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: May 21, 2026

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

KmalPred: a deep learning framework for lysine malonylation site prediction using protein language model

Shihu Jiao^1,2, Chunyan Ao^1,2, Quan Zou^1,2

¹Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, China.

|May 20, 2026

Summary

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

DiffuScope: A diffusion-regularized autoencoder for spatial transcriptomic clustering.

Computational biology and chemistry·2025

Same author

YModPred: an interpretable prediction method for multi-type RNA modification sites in S. cerevisiae based on deep learning.

BMC biology·2025

Same author

Feadm5C: Enhancing prediction of RNA 5-Methylcytosine modification sites with physicochemical molecular graph features.

Genomics·2025

Same author

Elevating VAPB-PTPIP51 integration repairs damaged mitochondria-associated endoplasmic reticulum membranes and inhibits lung fibroblasts activation.

International immunopharmacology·2025

Same author

Biological Sequence Classification: A Review on Data and General Methods.

Research (Washington, D.C.)·2024

Same author

Identification of histone acetylation modification sites in the striatum of subchronically manganese-exposed rats.

Epigenomics·2024

This summary is machine-generated.

KmalPred, a new deep learning tool, accurately predicts lysine malonylation sites by analyzing full protein sequences. This method improves upon existing predictors, aiding research into metabolic regulation and post-translational modifications.

Area of Science:

Biochemistry
Computational Biology
Proteomics

Background:

Lysine malonylation (Kmal) is a crucial reversible post-translational modification impacting metabolic regulation.
Experimental identification of Kmal sites is challenging due to its labor-intensive and time-consuming nature.
Current computational methods often miss long-range protein information.

Purpose of the Study:

To develop an advanced computational tool for accurate Kmal site prediction.
To overcome limitations of existing predictors by incorporating global protein context.

Main Methods:

Developed KmalPred, a deep learning framework utilizing ProtT5-derived residue representations and a bidirectional LSTM.
Implemented a sequence-first approach, encoding the entire protein before extracting lysine-centered windows.

Keywords:

Data imbalance Long short-term memory network Lysine malonylation Protein language model Sequence representation

More Related Videos

Specificity Analysis of Protein Lysine Methyltransferases Using SPOT Peptide Arrays

Specificity Analysis of Protein Lysine Methyltransferases Using SPOT Peptide Arrays

Published on: November 29, 2014

Related Experiment Videos

Last Updated: May 21, 2026

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

Specificity Analysis of Protein Lysine Methyltransferases Using SPOT Peptide Arrays

Specificity Analysis of Protein Lysine Methyltransferases Using SPOT Peptide Arrays

Published on: November 29, 2014

Leveraged full-sequence encoding to preserve global context and enhance efficiency.

Main Results:

KmalPred achieved 0.78 accuracy and 0.56 MCC on an independent test set, outperforming existing predictors.
The sequence-first strategy demonstrated superior performance compared to conventional segment-first methods.
ProtT5 representations proved more informative than other protein language models, with stable performance under class imbalance.

Conclusions:

KmalPred offers an effective and robust solution for large-scale Kmal site prediction.
Full-sequence protein language model representations are valuable for predicting post-translational modifications.
The KmalPred framework is adaptable for predicting other post-translational modification sites.