Development of a Protein-Ligand Extended Connectivity (PLEC) Fingerprint and Its Application for Binding Affinity Predictions.

2018 ◽  
Author(s):  
Maciej Wójcikowski ◽  
Michał Kukiełka ◽  
Marta Stepniewska-Dziubinska ◽  
Pawel Siedlecki
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Linear Model ◽  
Binding Affinity ◽  
Small Molecule ◽  
3D Structure ◽  
Protein Ligand Interactions ◽  
Core Set ◽  
Ligand Interactions ◽  
Extended Connectivity

<div>Fingerprints (FPs) are the most common small molecule representation in cheminformatics. There are a wide variety of fingerprints, and the Extended Connectivity Fingerprint (ECFP) is one of the best-suited for general applications. Despite the overall FP abundance, only a few FPs represent the 3D structure of the molecule, and hardly any encode protein-ligand interactions. Here, we present a Protein-Ligand Extended Connectivity (PLEC) fingerprint that implicitly encodes protein-ligand interactions by pairing the ECFP environments from the ligand and the protein. PLEC fingerprints were used to construct different machine learning (ML) models tailored for predicting protein-ligand affinities (pK<sub>i/d</sub>). Even the simplest linear model built on the PLEC fingerprint achieved R<sub>p</sub>=0.83 on the PDBbind v2016 "core set”, demonstrating its descriptive power. The PLEC fingerprint has been implemented in the Open Drug Discovery Toolkit (https://github.com/oddt/oddt).</div>

Development of a Protein-Ligand Extended Connectivity (PLEC) Fingerprint and Its Application for Binding Affinity Predictions.

2018 ◽  
Author(s):  
Maciej Wójcikowski ◽  
Michał Kukiełka ◽  
Marta Stepniewska-Dziubinska ◽  
Pawel Siedlecki
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Linear Model ◽  
Binding Affinity ◽  
Small Molecule ◽  
3D Structure ◽  
Protein Ligand Interactions ◽  
Core Set ◽  
Ligand Interactions ◽  
Extended Connectivity

<div>Fingerprints (FPs) are the most common small molecule representation in cheminformatics. There are a wide variety of fingerprints, and the Extended Connectivity Fingerprint (ECFP) is one of the best-suited for general applications. Despite the overall FP abundance, only a few FPs represent the 3D structure of the molecule, and hardly any encode protein-ligand interactions. Here, we present a Protein-Ligand Extended Connectivity (PLEC) fingerprint that implicitly encodes protein-ligand interactions by pairing the ECFP environments from the ligand and the protein. PLEC fingerprints were used to construct different machine learning (ML) models tailored for predicting protein-ligand affinities (pK<sub>i/d</sub>). Even the simplest linear model built on the PLEC fingerprint achieved R<sub>p</sub>=0.83 on the PDBbind v2016 "core set”, demonstrating its descriptive power. The PLEC fingerprint has been implemented in the Open Drug Discovery Toolkit (https://github.com/oddt/oddt).</div>

19F-NMR in Target-based Drug Discovery

2019 ◽  
Vol 26 (26) ◽  
pp. 4964-4983 ◽  
Author(s):  
CongBao Kang
Keyword(s):  
Drug Discovery ◽  
Conformational Changes ◽  
Protein Structures ◽  
19F Nmr ◽  
Binding Affinities ◽  
Protein Ligand Interactions ◽  
Compound Libraries ◽  
Ligand Interactions ◽  
Reference Ligand ◽  
Hit Identification

Solution NMR spectroscopy plays important roles in understanding protein structures, dynamics and protein-protein/ligand interactions. In a target-based drug discovery project, NMR can serve an important function in hit identification and lead optimization. Fluorine is a valuable probe for evaluating protein conformational changes and protein-ligand interactions. Accumulated studies demonstrate that 19F-NMR can play important roles in fragment- based drug discovery (FBDD) and probing protein-ligand interactions. This review summarizes the application of 19F-NMR in understanding protein-ligand interactions and drug discovery. Several examples are included to show the roles of 19F-NMR in confirming identified hits/leads in the drug discovery process. In addition to identifying hits from fluorinecontaining compound libraries, 19F-NMR will play an important role in drug discovery by providing a fast and robust way in novel hit identification. This technique can be used for ranking compounds with different binding affinities and is particularly useful for screening competitive compounds when a reference ligand is available.

