def main(aligner_fname, cascade_fname, image_fnames):
aligner = Aligner(aligner_fname)
cascade = load_cascade(cascade_fname)
images = (pvImage(fname) for fname in image_fnames)
return [
aligner.align_face(detect_faces(img, cascade)[0], img)
for img in images
]
def main(epitope_list=None,
alignments_dir=None,
alignment_score_threshold=None,
slope_parameter=None,
output_file=None):
# Compute MHC amplitudes for all neoantigens
a_val_by_index = {}
peptide_by_index = {}
sample_by_index = {}
with open(epitope_list) as f:
for data in csv.DictReader(f, delimiter='\t'):
index = data['id']
sample = data['sample']
mtpeptide = data['epitope']
kdwt = data['wt_score']
kdmt = data['mt_score']
kdmt = float(kdmt)
if kdwt == 'nan':
kdwt = 1000.
kdwt = float(kdwt)
index = int(index)
peptide_by_index[index] = mtpeptide.upper()
a_val_by_index[index] = kdwt / kdmt
sample_by_index[index] = sample
# Compute TCR-recognition probabilities for all neoantigens
aligner = Aligner()
for sname in set(sample_by_index.values()):
xml_path = join(alignments_dir, f'neoantigens_{sname}_iedb.xml')
aligner.read_all_blast_alignments(xml_path)
aligner.compute_rval(alignment_score_threshold, slope_parameter)
# Compute qualities for all epitopes and write the result
with open(output_file, 'w') as out:
header = [
'Sample', 'NeoantigenID', 'MT.Peptide.Form', 'NeoantigenQuality',
'NeoantigenAlignment', 'IEDB_EpitopeAlignment', 'AlignmentScore',
'IEDB_Epitope'
]
out.write('\t'.join(header) + '\n')
for index, peptide in peptide_by_index.items():
a_val = a_val_by_index[index]
[r_val, species, alignment] = aligner.get_rval(index)
neo_alignment = alignment[0]
epitope_alignment = alignment[1]
score = alignment[2]
quality = a_val * r_val
res = [
sample_by_index[index], index, peptide, quality, neo_alignment,
epitope_alignment, score, species
]
out.write('\t'.join(map(str, res)) + '\n')
def main(argv):
'''
command line parameters:
neofile - text file with neoantigen data (supplementary data)
alignmentDirectory - folder with precomputed alignments
a - midpoint parameter of the logistic function, alignment score threshold
k - slope parameter of the logistic function
outfile - path to a file where to output neoantigen fitness computation
'''
neofile=argv[1]
alignmentDirectory=argv[2]
a=float(argv[3])
k=float(argv[4])
outfile=sys.argv[5]
nmerl=float(argv[6])
[neoantigens,samples]=readNeoantigens(neofile, nmerl)
#Compute TCR-recognition probabilities for all neoantigens
aligner=Aligner()
for sample in samples:
xmlpath=alignmentDirectory+"/neoantigens_"+sample+"_iedb.xml"
aligner.readAllBlastAlignments(xmlpath)
aligner.computeR(a, k)
#Write neoantigen recognition potential
of=open(outfile,'w')
header=["NeoantigenID","Mutation","Sample","MutatedPeptide","ResidueChangeClass","MutantPeptide","WildtypePeptide","A","R","Excluded","NeoantigenRecognitionPotential"]
header="\t".join(header)
of.write(header+"\n")
for i in neoantigens:
neoantigen=neoantigens[i]
w=neoantigen.getWeight() #excludes neoantigens that mutated from a nonhydrophobic residue on position 2 or 9
A=neoantigens[i].getA() #MHC amplitude A
mtpeptide=neoantigens[i].mtPeptide #mutant peptide
wtpeptide=neoantigens[i].wtPeptide
R=aligner.getR(i)
# Residue change:
# HH: from hydrophobic to hydrophobic,
# NN: from non-hydrophobic to non-hydrophobic
# HN: from hydrophobic to non-hydrophobic,
# NH: from non-hydrophobic to hydrophobic
# other (WW, WH, HW, NW, WN) which include aminoacids without a clear classification
residueChange=neoantigen.residueChange
fitnessCost=A*R*w
l=[i, neoantigen.mid, neoantigen.sample, neoantigen.position, residueChange, mtpeptide, wtpeptide, A,R, 1-w, fitnessCost]#, neoAlignment, epitopeAlignment, score, species]
l="\t".join(map(lambda s: str(s),l))
of.write(l+"\n")
def alignOneChunk(pathToHtkModel, path_TO_OUTPUT, lyrics,
currPathToAudioFile, isLyricsFromFile, withSynthesis):
