Compound Data Sets Research Articles

Structure‐Based Computational Approach in Search of the Potent Molecules Targeting Phosphoglycerate Dehydrogenase (PHGDH) Enzyme for Cancer Treatment

AbstractThis work aims to target phosphoglycerate dehydrogenase (PHGDH), a promising druggable target, that is overexpressed in various types of cancer. A structure‐based approach was employed to identify novel inhibitors against the enzyme. A common five‐feature pharmacophore model (RRHDA) was constructed using the active site co‐crystalized ligands. These chemical features were responsible for showing inhibition. The generated models were subsequently subjected to the validation method using a test set, receiver‐operator characteristic analysis, enrichment factor, and Güner–Henry studies. The validated models were subjected to the screening of a dataset of natural compounds. The screened unique natural compounds (1795) were further selected for the interaction analysis and study of ligand binding affinity considering the effect of the hydrogen bonding and desolvation and hydrophobic interactions contribution to the binding. The natural compounds which exhibited good ligand binding efficiency were selected and further subjected to pharmacokinetics and pharmacodynamic study. The natural compounds which exhibited good ligand binding efficiency were selected and further subjected to pharmacokinetics and pharmacodynamic study. The finalized complexes were selected for the simulation studies and MM/PBSA‐based binding free energy calculations. This study expands the possibilities for the development of shortlisted molecules as novel anti‐cancer compounds.

Investigation of the Cyclohexene Oxidation Mechanism Through the Direct Measurement of Organic Peroxy Radicals.

Monoterpenes, the second most abundant biogenic volatile organic compounds globally, are crucial in forming secondary organic aerosols, making their oxidation mechanisms vital for addressing climate change and air pollution. This study utilized cyclohexene as a surrogate to explore first-generation products from its ozonolysis through laboratory experiments and mechanistic modeling. We employed proton transfer reaction mass spectrometry with NH4+ ion sources (NH4+-CIMS) and a custom-built OH calibration source to quantify organic peroxy radicals (RO2) and closed-shell species. Under near-real atmospheric conditions in a Potential Aerosol Mass-Oxidation Flow Reactor, we identified 30 ozonolysis products, expanding previous data sets of low-oxygen compounds. Combined with simulations based on the Generator for Explicit Chemistry and Kinetics of Organics in the Atmosphere and relevant literature, our results revealed that OH dominates over ozone in cyclohexene oxidation at typical atmospheric oxidant levels with H-abstraction contributing 30% of initial RO2 radicals. Highly oxidized molecules primarily arise from RO2 autoxidation initiated by ozone, and at least 15% of ozone oxidation products follow the overlooked nonvinyl hydroperoxides pathway. Gaps remain especially in understanding RO2 cross-reactions, and the structural complexity of monoterpenes further complicates research. As emissions decrease and afforestation increases, understanding these mechanisms becomes increasingly critical.

Quantitative structure-property relationship of glass transition temperatures for organic compounds

The glass transition temperatures (T gs) of materials used in the manufacture of organic light-emitting diodes (OLEDs) determine their thermal stability. Three Dragon descriptors, TPC, RBF and TDB04s, were adopted to develop quantitative structure-property relationships (QSPR) for the prediction of the T gs of 66 compounds (Data Set I) for OLED application, by applying random forest (RF) and support vector machine (SVM). The RF Model A, based on a training set (44 compounds), was validated with a test set (22 compounds). The RF Model A possesses a coefficient of determination R 2 of 0.942 and a root mean square (rms) error of 10.750 K for the training set and R 2 of 0.909 and rms error of 11.102 K for the test set, which are more accurate than the results from the SVM model. The RF Model A was further validated with 63 OLED molecules (Data Set II). Moreover, the three Dragon descriptors (TPC, RBF and TDB04s) were used to build another T g QSPR model (named RF Model B) for a large dataset of 1934 OLED molecules (Data Set III), which achieved rms errors of 16.79 K for Data Set III, 22.89 K for Data Set I and 20.17 K for Data Set II.

