From d31fb2b76e4394905668fd152c823d4f79672011 Mon Sep 17 00:00:00 2001 From: Andrea Ortiz Date: Thu, 3 May 2018 19:24:22 -0500 Subject: [PATCH 1/2] uses samples for 4 of the ant species --- mothur_otu.bat | 146 ++++++++++++++++++++++++++++--------------------- 1 file changed, 83 insertions(+), 63 deletions(-) diff --git a/mothur_otu.bat b/mothur_otu.bat index c150d43..c4c4623 100644 --- a/mothur_otu.bat +++ b/mothur_otu.bat @@ -8,74 +8,70 @@ set.dir(input=analysis) # summarize complete sequences -# output: analysis.trim.summary -summary.seqs(fasta=analysis.trim.fasta) +# output: analysis.trim.4ant.summary +#summary.seqs(fasta=analysis.trim.4ant.fasta) # simplifying the dataset to only unique sequences -# output: analysis.trim.names, analysis.trim.unique.fasta -unique.seqs(fasta=analysis.trim.fasta) +# output: analysis.trim.4ant.names, analysis.trim.4ant.unique.fasta +#unique.seqs(fasta=analysis.trim.4ant.fasta) # inspect unique sequences -# output: analysis.trim.unique.summary -summary.seqs(fasta=analysis.trim.unique.fasta, name=analysis.trim.names) +# output: analysis.trim.4ant.unique.summary +#summary.seqs(fasta=analysis.trim.4ant.unique.fasta, name=analysis.trim.4ant.names) # align our data to silva reference -# output: analysis.trim.unique.align, analysis.trim.unique.align.report, analysis.trim.unique.flip.accnos -align.seqs(fasta=analysis.trim.unique.fasta, reference=silva/silva.nr_v128.pcr.align, flip=T, processors=6) +# output: analysis.trim.4ant.unique.align, analysis.trim.4ant.unique.align.report, analysis.trim.4ant.unique.flip.accnos +#align.seqs(fasta=analysis.trim.4ant.unique.fasta, reference=silva/silva.nr_v128.pcr.align, flip=T, processors=6) # inspect aligned sequences -# output: analysis.trim.unique.summary -summary.seqs(fasta=analysis.trim.unique.align, name=analysis.trim.names) +# output: analysis.trim.4ant.unique.summary +#summary.seqs(fasta=analysis.trim.4ant.unique.align, name=analysis.trim.4ant.names) # remove sequences outside the desired range of alignment space -# output: analysis.trim.unique.good.align, analysis.trim.unique.bad.accnos, analysis.good.names, analysis.trim.good.groups file -screen.seqs(fasta=analysis.trim.unique.align, name=analysis.trim.names, group=analysis.groups, optimize=end, criteria=90, processors=6) +# output: analysis.trim.4ant.unique.good.align, analysis.trim.4ant.unique.bad.accnos, analysis.trim.4ant.good.names, analysis.4ant.good.groups file +#screen.seqs(fasta=analysis.trim.4ant.unique.align, name=analysis.trim.4ant.names, group=analysis.4ant.groups, optimize=end, criteria=90, processors=6) # inspect sequences -# output: analysis.trim.unique.good.summary -summary.seqs(fasta=analysis.trim.unique.good.align, name=analysis.trim.good.names) +# output: analysis.trim.4ant.unique.good.summary +#summary.seqs(fasta=analysis.trim.4ant.unique.good.align, name=analysis.trim.4ant.good.names) # filter alignment to remove columns that don't contain data # the parameter trump=. will remove any column that has a "." character, which indicates missing data # vertical=T option will remove any column that contains exclusively gaps -# output: analysis.trim.unique.good.filter.fasta, filter file -filter.seqs(fasta=analysis.trim.unique.good.align, vertical=T, processors=6) +# output: analysis.trim.4ant.unique.good.filter.fasta, filter file +#filter.seqs(fasta=analysis.trim.4ant.unique.good.align, vertical=T, processors=6) # remove redundant sequences in the alignment region -# output: analysis.trim.unique.good.filter.names, analysis.trim.unique.good.filter.unique.fasta -unique.seqs(fasta=analysis.trim.unique.good.filter.fasta, name=analysis.trim.good.names) +# output: analysis.trim.4ant.unique.good.filter.names, analysis.trim.4ant.unique.good.filter.unique.fasta +#unique.seqs(fasta=analysis.trim.4ant.unique.good.filter.fasta, name=analysis.trim.4ant.good.names) # pre-cluster within each group -# output: analysis.trim.unique.good.filter.unique.precluster.fasta, analysis.trim.unique.good.filter.unique.precluster.names, analysis.trim.unique.good.filter.unique.precluster.field.map, analysis.trim.unique.good.filter.unique.precluster.lab.map -pre.cluster(fasta=analysis.trim.unique.good.filter.unique.fasta, name=analysis.trim.unique.good.filter.names, group=analysis.good.groups, diffs=2, processors=6) +# output: analysis.trim.4ant.unique.good.filter.unique.precluster.fasta, analysis.trim.4ant.unique.good.filter.unique.precluster.names, analysis.trim.4ant.unique.good.filter.unique.precluster.field.map, analysis.trim.4ant.unique.good.filter.unique.precluster.lab.map +#pre.cluster(fasta=analysis.trim.4ant.unique.good.filter.unique.fasta, name=analysis.trim.4ant.unique.good.filter.names, group=analysis.4ant.good.groups, diffs=2, processors=6) # inspect the preclustered files -# output: analysis.trim.unique.good.filter.unique.precluster.summary -summary.seqs(fasta=analysis.trim.unique.good.filter.unique.precluster.fasta, name=analysis.trim.unique.good.filter.unique.precluster.names) +# output: analysis.trim.4ant.unique.good.filter.unique.precluster.summary +#summary.seqs(fasta=analysis.trim.4ant.unique.good.filter.unique.precluster.fasta, name=analysis.trim.4ant.unique.good.filter.unique.precluster.names) # detecting and removing chimeras (unnecessary since completed in SRA data) -# output: analysis.trim.unique.good.filter.unique.precluster.denovo.uchime.chimeras, analysis.trim.unique.good.filter.unique.precluster.denovo.uchime.accnos -#chimera.uchime(fasta=analysis.trim.unique.good.filter.unique.precluster.fasta, name=analysis.trim.unique.good.filter.unique.precluster.names, group=analysis.good.groups, processors=6) +# output: analysis.trim.4ant.unique.good.filter.unique.precluster.denovo.uchime.chimeras, analysis.trim.4ant.unique.good.filter.unique.precluster.denovo.uchime.accnos +#chimera.uchime(fasta=analysis.trim.4ant.unique.good.filter.unique.precluster.fasta, #name=analysis.trim.4ant.unique.good.filter.unique.precluster.names, group=analysis.4ant.good.groups, processors=6) #generate count table to be used -#output: analysis.trim.unique.good.filter.unique.precluster.count_table -count.seqs(name=analysis.trim.unique.good.filter.unique.precluster.names) +#count.seqs(name=analysis.trim.4ant.unique.good.filter.unique.precluster.names) #generate taxonomy file -#output: analysis.trim.unique.good.filter.unique.precluster.taxonomy -classify.seqs(fasta=analysis/analysis.trim.unique.good.filter.unique.precluster.fasta, count=analysis/analysis.trim.unique.good.filter.unique.precluster.count_table, reference=silva/silva.nr_v128.pcr.align, taxonomy=silva/silva.nr_v128.tax, cutoff=80) +#classify.seqs(fasta=analysis/analysis.trim.4ant.unique.good.filter.unique.precluster.fasta, count=analysis/analysis.trim.4ant.unique.good.filter.unique.precluster.count_table, reference=silva/silva.nr_v128.pcr.align, taxonomy=silva/silva.nr_v128.tax, cutoff=80) # rename files (rename command is unreliable) -system(cp analysis/analysis.trim.unique.good.filter.unique.precluster.fasta analysis/final.fasta) -#rename.file(input=analysis.trim.unique.good.filter.unique.precluster.fasta, output=final.fasta) -system(cp analysis/analysis.trim.unique.good.filter.unique.precluster.names analysis/final.names) -#rename.file(input=analysis.trim.unique.good.filter.unique.precluster.names, output=final.names) - -system(cp analysis/analysis.trim.unique.good.filter.unique.precluster.nr_v128.wang.taxonomy analysis/final.taxonomy) -#rename.file(input=analysis.trim.unique.good.filter.unique.precluster.nr_v128.wang.taxonomy, output=final.taxonomy) - -system(cp analysis/analysis.good.groups analysis/final.groups) -#rename.file(input=analysis.good.groups, output=final.groups) +#system(cp analysis/analysis.trim.4ant.unique.good.filter.unique.precluster.fasta analysis/final.4ant.fasta) +#rename.file(input=analysis.trim.4ant.unique.good.filter.unique.precluster.fasta, output=final.4ant.fasta) +#system(cp analysis/analysis.trim.4ant.unique.good.filter.unique.precluster.names analysis/final.4ant.names) +#rename.file(input=analysis.trim.4ant.unique.good.filter.unique.precluster.names, output=final.4ant.names) +#system(cp analysis/analysis.4ant.good.groups analysis/final.4ant.groups) +#rename.file(input=analysis.4ant.good.groups, output=final.4ant.groups) +#system(cp analysis/analysis.trim.4ant.unique.good.filter.unique.precluster.nr_v128.wang.taxonomy analysis/final.4ant.taxonomy) +#rename.file(input=analysis.trim.4ant.unique.good.filter.unique.precluster.nr_v128.wang.taxonomy, output=final.4ant.taxonomy) # Option 1 or 2 are different methods available to build OTUs # Output from Option 2 should be similar to Option 1 @@ -84,40 +80,64 @@ system(cp analysis/analysis.good.groups analysis/final.groups) # Option 1: generate distance matrix # cutoff of 0.15 means removing all pairwise distance larger than 0.15 # If output is >100 GBs of memory, something is wrong -# output: final.dist -dist.seqs(fasta=final.fasta, cutoff=0.15, processors=6) +# output: final.4ant.dist +#dist.seqs(fasta=final.4ant.fasta, cutoff=0.15, processors=6) # cluster sequences into OTUs based on distance matrix # cutoff is typically 0.03 for further analysis -# output: final.an.sabund, final.an.rabund, final.an.list -cluster(column=final.dist, name=final.names) +# output: final.4ant.an.sabund, final.4ant.an.rabund, final.4ant.an.list +#cluster(column=final.4ant.dist, name=final.4ant.names, cutoff=0.03) # Option 2: quick and dirty -#cluster.split(fasta=final.fasta, taxonomy=final.taxonomy, name=final.names, taxlevel=3, processors=6) +#cluster.split(fasta=final.4ant.fasta, taxonomy=final.4ant.taxonomy, name=final.4ant.names, taxlevel=3, processors=6) #The