def gene_feature(Y, X, learn_options):
'''
Things like the sequence of the gene, the DNA Tm of the gene, etc.
'''
gene_names = Y['Target gene']
gene_length = np.zeros((gene_names.values.shape[0], 1))
gc_content = np.zeros((gene_names.shape[0], 1))
temperature = np.zeros((gene_names.shape[0], 1))
molecular_weight = np.zeros((gene_names.shape[0], 1))
for gene in gene_names.unique():
seq = util.get_gene_sequence(gene)
gene_length[gene_names.values==gene] = len(seq)
gc_content[gene_names.values==gene] = SeqUtil.GC(seq)
temperature[gene_names.values==gene] = Tm.Tm_staluc(seq, rna=False)
molecular_weight[gene_names.values==gene] = SeqUtil.molecular_weight(seq, 'DNA')
all = np.concatenate((gene_length, gc_content, temperature, molecular_weight), axis=1)
df = pandas.DataFrame(data=all, index=gene_names.index, columns=['gene length',
'gene GC content',
'gene temperature',
'gene molecular weight'])
return df
def compute_stats(seq):
stats = SeqStats
stats.length = len(seq)
stats.gc = SeqUtils.GC(seq)
try:
stats.weight = SeqUtils.molecular_weight(seq)
except ValueError:
stats.weight = None
return stats
def target_genes_stats(genes=["HPRT1", "TADA1", "NF2", "TADA2B", "NF1", "CUL3", "MED12", "CCDC101"]):
for gene in genes:
seq = get_gene_sequence(gene)
if seq != None:
print "%s \t\t\t\t len: %d \t GCcont: %.3f \t Temp: %.4f \t molweight: %.4f" % (
gene,
len(seq),
SeqUtil.GC(seq),
Tm.Tm_staluc(seq, rna=False),
SeqUtil.molecular_weight(seq, "DNA"),
)
def SeqUtilFeatures(data):
'''
assuming '30-mer'is a key
get melting temperature features from:
0-the 30-mer ("global Tm")
1-the Tm (melting temperature) of the DNA:RNA hybrid from positions 16 - 20 of the sgRNA, i.e. the 5nts immediately proximal of the NGG PAM
2-the Tm of the DNA:RNA hybrid from position 8 - 15 (i.e. 8 nt)
3-the Tm of the DNA:RNA hybrid from position 3 - 7 (i.e. 5 nt)
'''
sequence = data['30mer'].values
num_features = 1
featarray = np.ones((sequence.shape[0], num_features))
for i, seq in enumerate(sequence):
assert len(seq) == 30, "seems to assume 30mer"
featarray[i, 0] = SeqUtil.molecular_weight(str(seq))
feat = pandas.DataFrame(pandas.DataFrame(featarray))
return feat
def target_genes_stats(genes=['HPRT1', 'TADA1', 'NF2', 'TADA2B', 'NF1', 'CUL3', 'MED12', 'CCDC101']):
for gene in genes:
seq = get_gene_sequence(gene)
if seq != None:
print '%s \t\t\t\t len: %d \t GCcont: %.3f \t Temp: %.4f \t molweight: %.4f' % (gene, len(seq), SeqUtil.GC(seq), Tm.Tm_staluc(seq, rna=False), SeqUtil.molecular_weight(seq, 'DNA'))
def molecular_weight(self):
return SeqUtils.molecular_weight(self.sequence, 'protein')
def molecular_weight(self):
return SeqUtils.molecular_weight(self.sequence, 'protein')
def average_molecule_weight(): weights = [bsu.molecular_weight(r, 'protein') for r in residues_list] return sum(weights)/len(weights)
def target_genes_stats(genes=['HPRT1', 'TADA1', 'NF2', 'TADA2B', 'NF1', 'CUL3', 'MED12', 'CCDC101']):
for gene in genes:
seq = get_gene_sequence(gene)
if seq != None:
print '%s \t\t\t\t len: %d \t GCcont: %.3f \t Temp: %.4f \t molweight: %.4f' % (gene, len(seq), SeqUtil.GC(seq), Tm.Tm_staluc(seq, rna=False), SeqUtil.molecular_weight(seq, 'DNA'))