Machine Learning and Deep Learning Models for Predicting Noncovalent Inhibitors of AmpC β-Lactamase.

Continuous use of antibiotics leads to the ability of bacteria to adapt by developing complex antibiotic resistance (AR) mechanisms. The synthesis of β-lactamases is a widely observed AR mechanism. The class C β-lactamase (AmpC) causes significant resistance toward β-lactam antibiotics, and new treatments are urgently needed. Noncovalent inhibitors have been developed against a broad spectrum of β-lactamases. In this study, we developed robust and accurate models for predicting noncovalent inhibitors of AmpC using large compound data sets and machine/deep learning modeling. We created support vector machine (SVM), random forest (RF), and feed-forward neural network (FFNN) classification models. The cross-validation (CV) accuracies varied between 80 and 82%, as combined models reached an accuracy of 83%. We analyzed the physicochemical characteristics of the noncovalent inhibitors and predicted the binding modes for some of them. Such models are helpful for identifying new noncovalent inhibitors in order to establish novel solutions against the growing resistance to standard β-lactam inhibitors. The best RF, SVM, and FFNN models for predicting noncovalent inhibitors of AmpC β-lactamase are available in the GitHub repository, https://github.com/UPCmctr/ML-DL-AmpC-B-lactamase.

The 3D-QSAR Study, Molecular Docking, and ADMET Analysis of Darunavir Derivatives of HIV-1 Protease Inhibitors

Background: Acquired Immunodeficiency Syndrome (AIDS) is one of most prevalent infectious diseases in the world , and HIV-1 protease (PR) is a vital target of drug design. Nowadays, three-dimensional quantitative structure-activity relationships (3D-QSAR) are applied to help design new protease inhibitions (PIs). Objective: The primary objective of this study is to apply the 3D-QSAR study to a series of 42 derivatives of Darunavir (DRV) and to design new molecules possessing high antivirus activity. Methods: Partial Least Squares (PLS) were used to cross-validate the dataset of compounds, and the optimal number of principal components (ONC), cross-validate coefficient (q²), standard error of estimate (SEE), non-cross-validated correlation coefficient (R²) and fisher test value (F) were calculated to assess model robustness. In this study, the CoMSIA-DAH model (q²=0.754, r²= 0.988, rpred2=0.57) possessed the highest predicted activity. Newly designed molecules were analyzed by docking studies with compound 25 taken as a template. Results: Within eight newly designed drugs, compound N02 possessed the highest antivirus activity (IC50=0.00461 nM) predicted by the CoMSIA-DAH model. The Surflex-Dock module of SYBYL-X 2.0 was used to affirm the predicted anti-PR activity of the newly designed compounds and the results of docking complex structure could be visualized. All newly designed molecules were in agreement with CSore above four and the docking study revealed that Asp29, Asp30, Ile50, Asp124, Asp128, Asp129 and Ile149 were critical residues in the process of inhibiting PR. Conclusion: One of the main aspects of this study is the successful design of a series of molecules with excellent investigatory values, which elucidates explicit quantitative structure-activity relationships of DRV derivatives and will provide significant suggestions for future pharmaceutical research.

Label distribution learning for compound facial expression recognition in‐the‐wild: A comparative study

AbstractHuman emotional states encompass both basic and compound facial expressions. However, current works primarily focus on basic expressions, consequently neglecting the broad spectrum of human emotions encountered in practical scenarios. Compound facial expressions involve the simultaneous manifestation of multiple emotions on an individual's face. This phenomenon reflects the complexity and richness of human states, where facial features dynamically convey a combination of feelings. This study embarks on a pioneering exploration of Compound Facial Expression Recognition (CFER), with a distinctive emphasis on leveraging the Label Distribution Learning (LDL) paradigm. This strategic application of LDL aims to address the ambiguity and complexity inherent in compound expressions, marking a significant departure from the dominant Single Label Learning (SLL) and Multi‐Label Learning (MLL) paradigms. Within this framework, we rigorously investigate the potential of LDL for a critical challenge in Facial Expression Recognition (FER): recognizing compound facial expressions in uncontrolled environments. We utilize the recently introduced RAF‐CE dataset, meticulously designed for compound expression assessment. By conducting a comprehensive comparative analysis pitting LDL against conventional SLL and MLL approaches on RAF‐CE, we aim to definitively establish LDL's superiority in handling this complex task. Furthermore, we assess the generalizability of LDL models trained on RAF‐CE by evaluating their performance on the EmotioNet and RAF‐DB Compound datasets. This demonstrates their effectiveness without domain adaptation. To solidify these findings, we conduct a comprehensive comparative analysis of 12 cutting‐edge LDL algorithms on RAF‐CE, S‐BU3DFE, and S‐JAFFE datasets, providing valuable insights into the most effective LDL techniques for FER in‐the‐wild.

