Introduction: Substructural Analysis is a scalable and chemically interpretable approach to ligand-based virtual screening, but ranking quality depends strongly on the fragmentweighting model used. This study benchmarks Genetic Programming for evolving symbolic fragment-weighting equations against a Genetic Algorithm baseline that directly optimises integer fragment weights under a fixed Substructural Analysis scoring structure. Methods: Using a ChEMBL-derived benchmark of 15 activity classes represented by MACCS 166-bit fingerprints, we conducted 10 runs per class under a stratified 90/10 train–test protocol. Early-recognition performance was evaluated using enrichment factor at the top 1% (EF@1%) on the test partition. Between-method differences were tested using a two-sided Mann–Whitney U test (α = 0.05), with Benjamini–Hochberg adjustment across activity classes. Results: The Genetic Algorithm baseline achieved higher median EF@1% than the Genetic Programming approach in most activity classes, with statistically significant advantages in 11 of 15 classes before adjustment and 10 of 15 classes after Benjamini–Hochberg adjustment. The Genetic Programming approach remained competitive for COX, 5HT1A, 5HT3, and ACHE; for COX, it produced a higher median EF@1% than the Genetic Algorithm baseline (19.05 vs 16.67), although the difference was not statistically significant (p = 0.333). Discussion: These findings suggest that symbolic fragment-weighting is feasible and inspectable, but that enrichment performance is sensitive to how the optimisation objective is defined for early-recognition screening. Conclusion: Genetic Programming can evolve symbolic Substructural Analysis weighting equations; however, the observed performance gap suggests that future GP fitness designs should be more directly aligned with early-recognition objectives.
Introduction: Linggan Wuwei Jiangxin decoction (LGD) is a classic herbal formula for alleviating symptoms in patients with asthma. The main functions of LGD are to relieve airway inflammation, alleviate cough, and eliminate phlegm. However, the components of the prescription and the pharmacological mechanisms for treating asthma still need further clarification. Objective: The study provides preliminary insights into the mechanism of action of LGD in treating asthma by analyzing its main components, using network pharmacology and molecular docking, and validating with animal experiments. Materials and Methods: Ultra-high-performance liquid chromatography coupled to quadrupole time-of-flight mass spectrometry (UPLC-Q-TOF-MS) was used to analyze the chemical components of LGD. Network pharmacology and molecular docking were used to predict the relevant targets. Male Sprague-Dawley rats were divided into control, model, LGD (L/M/H) (10.8, 21.6, and 43.2 g/kg/d), and Guilong cough and asthma capsules (GL, positive drug) (2.43 g/kg/d) groups. Intraperitoneal injection of an ovalbumin (OVA) mixture was used to sensitize the rats on days 1 and 7. After sensitization, the rats were exposed to a 1% OVA suspension for 30 min daily for 14 days, starting from day 14. Western blot analysis was used to assess the protein expression of TNF-α, VEGFA, and STAT3. Results: UPLC-Q-TOF-MS identified 44 compounds in LGD. Network pharmacology and molecular docking identified core target proteins including TNF-α, VEGFA, and STAT3. The experiments revealed that LGD reduces the serum levels of the inflammatory markers interleukin- 4 (IL-4), immunoglobulin E (IgE), and interferon-γ (IFN-γ) in asthmatic rats and affects energy metabolism. Additional studies revealed that LGD could inhibit the expression of TNF-α, VEGFA, and STAT3 proteins. Conclusions: This preliminary study indicates that LGD ameliorates asthma in rats by inhibiting the expression of TNF-α, VEGFA, and STAT3 proteins. More in vitro experiments are required to clarify the effects of LGD on these target proteins.
