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

Physiological Pharmacokinetic Models: Assumption with Protein Binding01:13

Physiological Pharmacokinetic Models: Assumption with Protein Binding

202
Physiological models with protein binding in pharmacokinetics offer a sophisticated approach to understanding drug disposition. These models consider drug-protein interactions, enabling them to effectively predict drug concentrations in different organs and tissues. This precision aids in accurate drug dosing, providing a significant advantage over conventional models. A key process within these models is equilibration, which ensures that drug concentrations achieve a steady state within the...
202
Protein Dynamics in Living Cells01:19

Protein Dynamics in Living Cells

2.6K
Different fluorescence-based techniques are used to study the protein dynamics in living cells. These techniques include FRAP, FRET, and PET.
Fluorescent recovery after photobleaching (FRAP) is a fluorescent-protein-based detection technique used to quantify protein movement rates within the cell. This method exposes a small portion of the cell to an intense laser beam. The laser beam causes permanent photobleaching of the fluorophore-tagged proteins in the exposed region. As the bleached...
2.6K
Intrinsically Disordered Proteins02:18

Intrinsically Disordered Proteins

19.2K
Intrinsically disordered proteins are a group of proteins that do not fold into specific three-dimensional structures. Their structural flexibility allows them to complement ordered proteins to perform functions that are inaccessible to rigid structures. They are more common in eukaryotes than prokaryotes and may either be exclusively intrinsically disordered or hybrid proteins, consisting of a mix of ordered and disordered regions. The absence of a rigid structure in these proteins can be...
19.2K
Conservation of Protein Domains Over Different Proteins02:26

Conservation of Protein Domains Over Different Proteins

14.0K
Protein domains are small structurally independent units that are part of a single amino acid chain.  Although these domains are often structurally independent, they may rely on synergistic effects to perform their functions as part of a larger protein. Protein domains may be conserved within the same organism, as well as across different organisms.
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
14.0K
Three-Dimensional Force System:Problem Solving01:30

Three-Dimensional Force System:Problem Solving

1.3K
A three-dimensional force system refers to a scenario in which three forces act simultaneously in three different directions. This type of problem is commonly encountered in physics and engineering, where it is necessary to calculate the resultant force on the system, which can then be used to predict or analyze the behavior of the object or structure under consideration.
To solve a three-dimensional force system, first resolve each force into its respective scalar components. Do this using...
1.3K
Mechanical Protein Function01:58

Mechanical Protein Function

2.4K
2.4K

You might also read

Related Articles

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

Sort by
Same author

Decentralized federated distillation for privacy-preserving cross-league basketball data collaboration.

Scientific reports·2026
Same author

HyRes: Accurate Physics-Based Simulation of Dynamic Protein Structures and Interactions in Complex Environments at Scale.

bioRxiv : the preprint server for biology·2026
Same author

Coupled Binding and Folding of NS2B/NS3 Protease and Linker Effects Revealed by Topology-Based Modeling.

The journal of physical chemistry. B·2026
Same author

Lipid Composition Drastically Alters Tau-Membrane Interaction: Implications for Alzheimer's Disease.

JACS Au·2026
Same author

Overcoming extrapolation challenges of deep learning by incorporating physics in protein sequence-function modeling.

PLoS computational biology·2026
Same author

Shared immune dysregulation in systemic lupus erythematosus and colorectal cancer: a multi-omics guided discovery of DNASE1L3-centric efferocytosis deficiency.

Frontiers in immunology·2026

Related Experiment Video

Updated: Jan 10, 2026

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
05:08

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

909

Overcoming Extrapolation Challenges of Deep Learning by Incorporating Physics in Protein Sequence-Function Modeling.

Shrishti Barethiya1, Jian Huang1, Xiao Liu2

  • 1Department of Chemistry, University of Massachusetts, Amherst, MA 01003, USA.

Biorxiv : the Preprint Server for Biology
|November 26, 2025
PubMed
Summary

Incorporating biophysics into deep learning models improves protein function prediction for unseen mutations. This approach enhances extrapolation capabilities, overcoming limitations of data scarcity in protein engineering and genetic disease studies.

More Related Videos

Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion
09:17

Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion

Published on: March 1, 2022

3.5K
Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

1.1K

Related Experiment Videos

Last Updated: Jan 10, 2026

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
05:08

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

909
Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion
09:17

Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion

Published on: March 1, 2022

3.5K
Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

1.1K

Area of Science:

  • Computational biology
  • Biophysics
  • Machine learning

Background:

  • Understanding protein sequence-to-function relationships is vital for genetic disease research, protein evolution studies, and protein engineering.
  • Deep learning models, including convolutional neural networks and transformers, are widely used for predicting protein function from sequence data.
  • A key challenge is the limited ability of these models to accurately predict the functional effects of mutations not present in the training data (extrapolation).

Purpose of the Study:

  • To investigate whether incorporating physics-based protein interaction and dynamics information can enhance the extrapolation capabilities of deep learning models for protein function prediction.
  • To quantify the energetic effects of mutations using physics-based modeling.
  • To integrate these physical energetics into neural network architectures to improve prediction accuracy for unseen variants.

Main Methods:

  • Utilized deep learning models, specifically (graph) convolutional neural networks, to learn protein sequence-to-function mappings.
  • Employed physics-based modeling to calculate the energetic impact of protein mutations.
  • Integrated biophysical energetic features directly into the neural network architecture alongside sequence data.
  • Evaluated model performance on predicting functional effects of mutations, focusing on extrapolation to unseen positions and mutation types.

Main Results:

  • Physics-based modeling effectively quantifies the energetic effects of mutations.
  • Incorporating biophysical energetic features significantly improved the positional and mutational extrapolation performance of convolutional and graph convolutional neural networks.
  • Models enhanced with physics-based insights outperformed those relying solely on sequence data when predicting functional effects of novel variants.

Conclusions:

  • Leveraging physical knowledge, specifically protein interaction energetics, is an effective strategy to overcome data scarcity limitations in deep learning models for protein function prediction.
  • Integrating biophysics into machine learning models enhances their ability to generalize and predict the functional impact of genetic variants accurately.
  • This approach holds promise for advancing studies in genetic diseases, protein evolution, and protein engineering by improving variant effect prediction.