Data-Driven Modelling of Substituted Pyrimidine and Uracil-Based Derivatives Validated with Newly Synthesized and Antiproliferative Evaluated Compounds.

The pyrimidine heterocycle plays an important role in anticancer research. In particular, the pyrimidine derivative families of uracil show promise as structural scaffolds relevant to cervical cancer. This group of chemicals lacks data-driven machine learning quantitative structure-activity relationships (QSARs) that allow for generalization and predictive capabilities in the search for new active compounds. To achieve this, a dataset of pyrimidine and uracil compounds from ChEMBL were collected and curated. A workflow was developed for data-driven machine learning QSAR using an intuitive dataset design and forwards selection of molecular descriptors. The model was thoroughly externally validated against available data. Blind validation was also performed by synthesis and antiproliferative evaluation of new synthesized uracil-based and pyrimidine derivatives. The most active compound among new synthesized derivatives, 2,4,5-trisubstituted pyrimidine was predicted with the QSAR model with differences of 0.02 compared to experimentally tested activity.

Neglected Tropical Diseases: A Chemoinformatics Approach for the Use of Biodiversity in Anti-Trypanosomatid Drug Discovery.

The development of new treatments for neglected tropical diseases (NTDs) remains a major challenge in the 21st century. In most cases, the available drugs are obsolete and have limitations in terms of efficacy and safety. The situation becomes even more complex when considering the low number of new chemical entities (NCEs) currently in use in advanced clinical trials for most of these diseases. Natural products (NPs) are valuable sources of hits and lead compounds with privileged scaffolds for the discovery of new bioactive molecules. Considering the relevance of biodiversity for drug discovery, a chemoinformatics analysis was conducted on a compound dataset of NPs with anti-trypanosomatid activity reported in 497 research articles from 2019 to 2024. Structures corresponding to different metabolic classes were identified, including terpenoids, benzoic acids, benzenoids, steroids, alkaloids, phenylpropanoids, peptides, flavonoids, polyketides, lignans, cytochalasins, and naphthoquinones. This unique collection of NPs occupies regions of the chemical space with drug-like properties that are relevant to anti-trypanosomatid drug discovery. The gathered information greatly enhanced our understanding of biologically relevant chemical classes, structural features, and physicochemical properties. These results can be useful in guiding future medicinal chemistry efforts for the development of NP-inspired NCEs to treat NTDs caused by trypanosomatid parasites.

Sulfotransferase-mediated phase II drug metabolism prediction of substrates and sites using accessibility and reactivity-based algorithms.