output from Option 2 should be about the same as Option 1. The remainder of this code uses Option 1 #create a table that indicates the number of times an OTU shows up in each sample also known as a shared file -#input: final.an.list and final.groups file -#output: final.an.shared file -make.shared(list=final.an.list, group=final.groups, label=0.03) +#input: final.4ant.an.list and final.4ant.groups file +#output: final.4ant.an.shared file +#make.shared(list=final.4ant.an.list, group=final.4ant.groups) #The final step to getting good OTU data is to normalize the number of sequences in each sample #First we need to know how many sequences are in each step -count.groups() - -#sub-sample all the samples to the sample with the fewest sequences(4420) -#input: final.an.shared file -#output: final.an.0.03.subsample.shared -sub.sample(shared=final.an.shared, size=4420) - -#get the taxonomy information for each of our OTUs -classify.otu(list=final.an.list, name=final.names, taxonomy=final.taxonomy, label=0.03) - -##Phylotype -#goes through the taxonomy file and bins sequences together that have the same taxonomy -phylotype(taxonomy=final.taxonomy, name=final.names, label=1) - -##Phylogenetic tree -#construct a phylip-formatted distance matrix -dist.seqs(fasta=final.fasta, output=phylip, processors=2) +#count.groups() + +#sub-sample all the samples to the sample with the fewest sequences(59768) +#input: final.4ant.an.shared file +#output: final.4ant.an.unique.subsample.shared +#sub.sample(shared=final.4ant.an.shared, size=59768) + +#Extract specific ant species to view in venn diagram using phylotype analysis +#goes through the taxonomy file and bins sequences together that have the same taxonomy, 6 different bins.These bins are known as phylotypes. +#output: final.4ant.tx.list, final.4ant.tx.rabund, final.4ant.tx.sabund +#phylotype(taxonomy=final.4ant.taxonomy, name=final.4ant.names) + +#get the taxonomy of each phylotype, there are 6 phylotypes +#produces consensus taxnomy & summary taxonomy files for each phylotype +#output files: +#final.4ant.tx.1.cons.taxonomy, final.4ant.tx.1.cons.tax.summary, +#final.4ant.tx.2.cons.taxonomy, final.4ant.tx.2.cons.tax.summary, +#final.4ant.tx.3.cons.taxonomy, final.4ant.tx.3.cons.tax.summary, +#final.4ant.tx.4.cons.taxonomy, final.4ant.tx.4.cons.tax.summary, +#final.4ant.tx.5.cons.taxonomy, final.4ant.tx.5.cons.tax.summary, +#final.4ant.tx.6.cons.taxonomy, final.4ant.tx.6.cons.tax.summary +#classify.otu(list=final.4ant.tx.list, name=final.4ant.names, taxonomy=final.4ant.taxonomy) + +#merge all the taxonomy summary files together in one file called final.4ant.cons.tax.summary +#merge.taxsummary(input=final.4ant.tx.1.cons.tax.summary-final.4ant.tx.2.cons.tax.summary-final.4ant.tx.3.cons.tax.summary-final.4ant.tx.4.cons.tax.summary-final.4ant.tx.5.cons.tax.summary-final.4ant.tx.6.cons.tax.summary, output=analysis/final.4ant.cons.tax.summary) + +#In terminal within the analysis folder,create final.4ant.list.tax.summary file to determine lowest taxonomic rank in merged taxonomy summary file, lowest taxonomic rank is genus +#selected 3 columns: +#taxlevels(put in