Calculate MD5 checksums of sequences and compare to DADA2/Deblur seqids

[lukenoaa]

Rule not working properly:

# mac: md5 / linux: md5sum
rule check_repseq_md5:
    input:
        "02-output-{method}/00-table-repseqs/representative_sequences.fasta"
    output:
        "02-output-{method}/00-table-repseqs/representative_sequences_md5_status.txt"
    shell:
        "seq1id=`head -n 1 {input} | sed 's/^>//'`; "
        "seq1md5=`head -n 2 {input} | tail -n 1 | md5 -q`; "
        "echo -n First representative sequence ID..... > {output}; "
        "echo $seq1id >> {output}; "
        "echo -n First representative sequence MD5.... >> {output}; "
        "echo $seq1md5 >> {output}; "
        "if [ '$seq1id' == '$seq1md5' ]; "
        "then echo 'First representative sequence has ID matching MD5 :)'; "
        "else echo 'First representative sequence has ID *not* matching MD5 :('; "
        "fi >> {output}; "
        "seq2id=`tail -n 2 {input} | head -n 1 | sed 's/^>//'`; "
        "seq2md5=`tail -n 1 {input} | md5 -q`; "
        "echo -n Last representative sequence ID..... >> {output}; "
        "echo $seq2id >> {output}; "
        "echo -n Last representative sequence MD5.... >> {output}; "
        "echo $seq2md5 >> {output}; "
        "if [ '$seq2id' == '$seq2md5' ]; "
        "then echo 'Last representative sequence has ID matching MD5 :)'; "
        "else echo 'Last representative sequence has ID *not* matching MD5 :('; "
        "fi >> {output}"