Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Fingerprinting Interactions between Proteins and Ligands for Facilitating Machine Learning in Drug Discovery

Journal Article · · Biomolecules
DOI:https://doi.org/10.3390/biom14010072· OSTI ID:2471231
 [1];  [2];  [2];  [1];  [1]
  1. US Food and Drug Administration (USFDA), Jefferson, AR (United States). National Center for Toxicological Research
  2. National Institutes of Health (NIH), Bethesda, MD (United States)
+ Show Author Affiliations
Molecular recognition is fundamental in biology, underpinning intricate processes through specific protein–ligand interactions. This understanding is pivotal in drug discovery, yet traditional experimental methods face limitations in exploring the vast chemical space. Computational approaches, notably quantitative structure–activity/property relationship analysis, have gained prominence. Molecular fingerprints encode molecular structures and serve as property profiles, which are essential in drug discovery. While two-dimensional (2D) fingerprints are commonly used, three-dimensional (3D) structural interaction fingerprints offer enhanced structural features specific to target proteins. Machine learning models trained on interaction fingerprints enable precise binding prediction. Recent focus has shifted to structure-based predictive modeling, with machine-learning scoring functions excelling due to feature engineering guided by key interactions. Notably, 3D interaction fingerprints are gaining ground due to their robustness. Various structural interaction fingerprints have been developed and used in drug discovery, each with unique capabilities. This review recapitulates the developed structural interaction fingerprints and provides two case studies to illustrate the power of interaction fingerprint-driven machine learning. The first elucidates structure–activity relationships in β2 adrenoceptor ligands, demonstrating the ability to differentiate agonists and antagonists. The second employs a retrosynthesis-based pre-trained molecular representation to predict protein–ligand dissociation rates, offering insights into binding kinetics. Despite remarkable progress, challenges persist in interpreting complex machine learning models built on 3D fingerprints, emphasizing the need for strategies to make predictions interpretable. Binding site plasticity and induced fit effects pose additional complexities. Interaction fingerprints are promising but require continued research to harness their full potential.
Research Organization:
Oak Ridge Institute for Science and Education (ORISE), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE Office of Science (SC)
Grant/Contract Number:
SC0014664
OSTI ID:
2471231
Journal Information:
Biomolecules, Journal Name: Biomolecules Journal Issue: 1 Vol. 14; ISSN 2218-273X
Publisher:
MDPICopyright Statement
Country of Publication:
United States
Language:
English

References (54)