numerical order) +#taxon name +#total no. of sequences for specific taxonomic rank +#cut -f 1,3,5 final.4ant.cons.tax.summary|sort -n > final.4ant.list.tax.summary + +##To make venn diagram of each ant species, split the sequences in the fasta, names and groups files into 4 groups, each group represents each ant species +# The four ant species groups are: +# Trachymyrmex_zeteki +# Cyphomyrmex_longiscapus +# Cyphomyrmex_muelleri +# Mycocepurus_smithii +# output: analysis.trim.4ant.Trachymyrmex_zeteki.fasta, analysis.4ant2.Trachymyrmex_zeteki.groups, analysis.trim.4ant.Trachymyrmex_zeteki.names; analysis.trim.4ant.Cyphomyrmex_longiscapus.fasta, analysis.4ant2.Cyphomyrmex_longiscapus.groups, analysis.trim.4ant.Cyphomyrmex_longiscapus.names; analysis.trim.4ant.Cyphomyrmex_muelleri.fasta, analysis.4ant2.Cyphomyrmex_muelleri.groups, analysis.trim.4ant.Cyphomyrmex_muelleri.names; analysis.trim.4ant.Mycocepurus_smithii.fasta, analysis.4ant2.Mycocepurus_smithii.groups, analysis.trim.4ant.Mycocepurus_smithii.names +mothur "#split.groups(fasta=analysis.trim.4ant.fasta, group=analysis.4ant2.groups, name=analysis.trim.4ant.names, groups=Trachymyrmex_zeteki-Cyphomyrmex_longiscapus-Cyphomyrmex_muelleri-Mycocepurus_smithii)" From 2278a728e6ef8604f4518b00f48e5a0e2b0a09ac Mon Sep 17 00:00:00 2001 From: Andrea Ortiz Date: Thu, 3 May 2018 19:26:07 -0500 Subject: [PATCH 2/2] uses samples for 4 of the ant species --- mothur_prep.sh | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/mothur_prep.sh b/mothur_prep.sh index 9925151..414bcb2 100755 --- a/mothur_prep.sh +++ b/mothur_prep.sh @@ -34,20 +34,24 @@ for x in `cat all.lst` mothur "#trim.seqs(fasta=$x.fasta, qfile=$x.qual, maxambig=1, maxhomop=8, flip=T, qaverage=25, minlength=200, processors=6)" done -# create group file +# create group file for lab or field # output mergegroups -mothur "#make.group(fasta=SRR655327.trim.fasta-SRR655328.trim.fasta-SRR655329.trim.fasta-SRR655330.trim.fasta-SRR655331.trim.fasta-SRR655332.trim.fasta-SRR655333.trim.fasta-SRR655334.trim.fasta-SRR655335.trim.fasta-SRR655336.trim.fasta-SRR655337.trim.fasta-SRR655338.trim.fasta-SRR655339.trim.fasta-SRR655340.trim.fasta-SRR655341.trim.fasta-SRR655342.trim.fasta-SRR655343.trim.fasta-SRR655344.trim.fasta-SRR655345.trim.fasta-SRR655346.trim.fasta-SRR655347.trim.fasta-SRR655348.trim.fasta-SRR655349.trim.fasta-SRR655350.trim.fasta-SRR655351.trim.fasta-SRR655352.trim.fasta-SRR655353.trim.fasta-SRR655354.trim.fasta-SRR655355.trim.fasta-SRR655356.trim.fasta-SRR655357.trim.fasta-SRR655358.trim.fasta-SRR655359.trim.fasta-SRR655360.trim.fasta-SRR655361.trim.fasta-SRR655362.trim.fasta-SRR655363.trim.fasta-SRR655364.trim.fasta-SRR655990.trim.fasta-SRR655991.trim.fasta-SRR655992.trim.fasta-SRR655993.trim.fasta-SRR655994.trim.fasta-SRR655995.trim.fasta-SRR655996.trim.fasta-SRR655997.trim.fasta-SRR655998.trim.fasta-SRR655999.trim.fasta-SRR656000.trim.fasta-SRR656001.trim.fasta-SRR656002.trim.fasta-SRR656003.trim.fasta-SRR656004.trim.fasta-SRR656005.trim.fasta-SRR656006.trim.fasta-SRR656022.trim.fasta-SRR656023.trim.fasta-SRR656024.trim.fasta-SRR656025.trim.fasta-SRR656026.trim.fasta-SRR656027.trim.fasta-SRR656028.trim.fasta-SRR656029.trim.fasta-SRR656030.trim.fasta-SRR656031.trim.fasta-SRR656032.trim.fasta-SRR656033.trim.fasta, groups=field-field-field-field-lab-lab-lab-lab-field-field-field-field-field-field-lab-lab-lab-lab-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-lab-lab-lab-field-field-field-field-field-field-field-field-field-field-field-field-field-field-lab-field-field)" +mothur "#make.group(fasta=SRR655327.trim.fasta-SRR655328.trim.fasta-SRR655329.trim.fasta-SRR655330.trim.fasta-SRR655331.trim.fasta-SRR655332.trim.fasta-SRR655333.trim.fasta-SRR655334.trim.fasta-SRR655335.trim.fasta-SRR655336.trim.fasta-SRR655337.trim.fasta-SRR655338.trim.fasta-SRR655339.trim.fasta-SRR655340.trim.fasta-SRR655341.trim.fasta-SRR655342.trim.fasta-SRR655343.trim.fasta-SRR655344.trim.fasta-SRR655345.trim.fasta-SRR655346.trim.fasta-SRR655351.trim.fasta-SRR655352.trim.fasta-SRR655353.trim.fasta-SRR655354.trim.fasta-SRR655355.trim.fasta-SRR655356.trim.fasta-SRR655990.trim.fasta-SRR655991.trim.fasta-SRR655992.trim.fasta-SRR655993.trim.fasta-SRR655994.trim.fasta-SRR655995.trim.fasta-SRR655996.trim.fasta-SRR655997.trim.fasta-SRR655998.trim.fasta-SRR655999.trim.fasta-SRR656000.trim.fasta-SRR656001.trim.fasta-SRR656002.trim.fasta-SRR656003.trim.fasta-SRR656004.trim.fasta-SRR656005.trim.fasta-SRR656006.trim.fasta-SRR656022.trim.fasta-SRR656023.trim.fasta-SRR656024.trim.fasta-SRR656025.trim.fasta-SRR656026.trim.fasta-SRR656027.trim.fasta-SRR656028.trim.fasta-SRR656029.trim.fasta-SRR656030.trim.fasta-SRR656031.trim.fasta-SRR656032.trim.fasta-SRR656033.trim.fasta, groups=field-field-field-field-lab-lab-lab-lab-field-field-field-field-field-field-lab-lab-lab-lab-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-field-lab-lab-lab-field-field-field-field-field-field-field-field-field-field-field-field-field-field-lab-field-field)" # rename groups file -cp mergegroups analysis.groups +cp mergegroups analysis.4ant.groups -# make master fasta file (combines individual fasta files into a single file, analysis.trim.fasta) -mothur "#merge.files(input=SRR655327.trim.fasta-SRR655328.trim.fasta-SRR655329.trim.fasta-SRR655330.trim.fasta-SRR655331.trim.fasta-SRR655332.trim.fasta-SRR655333.trim.fasta-SRR655334.trim.fasta-SRR655335.trim.fasta-SRR655336.trim.fasta-SRR655337.trim.fasta-SRR655338.trim.fasta-SRR655339.trim.fasta-SRR655340.trim.fasta-SRR655341.trim.fasta-SRR655342.trim.fasta-SRR655343.trim.fasta-SRR655344.trim.fasta-SRR655345.trim.fasta-SRR655346.trim.fasta-SRR655347.trim.fasta-SRR655348.trim.fasta-SRR655349.trim.fasta-SRR655350.trim.fasta-SRR655351.trim.fasta-SRR655352.trim.fasta-SRR655353.trim.fasta-SRR655354.trim.fasta-SRR655355.trim.fasta-SRR655356.trim.fasta-SRR655357.trim.fasta-SRR655358.trim.fasta-SRR655359.trim.fasta-SRR655360.trim.fasta-SRR655361.trim.fasta-SRR655362.trim.fasta-SRR655363.trim.fasta-SRR655364.trim.fasta-SRR655990.trim.fasta-SRR655991.trim.fasta-SRR655992.trim.fasta-SRR655993.trim.fasta-SRR655994.trim.fasta-SRR655995.trim.fasta-SRR655996.trim.fasta-SRR655997.trim.fasta-SRR655998.trim.fasta-SRR655999.trim.fasta-SRR656000.trim.fasta-SRR656001.trim.fasta-SRR656002.trim.fasta-SRR656003.trim.fasta-SRR656004.trim.fasta-SRR656005.trim.fasta-SRR656006.trim.fasta-SRR656022.trim.fasta-SRR656023.trim.fasta-SRR656024.trim.fasta-SRR656025.trim.fasta-SRR656026.trim.fasta-SRR656027.trim.fasta-SRR656028.trim.fasta-SRR656029.trim.fasta-SRR656030.trim.fasta-SRR656031.trim.fasta-SRR656032.trim.fasta-SRR656033.trim.fasta, output=analysis.trim.fasta)" +# create