text Unix CSV编辑

Posted 2021-05-01

## print these three columns separated by tabs to new file
awk '{print $2 "\t" $3 "\t" $5}' gene_info > gene_info_id-name-syns.tsv

## show duplicate rows with most frequent at top
sort gene_info_id-name-syns.tsv | uniq -cd | sort -nr > row_counts

## filter rows that contain either Symbol or NEWENTRY in second column
awk '$2 !~ /Symbol/ && $2 !~ /NEWENTRY/'

## filter file so that it only prints rows when first column equals 9606
awk '$1 == "9606"' gene_info > human_gene_info

## combine filters above to print only specific columns with row filters
awk '$1 == "9606"' gene_info | awk '{print $2 "\t" $3 "\t" $4 "\t" $5}' | awk '$2 !~ /Symbol/ && $2 !~ /NEWENTRY/' > human_genes_locus-id-name-syns.tsv

## replaces empty fields (-) with empty string
sed -e "s/\t-//g" gene_info
## and replace | with tab
sed -e "s/|/\t/g" gene_info