Adding docstrings

scripts/json2csv.py

@@ -1,3 +1,8 @@
+"""
+Convert JSON generated from Sierra processor into CSV format, retaining 
+only drug-specific resistance scores.
+"""
+
 import json
 import csv
 import argparse

scripts/timing.py

@@ -1,3 +1,7 @@
+"""
+Script to compare sierralocal and sierrapy runtimes on a sample of 10 files.
+"""
+
 import subprocess
 from sierralocal import main
 import os

sierralocal/jsonwriter.py

@@ -10,6 +10,12 @@
 
 
 class JSONWriter():
+    """
+    Define a class for handling the formatting for the final JSON output of
+    mutations and validation results. The main write function is in 
+    write_to_json. Generally, @param algorithm will be an instance of the 
+    HIVdb class.
+    """
     def __init__(self, algorithm, apobec_csv, unusual_csv, sdrms_csv, mutation_csv):
         # possible alternative drug abbrvs
         self.names = {'3TC': 'LMV'}

sierralocal/nucaminohook.py

@@ -153,13 +153,31 @@ def get_aligned_seq(self, nuc, sites):
         return aligned
 
     def makeReferenceFASTA(self, fragmentName, refSeq):
+        """
+        Makes a temporary FASTA file for the reference sequence of a given fragment.
+        @param fragmentName: str, name of fragment
+        @param refSeq: str, reference sequence for a given fragment
+        @return: str, path to temporary FASTA file
+        """
+
         tempFasta = tempfile.NamedTemporaryFile('w', prefix='postalign-ref-', suffix='.fas', delete=False)
         tempFasta.write(">Ref_{}\n".format(fragmentName))
         tempFasta.write("{}\n".format(refSeq))
         tempFasta.close()
         return os.path.abspath(tempFasta.name)
 
     def getConfigField(self, config, field):
+        """
+        Retrieves entry information from each fragmentConfig entry in the alignment 
+        config JSON file, and depending on whether the field is refSequence or not, 
+        stores the corresponding FASTA file path or the field value in a dictionary
+        that is mapping fragmentName to field value.
+        @param config: dict, JSON configuration for post-align
+        @param field: str, field to retrieve from config
+        @return: dict, dictionary of fragmentName to a path to a corresponding 
+        temporary FASTA filed and/or field value.
+        """
+
         resultmap = {}
         for entry in config['fragmentConfig']:
             if field == 'refSequence':
@@ -695,6 +713,11 @@ def is_unsequenced(self, triplet):
         return (triplet.replace("-", "N").count("N") > 1)  # TODO: incorporate !isInsertion &&
 
     def is_stop_codon(self, triplet):
+        """Determines whether a nucleotide triplet encodes a stop codon. ("*" is 
+        present in the translated triplet)
+        @param triplet: str, nucleotide triplet as a string
+        @return: bool, True when it is a stop codon
+        """
         return ("*" in self.translate_na_triplet(triplet))
 
     def is_apobec_drm(self, gene, consensus, position, AA):
@@ -739,7 +762,13 @@ def get_highest_mut_prevalance(self, mutation, gene, subtype):
 
     def get_mut_prevalence(self, position, cons, aa, gene, subtype):
         """
-        ???
+        Determines prevalence of a specific mutation in the subtype alignment, by looking up the position, consensus amino acid, mutant amino acid, gene and subtype in the prevalence dictionaries.
+        @param position: int, position of mutation relative to POL
+        @param cons: str, consensus amino acid at this position
+        @param aa: str, mutant amino acid at this position
+        @param gene: str, PR, RT, or INT
+        @param subtype: str, predicted from Subtyper.get_closest_subtype()
+        @return: float, prevalence of the mutation in the subtype alignment
         """
         key2 = str(position) + str(cons) + str(aa) + subtype
 

sierralocal/updater.py

@@ -163,6 +163,9 @@ def update_genotype_properties(target_dir=None):
         print("Couldn't update subtyper genotype property file, please get manually at: https://hivdb.stanford.edu/page/hiv-subtyper/")
 
 def main(updater_outdir=None): # pragma: no cover
+    """
+    Main function called when running updater.py directly.
+    """
     update_hivdb(updater_outdir)
     update_apobec(updater_outdir)
     update_is_unusual(updater_outdir)