docs: add docstrings to functions of TrueConsense.ORFs

TrueConsense/ORFs.py

@@ -1,4 +1,18 @@
 def in_orf(loc, gffd):
+    """If the location is in any of the ORFs, return True. Otherwise, return False
+
+    Parameters
+    ----------
+    loc
+        the current position
+    gffd
+        a dictionary of dictionaries, where the keys are the gene IDs, and the values are dictionaries containing the gene attributes
+
+    Returns
+    -------
+        A list of True/False values.
+
+    """
     exists = []
     for k in gffd.keys():
         start = gffd[k].get("start")
@@ -13,10 +27,36 @@ def in_orf(loc, gffd):
 
 
 def split_to_codons(seq):
+    """It takes a string of DNA and returns a list of codons (nucleotide triplets)
+
+    Parameters
+    ----------
+    seq
+        the sequence to split
+
+    Returns
+    -------
+        A list of codons
+
+    """
     return [seq[start : start + 3] for start in range(0, len(seq), 3)]
 
 
 def SolveTripletLength(uds, mds):
+    """Check wether the combination of the uds (upcoming stretch of deletions) and the mds (group of minority deletions) is divisible by 3. If it is, return the length of the triplet. If it is not, return None.
+
+    Parameters
+    ----------
+    uds
+        upcoming stretch of dels
+    mds
+        the minority-del group
+
+    Returns
+    -------
+        A boolean value.
+
+    """
     mdslen = len(mds)
     udslen = len(uds)
 
@@ -38,6 +78,25 @@ def SolveTripletLength(uds, mds):
 
 
 def CorrectStartPositions(gffd, shifts, p):
+    """Function takes a dictionary of gff data, a list of shifts, and a position. It then iterates
+    through the dictionary and updates the start position of each entry if the start position is greater
+    than the position
+
+    Parameters
+    ----------
+    gffd
+        a dictionary of dictionaries, where each key is a gene name, and each value is a dictionary of the
+        gene's attributes
+    shifts
+        the number of bases to shift the start positions by
+    p
+        the position of the first base of the insertion
+
+    Returns
+    -------
+        A dictionary with the updated start positions.
+
+    """
     for k in gffd.keys():
         start = gffd[k].get("start")
 
@@ -50,6 +109,31 @@ def CorrectStartPositions(gffd, shifts, p):
 
 
 def CorrectGFF(oldgffdict, newgffdict, cons, p, inserts, mincov, cov):
+    """This function corrects the start and end positions of the genes in the new GFF file
+
+    Parameters
+    ----------
+    oldgffdict
+        a dictionary of the old gff file
+    newgffdict
+        the new gff dictionary
+    cons
+        the consensus sequence
+    p
+        the position of the current base
+    inserts
+        a dictionary of insertions, where the key is the position of the insertion and the value is the
+    nucleotide inserted
+    mincov
+        minimum coverage to consider a position as a potential insertion
+    cov
+        coverage of the contig
+
+    Returns
+    -------
+        A dictionary of the corrected gff file.
+
+    """
 
     stopcodons = ["TAG", "TAA", "TGA"]
     # rvstopcodon = ["CAT"]