A Survey for Predicting ATP Binding Residues of Proteins Using Machine Learning Methods

2021 ◽  
Vol 28 ◽  
Author(s):  
Yu-He Yang ◽  
Jia-Shu Wang ◽  
Shi-Shi Yuan ◽  
Meng-Lu Liu ◽  
Wei Su ◽  
...  
Keyword(s):  
Machine Learning ◽  
Protein Function ◽  
Vital Role ◽  
Atp Binding ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Protein Ligand Interactions ◽  
Protein Functions ◽  
Ligand Interactions ◽  
Binding Residues

: Protein-ligand interactions are necessary for majority protein functions. Adenosine-5’-triphosphate (ATP) is one such ligand that plays vital role as a coenzyme in providing energy for cellular activities, catalyzing biological reaction and signaling. Knowing ATP binding residues of proteins is helpful for annotation of protein function and drug design. However, due to the huge amounts of protein sequences influx into databases in the post-genome era, experimentally identifying ATP binding residues is cost-ineffective and time-consuming. To address this problem, computational methods have been developed to predict ATP binding residues. In this review, we briefly summarized the application of machine learning methods in detecting ATP binding residues of proteins. We expect this review will be helpful for further research.

scholarly journals Prioritizing Small Molecule as Candidates for Drug Repositioning using Machine Learning

2018 ◽  
Author(s):  
Khader Shameer ◽  
Kipp W. Johnson ◽  
Benjamin S. Glicksberg ◽  
Rachel Hodos ◽  
Ben Readhead ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Small Molecule ◽  
Chemical Space ◽  
Drug Repositioning ◽  
Chemical Properties ◽  
Support Vector ◽  
Feature Engineering ◽  
Connectivity Map ◽  
Molecular Features

ABSTRACTDrug repositioning, i.e. identifying new uses for existing drugs and research compounds, is a cost-effective drug discovery strategy that is continuing to grow in popularity. Prioritizing and identifying drugs capable of being repositioned may improve the productivity and success rate of the drug discovery cycle, especially if the drug has already proven to be safe in humans. In previous work, we have shown that drugs that have been successfully repositioned have different chemical properties than those that have not. Hence, there is an opportunity to use machine learning to prioritize drug-like molecules as candidates for future repositioning studies. We have developed a feature engineering and machine learning that leverages data from publicly available drug discovery resources: RepurposeDB and DrugBank. ChemVec is the chemoinformatics-based feature engineering strategy designed to compile molecular features representing the chemical space of all drug molecules in the study. ChemVec was trained through a variety of supervised classification algorithms (Naïve Bayes, Random Forest, Support Vector Machines and an ensemble model combining the three algorithms). Models were created using various combinations of datasets as Connectivity Map based model, DrugBank Approved compounds based model, and DrugBank full set of compounds; of which RandomForest trained using Connectivity Map based data performed the best (AUC=0.674). Briefly, our study represents a novel approach to evaluate a small molecule for drug repositioning opportunity and may further improve discovery of pleiotropic drugs, or those to treat multiple indications.

scholarly journals Post hoc support vector machine learning for impedimetric biosensors based on weak protein–ligand interactions

The Analyst ◽  
2018 ◽  
Vol 143 (9) ◽  
pp. 2066-2075 ◽  
Author(s):  
Y. Rong ◽  
A. V. Padron ◽  
K. J. Hagerty ◽  
N. Nelson ◽  
S. Chi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Mobile Phone ◽  
Learning Algorithm ◽  
Support Vector ◽  
Machine Learning Algorithm ◽  
Protein Ligand Interactions ◽  
Ligand Interactions ◽  
Impedimetric Biosensor ◽  
Post Hoc

