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

Regulated mRNA Transport02:22

Regulated mRNA Transport

In eukaryotes, transcription and translation are compartmentalized; an mRNA is first synthesized in the nucleus and then selectively transported to the cytoplasm for protein synthesis. Before transport, a pre-mRNA undergoes several steps of post-transcriptional modifications including splicing, 5' capping, and the addition of a poly-adenine tail. Various proteins bind to the pre-mRNA during these modifications. The mRNA transport takes place with the help of multiple proteins playing specific...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Nuclear Localization Signals and Import01:46

Nuclear Localization Signals and Import

Proteins targeted to the nucleus carry short stretches of amino acid sequences called the nuclear localization signal or NLS. Classical nuclear localization signals are of two types: monopartite and bipartite NLS. Monopartite classical NLS (cNLS) consists of a single cluster of 4-8 amino acids. Bipartite cNLS consists of two clusters of  2-3 amino acids and a 9-12 residue long proline-rich linker bridging the two clusters. Signal clusters are rich in positively charged amino acids such as...
Cotranslational Protein Translocation01:20

Cotranslational Protein Translocation

Translocation of proteins across membranes is an ancient process that occurs even in bacteria and archaebacteria. In fact, the components of the translocation machinery are still conserved between prokaryotes and eukaryotes.
Sec61 channel partners for cotranslational translocation
During cotranslational translocation, the Sec61 channel partners with the signal recognition particle (SRP), the signal recognition particle receptor (SR), and the ribosomes to transport the nascent polypeptide chain...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Gene Ontology graph embeddings with Dynamic Thresholding based Deep Neural Networks for Multi-label protein subcellular localization prediction.

Computational biology and chemistry·2026
Same author

An Effective Framework for Protein Fold Prediction through the Fusion of Evolutionary Information and Attention Mechanism with Deep Neural Networks.

IEEE journal of biomedical and health informatics·2025
Same author

A Strategic Research Framework for Defeating Diabetes in India: A 21st-Century Agenda.

Journal of the Indian Institute of Science·2023
Same author

An Effective Multi-Label Protein Sub-Chloroplast Localization Prediction by Skipped-Grams of Evolutionary Profiles Using Deep Neural Network.

IEEE/ACM transactions on computational biology and bioinformatics·2020
Same author

An Enhanced Protein Fold Recognition for Low Similarity Datasets Using Convolutional and Skip-Gram Features With Deep Neural Network.

IEEE transactions on nanobioscience·2020
Same author

ProgSIO-MSA: Progressive-based single iterative optimization framework for multiple sequence alignment using an effective scoring system.

Journal of bioinformatics and computational biology·2020

Related Experiment Video

Updated: May 24, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Enhancing protein subcellular localization prediction through language model-based knowledge embeddings and machine

Karthik Avinash1, S Tejas1, Sriram Mamidala2

  • 1Department of Computer Science and Engineering, Indian Institute of Information Technology Dharwad, India.

Analytical Biochemistry
|May 22, 2026
PubMed
Summary

This study evaluates protein language models for predicting protein subcellular localization. ESM-2 with a Support Vector Machine achieved the best performance, improving accuracy by 3% over current models.

Keywords:
Bidirectional encoder representations from transformersEvolutionary scale modelingMulti-label classificationProtein embeddingProtein language modelsProtein subcellular localizationStrict accuracy

Related Experiment Videos

Last Updated: May 24, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Protein Science

Background:

  • Protein subcellular localization is crucial for function.
  • Traditional methods for PSCL prediction are becoming impractical due to large datasets.
  • High-accuracy multi-label PSCL prediction remains a challenge.

Purpose of the Study:

  • To evaluate embeddings from five Protein Language Models (PLMs) as input features for machine learning classifiers.
  • To assess the performance of different PLM architectures and classifier complexities for PSCL prediction.
  • To identify optimal combinations for improved prediction accuracy.

Main Methods:

  • Utilized five PLMs: ProtBERT-BFD, ESM-2, ProtALBERT, ProLLaMA, and ProtGPT-2.
  • Employed machine learning classifiers, including Support Vector Machine (SVM) with a polynomial kernel.
  • Conducted five-fold cross-validation on the Swiss-Prot dataset.

Main Results:

  • Encoder-based PLMs, especially ESM-2, combined with SVM (polynomial kernel), yielded the best performance.
  • Achieved a strict accuracy of 0.58, a 3 percentage point improvement over state-of-the-art models.
  • Demonstrated modest but consistent improvements in strict-accuracy metrics.

Conclusions:

  • ESM-2 embeddings with SVM offer a robust approach for PSCL prediction.
  • Current PLM embeddings provide strong performance but require further advancements.
  • Future work should focus on enhanced feature extraction and model architectures to significantly boost strict accuracy.