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 machine learning approach to computer-aided molecular design.

G Bolis1, L Di Pace, F Fabrocini

  • 1Farmitalia Carlo Erba srl, Erbamont Group, R&D/CAMD, Milan, Italy.

Journal of Computer-Aided Molecular Design
|December 1, 1991
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

Vitamin D protects human endothelial cells from oxidative stress through the autophagic and survival pathways.

The Journal of clinical endocrinology and metabolism·2013
Same author

Ten years survival of FIGO stage IIIC epithelial ovarian cancer cases due to lymph node metastases only.

European journal of gynaecological oncology·2013
Same author

Hypertrophic donavanosis in a young pregnant woman.

Journal of pediatric and adolescent gynecology·2012
Same author

Multimodal approach to ovarian cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2006
Same author

Epidoxorubicin versus no treatment as consolidation therapy in advanced ovarian cancer: results from a phase II study.

International journal of gynecological cancer : official journal of the International Gynecological Cancer Society·2006
Same author

Doxorubicin versus doxorubicin and cisplatin in endometrial carcinoma: definitive results of a randomised study (55872) by the EORTC Gynaecological Cancer Group.

Annals of oncology : official journal of the European Society for Medical Oncology·2003

This study introduces a machine learning approach for computer-aided molecular design in drug discovery. The artificial intelligence model identifies key molecular fragments to predict compound activity against target molecules.

Area of Science:

  • Computational chemistry
  • Medicinal chemistry
  • Artificial intelligence in drug discovery

Background:

  • Drug discovery relies on identifying molecules that interact with specific biological targets.
  • Traditional methods are often time-consuming and expensive.
  • Machine learning offers a promising avenue for accelerating molecular design and prediction.

Purpose of the Study:

  • To present preliminary results of a machine learning application for computer-aided molecular design.
  • To develop an artificial intelligence model for predicting compound activity in drug discovery.
  • To characterize the interaction between compounds and target molecules using machine learning.

Main Methods:

  • Utilizing machine learning techniques with active and inactive compounds as positive and negative examples.

Related Experiment Videos

  • Employing a twofold algorithm: specialization (identifying active/inactive pairs and generating a fragment dictionary) and generalization (combining fragments to form hypotheses).
  • Integrating a knowledge base of physical and chemical properties into the inductive learning process.

    • Main Results:

    • The machine learning algorithm successfully induced a molecular model characterizing compound-target interactions.
    • The specialization step identified crucial molecular fragments responsible for compound activity.
    • The generalization step selected plausible hypotheses based on the learned fragments and compound data.

    Conclusions:

    • Machine learning provides an effective framework for computer-aided molecular design in drug discovery.
    • The developed algorithm can aid in identifying potential drug candidates by predicting molecular interactions.
    • This approach has the potential to streamline and enhance the efficiency of the drug discovery pipeline.