HIV-1 (human immunodeficiency virus-1) has been causing severe pandemics by attacking the immune system of its host. Left untreated, it can lead to AIDS (acquired immunodeficiency syndrome), where death is inevitable due to opportunistic diseases. Therefore, discovering new antiviral drugs against HIV-1 is crucial. This study aimed to explore a novel machine learning approach to classify compounds that inhibit HIV-1 integrase and screen the dataset of repurposing compounds. The present study had two main stages: selecting the best type of fingerprint or molecular descriptor using the Wilcoxon signed-rank test and building a computational model based on machine learning. In the first stage, we calculated 16 different types of fingerprint or molecular descriptors from the dataset and used each of them as input features for 10 machine-learning models, which were evaluated through cross-validation. Then, a meta-analysis was performed with the Wilcoxon signed-rank test to select the optimal fingerprint or molecular descriptor types. In the second stage, we constructed a model based on the optimal fingerprint or molecular descriptor type. This data followed the machine learning procedure, including data preprocessing, outlier handling, normalization, feature selection, model selection, external validation, and model optimization. In the end, an XGBoost model and RDK7 fingerprint were identified as the most suitable. The model achieved promising results, with an average precision of 0.928 ± 0.027 and an F1-score of 0.848 ± 0.041 in cross-validation. The model achieved an average precision of 0.921 and an F1-score of 0.889 in external validation. Molecular docking was performed and validated by redocking for docking power and retrospective control for screening power, with the AUC metrics being 0.876 and the threshold being identified at −9.71 kcal mol−1. Finally, 44 compounds from DrugBank repurposing data were selected from the QSAR model, then three candidates were identified as potential compounds from molecular docking, and PSI-697 was detected as the most promising molecule, with in vitro experiment being not performed (docking score: −17.14 kcal mol−1, HIV integrase inhibitory probability: 69.81%)
Anaplastic lymphoma kinase (ALK), a tyrosine kinase receptor, is identified as a crucial target in the progression of anticancer therapeutics for non-small cell lung cancer. This study has executed a Graph Neural Network (GNN) model and compared it with three machine learning (ML) models based on fingerprints for rapid anticancer bioactivity prediction. ALK inhibitors with IC50 values were extracted from the REAXYS database. Following preprocessing, these inhibitors constituted a dataset of 1664 molecules. Subsequently, GNN and ML models were constructed on a training set. The generalizability of these models was assessed by internal and external validation procedures. The graph neural network model yielded promising results, with an average precision of $0.879\pm 0.041$ and an $F1$ score of $0.804\pm 0.049$ in cross-validation. In external validation, the model achieved an average precision of 0.938 and an $F1$ score of 0.863, surpassing the results of the ML models. Therefore, we can infer that the predictive model developed using the GNN is apt for the problem at hand and can be utilized to predict the biological activity of novel ALK inhibitors.
15 September 2025 in Journal of Computer-Aided Molecular Design
This study addresses the urgent need for novel Anaplastic lymphoma kinase (ALK) inhibitors in Non-Small Cell Lung Cancer (NSCLC) treatment, focusing on the ALK-positive mutation variant (5% of the cases). As only five Food and Drug Administration (FDA)-approved ALK inhibitors are on the market, the demand for effective drugs persists. Leveraging the power of Artificial Intelligence (AI) including machine learning (ML), and deep learning, our research aimed to expedite the screening of novel ALK inhibitors. Notably, the machine learning-based XGBoost algorithm exhibited compelling results with an external validation (EV)-f1 score of 0.921, and an EV-Average Precision (AP) of 0.961, alongside a cross-validation (CV)-f1 score of 0.888±0.039 and a CV-AP of 0.939±0.032. Besides, the deep learning-based Artificial Neural Network (ANN) model demonstrated excellent performance with an EV-f1 score of 0.930 and an EV-AP of 0.955, complemented by a CV-f1 score of 0.891±0.037 and a CV-AP of 0.934±0.040. The present study undertook a comparative analysis between the traditional ML models, the ANN model, and the Graph Neural Network (GNN) model, which is a product of our recent research endeavors. The findings reveal that, despite the advancements in neural network models, traditional machine learning models exhibited superior performance over the GNN model. During this research, these models were employed in conjunction with a consensus molecular docking model to screen a total of 120,571 compounds virtually, leading to the identification of three promising ALK inhibitors: CHEMBL1689515, CHEMBL2380351, and CHEMBL102714. The study recommends further molecular dynamic simulations, in vitro tests, target-specific experimental data acquisition for active learning, and application of advanced AI models like geometric interaction GNN and generative AI for molecular optimization.
