receptor_binding_sites = [x-1 for x in [159,169,170,172,173,203,207]]
sp=17
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H1N1',
'alignment_file':'data/H1N1_gisaid_epiflu_sequence.fasta',
'outgroup':'A/Tokyo/1/51',
'time_interval':(1990,2010),
'force_include':'source-data/H1N1_HI_strains.txt',
'force_include_all':True,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
'min_freq':0.10,
'cds':[0,None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
#'clade_designations': {},
'auspice_prefix':'H1N1_HI_',
'HI_fname':'source-data/H1N1_HI_titers.txt',
'html_vars': {'coloring': 'ep, ne, rb, lbi, dfreq, region, date, HI',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '3c2.a, 3c3.a'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
})
class H1N1_filter(flu_filter):
def __init__(self,min_length = 987, **kwargs):
'''
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':
'H1N1pdm',
'alignment_file':
'/Users/yujia_zhou/Documents/Work/H9_nextflu-master/augur/src/data/H1N1pdm_gisaid_epiflu_sequence.fasta',
'outgroup':
'A/Swine/Indiana/P12439/00',
'force_include':
'/Users/yujia_zhou/Documents/Work/H9_nextflu-master/augur/src/data/H1N1pdm_HI_strains.txt',
'force_include_all':
True,
'date_spec':
'year',
'max_global':
True, # sample as evenly as possible from different geographic regions
'cds': [0, None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
''''clade_designations': {
'2': [('HA1', 125, 'N'), ('HA1', 134 ,'A'), ('HA1', 183, 'S'), ('HA1', 31,'D'), ('HA1', 172,'N'), ('HA1', 186,'T')],
'3': [('HA1', 134 ,'T'), ('HA1', 183, 'P')],
'4': [('HA1', 125, 'D'), ('HA1', 134 ,'A'), ('HA1', 183, 'S')],
'5': [('HA1', 87, 'N'), ('HA1', 205, 'K'), ('HA1', 216, 'V'), ('HA1', 149, 'L')],
'6': [('HA1', 185,'T'), ('HA1', 97, 'N'), ('HA1', 197, 'A')],
'6c':[('HA1', 234,'I'), ('HA1', 97, 'N'), ('HA1', 197, 'A'), ('HA1', 283,'E')],
'6b':[('HA1', 163,'Q'), ('HA1', 256, 'T'), ('HA1', 197, 'A'), ('HA1', 283,'E')],
'7': [('HA1', 143,'G'), ('HA1', 97, 'D'), ('HA1', 197, 'T')],
'8': [('HA1', 186,'T'), ('HA1', 272,'A')],
'84N':[('HA1', 163,'Q'), ('HA1', 256, 'T'), ('HA1', 197, 'A'), ('HA1', 283,'E'), ('SigPep', 13, 'T'), ('HA1', 84, 'N')]
},'''
'HI_fname':
'/Users/yujia_zhou/Documents/Work/H9_nextflu-master/augur/src/data/H1N1pdm_HI_titers.txt',
'auspice_prefix':
'H1N1pdm_',
'html_vars': {
'coloring': 'ep, ne, rb, lbi, dfreq, region, date, cHI, HI_dist',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '6b, 6c'
},
'js_vars': {
'LBItau': 0.0005,
'LBItime_window': 0.5,
'dfreq_dn': 2
},
'layout':
'auspice',
})
from process import process, virus_config
from Bio import SeqIO
from Bio.Seq import Seq
from Bio.Align import MultipleSeqAlignment
import numpy as np
from itertools import izip
std_outgroup_file = '/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/source-data/outgroups.fasta'
virus_config.update({
# data source and sequence parsing/cleaning/processing
'fasta_fields': {
0: 'strain',
1: 'date',
2: 'isolate_id',
3: 'passage',
4: 'subtype',
5: 'ori_lab',
6: 'sub_lab',
7: 'submitter'
},
'cds': [0, None], # define the HA start i n 0 numbering
'auspice_prefix': 'H4_',
'verbose': 3
})
class mutation_tree(process, flu_filter, tree_refine, virus_clean):
"""docstring for mutation_tree"""
def __init__(self,
aln_fname,
outgroup,
outdir='./',
]
else '0' for pos in xrange(1,1725)])
receptor_binding_sites = [159,169,170,172,173,203,207]
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'Vic',
'alignment_file':'data/Vic_gisaid_epiflu_sequence.fasta',
'outgroup':'B/HongKong/02/1993',
#'force_include':'source-data/HI_strains.txt',