Sulphotransferases (SULTs) are a major phase II metabolic enzyme class contributing ~20 % to the Phase II metabolism of FDA-approved drugs. Ignoring the potential for SULT-mediated metabolism leaves a strong potential for drug-drug interactions, often causing late-stage drug discovery failures or black-boxed warnings on FDA labels. The existing models use only accessibility descriptors and machine learning (ML) methods for class and site of sulfonation (SOS) predictions for SULT. In this study, a variety of accessibility, reactivity, and hybrid models and algorithms have been developed to make accurate substrate and SOS predictions. Unlike the literature models, reactivity parameters for the aliphatic or aromatic hydroxyl groups (R/Ar-O-H), the Bond Dissociation Energy (BDE) gave accurate models with a True Positive Rate (TPR)=0.84 for SOS predictions. We offer mechanistic insights to explain these novel findings that are not recognized in the literature. The accessibility parameters like the ratio of Chemgauss4 Score (CGS) and Molecular Weight (MW) CGS/MW and distance from cofactor (Dis) were essential for class predictions and showed TPR=0.72. Substrates consistently had lower BDE, Dis, and CGS/MW than non-substrates. Hybrid models also performed acceptablely for SOS predictions. Using the best models, Algorithms gave an acceptable performance in class prediction: TPR=0.62, False Positive Rate (FPR)=0.24, Balanced accuracy (BA)=0.69, and SOS prediction: TPR=0.98, FPR=0.60, and BA=0.69. A rule-based method was added to improve the predictive performance, which improved the algorithm TPR, FPR, and BA. Validation using an external dataset of drug-like compounds gave class prediction: TPR=0.67, FPR=0.00, and SOS prediction: TPR=0.80 and FPR=0.44 for the best Algorithm. Comparisons with standard ML models also show that our algorithm shows higher predictive performance for classification on external datasets. Overall, these models and algorithms (SOS predictor) give accurate substrate class and site (SOS) predictions for SULT-mediated Phase II metabolism and will be valuable to the drug discovery community in academia and industry. The SOS predictor is freely available for academic/non-profit research via the GitHub link.

Cheminformatics analysis of indoleamine and tryptophan 2,3-dioxygenase inhibitors: A descriptor and fingerprint based machine learning approach to disclose selectivity measures

Indoleamine 2,3-dioxygenase (IDO) and tryptophan 2,3-dioxygenase (TDO) are attractive drug targets for cancer immunotherapy. After disappointing results of the epacadostat as a selective IDO inhibitor in phase III clinical trials, there is much interest in the development of the TDO selective inhibitors. In the current study, several data analysis methods and machine learning approaches including logistic regression, Random Forest, XGBoost and Support Vector Machines were used to model a data set of compounds retrieved from ChEMBL. Models based on the Morgan fingerprints revealed notable fragments for the selective inhibition of the IDO, TDO or both. Multiple fragment docking was performed to find the best set of bound fragments and their orientation in the space for efficient linking. Linking the fragments and optimization of the final molecules were accomplished by means of an artificial intelligence generative framework. Finally, selectivity of the optimized molecules was assessed and the top 4 lead molecules were filtered through PAINS, Brenk and NIH filters. Results indicated that phenyloxalamide, fluoroquinoline, and 3-bromo-4-fluroaniline confer selectivity towards the IDO inhibition. Correspondingly, 1-benzyl-1H-naphtho[2,3-d][1,2,3]triazole-4,9-dione was found to be an integral fragment for the selective inhibition of the TDO by constituting a coordination bond with the Fe atom of heme. In addition, furo[2,3-c]pyridine-2,3-diamine was found as a common fragment for inhibition of the both targets and can be used in the design of the dual target inhibitors of the IDO and TDO. The new fragments introduced here can be a useful building blocks for incorporation into the selective TDO or dual IDO/TDO inhibitors.

Integrated re-analysis of transcriptomic and proteomic datasets reveals potential mechanisms for Zika viral-based oncolytic therapy in neuroblastoma.

