Graphical classification of DNA sequences of HLA alleles by deep learning.

Hum Cell

Graduate School of Engineering Science, Osaka University, 1-3 Machikane-Yama, Toyonaka, Osaka, 560-8531, Japan.

Published: April 2018

Alleles of human leukocyte antigen (HLA)-A DNAs are classified and expressed graphically by using artificial intelligence "Deep Learning (Stacked autoencoder)". Nucleotide sequence data corresponding to the length of 822 bp, collected from the Immuno Polymorphism Database, were compressed to 2-dimensional representation and were plotted. Profiles of the two-dimensional plots indicate that the alleles can be classified as clusters are formed. The two-dimensional plot of HLA-A DNAs gives a clear outlook for characterizing the various alleles.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5852191PMC
http://dx.doi.org/10.1007/s13577-017-0194-6DOI Listing

Publication Analysis

Top Keywords

hla-a dnas
8
graphical classification
4
classification dna
4
dna sequences
4
sequences hla
4
alleles
4
hla alleles
4
alleles deep
4
deep learning
4
learning alleles
4

Similar Publications

Background: Severe acute respiratory syndrome coronavirus 2 was first reported in December 2019 and it has spread globally ever since. The HLA system is crucial in directing anti-viral immunity and recent studies are investigating the possible involvement of the HLA genes on the severity of immune inflammation in different phases of COVID-19.

Methods: In this cross-sectional study, peripheral blood-extracted genomic DNAs of 109 COVID-19 patients and 70 healthy controls were genotyped for different alleles of HLA-A, HLA-B, and HLA-DRB1 loci using sequence-specific primer PCR method.

View Article and Find Full Text PDF

The distribution of HLA class-II DRB1* and DQB1* alleles/ haplotypes were studied in 438 individuals of 8 Dravidian tribal groups inhabiting the Western Ghats, south India. The HLA typing was performed by PCR-SSP method. In order to identify the 5-locus Ancestral Extended Haplotypes (AEH), the alleles of HLA-A, -B and -C loci were typed for DNAs with predominant 2-locus haplotypes.

View Article and Find Full Text PDF

Genomic DNA (gDNA) obtained from whole blood samples is a critical element for genomic research and clinical diagnosis. PCR efficiencies of the targeted genes like HLA-A, -B, -C, DPB1 and DRB1 using such isolated gDNAs were variable in spite of having similar amounts of gDNA taken for PCR. We addressed such PCR variabilities by normalizing the gDNA's using an internal control of human coagulation factor XIII that was found to be variable with all samples and did not correlate with the observed A nm readings.

View Article and Find Full Text PDF

HLA genetics in bipolar disorder.

Acta Psychiatr Scand

November 2018

INSERM, U955, Translational Psychiatry, Paris-East University, School of Medicine, AP-HP, DHU PePSY, Pole of Psychiatry, Henri Mondor University Hospital, Créteil, France.

Objective: Bipolar Disorder (BD) is characterized by deregulated adaptive immune processes. Recent genome-wide association studies (GWAS) implicate the major histocompatibility complex (MHC) region in BD. The present study investigates the potential influence of variations in human leukocyte antigen (HLA) on BD risk and/or clinical presentations.

View Article and Find Full Text PDF

Graphical classification of DNA sequences of HLA alleles by deep learning.

Hum Cell

April 2018

Graduate School of Engineering Science, Osaka University, 1-3 Machikane-Yama, Toyonaka, Osaka, 560-8531, Japan.

Alleles of human leukocyte antigen (HLA)-A DNAs are classified and expressed graphically by using artificial intelligence "Deep Learning (Stacked autoencoder)". Nucleotide sequence data corresponding to the length of 822 bp, collected from the Immuno Polymorphism Database, were compressed to 2-dimensional representation and were plotted. Profiles of the two-dimensional plots indicate that the alleles can be classified as clusters are formed.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!