group file for selecting 4 ant species (in order listed here): Trachymyrmex_zeteki, Cyphomyrmex_longiscapus, Cyphomyrmex_muelleri, Mycocepurus_smithii +# output mergegroups +mothur "#make.group(fasta=SRR655327.trim.fasta-SRR655328.trim.fasta-SRR655329.trim.fasta-SRR655330.trim.fasta-SRR655331.trim.fasta-SRR655332.trim.fasta-SRR655333.trim.fasta-SRR655334.trim.fasta-SRR655351.trim.fasta-SRR655352.trim.fasta-SRR655353.trim.fasta-SRR655354.trim.fasta-SRR655355.trim.fasta-SRR655356.trim.fasta-SRR655335.trim.fasta-SRR655336.trim.fasta-SRR655337.trim.fasta-SRR655338.trim.fasta-SRR655345.trim.fasta-SRR655346.trim.fasta-SRR655339.trim.fasta-SRR655340.trim.fasta-SRR655341.trim.fasta-SRR655342.trim.fasta-SRR655343.trim.fasta-SRR655344.trim.fasta-SRR655990.trim.fasta-SRR655991.trim.fasta-SRR655992.trim.fasta-SRR655993.trim.fasta-SRR655994.trim.fasta-SRR655995.trim.fasta-SRR655996.trim.fasta-SRR655997.trim.fasta-SRR655998.trim.fasta-SRR655999.trim.fasta-SRR656000.trim.fasta-SRR656001.trim.fasta-SRR656002.trim.fasta-SRR656003.trim.fasta-SRR656004.trim.fasta-SRR656005.trim.fasta-SRR656006.trim.fasta-SRR656022.trim.fasta-SRR656023.trim.fasta-SRR656024.trim.fasta-SRR656025.trim.fasta-SRR656026.trim.fasta-SRR656027.trim.fasta-SRR656028.trim.fasta-SRR656029.trim.fasta-SRR656030.trim.fasta-SRR656031.trim.fasta-SRR656032.trim.fasta-SRR656033.trim.fasta, groups=Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Trachymyrmex_zeteki-Cyphomyrmex_longiscapus-Cyphomyrmex_longiscapus-Cyphomyrmex_longiscapus-Cyphomyrmex_longiscapus-Cyphomyrmex_longiscapus-Cyphomyrmex_longiscapus-Cyphomyrmex_muelleri-Cyphomyrmex_muelleri-Cyphomyrmex_muelleri-Cyphomyrmex_muelleri-Cyphomyrmex_muelleri-Cyphomyrmex_muelleri-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii-Mycocepurus_smithii)" + +# rename groups +cp mergegroups analysis.4ant2.groups + +# make master fasta file (combines individual fasta files into a single file for 4 ant species of interest, analysis.trim.4ant.fasta) with files listed in numerical order +mothur "#merge.files(input=SRR655327.trim.fasta-SRR655328.trim.fasta-SRR655329.trim.fasta-SRR655330.trim.fasta-SRR655331.trim.fasta-SRR655332.trim.fasta-SRR655333.trim.fasta-SRR655334.trim.fasta-SRR655335.trim.fasta-SRR655336.trim.fasta-SRR655337.trim.fasta-SRR655338.trim.fasta-SRR655339.trim.fasta-SRR655340.trim.fasta-SRR655341.trim.fasta-SRR655342.trim.fasta-SRR655343.trim.fasta-SRR655344.trim.fasta-SRR655345.trim.fasta-SRR655346.trim.fasta-SRR655351.trim.fasta-SRR655352.trim.fasta-SRR655353.trim.fasta-SRR655354.trim.fasta-SRR655355.trim.fasta-SRR655356.trim.fasta-SRR655990.trim.fasta-SRR655991.trim.fasta-SRR655992.trim.fasta-SRR655993.trim.fasta-SRR655994.trim.fasta-SRR655995.trim.fasta-SRR655996.trim.fasta-SRR655997.trim.fasta-SRR655998.trim.fasta-SRR655999.trim.fasta-SRR656000.trim.fasta-SRR656001.trim.fasta-SRR656002.trim.fasta-SRR656003.trim.fasta-SRR656004.trim.fasta-SRR656005.trim.fasta-SRR656006.trim.fasta-SRR656022.trim.fasta-SRR656023.trim.fasta-SRR656024.trim.fasta-SRR656025.trim.fasta-SRR656026.trim.fasta-SRR656027.trim.fasta-SRR656028.trim.fasta-SRR656029.trim.fasta-SRR656030.trim.fasta-SRR656031.trim.fasta-SRR656032.trim.fasta-SRR656033.trim.fasta, output=analysis.trim.4ant.fasta)" -# make