Search research articles

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

Activated Macrophages Promote TNF-α-Associated Tumor Cell Necroptosis in Pituitary Apoplexy Through the PIEZO1-NFATC2/REL Axis.

International journal of molecular sciences·2026

Same author

Research on the Formability of 2A12 Aluminum Alloy Sheet During High-Speed Hot Gas Bulging.

Materials (Basel, Switzerland)·2026

Same author

WTop: A Wavelet-Driven Framework for Comprehensive Proteoform Characterization in Top-Down Mass Spectrometry.

Analytical chemistry·2026

Same author

Vibration Compensation for a High-Precision Atomic Gravimeter Based on an Improved Whale Optimization Algorithm.

Sensors (Basel, Switzerland)·2026

Same author

Beyond Epilepsy Control: Repurposing Antiepileptic Drugs in Central Nervous System Tumor Therapy.

Cells·2026

Same author

Specific depletion of TIGIT<sup>high</sup> CD226<sup>-</sup> clonally expanded intratumoral Tregs defines safe and effective TIGIT targeting.

Journal for immunotherapy of cancer·2026

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: Aug 30, 2025

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

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

Published on: January 6, 2017

SADeepcry: a deep learning framework for protein crystallization propensity prediction using self-attention and

Shaokai Wang¹, Haochen Zhao^2,3

¹David R. Cheriton School of Computer Science, University of Waterloo, 200 University Ave W, Waterloo, ON N2L 3G1, Canada.

Briefings in Bioinformatics

|August 29, 2022

Summary

Predicting protein crystallization is challenging, with success rates below 10%. SADeepcry, a novel deep learning framework, accurately estimates multi-stage protein crystallization propensity, improving prediction accuracy for structural biology research.

Keywords:

Multi-stage prediction protein crystallization and deep learning

More Related Videos

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

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

Published on: January 26, 2024

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Aug 30, 2025

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

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

Published on: January 6, 2017

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

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

Published on: January 26, 2024

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Area of Science:

Structural Biology
Biophysics
Computational Biology

Background:

X-ray diffraction (XRD) is crucial for protein structure analysis but relies on challenging crystallization processes.
Current protein crystallization prediction tools lack accuracy and multi-stage prediction capabilities.
The low success rate (<10%) and resource intensiveness of protein crystallization hinder structural studies.

Purpose of the Study:

To develop a novel deep learning framework, SADeepcry, for predicting protein crystallization propensity.
To estimate the success rate of multi-stage protein crystallization experiments (production, purification, crystallization).
To improve the accuracy and efficiency of predicting protein crystallization outcomes.

Main Methods:

Developed SADeepcry, a deep learning framework utilizing optimized self-attention and auto-encoder modules.
Extracted sequence, structure, and physicochemical features from protein data.
Evaluated SADeepcry's performance against state-of-the-art methods on a benchmark dataset.

Main Results:

SADeepcry accurately predicts multi-stage protein crystallization propensity and overall success rates.
The framework captures complex global spatial long-distance dependencies in protein sequences.
Achieved significant improvements in Matthews correlation coefficient (100.3%) and area under the curve (13.4%) over DCFCrystal.

Conclusions:

SADeepcry offers a more accurate and reliable method for predicting protein crystallization.
The framework has the potential to significantly reduce the time and resources required for protein structure determination.
SADeepcry advances computational approaches in structural biology and drug discovery.