HIV-1 (Human immunodeficiency virus-1) has been causing severe pandemics by attacking the immune system of its host. Left untreated, it can lead to AIDS (acquired immunodeficiency syndrome), where death is inevitable due to opportunistic diseases. Therefore, discovering new antiviral drugs against HIV-1 is crucial. This study aimed to explore a novel machine learning approach to classify compounds that inhibit HIV-1 integrase and screen the dataset of repurposing compounds. The present study had two main stages: selecting the best type of fingerprint or molecular descriptor using the Wilcoxon signed-rank test and building a computational model based on machine learning. In the first stage, we calculated 16 different types of fingerprint or molecular descriptors from the dataset and used each of them as input features for 10 machine-learning models, which were evaluated through cross-validation. Then, a meta-analysis was performed with the Wilcoxon signed-rank test to select the optimal fingerprint or molecular descriptor types. In the second stage, we constructed a model based on the optimal fingerprint or molecular descriptor type. This data followed the machine learning procedure, including data preprocessing, outlier handling, normalization, feature selection, model selection, external validation, and model optimization. In the end, an XGBoost model and RDK7 fingerprint were identified to be the most suitable. The model achieved promising results, with an average precision of 0.928 ± 0.027 and an F1-score of 0.848 ± 0.041 in cross-validation. The model achieved an average precision of 0.921 and an F1-score of 0.889 in external validation. Molecular docking was performed and validated by redocking for docking power and retrospective control for screening power, with the AUC metrics being 0.876 and the threshold being identified at –9.71 kcal/mol. Finally, 44 compounds from DrugBank repurposing data were selected from the QSAR model, then three candidates were identified as potential compounds from molecular docking, and PSI-697 was detected as the most promising molecule, with in vitro experiment being not performed (docking score: -17.14 kcal/mol, HIV integrase inhibitory probability: 69.81%)
(VEGFR-2), which belongs to the protein tyrosine kinase family, emerges as one of the most significant targets of interest. The ongoing Food and Drug Administration (FDA) approval of novel therapeutic medicines towards VEGFR-2 emphasizes the urgent need to discover sophisticated molecular structures that are capable of reliably limiting VEGFR-2 activity. Recognizing the huge potential of deep learning-based molecular model advancements, we focused our study on exploring the chemical space to find small molecules potentially inhibiting VEGFR-2. To achieve this goal, we utilized the Junction Tree Variational Autoencoder in combination with two optimization approaches on the latent space: the local Bayesian optimization on the initial dataset and the gradient ascent on nine FDA-approved drugs targeting VEGFR-2. The optimization results yielded a set of 493 uncharted small molecules. Quantitative structure-activity relationship (QSAR) models and molecular docking were used to assess the generated molecules for their inhibitory potential using their predicted pIC50 and binding affinity. The QSAR model constructed on RDK7 fingerprints using the CatBoost algorithm achieved remarkable coefficients of determination (R2) of 0.792 ± 0.075 and 0.859 with respect to internal and external validation. Molecular docking was implemented using the 4ASD complex with optimistic retrospective control results (the ROC-AUC value being 0.710 and the binding activity threshold being -7.90 kcal/mol). Newly generated molecules possessing acceptable results corresponding to both assessments were shortlisted and checked for interactions with the protein at the binding site on important residues, including Cys919, Asp1046, and Glu885