| TCGA代码分析流程 | 您所在的位置：网站首页 › tcga基因id转换 › TCGA代码分析流程 |
|
1. 整理表达矩阵
下载的文件是按样本存放的，每个tsv文件中都记录着一个样本的基因表达量，需要将所有tsv文件合并，得到所有样本的基因表达量的表格。 转录组数据合并 rm(list = ls()) library(stringr) library(jsonlite) library(progress) options(stringsAsFactors = F) cancer_type {$patient_key}{'clin_shared:vital_status'}{'content'}; my $followup=$userxml->{$patient_key}{'clin_shared:days_to_last_followup'}{'content'}; my $death=$userxml->{$patient_key}{'clin_shared:days_to_death'}{'content'}; if($vital_status eq 'Alive'){ $survivalTime="$followup\t0"; } else{ $survivalTime="$death\t1"; } for my $i(keys %{$userxml->{$patient_key}{$follow_key}}){ eval{ $followup=$userxml->{$patient_key}{$follow_key}{$i}{'clin_shared:days_to_last_followup'}{'content'}; $vital_status=$userxml->{$patient_key}{$follow_key}{$i}{'clin_shared:vital_status'}{'content'}; $death=$userxml->{$patient_key}{$follow_key}{$i}{'clin_shared:days_to_death'}{'content'}; }; if($@){ for my $j(0..5){ #假设最多有6次随访 my $followup_for=$userxml->{$patient_key}{$follow_key}{$i}[$j]{'clin_shared:days_to_last_followup'}{'content'}; my $vital_status_for=$userxml->{$patient_key}{$follow_key}{$i}[$j]{'clin_shared:vital_status'}{'content'}; my $death_for=$userxml->{$patient_key}{$follow_key}{$i}[$j]{'clin_shared:days_to_death'}{'content'}; if( ($followup_for =~ /\d+/) || ($death_for =~ /\d+/) ){ $followup=$followup_for; $vital_status=$vital_status_for; $death=$death_for; my @survivalArr=split(/\t/,$survivalTime); if($vital_status eq 'Alive'){ if($followup>$survivalArr[0]){ $survivalTime="$followup\t0"; } } else{ if($death>$survivalArr[0]){ $survivalTime="$death\t1"; } } } } } my @survivalArr=split(/\t/,$survivalTime); if($vital_status eq 'Alive'){ if($followup>$survivalArr[0]){ $survivalTime="$followup\t0"; } } else{ if($death>$survivalArr[0]){ $survivalTime="$death\t1"; } } } print WF "$patient_barcode\t$survivalTime\t$age\t$gender\t$grade\t$pathologic_stage\t$pathologic_T\t$pathologic_M\t$pathologic_N\n"; } } close(RD); } } close(WF);
|
| CopyRight 2018-2019 实验室设备网 版权所有 |