comparison weblogolib/__init__.py @ 13:cd6c4bd14718

Uploaded
author davidmurphy
date Fri, 24 Feb 2012 09:26:11 -0500
parents 20716450be87
children 778f03497adb
comparison
equal deleted inserted replaced
12:b819394a2634 13:cd6c4bd14718
979 if comp.lower() == 'none': return None 979 if comp.lower() == 'none': return None
980 980
981 if weight is None and alphabet is not None: weight = float(len(alphabet)) 981 if weight is None and alphabet is not None: weight = float(len(alphabet))
982 if comp.lower() == 'equiprobable' : 982 if comp.lower() == 'equiprobable' :
983 prior = weight * equiprobable_distribution(len(alphabet)) 983 prior = weight * equiprobable_distribution(len(alphabet))
984 984 return prior
985 elif comp.lower() == 'escherichiacoli' : 985 elif comp.lower() == 'escherichiacoli' :
986 if(altype=="codonsT"): 986 if(altype=="codonsT"):
987 composition="{'CTT': 0.7616, 'ATG': 1.5872, 'ACA': 0.4096, 'ACG': 0.736, 'ATC': 1.1648, 'AAC': 1.5615999999999999, 'ATA': 0.2368, 'AGG': 0.1024, 'CCT': 0.5376000000000001, 'ACT': 0.512, 'AGC': 1.0624, 'AAG': 0.7744, 'AGA': 0.0896, 'CAT': 1.0112, 'AAT': 1.4016, 'ATT': 1.952, 'CTG': 3.0016, 'CTA': 0.3392, 'CTC': 0.672, 'CAC': 0.8383999999999999, 'AAA': 2.1248, 'CCG': 1.7087999999999999, 'AGT': 0.4608, 'CCA': 0.4224, 'CAA': 0.7744, 'CCC': 0.4096, 'TAT': 1.0752000000000002, 'GGT': 1.3632, 'TGT': 0.37760000000000005, 'CGA': 0.2752, 'CAG': 1.7728, 'TCT': 0.3648, 'GAT': 2.4255999999999998, 'CGG': 0.26239999999999997, 'TTT': 1.2608, 'TGC': 0.512, 'GGG': 0.5504, 'TAG': 1e-06, 'GGA': 0.5888, 'TAA': 0.1152, 'GGC': 2.1376, 'TAC': 0.9344, 'TTC': 0.96, 'TCG': 0.512, 'TTA': 0.9728, 'TTG': 0.7616, 'TCC': 0.352, 'ACC': 1.4592, 'TCA': 0.4992, 'GCA': 1.3504, 'GTA': 0.736, 'GCC': 2.0224, 'GTC': 0.7487999999999999, 'GCG': 2.464, 'GTG': 1.6896, 'GAG': 1.1776, 'GTT': 1.0752000000000002, 'GCT': 0.6848, 'TGA': 0.064, 'GAC': 1.312, 'CGT': 1.3504, 'TGG': 0.6848, 'GAA': 2.7968, 'CGC': 1.664}" 987 composition="{'CTT': 0.7616, 'ATG': 1.5872, 'ACA': 0.4096, 'ACG': 0.736, 'ATC': 1.1648, 'AAC': 1.5615999999999999, 'ATA': 0.2368, 'AGG': 0.1024, 'CCT': 0.5376000000000001, 'ACT': 0.512, 'AGC': 1.0624, 'AAG': 0.7744, 'AGA': 0.0896, 'CAT': 1.0112, 'AAT': 1.4016, 'ATT': 1.952, 'CTG': 3.0016, 'CTA': 0.3392, 'CTC': 0.672, 'CAC': 0.8383999999999999, 'AAA': 2.1248, 'CCG': 1.7087999999999999, 'AGT': 0.4608, 'CCA': 0.4224, 'CAA': 0.7744, 'CCC': 0.4096, 'TAT': 1.0752000000000002, 'GGT': 1.3632, 'TGT': 0.37760000000000005, 'CGA': 0.2752, 'CAG': 1.7728, 'TCT': 0.3648, 'GAT': 