We develop a simple, open source machine learning algorithm for analyzing impedimetric biosensor data using a mobile phone.

scholarly journals Halogen Bonding: An Underestimated Player in Membrane–drug Interactions

2020 ◽  
Author(s):  
Rafael Nunes ◽  
Diogo Vila Viçosa ◽  
Paulo J. Costa
Keyword(s):  
Drug Discovery ◽  
Chemical Space ◽  
Noncovalent Interactions ◽  
Halogen Bonding ◽  
Lewis Bases ◽  
Protein Ligand Interactions ◽  
Biochemical Systems ◽  
Ligand Interactions ◽  
Dynamics Simulations

<div>Halogen bonds (HaBs) are noncovalent interactions where halogen atoms act as electrophilic species interacting with Lewis bases. These interactions are relevant in biochemical systems being increasingly explored in drug discovery, mainly to modulate protein–ligand interactions. In this work, we report evidence for the existence of HaB-mediated halogen–phospholipid recognition phenomena as our molecular dynamics simulations support the existence of favorable interactions between halobenzene derivatives and both phosphate (PO) or ester (CO) oxygen acceptors from model phospholipid bilayers, thus providing insights into the role of HaBs in driving the permeation of halogenated drug like molecules across biological membranes. This represents a relevant molecular mechanism, previously overlooked, determining the pharmacological activity of halogenated molecules with implications in drug discovery and development, a place where halogenated molecules account for a significant part of the chemical space. Our data also shows that, as the ubiquitous hydrogen bond, HaBs should be accounted for in the development of membrane permeability models.</div>

Using molecular docking and molecular dynamics to investigate protein-ligand interactions

2021 ◽  
Vol 35 (08) ◽  
pp. 2130002
Author(s):  
Connor J. Morris ◽  
Dennis Della Corte
Keyword(s):  
Molecular Dynamics ◽  
Molecular Docking ◽  
Drug Discovery ◽  
State Of The Art ◽  
Ligand Complex ◽  
Protein Ligand Interactions ◽  
Art Methods ◽  
Ligand Interactions ◽  
Docking Calculations ◽  
Ligand Bond

Molecular docking and molecular dynamics (MD) are powerful tools used to investigate protein-ligand interactions. Molecular docking programs predict the binding pose and affinity of a protein-ligand complex, while MD can be used to incorporate flexibility into docking calculations and gain further information on the kinetics and stability of the protein-ligand bond. This review covers state-of-the-art methods of using molecular docking and MD to explore protein-ligand interactions, with emphasis on application to drug discovery. We also call for further research on combining common molecular docking and MD methods.

scholarly journals Preorganization in biological systems: Are conformational constraints worth the energy?

2007 ◽  
Vol 79 (2) ◽  
pp. 193-200 ◽  
Author(s):  
Stephen F. Martin
Keyword(s):  
Experimental Evidence ◽  
Binding Affinity ◽  
Three Dimensional ◽  
Common Belief ◽  
Flexible Control ◽  
Protein Ligand Interactions ◽  
Conformational Constraints ◽  
Ligand Interactions ◽  
Dimensional Shape ◽  
Three Dimensional Shape

It is generally assumed that preorganizing a flexible ligand in the three-dimensional shape it adopts when bound to a macromolecular receptor will provide a derivative having an increased binding affinity, primarily because the rigidified molecule is expected to benefit from a lesser entropic penalty during complexation. We now provide the first experimental evidence that demonstrates this common belief is not universally true. Indeed, we find that ligand preorganization may be accompanied by an unfavorable entropy of binding, even when the constrained ligand exhibits a higher binding affinity than its flexible control. Thus, the effects that ligand preorganization have upon energetics and structure in protein-ligand interactions must be reevaluated.

Sign in / Sign up

Export Citation Format

Share Document