def gatherFinalResults(profile, sequences, worstScoringMotif, strand):
""" Find all locations in the Agrobacterium tumefaciens C58 genome where our
profile achieves a score as high as the worst scoring motif (returned by gibbsSampling())
Args:
profile (dictionary): Profile of the motifs returned by gibbsSampling()
sequences (string): List of DNA sequences
worstScoringMotif (dictionary): Dictionary containing important info about the worst scoring motif
(from the best scoring ones got from gibbsSampling())
strand (int): 1 for the sequence from the file / 2 from the reverse complement
Returns:
dictionary: A list of dictionaries of the motifs that score as high as worstScoringMotif
"""
dnaScores = []
for sequenceNumber in range(0, len(sequences)):
# Applies a profile (gets single score for each subsequence) for each kmer in the current sequence
applyProfileScores = mf.applyProfile(profile, sequences[sequenceNumber])
for i in range(0, len(applyProfileScores)):
# Find motifs that has a score as high as the worst scoring motif's score
if applyProfileScores[i] >= worstScoringMotif["Score"]:
# Searches for the closest protein start codon
str1 = sequences[sequenceNumber][0 : i + 1]
str2 = sequences[sequenceNumber][i + len(profile) : len(sequences[sequenceNumber])]
str1Start = str1.rfind("ATG")
str2Start = str2.find("ATG")
if str1Start == -1:
str1Start = 1000
if str2Start == -1:
str2Start = 1000
if str1Start < str2Start:
start = str1Start
elif str1Start > str2Start:
start = str2Start + i + len(profile)
else:
start = "None"
# Adds the found motif and its info to a list of dictionaries that is gonna be returned by the function
dnaScores.append(
{
"50mer-Sequence": sequences[sequenceNumber][i : i + len(profile) + (50 - len(profile))],
"Position": i,
"Score": applyProfileScores[i],
"Closest-Protein-Coding-Gene": start,
"DNASequence#": sequenceNumber + 1,
"Strand #": strand,
}
)
return dnaScores
""" File containing the functions test for motifFinder.py """
import motifFinder
# Tests ------------------------------------------------------------------
print(motifFinder.readInput('TraR.txt'))
print(motifFinder.randomStart(['ACACGTAC', 'CCACGTCACA', 'TTCGTCGTACG'], 4))
print(motifFinder.getMotif(['ACACGTAC', 'CCACGTCACA', 'TTCGTCGTACG'], [3, 5, 2], 4))
print(motifFinder.constructProfile(['CGTA', 'TCAC', 'CGTC']))
print(motifFinder.getSingleScore(motifFinder.constructProfile(['CGTA', 'TCAC', 'CGTC']), 'CACA'))
print(motifFinder.applyProfile(motifFinder.constructProfile(['CGTA', 'TCAC', 'CGTC']), 'CCACGTCACA'))
print(motifFinder.randomlySelect([0.014994, 0.001249, 0.000833, 0.033736, 0.000833, 0.009996, 0.002499]))
print(motifFinder.nucleotideFrequencies(['ACACGTAC', 'CCACGTCACA', 'TTCGTCGTACG']))
print(motifFinder.scoreProfile([{'A': 0.142857, 'C': 0.428571, 'G': 0.142857, 'T': 0.285714}, {'A': 0.142857, 'C': 0.285714, 'G': 0.428571, 'T': 0.142857}, {'A': 0.285714, 'C': 0.142857, 'G': 0.142857, 'T': 0.428571}, {'A': 0.285714, 'C': 0.428571, 'G': 0.142857, 'T': 0.142857}], {'A': 0.241379, 'C': 0.379310, 'G': 0.172413, 'T': 0.206897}))