2.4255999999999998, 'CGG': 0.26239999999999997, 'TTT': 1.2608, 'TGC': 0.512, 'GGG': 0.5504, 'TAG': 1e-06, 'GGA': 0.5888, 'TAA': 0.1152, 'GGC': 2.1376, 'TAC': 0.9344, 'TTC': 0.96, 'TCG': 0.512, 'TTA': 0.9728, 'TTG': 0.7616, 'TCC': 0.352, 'ACC': 1.4592, 'TCA': 0.4992, 'GCA': 1.3504, 'GTA': 0.736, 'GCC': 2.0224, 'GTC': 0.7487999999999999, 'GCG': 2.464, 'GTG': 1.6896, 'GAG': 1.1776, 'GTT': 1.0752000000000002, 'GCT': 0.6848, 'TGA': 0.064, 'GAC': 1.312, 'CGT': 1.3504, 'TGG': 0.6848, 'GAA': 2.7968, 'CGC': 1.664}"
988 else: 988 else:
989 composition="{'CUU': 0.7616, 'AUG': 1.5872, 'ACA': 0.4096, 'ACG': 0.736, 'AUC': 1.1648, 'AAC': 1.5615999999999999, 'AUA': 0.2368, 'AGG': 0.1024, 'CCU': 0.5376000000000001, 'ACU': 0.512, 'AGC': 1.0624, 'AAG': 0.7744, 'AGA': 0.0896, 'CAU': 1.0112, 'AAU': 1.4016, 'AUU': 1.952, 'CUG': 3.0016, 'CUA': 0.3392, 'CUC': 0.672, 'CAC': 0.8383999999999999, 'AAA': 2.1248, 'CCG': 1.7087999999999999, 'AGU': 0.4608, 'CCA': 0.4224, 'CAA': 0.7744, 'CCC': 0.4096, 'UAU': 1.0752000000000002, 'GGU': 1.3632, 'UGU': 0.37760000000000005, 'CGA': 0.2752, 'CAG': 1.7728, 'UCU': 0.3648, 'GAU': 2.4255999999999998, 'CGG': 0.26239999999999997, 'UUU': 1.2608, 'UGC': 0.512, 'GGG': 0.5504, 'UAG': 1e-06, 'GGA': 0.5888, 'UAA': 0.1152, 'GGC': 2.1376, 'UAC': 0.9344, 'UUC': 0.96, 'UCG': 0.512, 'UUA': 0.9728, 'UUG': 0.7616, 'UCC': 0.352, 'ACC': 1.4592, 'UCA': 0.4992, 'GCA': 1.3504, 'GUA': 0.736, 'GCC': 2.0224, 'GUC': 0.7487999999999999, 'GCG': 2.464, 'GUG': 1.6896, 'GAG': 1.1776, 'GUU': 1.0752000000000002, 'GCU': 0.6848, 'UGA': 0.064, 'GAC': 1.312, 'CGU': 1.3504, 'UGG': 0.6848, 'GAA': 2.7968, 'CGC': 1.664}" 989 composition="{'CUU': 0.7616, 'AUG': 1.5872, 'ACA': 0.4096, 'ACG': 0.736, 'AUC': 1.1648, 'AAC': 1.5615999999999999, 'AUA': 0.2368, 'AGG': 0.1024, 'CCU': 0.5376000000000001, 'ACU': 0.512, 'AGC': 1.0624, 'AAG': 0.7744, 'AGA': 0.0896, 'CAU': 1.0112, 'AAU': 1.4016, 'AUU': 1.952, 'CUG': 3.0016, 'CUA': 0.3392, 'CUC': 0.672, 'CAC': 0.8383999999999999, 'AAA': 2.1248, 'CCG': 1.7087999999999999, 'AGU': 0.4608, 'CCA': 0.4224, 'CAA': 0.7744, 'CCC': 0.4096, 'UAU': 1.0752000000000002, 'GGU': 1.3632, 'UGU': 0.37760000000000005, 'CGA': 0.2752, 'CAG': 1.7728, 'UCU': 0.3648, 'GAU': 2.4255999999999998, 'CGG': 0.26239999999999997, 'UUU': 1.2608, 'UGC': 0.512, 'GGG': 0.5504, 'UAG': 1e-06, 'GGA': 0.5888, 'UAA': 0.1152, 'GGC': 2.1376, 'UAC': 0.9344, 'UUC': 0.96, 'UCG': 0.512, 'UUA': 0.9728, 'UUG': 0.7616, 'UCC': 0.352, 'ACC': 1.4592, 'UCA': 0.4992, 'GCA': 1.3504, 'GUA': 0.736, 'GCC': 2.0224, 'GUC': 0.7487999999999999, 'GCG': 2.464, 'GUG': 1.6896, 'GAG': 1.1776, 'GUU': 1.0752000000000002, 'GCU': 0.6848, 'UGA': 0.064, 'GAC': 1.312, 'CGU': 1.3504, 'UGG': 0.6848, 'GAA': 2.7968, 'CGC': 1.664}"