master qual file, analysis.trim.qual -mothur "#merge.files(input=SRR655327.trim.qual-SRR655328.trim.qual-SRR655329.trim.qual-SRR655330.trim.qual-SRR655331.trim.qual-SRR655332.trim.qual-SRR655333.trim.qual-SRR655334.trim.qual-SRR655335.trim.qual-SRR655336.trim.qual-SRR655337.trim.qual-SRR655338.trim.qual-SRR655339.trim.qual-SRR655340.trim.qual-SRR655341.trim.qual-SRR655342.trim.qual-SRR655343.trim.qual-SRR655344.trim.qual-SRR655345.trim.qual-SRR655346.trim.qual-SRR655347.trim.qual-SRR655348.trim.qual-SRR655349.trim.qual-SRR655350.trim.qual-SRR655351.trim.qual-SRR655352.trim.qual-SRR655353.trim.qual-SRR655354.trim.qual-SRR655355.trim.qual-SRR655356.trim.qual-SRR655357.trim.qual-SRR655358.trim.qual-SRR655359.trim.qual-SRR655360.trim.qual-SRR655361.trim.qual-SRR655362.trim.qual-SRR655363.trim.qual-SRR655364.trim.qual-SRR655990.trim.qual-SRR655991.trim.qual-SRR655992.trim.qual-SRR655993.trim.qual-SRR655994.trim.qual-SRR655995.trim.qual-SRR655996.trim.qual-SRR655997.trim.qual-SRR655998.trim.qual-SRR655999.trim.qual-SRR656000.trim.qual-SRR656001.trim.qual-SRR656002.trim.qual-SRR656003.trim.qual-SRR656004.trim.qual-SRR656005.trim.qual-SRR656006.trim.qual-SRR656022.trim.qual-SRR656023.trim.qual-SRR656024.trim.qual-SRR656025.trim.qual-SRR656026.trim.qual-SRR656027.trim.qual-SRR656028.trim.qual-SRR656029.trim.qual-SRR656030.trim.qual-SRR656031.trim.qual-SRR656032.trim.qual-SRR656033.trim.qual, output=analysis.trim.qual)" +# make master qual file (combines individual qual files into a single file for 4 ant species of interest, analysis.trim.4ant.qual) with files listed in numerical order +mothur "#merge.files(input=SRR655327.trim.qual-SRR655328.trim.qual-SRR655329.trim.qual-SRR655330.trim.qual-SRR655331.trim.qual-SRR655332.trim.qual-SRR655333.trim.qual-SRR655334.trim.qual-SRR655335.trim.qual-SRR655336.trim.qual-SRR655337.trim.qual-SRR655338.trim.qual-SRR655339.trim.qual-SRR655340.trim.qual-SRR655341.trim.qual-SRR655342.trim.qual-SRR655343.trim.qual-SRR655344.trim.qual-SRR655345.trim.qual-SRR655346.trim.qual-SRR655351.trim.qual-SRR655352.trim.qual-SRR655353.trim.qual-SRR655354.trim.qual-SRR655355.trim.qual-SRR655356.trim.qual-SRR655990.trim.qual-SRR655991.trim.qual-SRR655992.trim.qual-SRR655993.trim.qual-SRR655994.trim.qual-SRR655995.trim.qual-SRR655996.trim.qual-SRR655997.trim.qual-SRR655998.trim.qual-SRR655999.trim.qual-SRR656000.trim.qual-SRR656001.trim.qual-SRR656002.trim.qual-SRR656003.trim.qual-SRR656004.trim.qual-SRR656005.trim.qual-SRR656006.trim.qual-SRR656022.trim.qual-SRR656023.trim.qual-SRR656024.trim.qual-SRR656025.trim.qual-SRR656026.trim.qual-SRR656027.trim.qual-SRR656028.trim.qual-SRR656029.trim.qual-SRR656030.trim.qual-SRR656031.trim.qual-SRR656032.trim.qual-SRR656033.trim.qual, output=analysis.trim.4ant.qual)" -# clean up and reorganize -rm *.logfile mergegroups -mkdir sequences -mv SRR* all.lst sequences/ +rm *.logfile \ No newline at end of file