ABSTRACT
In order to provide a theoretical basis for better understanding the function and properties of proteins, we proposed a simple and effective feature extraction method for protein sequences to determine the subcellular localization of proteins. First, we introduced sparse coding combined with the information of amino acid composition to extract the feature values of protein sequences. Then the multilayer pooling integration was performed according to different sizes of dictionaries. Finally, the extracted feature values were sent into the support vector machine to test the effectiveness of our model. The success rates in data set ZD98, CH317 and Gram1253 were 95.9%, 93.4% and 94.7%, respectively as verified by the Jackknife test. Experiments showed that our method based on multilayer sparse coding can remarkably improve the accuracy of the prediction of protein subcellular localization.
Subject(s)
Algorithms , Amino Acid Sequence , Computational Biology , Protein Transport , Proteins , Subcellular Fractions , Support Vector MachineABSTRACT
Objective To compare the advantages and disadvantages of SNPscan and Sanger sequence which are both used to detect the common deafness gene mutations in non-syndromic hearing loss (NSHL) in Gansu Province.Methods Peripheral blood samples were obtained from Dongxiang, Yugu and Baoan people with moderately severe to profound sensorineural hearing loss in Gansu province to extract genomic DNA.SNPscan was used to detect the 115 mutations in the common pathogenic GJB2 gene, SLC26A4 gene and mtDNA gene.Results We used the SNPscan to screen the mutation of GJB2 gene,mtDNA A1555G and mtDNA C1494T, SLC26A4 gene of sensorinural deafness patients from Gansu Province.The mutation rate of these three genes was 23.18% (35/151), and the mutation rate of Dongxiang, Yugu, Baoan was 21.31% (26/122), 54.54% (6/11), 16.67% (3/18), respectively.Compared with the Sanger sequence, the results were statistically insignificant(P>0.05).The detection rates in the three genes of SNPscan were 11.26% (17/151), 1.32% (2/151) and 0.66% (1/151),respectively , and the detection rates of Sanger sequence were 9.93% (15/151), 1.32% (2/151) and 0.66% (1/151) ,respectively.The results of the two methods were compared.The results were statistically insignificant (P>0.05).Time, cost and flux, SNPscan method is superior to Sanger sequencing.Conclusion Compared with the Sanger sequence, SNPscan is more lighter in workload, less time-consuming, higher-throughput, lower cost, and can get more meaningful mutations and reduce the false negative rates.
ABSTRACT
Objective To investigate the prevalence and characteristics of GJB2 mutations in Uygur,Hui, Kazak and Kirgiz ethnic patients with non-syndromic hearing loss(NSHL)from the Xinjiang Uygur Autonomous Region of China.Methods With the permission,we collected 565 patients with moderately severe to profound sen-sorineural hearing loss,including Uygur,Hui,Kazak and Kirgiz ethnic minorities from 14 cities of Xinjiang.Pe-ripheral blood samples were obtained to extract genomic DNA.The SNP classification technology was for common pathogenic GJB2 gene mutations.ResuIts The pathogenic allele frequency of GJB2 gene were 10.16%(87/856 ), 15.85%(13/82),10.16%(13/128),1.56%(1/64)in the NSHL patients of Uygur,Hui,Kazak and Kirgiz minori-ties,respectively.And these differences were statistically significant (χ2 =8.140,P=0.043).c.235delc was only found in the Uygur and Hui with the allele frequency of 5.14 %(44/856)and 13.41 %(11/82),respectively.And c.35delG was found in Uyhur,Hui,Kazak and Kirgiz with allele frequencies were 3.15% (27/856),1.21% (1/82),8.59%(11/128)and 1.56% (1/64),respectively.ConcIusion GJB2 gene mutations had a higher incidence in Xinjiang NSHL patients,GJB2 gene mutation spectrum had differences in Uygur,Hui,Kazak and Kirgiz,c. 235delC the hotspot mutation region in Uygur and Hui nationalities NSHL patients,while c.35delG is the hotspot mutation region in NSHL patients of Uygur,Kazak and Kirgiz ethnicities.