Development of classification models for predicting inhibition of mitochondrial fusion and fission using machine learning methods

Multi-task pretrained language model with novel application domains enables more comprehensive health and ecological toxicity prediction

In silico models for screening substances of healthy and ecological concern are essential for effective chemical management. However, current data-driven toxicity prediction models confront formidable challenges related to expressive capacity, data scarcity, and reliability issues. Thus, this study introduces TOX-BERT, a SMILES-based pretrained model for screening health and ecological toxicity. Results show that masked atom recovery pretraining and multi-task learning offer promising solutions to enhance model capacity and address data scarcity issues. Two novel application domain (AD) parameters, termed PCA-AD and LDS, were proposed to improve prediction reliability of TOX-BERT with accuracy surpassing 90 % and mean absolute error (MAE) below 0.52. TOX-BERT was applied to 18,905 IECSC chemicals, revealing distinct toxicity relationships that align with experimental studies such as those between cardiotoxicity and acute ecotoxicity. In addition to previous PBT screening, 156 potential high-risk chemicals for specific endpoint were identified covering 7 categories. Furthermore, a SMILES-based toxicity site detection approach was developed for structural toxicity analysis. These advancements carry profound implications to address challenges faced by current data-driven toxicity prediction models. TOX-BERT emerges as a valuable tool for more comprehensive, reliable, and applicable predictions of health and ecological toxicity in chemical risk assessment and management.

Fragment-based investigation of thiourea derivatives as VEGFR-2 inhibitors: a cross-validated approach of ligand-based and structure-based molecular modeling studies

Angiogenesis is mediated by the vascular endothelial growth factor (VEGF) that plays a key role in the modulation of progression, invasion and metastasis, related to solid tumors and hematological malignancies. Several small-molecule VEGFR-2 inhibitors are marketed, but their usage is restricted to specific cancers due to severe toxicities. Therefore, cost-effective novel small molecule VEGFR-2 inhibitors may be an alternative to overcome these adverse effects. Here, a set of thiourea-based VEGFR-2 inhibitors were considered for a combined fragment-based QSAR technique, structure-based molecular docking followed by molecular dynamics simulation studies to acquire insights into the key structural attributes and the binding pattern of enzyme-ligand interactions. Noticeably, amine-substituted quinazoline phenyl ring and a higher number of nitrogen atoms, and the hydrazide function in the molecular structure are crucial for VEGFR-2 inhibition whereas methoxy groups are detrimental to VEGFR-2 inhibition. The MD simulation study of sorafenib and thiourea derivatives explored the significance of urea and thiourea moiety binding at VEGFR-2 active site that can be utilized further in the future to design molecules for greater binding stability and better VEGFR-2 selectivity. Therefore, such findings can be beneficial for the development of newer VEGFR-2 inhibitors for further refinement to acquire better therapeutic efficacy.Communicated by Ramaswamy H. Sarma.

Machine learning-based models for predicting gas breakthrough pressure of porous media with low/ultra-low permeability

Gas breakthrough pressure is a significant parameter for the gas exploration and safety evaluation of engineering barrier systems in the carbon dioxide storage, remediation of contaminated sites, and deep geological repository for disposal of high-level nuclear waste, etc. Test for determining gas breakthrough pressure is very difficult and time-consuming, due to the low/ultra-low conductivity of the specimen. It is also difficult to get a comprehensive and high-precision model based on limited results obtained through individual experiments, as the measurements of gas breakthrough pressure were influenced by many factors. In this study, a collected database was built that covered a lot of former test data, and then, two models were developed by the random forest (RF) algorithm and multiexpression programming (MEP) method. The MEP model constructed with explicit expressions for the gas breakthrough pressure overcame the drawbacks of common "black box" models. Meanwhile, five significant indicators were selected from ten common features using the permutation importance algorithm. The RF model was interpreted by the Shapley value and the PDP/ICE plots, while the MEP model was analyzed through the proposed explicit expression, showing strong consistence with that in former studies. Finally, robustness analysis was conducted, and stability of the proposed two models was verified.

Critical features identification for chemical chronic toxicity based on mechanistic forecast models

