########################### ##### MothurQC-Mothur ##### ########################### pcr.seqs(fasta=silva.bacteria.fasta, start=1, end=11894, keepdots=F) system(mv silva.bacteria.pcr.fasta silva.V1V3.fasta) make.contigs(file=mock.files, processors=4) summary.seqs(fasta=mock.trim.contigs.fasta) screen.seqs(fasta=mock.trim.contigs.fasta, group=mock.contigs.groups, summary=mock.trim.contigs.summary, maxambig=8, maxhomop=8, maxlength=520) unique.seqs(fasta=mock.trim.contigs.fasta) count.seqs(name=mock.trim.contigs.good.names, group=mock.contigs.good.groups) align.seqs(fasta=mock.trim.contigs.good.unique.fasta, reference=silva.V1V3.fasta, flip=true) summary.seqs(fasta=mock.trim.contigs.good.unique.align, count=mock.trim.contigs.good.count_table) screen.seqs(fasta=mock.trim.contigs.good.unique.align, count=mock.trim.contigs.good.count_table, summary=mock.trim.contigs.good.unique.summary, start=1043, end=11891, maxhomop=8, maxambig=8, optimize=end) filter.seqs(fasta=mock.trim.contigs.good.unique.good.align, vertical=T, trump=.) unique.seqs(fasta=mock.trim.contigs.good.unique.good.filter.fasta, count=mock.trim.contigs.good.good.count_table) pre.cluster(fasta=mock.trim.contigs.good.unique.good.filter.unique.fasta, count=mock.trim.contigs.good.unique.good.filter.count_table, diffs=2) chimera.uchime(fasta=mock.trim.contigs.good.unique.good.filter.unique.precluster.fasta, count=mock.trim.contigs.good.unique.good.filter.unique.precluster.count_table, processors=1, dereplicate=t) remove.seqs(fasta=mock.trim.contigs.good.unique.good.filter.unique.precluster.fasta, accnos=mock.trim.contigs.good.unique.good.filter.unique.precluster.uchime.accnos) classify.seqs(fasta=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.fasta, count=mock.trim.contigs.good.unique.good.filter.unique.precluster.uchime.pick.count_table, reference=trainset9_032012.pds.fasta, taxonomy=trainset9_032012.pds.tax, cutoff=80) remove.lineage(fasta=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.fasta, count=mock.trim.contigs.good.unique.good.filter.unique.precluster.uchime.pick.count_table, taxonomy=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pds.wang.taxonomy, taxon=Chloroplast-Mitochondria-unknown-Archaea-Eukaryota) summary.seqs(fasta=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pick.fasta) # OTU analysis dist.seqs(fasta=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pick.fasta, cutoff=0.2) cluster(column=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pick.dist, count=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pick.count_table) make.shared(list=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pick.an.unique_list.list, count=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pick.count_table, label=0.03) classify.otu(list=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pick.an.unique_list.list, count=mock.trim.contigs.good.unique.good.filter.unique.precluster.denovo.uchime.pick.pick.count_table, taxonomy=mock.trim.contigs.good.unique.good.filter.unique.precluster.pick.pds.wang.pick.taxonomy, label=0.03) ########################## ##### MeFiTQC-Mothur ##### ########################## ### QC steps (non-Mothur commands) $ mefit -s mock.meep1 -r1 mock_R1.fastq -r2 mock_R2.fastq -nonovlp -n 15 -meep 1 Output Files: mock.meep1.ovlp.hq.fastq, mock.meep1.nonovlp.hq.fastq # Convert the high-quality amplicons to FASTA format. # mock.meep1.ovlp.hq.fastq + mock.meep1.nonovlp.hq.fastq --> mock.meep1.fasta Output File: mock.meep1.fasta # Mothur commands pcr.seqs(fasta=silva.bacteria.fasta, start=1, end=11894, keepdots=F) system(mv silva.bacteria.pcr.fasta silva.V1V3.fasta) unique.seqs(fasta=mock.meep1.fasta) count.seqs(name=mock.meep1.unique.fasta, group=mock.meep1.groups) align.seqs(fasta=mock.meep1.unique.fasta, reference=silva.V1V3.fasta, flip=true, processors=4) summary.seqs(fasta=mock.meep1.unique.align, count=mock.meep1.count_table) screen.seqs(fasta=mock.meep1.unique.align, count=mock.meep1.count_table, summary=mock.meep1.unique.summary, start=1043, end=11891, maxhomop=8, maxambig=8, optimize=end) filter.seqs(fasta=mock.meep1.unique.good.align, vertical=T, trump=.) unique.seqs(fasta=mock.meep1.unique.good.filter.fasta, count=mock.meep1.good.count_table) pre.cluster(fasta=mock.meep1.unique.good.filter.unique.fasta, count=mock.meep1.unique.good.filter.count_table, diffs=2) chimera.uchime(fasta=mock.meep1.unique.good.filter.unique.precluster.fasta, count=mock.meep1.unique.good.filter.unique.precluster.count_table, processors=1, dereplicate=t) remove.seqs(fasta=mock.meep1.unique.good.filter.unique.precluster.fasta, accnos=mock.meep1.unique.good.filter.unique.precluster.uchime.accnos) classify.seqs(fasta=mock.meep1.unique.good.filter.unique.precluster.pick.fasta, count=mock.meep1.unique.good.filter.unique.precluster.uchime.pick.count_table, reference=trainset9_032012.pds.fasta, taxonomy=trainset9_032012.pds.tax, cutoff=80) remove.lineage(fasta=mock.meep1.unique.good.filter.unique.precluster.pick.fasta, count=mock.meep1.unique.good.filter.unique.precluster.uchime.pick.count_table, taxonomy=mock.meep1.unique.good.filter.unique.precluster.pick.pds.wang.taxonomy, taxon=Chloroplast-Mitochondria-unknown-Archaea-Eukaryota) summary.seqs(fasta=mock.meep1.unique.good.filter.unique.precluster.pick.pick.fasta) # OTU analysis dist.seqs(fasta=mock.meep1.unique.good.filter.unique.precluster.pick.pick.fasta, cutoff=0.2) cluster(column=mock.meep1.unique.good.filter.unique.precluster.pick.pick.dist, count=mock.meep1.unique.good.filter.unique.precluster.pick.pick.count_table) make.shared(list=mock.meep1.unique.good.filter.unique.precluster.pick.pick.an.unique_list.list, count=mock.meep1.unique.good.filter.unique.precluster.pick.pick.count_table, label=0.03) classify.otu(list=mock.meep1.unique.good.filter.unique.precluster.pick.pick.an.unique_list.list, count=mock.meep1.unique.good.filter.unique.precluster.uchime.pick.pick.count_table, taxonomy=mock.meep1.unique.good.filter.unique.precluster.pick.pds.wang.pick.taxonomy, label=0.03)