Facilitating structure-based drug discovery with an artificial intelligence-driven virtual screening platform.

Topological deep learning for drug–target interaction, virtual screening, and docking scoring: a practical, benchmark-driven review

A decision-oriented taxonomy and a benchmark-driven evaluation playbook that specifies minimum standards for splits, metrics, baselines, and ablations to isolate the topological contribution are presented.

ARTIFICIAL INTELLIGENCE-ASSISTED DRUG DESIGN COMBINED WITH MOLECULAR DOCKING FOR PRIORITIZATION OF POTENTIAL LEAD MOLECULES ACROSS FIVE THERAPEUTIC TARGETS

Background: Artificial intelligence-assisted drug discovery can reduce the chemical search space by integrating molecular generation, drug-likeness assessment and structure-based docking. However, computational rankings require careful validation and should be interpreted as prioritization rather than evidence of therapeutic efficacy. Objectives: To integrate AI-assisted molecular design, physicochemical/ADMET screening, molecular docking and ligand–protein interaction analysis for identification of potential leads across selected cancer, metabolic and neurodegenerative targets. Methods: A documented computational workflow was applied to five ligand-bound human targets—EGFR (1M17), KRAS G12C (5V71), DPP-4 (1X70), PTP1B (1C83) and AChE (4EY7). The supplied thesis dataset described progressive filtering of a 1350-member virtual library to 14 final candidates, followed by drug-likeness/ADMET assessment, AutoDock Vina docking and redocking validation. Candidate prioritization integrated docking score, target-relevant interactions and computational pharmacokinetic/toxicity characteristics. Results: All five reference systems passed the predefined redocking criterion of <2.0 Å, with RMSD values of 0.65–1.14 Å. The prioritized leads were CAN-AI-01 (EGFR, −9.71 kcal/mol), KRA-AI-01 (KRAS G12C, −9.12 kcal/mol), DIA-AI-01 (DPP-4, −9.35 kcal/mol), PTP-AI-01 (PTP1B, −8.84 kcal/mol) and NEU-AI-01 (AChE, −12.42 kcal/mol). All five showed zero reported Lipinski violations, high predicted gastrointestinal absorption, negative Ames predictions and no predicted hERG inhibition or hepatotoxicity in the supplied screening dataset. Conclusions: The integrated workflow supports computational narrowing of chemical space and target-specific lead prioritization. The identified molecules should be considered computational leads requiring biochemical, cellular, pharmacokinetic and toxicity validation before any therapeutic claim is made.

Open-Sourced In Silico Drug Screening.

Real-World Assessment of Machine-Learned Docking Using Bioassay-Derived Benchmarks.

The rapid expansion of compound libraries has significantly advanced drug discovery, especially through ultralarge library screenings that provide access to vast chemical spaces. However, the sheer scale of these libraries introduces substantial challenges in the early stages of drug discovery. While it is true that searching larger libraries can improve the hit rate of a virtual screening campaign, as the available chemical space has increased to over 64 billion molecules, identifying relevant information becomes a complex and time-consuming task. Machine learning (ML)-based docking methods and scoring functions offer a potential solution by providing increased speed and scalability. However, much of their reported success is based on benchmark data sets that rely on constructed decoys and ligand sets, which often have hidden biases that can artificially inflate performance and fail to capture the challenges of real-world screening. In this work, we systematically evaluate the performance of a popular ML-based docking method, DiffDock-Pocket, on high-throughput screening (HTS) data sets derived from the PubChem BioAssay database, a premier source of bioactivity data. By using HTS data sets as a more realistic benchmark, we aim to provide a clearer picture of how ML models perform in practical virtual screening scenarios compared to traditional physics-based docking approaches. Our work highlights the strengths and limitations of current ML methods and offers insights into their reliability and applicability to prospective applications in drug discovery.

Quantum-Driven High-Throughput Docking: Advances in Molecular Scoring and Drug Discovery.

Recent developments in QM-based molecular docking and HTD are reviewed, focusing on cases where QM is used explicitly in docking workflows.

SurroDock: A Deep Learning Surrogate for Accelerated Pre-Docking Ligand Prioritization in Structure-Based Virtual Screening

Results indicate that 2D-based docking-score surrogate modeling can provide a reproducible and retrainable strategy for large-scale structure-based virtual screening by concentrating docking resources on a smaller, enriched subset of compounds.