数据下载

wget -c "https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE145370&format=file" -O GSE145370_RAW.tar
#解压
tar xvf GSE145370_RAW.tar

准备map.txt 文件：

#accession	SampleID	gender	age	pathological_stage	tissue_type	patient
GSM4317409	S133A	 Male	60	IIIB	T	S133
GSM4317410	S134A	 Female	53	IIIA	T	S134
GSM4317411	S135A	 Male	71	IIA	T	S135
GSM4317412	S149A	 Male	81	IIA	T	S149
GSM4317413	S150A	 Male	73	IIIB	T	S150
GSM4317414	S158A	 Male	55	IIB	T	S158
GSM4317415	S159A	 Male	54	IIIB	T	S159
GSM4317416	S133B	 Male	60	IIIB	N	S133
GSM4317417	S134B	 Female	53	IIIA	N	S134
GSM4317418	S135B	 Male	71	IIA	N	S135
GSM4317419	S149B	 Male	81	IIA	N	S149
GSM4317420	S150B	 Male	73	IIIB	N	S150
GSM4317421	S158B	 Male	55	IIB	N	S158
GSM4317422	S159B	 Male	54	IIIB	N	S159

批量解压：

cat map.txt |grep -v "#"|while read a b c ;do mkdir $b;tar zxvf ${a}_${b}_filtered_feature_bc_matrix.tar.gz -C $b;done

结果目录：

循环读入数据做质控：

cat map.txt|grep -v "#"|while read a b c d e f g;do

 Rscript $scripts/seurat_sc_qc.r  --data.dir   $b/filtered_feature_bc_matrix  --project GSE145370  \
    --nUMI.min 500 \
    --nUMI.max 50000 \
  --nGene.min 250 \
  --mito.gene.pattern "^MT.*-" \
  --percent_mito 25 \
  --log10GenesPerUMI 0.7 \
   -p $b  \
  --metadata.col.name accession SampleID gender age pathological_stage tissue_type patient \
  --metadata.value $a $b $c $d $e $f $g
done
#合并数据
Rscript $scripts/merge_seurat_obj.r -i  $(ls *.afterQC.rds) \
 -o 02.merge -p GSE145370

#分群聚类
Rscript $scripts/seurat_sc_cluster.r --rds 02.merge/GSE145370.rds  \
 -p GSE145370  --resolution 0.5  -d 30 -o 03.cluster \
 --vars.to.regress nUMI  percent_mito --high.variable.genes 2000