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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Cell painting and thermal proteome profiling for inference of drug targets and mechanism of action.

Molecular systems biology·2026
Same author

Counting cells can accurately predict small-molecule bioactivity benchmarks.

Nature communications·2026
Same author

Cohort profile: The Dutch wound monitor cohort and the Swedish Region Halland Integrated Platform (RHIP) wound cohort.

PloS one·2026
Same author

Precise mapping of single-stranded DNA breaks by sequence-templated erroneous DNA polymerase end-labelling.

Nature communications·2025
Same author

Conformal prediction enables disease course prediction and allows individualized diagnostic uncertainty in multiple sclerosis.

NPJ digital medicine·2025
Same author

Computational drug repurposing: approaches, evaluation of in silico resources and case studies.

Nature reviews. Drug discovery·2025

Related Experiment Video

Updated: Nov 1, 2025

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

793

Machine Learning Strategies When Transitioning between Biological Assays.

Staffan Arvidsson McShane1, Ernst Ahlberg1,2,3, Tobias Noeske4

  • 1Department of Pharmaceutical Biosciences and Science for Life Laboratory, Uppsala University, 751 24 Uppsala, Sweden.

Journal of Chemical Information and Modeling
|June 21, 2021
PubMed
Summary

This study introduces a new method for drug development, combining old and new assay data for conformal prediction models. The proposed strategy enhances model validity and efficiency, especially for regression tasks.

More Related Videos

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
09:05

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow

Published on: October 17, 2025

131
An Organotypic High Throughput System for Characterization of Drug Sensitivity of Primary Multiple Myeloma Cells
09:41

An Organotypic High Throughput System for Characterization of Drug Sensitivity of Primary Multiple Myeloma Cells

Published on: July 15, 2015

8.8K

Related Experiment Videos

Last Updated: Nov 1, 2025

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

793
Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
09:05

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow

Published on: October 17, 2025

131
An Organotypic High Throughput System for Characterization of Drug Sensitivity of Primary Multiple Myeloma Cells
09:41

An Organotypic High Throughput System for Characterization of Drug Sensitivity of Primary Multiple Myeloma Cells

Published on: July 15, 2015

8.8K

Area of Science:

  • Computational chemistry
  • Pharmacology
  • Machine learning in drug discovery

Background:

  • Machine learning models predict biological activity from chemical structures in drug development.
  • Transitioning models between experimental setups for the same biological endpoint is understudied.

Purpose of the Study:

  • To explore modeling strategies for combining data from old and new assays during conformal prediction model training.
  • To propose and evaluate a method for maximizing data utility during assay transitions.

Main Methods:

  • Retrospective study using data from hERG and NaV assays.
  • Training inductive conformal prediction models with varying data combinations from old and new assays.
  • Monitoring model validity and efficiency based on accumulated data.

Main Results:

  • A proposed strategy augments training sets with old assay data while using new assay data for calibration, yielding valid and more efficient models.
  • Model performance is analyzed across different assay data sizes and for both regression and classification tasks.
  • The strategy proves more beneficial for regression compared to classification.

Conclusions:

  • Continuous monitoring of model validity and efficiency is crucial for selecting optimal strategies during assay transitions.
  • The proposed data augmentation and calibration strategy effectively leverages historical data, improving model performance.
  • Assay transition strategies offer greater advantages in regression tasks due to their inherent complexity.