Merge pull request #563 from nf-core/nuc_cont_parsing_fix

Bugfix. Corrected number of relevant SNPs and NAs in `print_x_contamination.py`.

Author: jfy133

CHANGELOG.md

@@ -57,6 +57,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 * Nuclear contamination is now reported with the correct library names.
 * Merged all tutorials and FAQs into `usage.md` for display on nf-co.re
 * Corrected header of nuclear contamination table (`nuclear_contamination.txt`).
+* Fixed a bug with `nSNPs` definition in `print_x_contamination.py`. Number of SNPs now correctly reported.
+* `print_x_contamination.py` now correctly converts all NA values to "N/A".
 
 ### `Dependencies`
 

bin/print_x_contamination.py

@@ -7,11 +7,11 @@
 
 ## Function to convert a set of elements into floating point numbers, when possible, else leave them be.
 def make_float(x):
-    print (x)
+    # print (x)
     output=[None for i in range(len(x))]
     ## If value for an estimate/error is -nan, replace with "NA". JSON does not accept NaN as a valid field.
     for i in range(len(x)):
-        if x[i] == "-nan":
+        if x[i] == "-nan" or x[i] == "nan":
             output[i]="N/A"
             continue
         try:
@@ -32,13 +32,14 @@ def make_float(x):
     ml1, err_ml1="N/A","N/A"
     mom2, err_mom2= "N/A","N/A"
     ml2, err_ml2="N/A","N/A"
+    nSNPs="0"
     with open(fn, 'r') as f:
         Estimates={}
         Ind=re.sub('\.X.contamination.out$', '', fn).split("/")[-1]
         for line in f:
             fields=line.strip().split()
-            if line.strip()[0:21] == "[readicnts] Has read:":
-                nSNPs=fields[4]
+            if line.strip()[0:19] == "We have nSNP sites:":
+                nSNPs=fields[4].rstrip(",")
             elif line.strip()[0:7] == "Method1" and line.strip()[9:16] == 'new_llh':
                 mom1=fields[3].split(":")[1]
                 err_mom1=fields[4].split(":")[1]