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

Phylogenetic Trees03:21

Phylogenetic Trees

47.8K
Phylogenetic trees come in many forms. It matters in which sequence the organisms are arranged from the bottom to the top of the tree, but the branches can rotate at their nodes without altering the information. The lines connecting individual nodes can be straight, angled, or even curved.
47.8K
Survival Tree01:19

Survival Tree

172
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
172
Evolutionary Relationships through Genome Comparisons02:54

Evolutionary Relationships through Genome Comparisons

6.3K
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
6.3K
Conserved Binding Sites01:49

Conserved Binding Sites

4.5K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.5K
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

36.4K
VSEPR Theory for Determination of Electron Pair Geometries
36.4K

You might also read

Related Articles

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

Sort by
Same author

Machine Learning-Driven Drug Repurposing for KRAS G12C and KRAS G12D Inhibition.

ACS omega·2026
Same author

Mechanism of Hydrolytic Instability of ZIF‑8 in Aqueous and Buffered Media: Implications on Drug Delivery Applications.

ACS omega·2026
Same author

BA-Pred and RMSD-Pred: Integrated Graph Neural Network Models for Accurate Protein-Ligand Binding Affinity and Binding Pose Prediction.

Journal of chemical information and modeling·2026
Same author

Docking of millions: accelerating a million-scale virtual screening using deep learning.

Briefings in bioinformatics·2026
Same author

Graph Neural Networks Model Based on Atomic Hybridization for Predicting Drug Targets.

Journal of chemical information and modeling·2026
Same author

SwinSite: 3D Structure-Based Prediction of Protein-Ligand Binding Sites Using a Combined Vision Transformer and Convolution Model.

Journal of chemical information and modeling·2026

Related Experiment Video

Updated: Sep 30, 2025

Using Phylogenetic Analysis to Investigate Eukaryotic Gene Origin
08:57

Using Phylogenetic Analysis to Investigate Eukaryotic Gene Origin

Published on: August 14, 2018

16.1K

Protein pKa Prediction by Tree-Based Machine Learning.

Ada Y Chen1,2, Juyong Lee3, Ana Damjanovic4

  • 1Department of Physics & Astronomy, Johns Hopkins University, Baltimore, Maryland 21218, United States.

Journal of Chemical Theory and Computation
|March 15, 2022
PubMed
Summary
This summary is machine-generated.

Accurately predicting protein pKa values is vital for understanding biological processes. New machine learning models, including Random Forest and XGBoost, show improved accuracy over existing tools for these crucial protein property predictions.

More Related Videos

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
06:50

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

2.0K
A Practical Guide to Phylogenetics for Nonexperts
12:00

A Practical Guide to Phylogenetics for Nonexperts

Published on: February 5, 2014

35.5K

Related Experiment Videos

Last Updated: Sep 30, 2025

Using Phylogenetic Analysis to Investigate Eukaryotic Gene Origin
08:57

Using Phylogenetic Analysis to Investigate Eukaryotic Gene Origin

Published on: August 14, 2018

16.1K
Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
06:50

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

2.0K
A Practical Guide to Phylogenetics for Nonexperts
12:00

A Practical Guide to Phylogenetics for Nonexperts

Published on: February 5, 2014

35.5K

Area of Science:

  • Biochemistry and Structural Biology
  • Computational Biology
  • Biophysics

Background:

  • Protonation states of ionizable protein residues are critical for biological functions.
  • Accurate prediction of pKa values is essential for molecular modeling and understanding protein behavior.
  • Existing methods for pKa prediction have limitations, especially for internal residues.

Purpose of the Study:

  • To develop and evaluate tree-based machine learning models for predicting protein residue pKa values.
  • To compare the performance of Random Forest, Extra Trees, XGBoost, and LightGBM models.
  • To assess the accuracy of predictions for both surface and buried residues.

Main Methods:

  • Training four tree-based machine learning models: Random Forest, Extra Trees, XGBoost, and LightGBM.
  • Utilizing three experimental protein pKa datasets, including those with internal residues.
  • Evaluating model performance using root-mean-square error (RMSE) and comparing against established tools like PROPKA and DelPhiPKa.

Main Results:

  • All four machine learning models demonstrated comparable performance.
  • The best model achieved a 37% improvement over PROPKA and 15% over DelPhiPKa.
  • The best model yielded an overall RMSE of 0.69 (0.56 for surface, 0.78 for buried residues) for six residue types.

Conclusions:

  • Tree-based machine learning models offer a significant improvement in protein pKa prediction accuracy.
  • These models provide reliable pKa predictions for a wide range of residues, including internal ones.
  • Application to the human proteome revealed that 1% of Asp/Glu/Lys residues exhibit significantly shifted pKa values near physiological pH.