IChem: A Versatile Toolkit for Detecting, Comparing, and Predicting Protein–Ligand Interactions journal November 2017
Combined docking and machine learning identify key molecular determinants of ligand pharmacological activity on β2 adrenoceptor
  • Jiménez‐Rosés, Mireia; Morgan, Bradley Angus; Jimenez Sigstad, Maria
  • Pharmacology Research & Perspectives, Vol. 10, Issue 5 https://doi.org/10.1002/prp2.994
journal August 2022
Machine-learning scoring functions to improve structure-based binding affinity prediction and virtual screening: Machine-learning SFs to improve structure-based binding affinity prediction and virtual screening
  • Ain, Qurrat Ul; Aleksandrova, Antoniya; Roessler, Florian D.
  • Wiley Interdisciplinary Reviews: Computational Molecular Science, Vol. 5, Issue 6 https://doi.org/10.1002/wcms.1225
journal August 2015
Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges journal August 2018
Protein-protein recognition journal January 1995
Protein binding site analysis by means of structural interaction fingerprint patterns journal November 2011
Molecular interaction fingerprint approaches for GPCR drug discovery journal October 2016
Simple Ligand–Receptor Interaction Descriptor (SILIRID) for alignment-free binding site comparison journal June 2014
Machine learning in chemoinformatics and drug discovery journal August 2018
Harnessing systematic protein–ligand interaction fingerprints for drug discovery journal October 2022
Concepts and applications of chemical fingerprint for hit and lead screening journal November 2022
Arpeggio: A Web Server for Calculating and Visualising Interatomic Interactions in Protein Structures journal February 2017
Analysis and comparison of 2D fingerprints: Insights into database screening performance using eight fingerprint methods journal September 2010
Polypharmacology rescored: Protein–ligand interaction profiles for remote binding site similarity assessment journal November 2014
Statistical and machine learning approaches to predicting protein–ligand interactions journal April 2018
Molecular fingerprint similarity search in virtual screening journal January 2015
Developing QSAR Models with Defined Applicability Domains on PPARγ Binding Affinity Using Large Data Sets and Machine Learning Algorithms journal April 2021
Baseline Model for Predicting Protein–Ligand Unbinding Kinetics through Machine Learning journal November 2020
Prioritizing Virtual Screening with Interpretable Interaction Fingerprints journal September 2022
K DEEP : Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks journal January 2018
PotentialNet for Molecular Property Prediction journal November 2018
Public Data Set of Protein–Ligand Dissociation Kinetic Constants for Quantitative Structure–Kinetics Relationship Studies journal May 2022
Structure–Kinetic Relationship for Drug Design Revealed by a PLS Model with Retrosynthesis-Based Pre-Trained Molecular Representation and Molecular Dynamics Simulation journal May 2023
Electrotopological State Indices for Atom Types: A Novel Combination of Electronic, Topological, and Valence State Information journal November 1995
Reoptimization of MDL Keys for Use in Drug Discovery journal November 2002
Extended-Connectivity Fingerprints journal April 2010
Large-Scale Systematic Analysis of 2D Fingerprint Methods and Parameters to Improve Virtual Screening Enrichments journal April 2010
Encoding Protein–Ligand Interaction Patterns in Fingerprints and Graphs journal March 2013
Structural Protein–Ligand Interaction Fingerprints (SPLIF) for Structure-Based Virtual Screening: Method and Benchmark Study journal August 2014
Optimizing Fragment and Scaffold Docking by Use of Molecular Interaction Fingerprints journal December 2006
Mold 2 , Molecular Descriptors from 2D Structures for Chemoinformatics and Toxicoinformatics journal June 2008
Ligand-Target Interaction-Based Weighting of Substructures for Virtual Screening journal September 2008
APIF: A New Interaction Fingerprint Based on Atom Pairs and Its Application to Virtual Screening journal April 2009
Current Trends in Ligand-Based Virtual Screening: Molecular Representations, Data Mining Methods, New Application Areas, and Performance Evaluation journal January 2010
Structural Interaction Fingerprint (SIFt):  A Novel Method for Analyzing Three-Dimensional Protein−Ligand Binding Interactions journal January 2004
Correlation of Biological Activity of Phenoxyacetic Acids with Hammett Substituent Constants and Partition Coefficients journal April 1962
Are 2D fingerprints still valuable for drug discovery? journal January 2020
A workflow for exploring ligand dissociation from a macromolecule: Efficient random acceleration molecular dynamics simulation and interaction fingerprint analysis of ligand trajectories journal September 2020
Binding affinity in drug design: experimental and computational techniques journal May 2019
Development of a protein–ligand extended connectivity (PLEC) fingerprint and its application for binding affinity predictions journal September 2018
PLIP: fully automated protein–ligand interaction profiler journal April 2015
Open Babel: An open chemical toolbox journal October 2011
Open Drug Discovery Toolkit (ODDT): a new open-source player in the drug discovery field journal June 2015
Structure–activity relationship-based chemical classification of highly imbalanced Tox21 datasets journal October 2020
ProLIF: a library to encode molecular interactions as fingerprints journal September 2021
Quantitative Structure–Activity Relationship Models for Predicting Inflammatory Potential of Metal Oxide Nanoparticles journal June 2020
fingeRNAt—A novel tool for high-throughput analysis of nucleic acid-ligand interactions journal June 2022
Computational Methods in Developing Quantitative Structure-Activity Relationships (QSAR): A Review journal March 2006
Predictions of the ADMET Properties of Candidate Drug Molecules Utilizing Different QSAR/QSPR Modelling Approaches journal May 2010
Electrotopological State Atom (E-State) Index in Drug Design, QSAR, Property Prediction and Toxicity Assessment journal April 2012
Machine learning models for rat multigeneration reproductive toxicity prediction journal September 2022
Insights into Protein–Ligand Interactions: Mechanisms, Models, and Methods journal January 2016
Deep Learning Models for Predicting Gas Adsorption Capacity of Nanomaterials journal September 2022
PyPLIF: Python-based Protein-Ligand Interaction Fingerprinting journal March 2013

Similar Records

Protein-ligand binding affinity prediction using multi-instance learning with docking structures
Journal Article · Thu Jan 02 19:00:00 EST 2025 · Frontiers in Pharmacology · OSTI ID:2516789

Related Subjects

3D structural interaction fingerprints
59 BASIC BIOLOGICAL SCIENCES
biochemistry & molecular biology
drug discovery
machine learning
molecular fingerprints
predictive modeling
protein–ligand interactions
structure–activity relationships