Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Generalized fragment-substructure based property prediction method.

Matthew Clark¹

¹Locus Pharmaceuticals Four Valley Square, 512 Township Line Road, Blue Bell, Pennsylvania 19422, USA. mclark@locuspharma.com

Journal of Chemical Information and Modeling

|January 26, 2005

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A phase 1 randomized controlled trial to evaluate the safety and immunogenicity of a HIV monomeric gp120 protein B-cell lineage targeting HIV vaccine in healthy adults.

medRxiv : the preprint server for health sciences·2026

Same author

Post-COVID rebound in invasive pneumococcal disease driven by resurgence of serotype 4 among American Indian individuals in the Southwest United States.

The Journal of infectious diseases·2026

Same author

Induction of multiple HIV-1 neutralizing B Cell Precursors in Humans.

medRxiv : the preprint server for health sciences·2026

Same author

Phase II trial with nivolumab and sorafenib in HCC identified enrichment of immunosuppressive monocytes in patients with Child-Pugh B liver dysfunction.

JHEP reports : innovation in hepatology·2026

Same author

Development of A Screening Tool to Predict Post Intensive Care Syndrome (PICS) in Critically Ill Adults in a Prospective Cohort.

Journal of intensive care medicine·2026

Same author

Shared Maturation Pathways of HIV-1 Envelope-reactive V3-glycan bnAb Lineages in Human and Rhesus Macaque.

bioRxiv : the preprint server for biology·2026

Same journal

Advancing Biochemical Molecule Registration, Representation and Search for New Drug Modalities.

Journal of chemical information and modeling·2026

Same journal

A Unified Molecular Graph and Protein Language Model Framework for Predicting Human Drug-Hormone Receptor Interactions with Structure-Aware Validation.

Journal of chemical information and modeling·2026

Same journal

Intricate Role of Cholesterol in Membrane Fusion.

Journal of chemical information and modeling·2026

Same journal

tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES.

Journal of chemical information and modeling·2026

Same journal

QSAR in the Browser: An Interactive Cheminformatics Web Application.

Journal of chemical information and modeling·2026

Same journal

FoldDoF: Utilizing the Primary Degrees of Freedom of Protein Backbone for Geometric Modeling and Generation.

Journal of chemical information and modeling·2026

See all related articles

This study introduces a novel 2D structure-based method for predicting drug properties like logP, solubility, and melting point. The fragment-based approach aids in understanding molecular modifications for improved drug development.

Area of Science:

Computational chemistry
Medicinal chemistry
Drug discovery

Background:

Increasing demand for rapid prediction of pharmaceutical properties in drug discovery.
Need for early identification of pharmacokinetic issues to reduce clinical development costs.

Purpose of the Study:

To develop a novel predictive modeling method based on 2D structural fragments.
To model key pharmaceutical properties: logP, water solubility (logS), and melting point.
To facilitate understanding of molecular alterations for property improvement.

Main Methods:

Decomposition of 2D molecular structures into relevant chemical fragments.
Utilizing a substructure searching algorithm and pharmaceutically relevant fragment sets.
Employing partial least squares (PLS) for predictive model development.

Related Experiment Videos

Main Results:

Achieved high correlation coefficients: 0.86 for logP, 0.73 for logS, and 0.64 for melting point.
Models were developed using diverse datasets of 11,447 (logP), 2427 (logS), and 5598 (melting point) molecules.
Model performance was validated using independent test sets.

Conclusions:

The fragment-based 2D structure descriptor method provides accurate predictions for key pharmaceutical properties.
This approach supports efficient in-silico screening and aids in optimizing drug candidates.
The method enhances understanding of structure-property relationships for drug design.