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

Associative Learning01:27

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Predicting Reaction Outcomes02:24

Predicting Reaction Outcomes

Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
Observational Learning01:12

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning because...
Purposive Learning01:22

Purposive Learning

E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a bonus...
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
Predicting Products: Substitution vs. Elimination02:52

Predicting Products: Substitution vs. Elimination

When a nucleophile and an alkyl halide react, nucleophilic substitution and β-elimination reactions compete to generate products.
The following factors can influence the mechanisms competing against each other:

You might also read

Related Articles

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

Sort by
Same author

Scalable, fast and accurate differential gene expression testing from millions of cells of multiple patients.

Nature communications·2026
Same author

CRAK-Velo: chromatin accessibility kinetics integration improves RNA velocity estimation.

Genome biology·2026
Same author

Extending differential gene expression testing to handle genome aneuploidy in cancer.

PLoS computational biology·2026
Same author

Interpretable learning of temporal cellular dynamics from single-cell data.

Cell reports methods·2026
Same author

Machine learning for RNA secondary structure prediction: a review of current methods and challenges.

RNA (New York, N.Y.)·2026
Same author

The ribosome-associated complex regulates cytosolic translation upon mitoprotein-induced stress.

The FEBS journal·2025
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
Same journal

Computational investigation of antioxidant activities and mechanisms of catechol analogues through a DFT study.

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

Related Experiment Video

Updated: May 21, 2026

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
06:50

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

Multi-task learning for pKa prediction.

Grigorios Skolidis1, Katja Hansen, Guido Sanguinetti

  • 1Department of Statistical Science, University College London, Gower Street, London WC1E 6BT, UK. g.skolidis@ucl.ac.uk

Journal of Computer-Aided Molecular Design
|June 21, 2012
PubMed
Summary
This summary is machine-generated.

Predicting compound properties like dissociation constants is crucial. Multi-task learning enhances computational models, especially with limited data, by leveraging related chemical classes for improved accuracy.

Related Experiment Videos

Last Updated: May 21, 2026

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
06:50

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

Area of Science:

  • Computational chemistry
  • Machine learning in chemistry

Background:

  • Compound properties often depend on dissociation constants of acidic and basic groups.
  • Predicting these constants computationally is vital for chemical research.
  • Current linear regression models often require class-specific data, which can be scarce for new compound series.

Purpose of the Study:

  • To investigate the efficacy of multi-task learning for predicting dissociation constants in low sample size regimes.
  • To compare the performance of single-task, pooling, and multi-task Gaussian process regression models.
  • To demonstrate an approach for improving molecular property predictions when experimental data is limited.

Main Methods:

  • Utilized linear Gaussian process regression models, including single-task, pooling, and multi-task variants.
  • Employed the intrinsic model of co-regionalization and incomplete Cholesky decomposition for the multi-task model.
  • Evaluated models on a dataset of 698 compounds, divided into 15 chemical classes, focusing on the low sample size scenario.

Main Results:

  • The multi-task regression model consistently outperformed single-task and pooling models in the low sample size regime.
  • The best-performing multi-task model achieved superior predictions in 85% of experimental trials.
  • Demonstrated significant improvement in prediction accuracy by leveraging data from related chemical classes.

Conclusions:

  • Multi-task learning, particularly with the intrinsic model of co-regionalization, offers a powerful approach to enhance dissociation constant predictions with limited data.
  • This methodology is applicable to estimating other molecular properties where experimental measurements are scarce.
  • The findings support the use of advanced machine learning techniques to overcome data limitations in computational chemistry.