in phase equilibrium and process design. [Display omitted] • A dataset containing 7783 data points is collected. • Three deep learning models, DNN, CNN, and CDNN are developed. • The CDNN model performs slightly better than the other two models. • The method of SHAP is adopted to interpret the deep learning model. [ABSTRACT FROM AUTHOR]

Because the health effects of many compounds are unknown, regulatory toxicology must often rely on the development of quantitative structure–activity relationship (QSAR) models to efficiently discover molecular initiating events (MIEs) in the adverse-outcome pathway (AOP) framework. However, the QSAR models used in numerous toxicity prediction studies are publicly unavailable, and thus, they are challenging to use in practical applications. Approaches that simultaneously identify the various toxic responses induced by a compound are also scarce. The present study develops Toxicity Predictor, a web application tool that comprehensively identifies potential MIEs. Using various chemicals in the Toxicology in the 21st Century (Tox21) 10K library, we identified potential endocrine-disrupting chemicals (EDCs) using a machine-learning approach. Based on the optimized three-dimensional (3D) molecular structures and XGBoost algorithm, we established molecular descriptors for QSAR models. Their predictive performances and applicability domain were evaluated and applied to Toxicity Predictor. The prediction performance of the constructed models matched that of the top model in the Tox21 Data Challenge 2014. These advanced prediction results for MIEs are freely available on the Internet.