Paediatric neuroblastoma and brain tumours account for a third of all childhood cancer-related mortality. High-risk neuroblastoma is highly aggressive and survival is poor despite intensive multi-modal therapies with significant toxicity. Novel therapies are desperately needed. The Zika virus (ZIKV) can access the nervous system and there is growing interest in employing ZIKV as a potential therapy against paediatric nervous system tumours, including neuroblastoma. Here, we perform extensive data mining, integration and re-analysis of ZIKV infection datasets to highlight molecular mechanisms that may govern the oncolytic response in neuroblastoma cells. We collate infection data of multiple neuroblastoma cell lines by different ZIKV strains from a body of published literature to inform the susceptibility of neuroblastoma to the ZIKV oncolytic response. Integrating published transcriptomics, interaction proteomics, dependency factor and compound datasets we propose the involvement of multiple host systems during ZIKV infection. Through data mining of published literature, we observed most paediatric neuroblastoma cell lines to be highly susceptible to ZIKV infection and propose the PRVABC59 ZIKV strain to be the most promising candidate for neuroblastoma oncolytic virotherapy. ZIKV induces TNF signalling, lipid metabolism, the Unfolded Protein Response (UPR), and downregulates cell cycle and DNA replication processes. ZIKV infection is dependent on sterol regulatory element binding protein (SREBP)-regulated lipid metabolism and three protein complexes; V-ATPase, ER Membrane Protein Complex (EMC) and mammalian translocon. We propose ZIKV non-structural protein 4B (NS4B) as a likely mediator of ZIKVs interaction with IRE1-mediated UPR, lipid metabolism and mammalian translocon. Our work provides a significant understanding of ZIKV infection in neuroblastoma cells, which will facilitate the progression of ZIKV-based oncolytic virotherapy through pre-clinical research and clinical trials.

Predicting drug solubility in organic solvents mixtures: A machine-learning approach supported by high-throughput experimentation

A novel approach based on supervised machine-learning is proposed to predict the solubility of drugs and drug-like molecules in mixtures of organic solvents. Similar to quantitative structure–property relationship (QSPR) models, different solvent types are identified by molecular descriptors, which, in this study, are considered as UNIFAC subgroups. To overcome the potential lack of UNIFAC subgroups for the complex Active Pharmaceutical Ingredients (APIs) currently developed in the pharmaceutical industry, the API molecule is considered as a unique entity in the proposed modelling approach. Therefore, API solubility is predicted as a function of temperature, functional subgroups of the solvents and composition of the solvent mixture; in turn, regressors’ correlation is handled through Partial Least-Squares (PLS) regression. The method is developed and tested with experimental data of a real API and 14 organic solvents that are industrially employed for crystallisation. Solubility predictions are accurate and precise for single solvents, binary mixtures and ternary mixtures of organic solvents at different compositions and temperatures, with a determination coefficient R2 ≥ 0.90.To further test the applicability of the model, the proposed approach is applied to 9 literature organic solubility datasets of drugs and drug-like compounds and compared to benchmark solubility models in the literature. Results show that the proposed approach provides satisfactory predictions: the majority of validation and calibration data have R2 = 0.95–0.99; the ratio between RMSE (root mean squared error) of the proposed method and the range of measured solubility values is from 1 to 3 orders of magnitude smaller than the RMSE ratio obtained by the benchmark models.

Small-Molecule Inhibitors of TIPE3 Protein Identified through Deep Learning Suppress Cancer Cell Growth In Vitro.

Tumor necrosis factor-α-induced protein 8-like 3 (TNFAIP8L3 or TIPE3) functions as a transfer protein for lipid second messengers. TIPE3 is highly upregulated in several human cancers and has been established to significantly promote tumor cell proliferation, migration, and invasion and inhibit the apoptosis of cancer cells. Thus, inhibiting the function of TIPE3 is expected to be an effective strategy against cancer. The advancement of artificial intelligence (AI)-driven drug development has recently invigorated research in anti-cancer drug development. In this work, we incorporated DFCNN, Autodock Vina docking, DeepBindBC, MD, and metadynamics to efficiently identify inhibitors of TIPE3 from a ZINC compound dataset. Six potential candidates were selected for further experimental study to validate their anti-tumor activity. Among these, three small-molecule compounds (K784-8160, E745-0011, and 7238-1516) showed significant anti-tumor activity in vitro, leading to reduced tumor cell viability, proliferation, and migration and enhanced apoptotic tumor cell death. Notably, E745-0011 and 7238-1516 exhibited selective cytotoxicity toward tumor cells with high TIPE3 expression while having little or no effect on normal human cells or tumor cells with low TIPE3 expression. A molecular docking analysis further supported their interactions with TIPE3, highlighting hydrophobic interactions and their shared interaction residues and offering insights for designing more effective inhibitors. Taken together, this work demonstrates the feasibility of incorporating deep learning and MD simulations in virtual drug screening and provides inhibitors with significant potential for anti-cancer drug development against TIPE3-.

