model = args.model
if not model.endswith('/'):
model +='/'
kDir = model+f'{args.k}'+'/'
modelName = model.split('/')[-2]
# Check if file exists and open if so, else skip this iteration of the loop
hmm = pickle.load(open(kDir+'hmm.mkv','rb'))
# Explicitly determine k from the size of the log matrix and the size of the alphabet used to generate it
k = int(log(len(hmm['E']['+'].keys()),len(args.a)))
kmers = [''.join(p) for p in product(alphabet,repeat=k)] # generate k-mers
target = Reader(args.db)
targetSeqs,targetHeaders = target.get_seqs(),target.get_headers()
targetMap = defaultdict(list)
#Pool processes onto number of CPU cores specified by the user
with pool.Pool(args.n) as multiN:
jobs = multiN.starmap(hmmCalc,product(*[list(zip(targetHeaders,targetSeqs))]))
dataDict = dict(jobs)
#Check if no hits were found
# if not all(v == None for v in dataDict.values()):
dataFrames = pd.concat([df for df in dataDict.values() if not None])
dataFrames['Length'] = dataFrames['End'] - dataFrames['Start']
dataFrames = dataFrames[['Start','End','Length','kmerLLR','seqName','Sequence']]
if not args.fasta:
dataFrames = dataFrames[['Start','End','Length','kmerLLR','seqName']]
finalCoords = []
for k, g in groupby(enumerate(flatCoords),lambda kv:kv[0]-kv[1]):
finalCoords.append(list(map(itemgetter(1), g)))
return finalCoords
def nsmall(a, n):
return np.partition(a, n)[n]
k = 4
BCD = np.load('./mamBCD4.mkv.npy')
AE = np.load('./mamAE4.mkv.npy')
mm10Genes = Reader('gencodeGenesMm10.fa')
mm10Seq = mm10Genes.get_seqs()
mm10Head = mm10Genes.get_headers()
w=200
s=20
seqMap = defaultdict(list)
initModelMap = {'BCD':BCD,'AE':AE}
for head,seq in tqdm(zip(mm10Head,mm10Seq),total=len(mm10Seq)):
tiles = [seq[i:i+w] for i in range(0,len(seq)-w+1,s)]
mapMm10BCD = np.array([classify(tile,k,initModelMap['BCD']) for tile in tiles])
mapMm10AE = np.array([classify(tile,k,initModelMap['AE']) for tile in tiles])
whereHitBCD = np.array(np.nonzero(mapMm10BCD < 0))
whereHitAE = np.array(np.nonzero(mapMm10AE < 0))
whereHit = np.unique(np.concatenate((whereHitBCD,whereHitAE),axis=None))
if whereHit.size > 0:
coords = setCoords(whereHit)
conds[i, j] = kmers[ci + cj] / float(tot)
return conds
# Null Model
genomeRawCounts = BasicCounter(
'/Users/danielsprague/Downloads/gencode.vM21.transcripts.fa',
k=k,
mean=False,
std=False,
log2=False,
alphabet='ATCG')
genomeFa = Reader('/Users/danielsprague/Downloads/gencode.vM21.transcripts.fa')
genomeSeqs = genomeFa.get_seqs()
genomeSeqLens = [len(i) for i in genomeSeqs]
genomeRawCounts.get_counts()
unNormGenomeCounts = genomeRawCounts.counts.T * genomeSeqLens / 1000
genomeCounts = np.rint(unNormGenomeCounts.T)
weightedAvgGenomeCounts = np.average(genomeCounts,
weights=genomeSeqLens,
axis=0)
kmers = [''.join(p) for p in itertools.product('ATCG', repeat=k)]
curr_kmers = dict(zip(kmers, weightedAvgGenomeCounts))
genome_avg = markov_chain(curr_kmers, k, 'ATCG')
np.save(f'./genome{k}.mkv.npy', genome_avg)
# initModel
type=int,
help=
'Number of CPU cores. Each job corresponds to a value of k, and the program scales well with multiprocessing',
default=1)
args = parser.parse_args()
if __name__ == '__main__':
# Read in specified values of k, and the alphabet
kVals = [int(i) for i in args.k.split(',')]
a = args.a.upper()
#SEEKR fasta reader module
F = Reader(args.fasta)
fS = F.get_seqs()
#Join sequences together using $ delimiter character
fString = '$'.join(fS).upper()
lenFString = sum([len(i) for i in fS])
# Need to figure out how to deal with very long fasta files (~ 2-3X the size of the transcriptome in mice)
# if lenFString >= 2147483647:
# fString='$'.join(fS[::10]).upper()
#Split jobs onto processors and call kmers.pyx cython file
with pool.Pool(args.n) as multiN:
jobs = multiN.starmap(kmers.main, product(*[[fString], kVals, [a]]))
dataDict = dict(jobs)
#Save data
parser = argparse.ArgumentParser()
parser.add_argument("-k",type=int)
parser.add_argument('--db',type=str,help='Path to fasta file containing training sequences')
parser.add_argument('--prior',type=str,help='Path to binary .mkv file output from train.py (e.g. markovModels/D_null/2/hmm.mkv')
parser.add_argument('-cf','--createfile',action='store_true',help='Create new file rather than overwrite')
parser.add_argument('--its',type=int,help='Iterations to do, default=100',default=20)
args = parser.parse_args()
assert args.its > 0, 'Please provide an integer greater than or equal to 1'
assert args.k > 0, 'Please provide an integer greater than or equal to 1'
fa = Reader(args.db)
seqs = '$'.join(fa.get_seqs())
model = args.prior
k = args.k
# Identify the location of any ambiguous nucleotides (N)
O,oIdx,nBP = corefunctions.kmersWithAmbigIndex(seqs,k)
# Load in train.py output
hmm = pickle.load(open(args.prior,'rb'))
'''
A - transition matrix (dictionary)
E - emission matrix (dictionary)
pi - initial state probabilities (always 50/50)
states - list of states (query,null)
'''