From 47cc54decd8d2a14a413bab57f8414214825155b Mon Sep 17 00:00:00 2001
From: Calvin <calvin@EESI>
Date: Thu, 16 May 2013 14:53:58 -0400
Subject: used newlines in readme for clarity, update our references to the
 ../../../data/

---
 .../multifasta2otu/multifasta2otutable_gg1194.m    | 109 ---------------------
 1 file changed, 109 deletions(-)
 delete mode 100644 src/matlab/multifasta2otu/multifasta2otutable_gg1194.m

(limited to 'src/matlab/multifasta2otu/multifasta2otutable_gg1194.m')

diff --git a/src/matlab/multifasta2otu/multifasta2otutable_gg1194.m b/src/matlab/multifasta2otu/multifasta2otutable_gg1194.m
deleted file mode 100644
index a2872a4..0000000
--- a/src/matlab/multifasta2otu/multifasta2otutable_gg1194.m
+++ /dev/null
@@ -1,109 +0,0 @@
-%This is an example of how to run Multifasta Quikr with a custom 
-%training database (in this case Greengenes OTU's within 94% identity)
-
-%make sure Matlab/Octave is in your path
-%cd /path/to/Quikr
-
-%User-defined variables
-input_directory='../../separated_samples'; %path to input directory of samples
-output_directory='quikr_results'; %path to where want output files to go
-otu_table_name='gg1194_otu_table.txt'; %name of output otu_table filename
-trainingdatabasefilename='../gg_94_otus_4feb2011.fasta'; %full path to the FASTA file you wish to use as a training database
-
-
-mkdir([output_directory])
-thedirs=dir([input_directory]);
-thetime=zeros(numel(thedirs)-1,1);
-names={};
-
-
-tic()
-k=6; %pick a k-mer size
-trainingmatrix=quikrTrain(trainingdatabasefilename,k); %this will return the training database
-'Training time:'
-[headers,~]=fastaread(trainingdatabasefilename); %read in the training database
-lambda=10000; 
-training_time=toc()
-
-species=containers.Map;
-
-tic()
-
-
-i=0;
-%for numdirs=3:5
-for numdirs=3:numel(thedirs)
-i=i+1;
-[num2str(i) ' out of ' num2str(numel(thedirs)-2)]
-fastafilename=[input_directory '/' thedirs(numdirs).name];
-[loadfasta,~]=fastaread(fastafilename);
-numreads=numel(loadfasta);
-xstar=quikrCustomTrained(trainingmatrix,fastafilename,k,lambda);
-
-nonzeroentries=find(xstar); %get the indicies of the sequences quikr predicts are in your sample
-proportionscell=num2cell(xstar(nonzeroentries)); %convert the concentrations into a cell array
-namescell=headers(nonzeroentries); %Get the names of the sequences
-namesandproportions={namescell{:}; proportionscell{:}}; %This cell array contains the (unsorted) names of the reconstructed sequences and their concentrations (in the first and second columns respectively)
-
-[a cols]=size(namesandproportions);
-amount=zeros(cols,1);
-for j=1:cols
-  names{j}=namesandproportions{1,j};
-  amount(j)=namesandproportions{2,j};
-  if isKey(species,names{j})
-	 temp=species(names{j});
-      temp(i)=round(amount(j).*numreads);
-      species(names{j})=temp;
-  else
-      temp=zeros(numel(thedirs)-3+1,1);
-      temp(i)=round(amount(j).*numreads);
-      species(names{j})=temp;
-  end
-end
-
-thefa=strfind(thedirs(numdirs).name,'.fa');
-
-if ~isempty(thedirs(numdirs).name(1:thefa-1))
-	sampleid{i}=thedirs(numdirs).name(1:thefa-1);
-else
-	sampleid{i}='empty_sampleid';
-end
-
-thetime(i+1)=toc();
-thetime(i+1)
-
-end
-
-'Total time to compute Quikr'
-toc()
-'Quickr Average time per file'
-mean(diff(thetime(1:i+1)))
-
-tic
-numits=i;
-
-fid=fopen([output_directory '/' otu_table_name],'w');
-fprintf(fid,'# QIIME vGail OTU table\n');
-fprintf(fid,'#OTU_ID\t');
-for i=1:numits
-if i<numits
-fprintf(fid,'%s\t',sampleid{i});
-else
-fprintf(fid,'%s',sampleid{i});
-end
-end
-fprintf(fid,'\n');
-
-thekeys=species.keys;
-for k=1:species.Count
- fprintf(fid,'%s',thekeys{k})
- temp(:,k)=species(thekeys{k});
-        for i=1:numits
-                fprintf(fid,'\t%d',temp(i,k));
-        end
-fprintf(fid,'\n');
-end
-fclose(fid);
-
-'Time to output OTU Table'
-toc
-- 
cgit v1.2.3