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 Videos

Predicting the subcellular localization of human proteins using machine learning and exploratory data analysis.

George K Acquaah-Mensah¹, Sonia M Leach, Chittibabu Guda

¹Department of Pharmaceutical Sciences, School of Pharmacy-Worcester, Massachusetts College of Pharmacy and Health Sciences, Worcester, MA 01608-1715, USA. george.acquaah-mensah@mcphs.edu

Genomics, Proteomics & Bioinformatics

|September 15, 2006

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

Circulating and brain-resident memory CD8+ T cells seed distinct bystander T <sub>RM</sub> -like populations in glioblastoma.

bioRxiv : the preprint server for biology·2026

Same author

Machine learning-driven QSAR modeling combined with single cell transcriptomics identifies novel drug targets for lung cancer.

Journal of translational medicine·2026

Same author

Metabolic alterations in cystic fibrosis lymphocyte memory accompanies restoration of CFTR function.

American journal of respiratory cell and molecular biology·2026

Same author

Heroin addiction modulates transcription factor binding in regulatory regions of the human putamen.

Scientific reports·2026

Same author

Molecular characterisation of progressive pulmonary sarcoidosis: protocol for a longitudinal multi-centre study to develop peripheral blood circulating biomarkers for predicting pulmonary sarcoidosis progression.

BMJ open·2026

Same author

Transcriptomic signatures in tetrapartite brain region identifies shared and unique gene signatures for substance-use.

Frontiers in cellular neuroscience·2026

Same journal

Single-cell RNA Sequencing Reveals A Tumor-Promoting Role of EGR1+CD4+ T Cells in Papillary Thyroid Cancer.

Genomics, proteomics & bioinformatics·2026

Same journal

Long-read Sequencing: from Complete Molecules to Context-resolved Biology.

Genomics, proteomics & bioinformatics·2026

Same journal

A Cattle BodyMap of Transcriptome across 52 Tissues and 3 Developmental Stages Reveals New Genetic Insights into Beef Production Traits.

Genomics, proteomics & bioinformatics·2026

Same journal

Real-time Targeted Enrichment in Single-cell Long-read Sequencing.

Genomics, proteomics & bioinformatics·2026

Same journal

Decoding RNA N6-Methyladenosine Methylome of Wheat Using Machine Learning and Nanopore Direct RNA Sequencing.

Genomics, proteomics & bioinformatics·2026

Same journal

Tranquillyzer: A Neural Network Framework for Long-read Annotation and Demultiplexing.

Genomics, proteomics & bioinformatics·2026

See all related articles

Machine learning accurately predicts human protein subcellular localization using amino acid sequences. Exploratory Data Analysis reveals distinct sequence features for proteins in different cellular compartments, aiding functional annotation.

Area of Science:

Bioinformatics
Computational Biology
Molecular Biology

Background:

Subcellular protein localization is crucial for understanding protein function and gene products.
Accurate prediction of protein localization aids in functional annotation and biological pathway elucidation.

Purpose of the Study:

To apply Machine Learning and Exploratory Data Analysis (EDA) for predicting human protein subcellular localization based on amino acid sequences.
To characterize sequence features associated with proteins in nine distinct cellular compartments.

Main Methods:

Utilized a dataset of 3,749 human protein sequences from the SWISS-PROT database.
Developed feature vectors capturing amino acid sequence characteristics.
Compared C4.5 Decision Tree, Support Vector Machine, Multi-layer Perceptron, and Naive Bayes classifiers for prediction accuracy.

Related Experiment Videos

Employed EDA for visualizing and characterizing protein sequence features per compartment.

Main Results:

The C4.5 Decision Tree algorithm demonstrated the highest consistency and reliability in predicting subcellular localization (average Precision=0.88, average Sensitivity=0.86).
EDA identified specific amino acid composition patterns: hydrophobic amino acids in plasma membrane proteins, neutral amino acids in cytoplasmic proteins, and a mix in mitochondrial proteins.

Conclusions:

Machine learning, particularly the C4.5 classifier, is effective for predicting human protein subcellular localization from amino acid sequences.
EDA provides valuable insights into sequence-based characteristics differentiating proteins across cellular compartments.
These computational approaches enhance the functional annotation of human proteins.