www.gusucode.com > bioinfo 案例源码程序 matlab代码 > bioinfo/FilterNextgenerationSequencingDataExample.m

    %% Filter next-generation sequencing data
% 
%%
% Filter out sequences with more than 10% of low quality bases, where a
% base is considered low quality when its quality score is less than 20.
 [outFile,in,out] = seqfilter('SRR005164_1_50.fastq',...
                              'Method','MaxPercentLowQualityBases',...
                              'Threshold',[10 20]) ;
%%
% Check the number of sequences saved in the output file.
in
%%
% Check the number of sequences filtered out.
out
%%
% Filter out sequences having an average quality score of below 20.
% 
%   [outFile,in,out] = seqfilter('SRR005164_1_50.fastq',...
%                                'Method','MeanQuality',...
%                                'Threshold',20); 

%%
% Apply the filtering criterion to every 10 bases as a sliding window.
%
%   [outFile,in,out] = seqfilter('SRR005164_1_50.fastq',...
%                                'Method','MeanQuality',...
%                                'Threshold',20,'WindowSize',10); 

%%
% Filter out sequences with less than 100 bases.
%
%   [outFile,in,out] = seqfilter('SRR005164_1_50.fastq',...
%                                'Method','MinLength',...
%                                'Threshold',100);