if not (os.path.isdir(path_TO_OUTPUT)):
os.mkdir(path_TO_OUTPUT)
chunkAligner = Aligner(pathToHtkModel, currPathToAudioFile, lyrics,
isLyricsFromFile, withSynthesis)
baseNameAudioFile = os.path.splitext(
os.path.basename(chunkAligner.pathToAudioFile))[0]
outputHTKPhoneAlignedURI = os.path.join(
path_TO_OUTPUT, baseNameAudioFile) + HTK_MLF_ALIGNED_SUFFIX
chunkAligner.alignAudio(0, path_TO_OUTPUT, outputHTKPhoneAlignedURI)
return outputHTKPhoneAlignedURI
def main(argv):
'''
command line parameters:
neofile - text file with neoantigen data (supplementary data)
alignmentDirectory - folder with precomputed alignments
a - midpoint parameter of the logistic function, alignment score threshold
k - slope parameter of the logistic function
outfile - path to a file where to output neoantigen fitness computation
'''
neofile=argv[1]
alignmentDirectory=argv[2]
a=float(argv[3])
k=float(argv[4])
outfile=sys.argv[5]
xmlpath=sys.argv[6]
[neoantigens,samples]=readNeoantigens(neofile)
#Compute TCR-recognition probabilities for all neoantigens
aligner=Aligner()
#for sample in samples:
# xmlpath=alignmentDirectory+"/neoantigens_"+sample+"_iedb.xml"
# aligner.readAllBlastAlignments(xmlpath)
#xmlpath=alignmentDirectory+"/neoantigens_5NSAK_iedb.xml"
#xmlpath="/scratch/eknodel/cohen_melanoma/validated_peptides/3466/3466_lukszablast.out"
aligner.readAllBlastAlignments(xmlpath)
aligner.computeR(a, k)
#Write neoantigen recognition potential
of=open(outfile,'w')
#header=["NeoantigenID","Mutation","Sample","MutatedPeptide","ResidueChangeClass","MutantPeptide","WildtypePeptide","A","R","Excluded","NeoantigenRecognitionPotential"]
header=["NeoantigenID","Mutation","Sample","MutantPeptide","WildtypePeptide","A","R","w","wc","Fitness"]
header="\t".join(header)
of.write(header+"\n")
for i in neoantigens:
#print(i)
neoantigen=neoantigens[i]
#print(neoantigen)
w=neoantigen.getHydro() #calculates neoantigen fraction based on Luksza definition
wc = neoantigen.getConsortiumHydro() #Calcuculates neoantigen fraction based on Consortium's definition (https://doi.org/10.1016/j.cell.2020.09.015)
A=neoantigens[i].getA() #MHC amplitude A
#print(A)
mtpeptide=neoantigens[i].mtPeptide #mutant peptide
wtpeptide=neoantigens[i].wtPeptide
R=aligner.getR(i)
#print(R)
# Residue change:
# HH: from hydrophobic to hydrophobic,
# NN: from non-hydrophobic to non-hydrophobic
# HN: from hydrophobic to non-hydrophobic,
# NH: from non-hydrophobic to hydrophobic
# other (WW, WH, HW, NW, WN) which include aminoacids without a clear classification
#residueChange=neoantigen.residueChange
#print(residueChange)
fitnessCost=A*R*w
#fitnessCost=A*R
#l=[i, neoantigen.mid, neoantigen.sample, neoantigen.position, residueChange, mtpeptide, wtpeptide, A,R, 1-w, fitnessCost]#, neoAlignment, epitopeAlignment, score, species]
l=[i, neoantigen.mid, neoantigen.sample, mtpeptide, wtpeptide, A,R,w,wc, fitnessCost]#, neoAlignment, epitopeAlignment, score, species]
l="\t".join(map(lambda s: str(s),l))
of.write(l+"\n")
import sys
from Aligner import Aligner
from SentenceSplitter import SentenceSplitter
import pickle
import codecs
#UTF8Writer = codecs.getwriter('utf8')
#sys.stdout = UTF8Writer(sys.stdout)
char_stream = codecs.getreader("utf-8")(sys.stdin)
#UTF8Reader = codecs.getreader('utf8')
#sys.stdin = UTF8Reader(sys.stdin)
pkl_file = open('../../dictionaries/dictionary.pkl', 'rb')
lang_dict = pickle.load(pkl_file)
pkl_file.close()
pkl_file = open('../../dictionaries/rev_dictionary.pkl', 'rb')
rev_lang_dict = pickle.load(pkl_file)
pkl_file.close()
aligner = Aligner(lang_dict, rev_lang_dict)
splitter = SentenceSplitter()
for line in char_stream:
try:
[sentence, translation] = line.strip().split('\t')
[sentence, dummy] = splitter.split_sentence(sentence)
[translation, dummy] = splitter.split_english_sentence(translation)
aligner.print_dict_alignments(sentence, translation, 5)
except ValueError:
pass
