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

On the state of protein function prediction: a report on the fourth CAFA challenge.

bioRxiv : the preprint server for biology·2026
Same author

RNAdetector: fast and accurate predictor of RNA type-specific binding residues in protein sequences.

Nucleic acids research·2026
Same author

PROBind: A Web Server for Prediction, Analysis, and Visualization of Protein-Protein and Protein-Nucleic Acid Binding Residues.

Genomics, proteomics & bioinformatics·2026
Same author

Modern resources for intrinsic disorder predictions: protein language models, deep learning, meta-servers, and databases.

Cellular and molecular life sciences : CMLS·2026
Same author

A geometric deep learning framework for genome-wide prediction of enzyme turnover number.

Genome biology·2026
Same author

flDPnn3: Fast and Accurate Prediction of Intrinsic Disorder in Protein Sequences.

Journal of molecular biology·2026
Same journal

Characterization of putative proteins encoded by variable ORFs in white spot syndrome virus genome.

BMC structural biology·2019
Same journal

Correction to: Classification of the human THAP protein family identifies an evolutionarily conserved coiled coil region.

BMC structural biology·2019
Same journal

Effect of low complexity regions within the PvMSP3α block II on the tertiary structure of the protein and implications to immune escape mechanisms.

BMC structural biology·2019
Same journal

QRNAS: software tool for refinement of nucleic acid structures.

BMC structural biology·2019
Same journal

Classification of the human THAP protein family identifies an evolutionarily conserved coiled coil region.

BMC structural biology·2019
Same journal

A new technique for predicting intrinsically disordered regions based on average distance map constructed with inter-residue average distance statistics.

BMC structural biology·2019
See all related articles

Related Experiment Video

Updated: Jun 21, 2026

High-Throughput Screening to Obtain Crystal Hits for Protein Crystallography
06:19

High-Throughput Screening to Obtain Crystal Hits for Protein Crystallography

Published on: March 10, 2023

CRYSTALP2: sequence-based protein crystallization propensity prediction.

Lukasz Kurgan1, Ali A Razib, Sara Aghakhani

  • 1Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada. lkurgan@ece.ualberta.ca

BMC Structural Biology
|August 4, 2009
PubMed
Summary
This summary is machine-generated.

CRYSTALP2 accurately predicts protein crystallization propensity using sequence data, improving structural genomics. This kernel-based method enhances existing approaches for identifying crystallizable proteins.

More Related Videos

Combining Wet and Dry Lab Techniques to Guide the Crystallization of Large Coiled-coil Containing Proteins
11:14

Combining Wet and Dry Lab Techniques to Guide the Crystallization of Large Coiled-coil Containing Proteins

Published on: January 6, 2017

Improving the Success Rate of Protein Crystallization by Random Microseed Matrix Screening
12:24

Improving the Success Rate of Protein Crystallization by Random Microseed Matrix Screening

Published on: August 31, 2013

Related Experiment Videos

Last Updated: Jun 21, 2026

High-Throughput Screening to Obtain Crystal Hits for Protein Crystallography
06:19

High-Throughput Screening to Obtain Crystal Hits for Protein Crystallography

Published on: March 10, 2023

Combining Wet and Dry Lab Techniques to Guide the Crystallization of Large Coiled-coil Containing Proteins
11:14

Combining Wet and Dry Lab Techniques to Guide the Crystallization of Large Coiled-coil Containing Proteins

Published on: January 6, 2017

Improving the Success Rate of Protein Crystallization by Random Microseed Matrix Screening
12:24

Improving the Success Rate of Protein Crystallization by Random Microseed Matrix Screening

Published on: August 31, 2013

Area of Science:

  • Structural Biology
  • Computational Biology
  • Biophysics

Background:

  • Protein crystallization is crucial for structural genomics but has a low success rate (<30%).
  • Automated prediction of crystallizable proteins can significantly improve high-throughput structural genomics efforts.

Purpose of the Study:

  • Introduce CRYSTALP2, a kernel-based method for predicting protein crystallization propensity from primary sequences.
  • Enhance prediction quality and enable predictions for proteins of unrestricted sequence size.

Main Methods:

  • Utilizes amino acid composition and collocation, isoelectric point, and hydrophobicity from primary sequences.
  • Employs a kernel-based approach for prediction.
  • Extends the CRYSTALP method for broader applicability.

Main Results:

  • CRYSTALP2 outperforms existing sequence-based predictors like CRYSTALP, OB-score, and SECRET.
  • Achieves accuracy, Matthews Correlation Coefficient (MCC), and Area Under the Receiver Operating Characteristic Curve (AROC) ranging from 69.3-77.5%, 0.39-0.55, and 0.72-0.79, respectively.
  • Predictions are comparable and complementary to recent methods such as ParCrys and XtalPred.

Conclusions:

  • CRYSTALP2 offers accurate protein crystallization propensity predictions, outperforming or complementing existing methods.
  • The method supports efforts to increase the success rate of obtaining diffraction-quality protein crystals.