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 Experiment Video

Updated: Apr 4, 2026

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.5K

AcconPred: Predicting Solvent Accessibility and Contact Number Simultaneously by a Multitask Learning Framework under

Jianzhu Ma1, Sheng Wang2

  • 1Toyota Technological Institute at Chicago, 6045 S. Kenwood Avenue, Chicago, IL 60637, USA.

Biomed Research International
|September 5, 2015
PubMed
Summary
This summary is machine-generated.

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

Dango: Predicting higher-order genetic interactions.

Cell systems·2026
Same author

Unified modeling of 3D molecular generation via atomic interactions with PocketXMol.

Cell·2026
Same author

Learning Protein Structure Representation with Orientation-Aware Networks.

Journal of computational biology : a journal of computational molecular cell biology·2025
Same author

Author Correction: Peptide design through binding interface mimicry with PepMimic.

Nature biomedical engineering·2025
Same author

LiteAT: A Data-Lightweight and User-Adaptive VR Telepresence System for Remote Education.

IEEE transactions on visualization and computer graphics·2025
Same author

Peptide design through binding interface mimicry with PepMimic.

Nature biomedical engineering·2025
Same journal

Resveratrol Mitigates Noise-Induced Cochlear Damage and Delays Hearing Loss in Wistar Rats.

BioMed research international·2026
Same journal

RETRACTION: Green Fabrication of Silver Nanoparticles Using Euphorbia Serpens Kunth Aqueous Extract, their Characterization, and Investigation of its in Vitro Antioxidative, Antimicrobial, Insecticidal, and Cytotoxic Activities.

BioMed research international·2026
Same journal

Predictors of Prolonged Hospital Length of Stay in Patients With Odontogenic Infections in Ghana.

BioMed research international·2026
Same journal

Traditional Chinese Medicine Bone-Setting Techniques Research Progress for the Treatment of Knee Osteoarthritis.

BioMed research international·2026
Same journal

RETRACTION: miR-375 Inhibits the Proliferation and Invasion of Nasopharyngeal Carcinoma Cells by Suppressing PDK1.

BioMed research international·2026
Same journal

Exploring the Therapeutic Potential of Nobiletin in Nonsmall Cell Lung Cancer.

BioMed research international·2026
See all related articles

Predicting protein solvent accessibility and contact number simultaneously is crucial for understanding protein folding and structure. AcconPred, a novel multitask learning method, accurately predicts these properties by leveraging their interdependence.

Area of Science:

  • Computational biology
  • Structural bioinformatics
  • Machine learning in bioinformatics

Background:

  • Protein residue solvent accessibility influences protein folding.
  • Residue contact number restricts protein conformational possibilities.
  • Predicting these properties from sequence aids protein structure and function studies.

Purpose of the Study:

  • To develop a method for simultaneous prediction of protein solvent accessibility and contact number.
  • To exploit the dependency between solvent accessibility and contact number for improved prediction accuracy.

Main Methods:

  • Utilized a shared-weight multitask learning framework.
  • Employed the conditional neural fields (CNF) model.
  • Modeled complex input-feature-to-label relationships and interdependencies among adjacent labels.

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

2.7K

Related Experiment Videos

Last Updated: Apr 4, 2026

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.5K
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

2.7K

Main Results:

  • AcconPred achieved 0.68 three-state accuracy for solvent accessibility and 0.75 correlation for contact number on monomeric soluble globular protein datasets.
  • On CASP11 domain datasets, AcconPred reached 0.64 accuracy for solvent accessibility, outperforming existing methods.

Conclusions:

  • Simultaneous prediction using multitask learning enhances accuracy.
  • AcconPred effectively predicts solvent accessibility and contact number by leveraging their interdependence.