Facing billions of tons of pollutants entering the ocean each year, aquatic toxicity is becoming a crucial endpoint for evaluating chemical adverse effects on ecosystems. Notably, huge amount of toxic chemicals at environmental relevant doses can cause potential adverse effects. However, chronic aquatic toxicity effects of chemicals are much scarcer, especially at population level. Rotifers are highly sensitive to toxicants even at chronic low-doses and their communities are usually considered as effective indicators for assessing the status of aquatic ecosystems. Therefore, the no observed effect concentration (NOEC) for population abundance of rotifers were selected as endpoints to develop machine learning models for the prediction of chemical aquatic chronic toxicity. In this study, forty-eight binary models were built by eight types of chemical descriptors combined with six machine learning algorithms. The best binary model was 1D & 2D molecular descriptors - random trees model (RT) with high balanced accuracy (BA) (0.83 for training and 0.83 for validation set), and Matthews correlation coefficient (MCC) (0.72 for training set and 0.67 for validation set). Moreover, the optimal model identified the primary factors (SpMAD_Dzp, AMW, MATS2v) and filtered out three high alerting substructures [c1cc(Cl)cc1, CNCO, CCOP(=S)(OCC)O] influencing the chronic aquatic toxicity. These results showed that the compounds with low molecular volume, high polarity and molecular weight could contribute to adverse effects on rotifers, facilitating the deeper understanding of chronic toxicity mechanisms. In addition, forecast models had better performances than the common models embedded into ECOSAR software. This study provided insights into structural features responsible for the toxicity of different groups of chemicals and thereby allowed for the rational design of green and safer alternatives.

Graph Attention Network Model with Defined Applicability Domains for Screening PBT Chemicals

In silico models for screening environmentally persistent, bio-accumulative, and toxic (PBT) substances are necessary for sound management of chemicals. Due to the complex structure-activity landscapes (SALs) on the PBT attributes, previous models for screening PBT chemicals lack either applicability domain (AD) characterizations or interpretability, restricting their applications. Herein, graph attention networks (GATs), a novel neural network architecture, were introduced to construct models for screening PBT chemicals. Results show that the GAT model not only outperformed those in previous studies but also exhibited interpretability since it optimizes attention weight parameters (P_AW) that indicate contributions of each atom to the PBT attributes. An AD characterization termed AD_FP-AC, which considers both molecular fingerprint (FP) similarities and compounds at activity cliffs (ACs) of SALs, was proposed to describe the ADs, which further assured the performance of the GAT model. Eight previously unidentified classes of compounds were identified as PBT chemicals from the Inventory of Existing Chemical Substances in China. The GAT model together with the AD_FP-AC characterization may serve as efficient tools for screening PBT chemicals, and the modeling methodology can be applied to other physicochemical, environmental, behavioral, and toxicological parameters of chemicals that are necessary for their risk assessment and management.

Machine learning models on chemical inhibitors of mitochondrial electron transport chain

Chemicals can induce adverse effects in humans by inhibiting mitochondrial electron transport chain (ETC) such as disrupting mitochondrial membrane potential, enhancing oxidative stress and causing some diseases. Thus, identifying ETC inhibitors (ETCi) is important to chemical risk assessment and protecting the public health. However, it is not feasible to identify all ETCi with experimental methods. Quantitative structure-activity relationship (QSAR) modeling is a promising method to rapidly and effectively identify ETCi. In this study, QSAR models for predicting ETCi were developed using machine learning methods. A clustering-based under-sampling (CBUS) method was developed to handle the imbalance issue in training sets. Structure-activity landscapes were generated and analyzed for training sets generated by the CBUS method. The consensus QSAR models constructed with CBUS achieved satisfactory performances (balanced accuracy = 0.852) in 100 iterations of five-fold cross validations, indicating the models can effectively classify ETCi. The classification model was further employed to screen chemicals in the Inventory of Existing Chemical Substances of China and 13 chemicals were identified as ETCi. Fifteen structural alerts for ETCi were identified in this study. These results demonstrated that the model and structural alerts are useful to screen ETCi.

A robust classification-dependent multi-molecular modelling study on some biphenyl sulphonamide based MMP-8 inhibitors

Matrix metalloproteinases (MMPs) are a group of zinc and calcium-dependent endopeptidases, which contribute to different physiological and biological activities via extracellular matrix (ECM) degradation. Matrix metalloproteinase-8 (MMP-8) belongs to type-II collagenases of the MMP family that has contribution in several physiological disorders such as cardiovascular diseases, joint, renal, digestive and respiratory disorders as well as in cancer. In clinical study, MMP-8 is found to be associated with periodontal disease condition. Therefore, MMP-8 specific inhibitors should be developed to target these disorders. The biphenyl sulphonamide (BPS) moiety is one of the crucial structural characteristics found in several MMP-8 inhibitors. Here, different classification-based molecular modelling methods were used to explore the structural features that lead to the activity variation of a series of MMP-8 inhibitors possessing a BPS moiety. Our current classification-based structural analysis of these BPS-derived MMP-8 inhibitors was able to identify the importance of several structural features such as the tetrahydroisoquinoline and N-Boc pyridyl groups, which have positive influences on MMP-8 inhibition. This study was also reflected the importance of the zinc-binding groups (ZBGs) like the hydroxamate and phosphonate for potent and sub-nanomolar range MMP-8 inhibition, which may benefit the development of highly potent MMP-8 inhibitors.