Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A shape-based machine learning tool for drug design

A N Jain1, T G Dietterich, R H Lathrop

  • 1Arris Pharmaceutical Corporation, South San Francisco, CA 94080, USA.

Journal of Computer-Aided Molecular Design
|December 1, 1994
PubMed
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

Understanding the hydrological and landscape connectivity of lakes.

Landscape ecology·2025
Same author

First results from five multidisciplinary diagnostic centre (MDC) projects for non-specific but concerning symptoms, possibly indicative of cancer.

British journal of cancer·2020
Same author

Factors predictive of an advanced stage of colorectal cancer at presentation - a bi-national study.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2020
Same author

Dose profiles and x-ray energy optimization for microbeam radiation therapy by high-dose, high resolution dosimetry using Sm-doped fluoroaluminate glass plates and Monte Carlo transport simulation.

Physics in medicine and biology·2020
Same author

Temporal variation in the vocal behaviour of southern right whales in the Auckland Islands, New Zealand.

Royal Society open science·2019
Same author

Multiple image x-radiography for functional lung imaging.

Physics in medicine and biology·2017
Same journal

RANQSAR: a standalone open-source application for reproducible machine learning-based QSAR analysis.

Journal of computer-aided molecular design·2026
Same journal

Integrating evolutionary and compositional features with ML and DL for robust and interpretable druggable protein prediction.

Journal of computer-aided molecular design·2026
Same journal

QUAD: a composite risk framework integrating uncertainty, applicability domain, and model disagreement for reliable QSAR predictions.

Journal of computer-aided molecular design·2026
Same journal

Comparative quantum-chemical investigation of 2-chloro-N-(4-methoxyphenyl)acetamide and 2-(4-methoxyphenylamino)-2-oxoethyl meth/acrylate: DFT, TD-DFT, and non-covalent interaction analyses.

Journal of computer-aided molecular design·2026
Same journal

Discovery of a novel CaMKⅡα inhibitor by machine learning, molecular docking and molecular dynamics simulation.

Journal of computer-aided molecular design·2026
Same journal

Explainable QSAR models of 5-HT1A receptor ligands using conceptual DFT descriptors and no-code machine learning tools.

Journal of computer-aided molecular design·2026
See all related articles

This study introduces Compass, a novel computational method for drug design. Compass accurately predicts molecular properties by analyzing shape and using neural networks, even without target protein structures.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning in drug discovery

Background:

  • Predictive modeling for drug design is challenging without target protein structures.
  • Accurate prediction requires effective molecular conformation and alignment.
  • Existing methods struggle with diverse chemical classes.

Purpose of the Study:

  • To present a novel technique, Compass, for predictive modeling in drug design.
  • To overcome the obstacle of unknown target protein structures.
  • To enable accurate prediction across chemically distinct molecules.

Main Methods:

  • Compass combines explicit molecular shape representation with neural network learning.
  • The technique automatically selects molecular conformations and alignments.

Related Experiment Videos

  • No prior knowledge of a characterized active site is required.

    • Main Results:

    • Compass produces highly predictive models for molecular properties.
    • The method demonstrates accuracy across chemically distinct molecular classes.
    • Application to predicting musk odor perception provides graphical guidance for chemical modifications.

    Conclusions:

    • Compass offers a robust approach for iterative drug design.
    • The technique facilitates accurate predictions without target structural information.
    • Compass aids in guiding chemical modifications for desired properties.