fix: harmonize filenames in awk exercises

9_batch_processing.Rmd

@@ -184,13 +184,13 @@ awk -vFS='\t' -vOFS='' '{print $1 "\n";}' two_column_sample_tab.txt > seq_name.t
 Convert a multiline fasta file into a single line fasta file
 
 ```sh
-awk '!/^>/ { printf "%s", $0; n = "\n" } /^>/ { print n $0; n = "" } END { printf "%s", n }' sample.fa > sample1_singleline.fa
+awk '!/^>/ { printf "%s", $0; n = "\n" } /^>/ { print n $0; n = "" } END { printf "%s", n }' sample.fa > sample_singleline.fa
 ```
 
 Convert fasta sequences to uppercase
 
 ```sh
-awk '/^>/ {print($0)}; /^[^>]/ {print(toupper($0))}' file.fasta > file_upper.fasta
+awk '/^>/ {print($0)}; /^[^>]/ {print(toupper($0))}' sample.fa > sample_upper.fa
 ```
 
 Modify this command to only get a list of sequence names in a fasta file un lowercase
@@ -198,7 +198,7 @@ Modify this command to only get a list of sequence names in a fasta file un lowe
 <details><summary>Solution</summary>
 <p>
 ```sh
-awk '/[^>]/ {print(tolower($0))}' file.fasta > seq_name_lower.txt
+awk '/[^>]/ {print(tolower($0))}' sample.fa > seq_name_lower.txt
 ```
 </p>
 </details>
@@ -206,19 +206,19 @@ awk '/[^>]/ {print(tolower($0))}' file.fasta > seq_name_lower.txt
 Return a list of sequence_id sequence_length from a fasta file
 
 ```sh
-awk 'BEGIN {OFS = "\n"}; /^>/ {print(substr(sequence_id, 2)" "sequence_length); sequence_length = 0; sequence_id = $0}; /^[^>]/ {sequence_length += length($0)}; END {print(substr(sequence_id, 2)" "sequence_length)}' file.fasta
+awk 'BEGIN {OFS = "\n"}; /^>/ {print(substr(sequence_id, 2)" "sequence_length); sequence_length = 0; sequence_id = $0}; /^[^>]/ {sequence_length += length($0)}; END {print(substr(sequence_id, 2)" "sequence_length)}' sample.fa
 ```
 
 Count the number of bases in a fastq.gz file
 
 ```sh
-(gzip -dc $0) | awk 'NR%4 == 2 {basenumber += length($0)} END {print basenumber}'
+sample.fq.gz | (gzip -dc $0) | awk 'NR%4 == 2 {basenumber += length($0)} END {print basenumber}'
 ```
 
-Only read with more than 20bp from a fastq
+Extract the reads with more than 20bp from a fastq
 
 ```sh
-awk 'BEGIN {OFS = "\n"} {header = $0 ; getline seq ; getline qheader ; getline qseq ; if (length(seq) >= 20){print header, seq, qheader, qseq}}' < input.fastq > output.fastq
+awk 'BEGIN {OFS = "\n"} {header = $0 ; getline seq ; getline qheader ; getline qseq ; if (length(seq) >= 20){print header, seq, qheader, qseq}}' < input.fq > output.fq
 ```