def get_psedpc_matrix(filename,
n,
r,
w,
pattern_list=[
'A', 'C', 'G', 'U', 'A-U', 'U-A', 'G-C', 'C-G',
'G-U', 'U-G'
]):
'''This is a complete process in PseSSC, aim to generate feature vector.
The FASTA format of the input file is as follows:
>sequence name
An RNA sequence should be consist of AGCU
Secondary structure
:param filename: Name of input file.
:param n: The maximum distance between structure statuses.
:param r: The highest counted rank (or tier) of the structural correlation along a RNA chain.
:param w: The wight of theta, from 0.1 to 1.
:param pattern_list: Structure statuses, default:['A', 'C', 'G', 'U', 'A-U', 'U-A', 'G-C', 'C-G', 'G-U', 'U-G'].'''
with open(filename) as f:
seqsslst = get_rnasc_data(f)
features = []
for seqss in seqsslst:
vector = get_psedpc_vector(seqss, n, r, w, pattern_list)
features.append(vector)
return features
def get_psedpc_matrix(filename, n, r, w, pattern_list = ['A', 'C', 'G', 'U', 'A-U', 'U-A', 'G-C', 'C-G', 'G-U', 'U-G']):
'''This is a complete process in PseSSC, aim to generate feature vector.
The FASTA format of the input file is as follows:
>sequence name
An RNA sequence should be consist of AGCU
Secondary structure
:param filename: Name of input file.
:param n: The maximum distance between structure statuses.
:param r: The highest counted rank (or tier) of the structural correlation along a RNA chain.
:param w: The wight of theta, from 0.1 to 1.
:param pattern_list: Structure statuses, default:['A', 'C', 'G', 'U', 'A-U', 'U-A', 'G-C', 'C-G', 'G-U', 'U-G'].'''
with open(filename) as f:
seqsslst= get_rnasc_data(f)
features = []
for seqss in seqsslst:
vector = get_psedpc_vector(seqss, n, r, w, pattern_list)
features.append(vector)
return features
def get_triplet_matrix(filename):
'''This is a complete process in triplet,aim to generate feature vectors.
The FASTA format of the input file is as follows:
>Sequence name
An RNA sequence should be consist of AGCU
Secondary structure
:param filename: Name of inputfile.
:return: Feature matrix through Triplet.
'''
letter = ["(","."]
alphabet = 'AGCU' #Don't change the alphabetical, or the order of features will change.
with open(filename) as f:
seqsslst= get_rnasc_data(f)
tripletdict = get_triplet_dict(letter, 3, alphabet)
features = []
for seqss in seqsslst:
vector = get_triplet_vector(seqss, tripletdict)
features.append(vector)
return features
def get_triplet_matrix(filename):
'''This is a complete process in triplet,aim to generate feature vectors.
The FASTA format of the input file is as follows:
>Sequence name
An RNA sequence should be consist of AGCU
Secondary structure
:param filename: Name of inputfile.
:return: Feature matrix through Triplet.
'''
letter = ["(","."]
alphabet = 'AGCU' #Don't change the alphabetical, or the order of features will change.
with open(filename) as f:
seqsslst= get_rnasc_data(f)
tripletdict = get_triplet_dict(letter, 3, alphabet)
features = []
for seqss in seqsslst:
vector = get_triplet_vector(seqss, tripletdict)
features.append(vector)
return features
def get_pseknc_matrix(filename, k):
'''This is a complete process in PseKNC,aim to generate feature matrix.
The FASTA format of the input file is as follows:
>Sequence name
An RNA sequence should be consist of AGCU
Secondary structure
:param filename: Name of input file.
:return: Feature matrix through PseKNC.
'''
alphabet = 'ACGU'
letter = list(alphabet)
with open(filename) as f:
seqsslst = get_rnasc_data(f)
psekncdict = get_pseknc_dict(letter, k)
features = []
for seqss in seqsslst:
vector = get_pseknc_vector(seqss, psekncdict, k)
features.append(vector)
return features
def get_pseknc_matrix(filename, k):
'''This is a complete process in PseKNC,aim to generate feature matrix.
The FASTA format of the input file is as follows:
>Sequence name
An RNA sequence should be consist of AGCU
Secondary structure
:param filename: Name of input file.
:return: Feature matrix through PseKNC.
'''
alphabet = 'ACGU'
letter = list(alphabet)
with open(filename) as f:
seqsslst = get_rnasc_data(f)
psekncdict = get_pseknc_dict(letter, k)
features = []
for seqss in seqsslst:
vector = get_pseknc_vector(seqss, psekncdict, k)
features.append(vector)
return features