A Machine Learning Model for Evaluation of the Corrosion Inhibition Capacity of Quinoxaline Compounds

Investigating potential corrosion inhibitors via empirical research is a labor- and resource-intensive process. In this work, we evaluated various linear and non-linear algorithms as predictive models for corrosion inhibition efficiency (CIE) values using a machine learning (ML) paradigm based on the quantitative structure-property relationship (QSPR) model. In the quinoxaline compound dataset, our analysis showed that the XGBoost model performed the best predictor of other ensemble-based models. The coefficient of determination (R2), mean absolute percentage error (MAPE), and root mean squared error (RMSE) metrics were used to objectively assess this superiority. To sum up, our study offers a fresh viewpoint on the effectiveness of machine learning algorithms in determining the ability of organic compounds like quinoxaline to suppress corrosion on iron surfaces.

Towards tailored thermoelectric materials: An artificial intelligence-powered approach to material design

The pursuit of novel thermoelectric (TE) materials with exceptional properties stands as a critical frontier in material science. This transformative endeavor demands a paradigm shift in materials discovery, necessitating the integration of cutting-edge computational approaches. In this groundbreaking study, we employ the power of artificial neural networks (ANNs) to accelerate the identification of promising TE candidates. By meticulously training an ANN model on a comprehensive dataset of TE compounds and their corresponding properties, we have established a powerful tool capable of accurately predicting atoms that can be substituted into a TE material's structure to achieve desired TE properties. Our findings, validated the Materials Research Laboratory (MRL) dataset, demonstrate the exceptional accuracy of the ANN model, with an r2 detection coefficient of 0.97 in the best architectural case. This underscores the transformative potential of ANNs in propelling materials discovery forward, offering a promising avenue for the development of next-generation TE devices.

Do Chemformers Dream of Organic Matter? Evaluating a Transformer Model for Multistep Retrosynthesis.

Synthesis planning of new pharmaceutical compounds is a well-known bottleneck in modern drug design. Template-free methods, such as transformers, have recently been proposed as an alternative to template-based methods for single-step retrosynthetic predictions. Here, we trained and evaluated a transformer model, called the Chemformer, for retrosynthesis predictions within drug discovery. The proprietary data set used for training comprised ∼18 M reactions from literature, patents, and electronic lab notebooks. Chemformer was evaluated for the purpose of both single-step and multistep retrosynthesis. We found that the single-step performance of Chemformer was especially good on reaction classes common in drug discovery, with most reaction classes showing a top-10 round-trip accuracy above 0.97. Moreover, Chemformer reached a higher round-trip accuracy compared to that of a template-based model. By analyzing multistep retrosynthesis experiments, we observed that Chemformer found synthetic routes, leading to commercial starting materials for 95% of the target compounds, an increase of more than 20% compared to the template-based model on a proprietary compound data set. In addition to this, we discovered that Chemformer suggested novel disconnections corresponding to reaction templates, which are not included in the template-based model. These findings were further supported by a publicly available ChEMBL compound data set. The conclusions drawn from this work allow for the design of a synthesis planning tool where template-based and template-free models work in harmony to optimize retrosynthetic recommendations.

Based on Virtual Screening and Simulation Exploring the Mechanism of Plant-Derived Compounds with PINK1 to Postherpetic Neuralgia.

Accumulating evidence strongly supports that PINK1 mutation can mediate mitochondrial autophagy dysfunction in dopaminergic neurons. This study was conducted to determine the role of PINK1 in the pathogenesis of postherpetic neuralgia (PHN) and find new targets for its treatment. A rigorous literature review was conducted to identify 2801 compounds from more than 200 plants in Asia. Virtual screening was used to shortlist the compounds into 20 groups based on their binding energies. MM/PBSA was used to further screen the compound dataset, and vitexin, luteoloside, and 2'-deoxyadenosine-5'-monophosphate were found to have a score of - 59.439, - 52.421, and - 47.544kcal/mol, respectively. Pain behavioral quantification, enzyme-linked immunosorbent assay, quantitative polymerase chain reaction, western blotting, and transmission electron microscopy were used to confirm the effective mechanism. Vitexin had the most significant therapeutic effect on rats with PHN followed by luteoloside; 2'-deoxyadenosine-5'-monophosphate had no significant effect. Our findings suggested that vitexin could alleviate PHN by regulating mitochondrial autophagy through PINK1.