Introduction: Diabetes mellitus is a rapidly expanding chronic disease, prompting interest in plant-derived natural products as adjuncts to conventional therapy because of their improvements in glycaemic control and reduced complications. To evaluate phytochemicals' potential as α-amylase inhibitors using an integrated in-silico workflow. Methods: Acacia senegal phytochemicals retrieved from the IMPPAT 2.0 database were evaluated their in-silico studies against α-amylase inhibitors using molecular docking, DFT, pharmacokinetic and toxicity profiling, in addition to PASS prediction, network pharmacology and MD simulations. Results: Docking of 31 compounds was carried out, and the top three ligands, which are: IMPHY014840 (-9.321 kcal/mol), IMPHY014838 (-9.208 kcal/mol) and IMPHY006972 (-9.026 kcal/mol), were selected. Their favorable binding energies indicated strong predicted affinity toward the selected enzyme target. DFT calculations showed identical HOMO-LUMO gaps of 6.936 eV for the first two ligands, whereas the third one displayed a larger gap of 9.484 eV, indicating lower chemical reactivity. Furthermore, pharmacokinetic screening indicated high human intestinal absorption (75-86 %) and favorable Caco-2 permeability for the top three compounds, particularly for IMPHY014840 and IMPHY014838. PASS analysis suggested protease target affinity for IMPHY014840 and GPCR/transcription factor activity for IMPHY014838, expanding their therapeutic scope beyond α-amylase inhibition. MD trajectories confirmed overall complex stability, with IMPHY014838 exhibiting marginally lower ligand RMSD and therefore slightly superior dynamical stability. Discussion: The present study identified IMPHY014840 and IMPHY014838 as promising α- amylase inhibitors, with docking scores of -9.321 and -9.208 kcal/mol, respectively. DFT, ADMET, toxicity, PASS, and 100 ns MD simulations indicate stable enzyme-ligand binding, high predicted intestinal absorption, and multitarget potential. Network pharmacology further suggests that these compounds act on a broad set of diabetes related targets, supporting their value as antidiabetic lead candidates. Conclusion: The combined computational evidence supports IMPHY014840 and IMPHY014838 as promising natural α-amylase inhibitors for type 2 DM management, and recommends in vitro, in vivo, and formulation optimization to address their limitations.
Introduction: Virtual screening (VS) is a widely used computational strategy in early- stage drug discovery for identifying bioactive compounds from large chemical libraries. Although structure-based and ligand-based approaches have demonstrated success individually, their integration into a unified deep learning framework remains limited. This study presents NNGeoGVS (Neural Network Geometric Graph-based Virtual Screening), an Equivariant Graph Neural Network (EGNN)-based framework that integrates ligand molecular topology and protein active-site geometry for activity prediction. Methods: NNGeoGVS represents ligands and protein binding sites as molecular graphs and learns structure–activity relationships through end-to-end message passing using PyTorch Geometric. The framework combines node-level atomic features, edge-level bond descriptors, and global geometric and pharmacophore descriptors. Active-site geometry is characterized using Ultra-Fast Shape Recognition (USR) and convex hull algorithms. These features are integrated through a multi-branch GNN architecture with late fusion, while focal loss optimization and graph-level augmentation address class imbalance. Results: NNGeoGVS was evaluated on the DUD-E dataset (8 kinase targets) and the LITPCBA benchmark (15 targets). Compared with NNGeoAS and other GNN-based methods, it achieved average EF1% values of 35.92 and 17.03 and ROC-AUC scores of 0.98 and 0.77 on DUD-E and LIT-PCBA, respectively. Discussion: The integration of ligand topology with protein active-site geometry improves enrichment and classification performance, demonstrating the effectiveness of combining complementary structural information within a unified EGNN framework. Conclusion: We proposed NNGeoGVS, a robust framework for virtual screening that integrates structural information of both proteins and ligands and demonstrated robust predictive performance on benchmark datasets.
Introduction: Colonization by Staphylococcus aureus is a key event preceding invasive infections. During host interaction, the bacterium expresses Microbial Surface Components Recognizing Adhesive Matrix Molecules (MSCRAMMs), a family of surface-associated adhesins that mediate attachment to extracellular matrix components and promote persistence. Targeting conserved MSCRAMM proteins may provide a preventive strategy to limit bacterial establishment. Materials and Methods: A total of 249,079 bioactive compounds were compiled from the published literature and public databases. Following screening for drug-likeness and pharmacokinetic properties, 1,600 compounds were shortlisted. Core-genome analysis of MSCRAMM proteins was conducted using panX to identify conserved targets. Druggability and safety profiling were performed using the Target-Pathogen database and sequence similarity analysis against the human proteome to minimize off-target effects. Selected compounds were subjected to molecular docking, inhibition constant estimation, and molecular dynamics simulations to evaluate binding affinity and complex stability. Results: Among the 24 MSCRAMM proteins identified, six conserved proteins were prioritized as potential therapeutic targets. All demonstrated favorable druggability characteristics and minimal similarity to human proteins. Docking analysis revealed 18 compounds with strong binding affinities, of which 12 were non-hepatotoxic and exhibited stable interactions with multiple targets. Molecular dynamics simulations confirmed the structural integrity and sustained binding of the selected protein–ligand complexes. Discussion: These findings highlight the potential of targeting conserved MSCRAMM proteins as an anti-virulence approach and provide a basis for the future development of alternative strategies against antibiotic-resistant S. aureus. Conclusion: The identified compounds represent promising candidates for further experimental validation aimed at preventing S. aureus colonization.
