Related Experiment Video
Updated: Nov 9, 2025

Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro
Published on: September 26, 2025
Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on
Christian Feldmann1, Jürgen Bajorath2
1Department of Life Science Informatics and Data Science, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität, Friedrich-Hirzebruch-Allee 6, 53115, Bonn, Germany.
Understanding multi-target drug compounds is key in drug discovery. Machine learning revealed that promiscuous compounds possess specific structural features, but these vary by target combination, not universally.
Area of Science:
- Medicinal Chemistry
- Computational Drug Discovery
- Pharmacology
Background:
- Multi-target compounds (promiscuity) are vital in modern drug discovery.
- The molecular underpinnings of multi-target activity remain poorly understood.
- Generalizable structural features distinguishing promiscuous from single-target compounds are unknown.
Purpose of the Study:
- To systematically investigate structural characteristics of multi-target compounds.
- To determine if generalizable structural features define promiscuity.
- To leverage machine learning for analyzing structure-activity relationships in promiscuous compounds.
Main Methods:
- Developed a machine learning-based test system for analyzing compound promiscuity.
- Performed over 860,000 diagnostic predictions on compound structures.
- Utilized feature weighting and mapping to identify characteristic substructures.
Main Results:
- Identified specific structural features associated with multi-target activity.
- Demonstrated that these features are target-combination dependent, not general.
- Characteristic substructures were successfully mapped in test compounds.
Conclusions:
- Compelling evidence supports the existence of target-specific structural characteristics for promiscuous compounds.
- Findings indicate a lack of universal structural markers for promiscuity.
- Results offer valuable insights for designing novel multi-target drugs.
More Related Videos
07:51High-throughput Identification of Synergistic Drug Combinations by the Overlap2 Method
Published on: May 21, 2018
09:04Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow
Published on: April 18, 2019
Related Concept Videos
Drug-Receptor Bonds
In...
Drug Discovery: Overview
Structure-Activity Relationships and Drug Design
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
Conserved Binding Sites
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Protein-protein Interfaces