An explainable AI-assisted web application in cancer drug value prediction

In recent years, there has been an increase in the interest in adopting Explainable Artificial Intelligence (XAI) for healthcare. The proposed system includes•An XAI model for cancer drug value prediction. The model provides data that is easy to understand and explain, which is critical for medical decision-making. It also produces accurate projections.•A model outperformed existing models due to extensive training and evaluation on a large cancer medication chemical compounds dataset.•Insights into the causation and correlation between the dependent and independent actors in the chemical composition of the cancer cell.While the model is evaluated on Lung Cancer data, the architecture offered in the proposed solution is cancer agnostic. It may be scaled out to other cancer cell data if the properties are similar. The work presents a viable route for customizing treatments and improving patient outcomes in oncology by combining XAI with a large dataset. This research attempts to create a framework where a user can upload a test case and receive forecasts with explanations, all in a portable PDF report.

Machine-Learning-Based Prediction of Plant Cuticle-Air Partition Coefficients for Organic Pollutants: Revealing Mechanisms from a Molecular Structure Perspective.

Accurately predicting plant cuticle-air partition coefficients (Kca) is essential for assessing the ecological risk of organic pollutants and elucidating their partitioning mechanisms. The current work collected 255 measured Kca values from 25 plant species and 106 compounds (dataset (I)) and averaged them to establish a dataset (dataset (II)) containing Kca values for 106 compounds. Machine-learning algorithms (multiple linear regression (MLR), multi-layer perceptron (MLP), k-nearest neighbors (KNN), and gradient-boosting decision tree (GBDT)) were applied to develop eight QSPR models for predicting Kca. The results showed that the developed models had a high goodness of fit, as well as good robustness and predictive performance. The GBDT-2 model (Radj2 = 0.925, QLOO2 = 0.756, QBOOT2 = 0.864, Rext2 = 0.837, Qext2 = 0.811, and CCC = 0.891) is recommended as the best model for predicting Kca due to its superior performance. Moreover, interpreting the GBDT-1 and GBDT-2 models based on the Shapley additive explanations (SHAP) method elucidated how molecular properties, such as molecular size, polarizability, and molecular complexity, affected the capacity of plant cuticles to adsorb organic pollutants in the air. The satisfactory performance of the developed models suggests that they have the potential for extensive applications in guiding the environmental fate of organic pollutants and promoting the progress of eco-friendly and sustainable chemical engineering.

Composite descriptor based on contour and appearance for plant species identification

In this paper, we propose an effective composite descriptor combining contour and appearance features for plant species identification. The composite descriptor uses two different fusion schemes: the first is a method based on the fusion of low-level local contour and appearance features; that is, we use local triangle features and local speeded-up robust features (SURF) to describe leaf images, respectively. Then, we utilize the Hausdorff distance to measure the leaf discrepancy to complete the plant identification task. The second is a method of global feature fusion based on high-level shape and appearance features. Specifically, the Fisher vector encodes the local triangle, and SURF features into high-level shape and appearance features. Then, the Euclidean distance is used to compute the dissimilarity of leaves to realize plant leaf recognition. The composite descriptor based on these two fusion schemes can well describe the characteristics of leaf images and improve the ability to identify plant leaves. This composite descriptor is extensively tested on several standard plant databases, including simple, compound, and natural scene plant leaf datasets. Experimental results demonstrate that the composite descriptor achieves high recognition accuracy, outperforming existing state-of-the-art benchmarks. In addition, we further applied our method directly to shape recognition and achieved good recognition results, demonstrating the wide range of applications of our method.