Merge pull request #13 from pommevilla/iss-6

Iss 6

src/count_richness → src/count_presence

@@ -1,10 +1,16 @@
 #!/usr/bin/python3 
 """
-This script count how many hit found ; cutoff = 80 percent identity
-usage: python make_count_diamond.py mgm4477807.3.fastq.m8 mgm4477807.3.fastq.m8
-python make_count_sample_diamond.py *.m8 > gene_presence.txt
+Quantifies the presence of the genes within a directory of *.m8 files.
+The presence of a gene is how many samples a gene appears in.
 
-Richness is how many samples a gene appears in.
+Usage:
+    count_presence dir
+
+Inputs:
+    - dir, a directory of .m8 files
+
+Outputs:
+    - two tab-separated columns of gene name and its presence
 """
 
 import sys

src/mfpcount

@@ -120,7 +120,7 @@ echo "Input directory: $(readlink -f $input_dir)" >> $shortdir.log
 echo "Cumulative abundance threshold: $thresh" >> $shortdir.log
 echo "Summary file: $shortdir.summary.tsv" >> $shortdir.log
 
-join -j 1 -t '	' <(count_richness $input_dir | sort -k 1) <(count_abundance $input_dir | sort -k 1) > "$shortdir.summary.tsv"
+join -j 1 -t '	' <(count_presence $input_dir | sort -k 1) <(count_abundance $input_dir | sort -k 1) > "$shortdir.summary.tsv"
 
 # sorting by newS
 calc_sscore "$shortdir.summary.tsv" | sort -nrk 4 > temp