Headed to ACS San Diego? Join us for Happy Hour!
← Back to glossary

Virtual Screening

Field
Field
Field

Virtual screening is a computational technique used to identify potential ligands from large libraries of compounds by predicting their interactions with a biological target. It is analogous to High-Throughput Screening, except less time-consuming or costly. It involves the use of various algorithms and models to evaluate the binding affinity and other properties of the compounds.

There are two main types of virtual screening:

  1. Ligand-Based Virtual Screening (LBVS): Uses information about known active ligands to identify new compounds with similar properties.
  2. Structure-Based Virtual Screening (SBVS): Uses the 3D structure of the biological target to predict the complementarity of different molecules.

Importance in Computational Drug Discovery

  1. Efficiency: Virtual screening allows for the rapid evaluation of up to billions of compounds, which would not be possible with the experimental equivalent, High-Throughput Screening (HTS).
  2. Cost-Effectiveness: It reduces the need for expensive and time-consuming experimental screening by prioritizing the most promising candidates for further testing.
  3. Hit Identification: Helps identify initial "hit" compounds that can be optimized through further studies and development.
  4. Optimization: Assists in the optimization of lead compounds by predicting modifications that can enhance binding affinity and selectivity.
  5. Diversity: Enables the exploration of diverse chemical spaces, increasing the chances of finding unique ligands.

Key Tools

1. AutoDock Vina: An open-source program for molecular docking and virtual screening.

2. Schrödinger's Glide: A software tool for molecular docking and virtual screening.

3. MOE (Molecular Operating Environment): A comprehensive suite for molecular modeling, including virtual screening.

4. LigandScout: A software tool for creating pharmacophore models and performing virtual screening.

Literature

"Virtual Screening in Drug Discovery"

Publication Date: 2006-11-02

DOI: 10.1002/9780470131862.CH3

Summary: Focuses on methodologies applied to computer-based, in silico, or virtual screening in the early stages of drug discovery.

"Virtual Screening Algorithms in Drug Discovery: A Review Focused on Machine and Deep Learning Methods"

Publication Date: 2023-05-05

DOI: 10.3390/ddc2020017

Summary: Provides an overview of algorithms used in virtual screening, including machine and deep learning methods, and their contributions to drug discovery.

"Quantum Machine Learning Framework for Virtual Screening in Drug Discovery: A Prospective Quantum Advantage"

Publication Date: 2022-04-08

DOI: 10.1088/2632-2153/acb900

Summary: Proposes a framework combining a classical Support Vector Classifier with quantum kernel estimation for ligand-based virtual screening.

"Insights into Machine Learning-Based Approaches for Virtual Screening in Drug Discovery: Existing Strategies and Streamlining through FP-CADD"

Publication Date: 2020-08-06

DOI: 10.2174/1570163817666200806165934

Summary: Discusses major machine learning approaches in ligand-based virtual screening and introduces a protocol named FP-CADD for drug discovery.

"An Artificial Intelligence Accelerated Virtual Screening Platform for Drug Discovery"

Publication Date: 2024-03-29

DOI: 10.1101/2024.03.28.587262

Summary: Describes a highly accurate structure-based virtual screening method, RosettaVS, for predicting docking poses and binding affinities, and its application in screening multi-billion compound libraries.

"Merging Ligand-Based and Structure-Based Methods in Drug Discovery: An Overview of Combined Virtual Screening Approaches"

Publication Date: 2020-10-01

DOI: 10.3390/molecules25204723

Summary: Analyzes strategies for combining ligand-based and structure-based virtual screening methods to enhance drug discovery success.

"QSAR-Based Virtual Screening: Advances and Applications in Drug Discovery"

Publication Date: 2018-11-13

DOI: 10.3389/fphar.2018.01275

Summary: Summarizes recent trends in QSAR-based virtual screening and demonstrates successful applications in identifying compounds with desired properties.

"Per-Residue Energy Decomposition Pharmacophore Model to Enhance Virtual Screening in Drug Discovery: A Study for Identification of Reverse Transcriptase Inhibitors as Potential Anti-HIV Agents"

Publication Date: 2016-04-11

DOI: 10.2147/DDDT.S95533

Summary: Introduces a novel virtual screening approach using per-residue energy decomposition from MD simulation ensembles to create more reliable pharmacophore models.

"Structure-Based Virtual Screening of Vast Chemical Space as a Starting Point for Drug Discovery"

Publication Date: 2024-06-06

DOI: 10.1016/j.sbi.2024.102829

Summary: Reviews structure-based virtual screening of vast chemical spaces, highlighting successful applications in drug discovery for therapeutically important targets.

"First Fully-Automated AI/ML Virtual Screening Cascade Implemented at a Drug Discovery Centre in Africa"

Publication Date: 2022-12-15

DOI: 10.1038/s41467-023-41512-2

Summary: Presents ZairaChem, an AI/ML-based tool for small-molecule activity prediction models, demonstrating increased rate of progression in drug discovery.