Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 26, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Predicting residue-residue contact maps by a two-layer, integrated neural-network method.

Bin Xue¹, Eshel Faraggi, Yaoqi Zhou

¹Indiana University School of Informatics, Indiana University-Purdue University, Indianapolis, Indiana 46202, USA.

|January 13, 2009

Summary

A new neural network method, SPINE-2D, accurately predicts protein residue-residue contact maps. This sequence-based approach enhances protein structure prediction accuracy, offering a valuable tool for bioinformatics research.

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

New Rolling Circle Transcription Based on Allosteric Transcription Factors (aTFs) for Trace Detection of Water Contaminants.

Analytical chemistry·2025

Same author

Bicarbonate-Rich Mineral Water Mitigates Hypoxia-Induced Osteoporosis in Mice via Gut Microbiota and Metabolic Pathway Regulation.

Nutrients·2025

Same author

Enhanced Mechanical Properties and Sensing Performance of MXene-Based Dual-Crosslinked Hydrogel via EGCG Coating and Dynamic Covalent Bond.

Small (Weinheim an der Bergstrasse, Germany)·2025

Same author

Structure-Guided Engineering of Carbonyl Reductase <i>Lb</i>CR to Simultaneously Enhance Catalytic Activity and Thermostability toward Bulky Ketones.

Journal of agricultural and food chemistry·2025

Same author

Hydrogels with programmed spatiotemporal mechanical cues for stem cell-assisted bone regeneration.

Nature communications·2025

Same author

Hydrogels with prestressed tensegrity structures.

Nature communications·2025

Area of Science:

Computational biology
Bioinformatics
Structural bioinformatics

Background:

Predicting residue-residue contact maps is crucial for protein structure determination.
Previous methods have limitations in accuracy and scope.
Neural networks show promise in complex biological predictions.

Purpose of the Study:

Introduce SPINE-2D, a novel neural network method for sequence-based prediction of residue-residue contact maps.
Evaluate the accuracy and performance of SPINE-2D compared to existing methods.
Provide a webserver for accessible use of the SPINE-2D tool.

Main Methods:

Utilized a two-layer neural network architecture.
Employed large-scale training with overfit protection.

Related Experiment Videos

Last Updated: Jun 26, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Leveraged sequence information for contact prediction.

Main Results:

Achieved 47% accuracy for top L/5 predicted contacts (sequence separation >= 6).
Reached 24% accuracy for nonlocal contacts (sequence separation >= 24).
Demonstrated competitive accuracy against other contact map prediction methods on independent datasets.

Conclusions:

SPINE-2D is an accurate and effective method for predicting residue-residue contact maps.
The method builds upon previous successes in predicting protein structural features.
SPINE-2D offers a valuable resource for the scientific community via a webserver.