1002 prior = weight * asarray(aa_composition, float64) 1002 prior = weight * asarray(aa_composition, float64)
1003 else : 1003 else :
1004 prior = weight * equiprobable_distribution(len(alphabet)) 1004 prior = weight * equiprobable_distribution(len(alphabet))
1005 elif comp in std_percentCG : 1005 elif comp in std_percentCG :
1006 prior = weight * base_distribution(std_percentCG[comp]) 1006 prior = weight * base_distribution(std_percentCG[comp])
1007 1007 return prior
1008 elif comp[-1] == '%' : 1008 elif comp[-1] == '%' :
1009 prior = weight * base_distribution( float(comp[:-1])) 1009 prior = weight * base_distribution( float(comp[:-1]))
1010 1010 return prior
1011 elif isfloat(comp) : 1011 elif isfloat(comp) :
1012 prior = weight * base_distribution( float(comp)*100. ) 1012 prior = weight * base_distribution( float(comp)*100. )
1013 1013 return prior
1014 if composition[0] == '{' and composition[-1] == '}' : 1014 if composition[0] == '{' and composition[-1] == '}' :
1015 explicit = composition[1: -1] 1015 explicit = composition[1: -1]
1016 explicit = explicit.replace(',',' ').replace("'", ' ').replace('"',' ').replace(':', ' ').split() 1016 explicit = explicit.replace(',',' ').replace("'", ' ').replace('"',' ').replace(':', ' ').split()
1017 1017
1018 if len(explicit) != len(alphabet)*2 : 1018 if len(explicit) != len(alphabet)*2 :
1644 1644
1645 data_grp.add_option( "", "--composition", 1645 data_grp.add_option( "", "--composition",
1646 dest="composition", 1646 dest="composition",
1647 action="store", 1647 action="store",
1648 type="string", 1648 type="string",
1649 default = "auto", 1649 default = "equiprobable",
1650 help="The expected composition of the sequences: 'auto' (default), 'equiprobable', 'none' (Do not perform any compositional adjustment), or 'escherichiacoli' 'homosapiens' 'saccharomycescerevisiae' for ecoli, human and SC codon frequencies.", 1650 help="The expected composition of the sequences: 'equiprobable'(default), 'none' (Do not perform any compositional adjustment), or 'escherichiacoli' 'homosapiens' 'saccharomycescerevisiae' for ecoli, human and SC codon frequencies.",
1651 metavar="COMP.") 1651 metavar="COMP.")
1652 1652
1653 data_grp.add_option( "", "--weight", 1653 data_grp.add_option( "", "--weight",
1654 dest="weight", 1654 dest="weight",
1655 action="store", 1655 action="store",