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

Structural Protein Function01:56

Structural Protein Function

29.9K
Structural proteins are a category of proteins responsible for functions ranging from cell shape and movement to providing support to major structures such as bones, cartilage, hair, and muscles. This group includes proteins such as collagen, actin, myosin, and keratin.
Collagen, the most abundant protein in mammals, is found throughout the body. In connective tissue, such as skin, ligaments, and tendons, it provides tensile strength and elasticity.  In bones and teeth, it mineralizes to...
29.9K
Structural Protein Function01:56

Structural Protein Function

3.3K
3.3K
Mechanical Protein Functions01:58

Mechanical Protein Functions

5.6K
Proteins perform many mechanical functions in a cell. These proteins can be classified into two general categories- proteins that generate mechanical forces and proteins that are subjected to mechanical forces. Proteins providing mechanical support to the structure of the cell, such as keratin, are subjected to mechanical force, whereas proteins involved in cell movement and transport of molecules across cell membranes, such as an ion pump, are examples of generating mechanical force. 
5.6K
Introduction to z Scores01:06

Introduction to z Scores

11.2K
A z score (or standardized value) is measured in units of the standard deviation. It tells you how many standard deviations the value x is above (to the right of) or below (to the left of) the mean, μ. Values of x that are larger than the mean have positive z scores, and values of x that are smaller than the mean have negative z scores. If x equals the mean, then x has a zero z score. It is important to note that the mean of the z scores is zero, and the standard deviation is one.
z scores...
11.2K
Introduction to z Scores01:05

Introduction to z Scores

1.3K
A z score (or standardized value) is measured in units of the standard deviation. It indicates how many standard deviations the value x is above (to the right of) or below (to the left of) the mean, μ. Values of x that are larger than the mean have positive z scores, and values of x that are smaller than the mean have negative z scores. If x equals the mean, then x has a zero z score. It is important to note that the mean of the z scores is zero, and the standard deviation is one.
z scores...
1.3K
z Scores and Area Under the Curve01:17

z Scores and Area Under the Curve

19.6K
z scores are the standardized values obtained after converting a normal distribution into a standard normal distribution. A z score is measured in units of the standard deviation. The z score tells you how many standard deviations the value x is above (to the right of) or below (to the left of) the mean, μ. Values of x that are larger than the mean have positive z scores, and values of x that are smaller than the mean have negative z scores. If x equals the mean, then x has a z score of...
19.6K

You might also read

Related Articles

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

Sort by
Same author

Quantum-Centric Alchemical Free Energy Calculations.

Journal of chemical theory and computation·2026
Same author

Molecular Quantum Computations on a Protein.

Journal of chemical theory and computation·2026
Same author

Advancing Reproducibility and Open Data in Theoretical and Computational Chemistry.

Journal of chemical theory and computation·2026
Same author

Multisite Phosphorylation Regulates the Structure and Auto-Inhibitory Function of the Intrinsically Disordered N‑Terminal Domain of p53.

JACS Au·2026
Same author

Automated Force Field Developer and Optimizer Platform: Torsion Reparameterization.

Journal of chemical information and modeling·2026
Same author

QUICK and Robust ESP and RESP Charges for Computational Biochemistry: Open-Source GPU Implementation.

Journal of chemical information and modeling·2026

Related Experiment Video

Updated: Jan 29, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.5K

Random Forest Refinement of the KECSA2 Knowledge-Based Scoring Function for Protein Decoy Detection.

Jun Pei1, Zheng Zheng1, Kenneth M Merz1,2

  • 1Department of Chemistry , Michigan State University , 578 S. Shaw Lane , East Lansing , Michigan 48824 , United States.

Journal of Chemical Information and Modeling
|February 7, 2019
PubMed
Summary
This summary is machine-generated.

Random Forest models improve protein structure prediction by assigning importance to atom pairs. These models effectively identify native protein structures from decoys, outperforming conventional methods.

More Related Videos

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.8K
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

584

Related Experiment Videos

Last Updated: Jan 29, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.5K
A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.8K
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

584

Area of Science:

  • Computational Biology
  • Structural Bioinformatics
  • Machine Learning in Biochemistry

Background:

  • Knowledge-based potentials often outperform physics-based scoring functions for identifying native protein structures from decoys.
  • Conventional knowledge-based potentials struggle to assign differential importance to various atom/residue pairs.
  • A reference state is used to isolate pure interactions between atom/residue pairs by removing ideal-gas state contributions.

Purpose of the Study:

  • To develop and evaluate Random Forest (RF) models for enhanced protein structure recognition.
  • To assign differential importance factors to atom pair potentials for improved native protein identification.
  • To investigate the impact of peak positions versus peak heights in probability functions on model performance.

Main Methods:

  • Generation of RF models using unbalanced datasets and the "comparison" concept to assign importance factors to atom pair potentials.
  • Testing RF model performance on individual and combined datasets from 12 decoy sets.
  • Validation using models with scrambled atom types and uniform probability functions to assess algorithm robustness and key feature importance.

Main Results:

  • RF models significantly enhance the recognition of native protein structures without compromising the identification of optimal decoy structures.
  • Models generated from scrambled atom types demonstrated significantly lower quality compared to those using unscrambled probability functions.
  • Uniform probability functions, matching peak positions of original potentials, yielded models of comparable quality, highlighting the importance of peak positions.

Conclusions:

  • RF models offer a powerful approach to enhance native protein structure recognition in computational structural biology.
  • The "comparison" concept and RF algorithm effectively address limitations in conventional knowledge-based potentials.
  • Peak positions in probability functions are critical for the success of these models, more so than interaction-specific peak heights.