'force_include_all':False,
'max_global':True, # sample as evenly as possible from different geographic regions
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'clade_designations': {
'1A': [('HA1', 75,'K'), ('HA1', 58, 'L'), ('HA1', 165, 'K')],
'1B': [('HA1', 75,'K'), ('HA1', 58, 'P'), ('HA1', 165, 'K')]
},
'html_vars': {'coloring': 'lbi, dfreq, region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '1A, 1B'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
})
class BVic_filter(flu_filter):
def __init__(self,min_length = 987, **kwargs):
'''
parameters
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus': 'H3N2',
'alignment_file': 'data/H3N2_gisaid_epiflu_sequence.fasta',
'outgroup': 'A/Beijing/32/1992',
#'force_include':'source-data/HI_strains.txt',
'force_include_all': False,
'max_global':
True, # sample as evenly as possible from different geographic regions
'cds': [0, None], # define the HA1 start i n 0 numbering
'n_iqd': 8,
'min_mutation_frequency': 0.1,
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at HA1 start, adding sp to obtain numbering from methionine
'clade_designations': {
"3c3.a": [('HA1', 128, 'A'), ('HA1', 142, 'G'), ('HA1', 159, 'S')],
"3c3": [('HA1', 128, 'A'), ('HA1', 142, 'G'), ('HA1', 159, 'F')],
"3c2.a": [('HA1', 144, 'S'), ('HA1', 159, 'Y'), ('HA1', 225, 'D'),
('HA1', 311, 'H'), ('HA2', 160, 'N')],
"3c2": [('HA1', 144, 'N'), ('HA1', 159, 'F'), ('HA1', 225, 'N'),
('HA2', 160, 'N'), ('HA1', 142, 'R')],
"3c3.b": [('HA1', 83, 'R'), ('HA1', 261, 'Q'), ('HA1', 62, 'K'),
('HA1', 122, 'D')]
},
'html_vars': {
'coloring': 'ep, ne, rb, lbi, dfreq, region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '3c2.a, 3c3.a'
},
'js_vars': {
'LBItau': 0.0005,
'LBItime_window': 0.5,
'dfreq_dn': 2
},
})
sp = 17
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus': 'H1N1',
'alignment_file': 'data/H1N1_gisaid_epiflu_sequence.fasta',
'outgroup': 'A/Tokyo/1/51',
'time_interval': (1990, 2010),
'force_include': 'source-data/H1N1_HI_strains.txt',
'force_include_all': True,
'date_spec': 'year',
'max_global':
True, # sample as evenly as possible from different geographic regions
'min_freq': 0.10,
'cds': [0, None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
#'clade_designations': {},
'auspice_prefix': 'H1N1_HI_',
'HI_fname': 'source-data/H1N1_HI_titers.txt',
'html_vars': {
'coloring': 'ep, ne, rb, lbi, dfreq, region, date, HI',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '3c2.a, 3c3.a'
},
'js_vars': {
'LBItau': 0.0005,
'LBItime_window': 0.5,
'dfreq_dn': 2
},
})
100,
132,
139 #Cb
] else '0' for pos in xrange(1, 1725)
])
receptor_binding_sites = [x - 1 for x in [159, 169, 170, 172, 173, 203, 207]]
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus': 'H1N1',
'alignment_file': 'data/H1N1_gisaid_epiflu_sequence.fasta',
'outgroup': 'A/Tokyo/1/51',
'time_interval': (1990, 2010),
#'force_include':'source-data/HI_strains.txt',
'force_include_all': False,
'max_global':
True, # sample as evenly as possible from different geographic regions
'cds': [0, None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
'clade_designations': {},
'auspice_prefix': 'H1N1_',
})
class H1N1_filter(flu_filter):
def __init__(self, min_length=987, **kwargs):
'''
parameters
min_length -- minimal length for a sequence to be acceptable
'''
receptor_binding_sites = [159, 169, 170, 172, 173, 203, 207]
virus_config.update(
{
# data source and sequence parsing/cleaning/processing
"virus": "Vic",
"alignment_file": "data/Vic_gisaid_epiflu_sequence.fasta",
"outgroup": "B/HongKong/02/1993",
#'force_include':'source-data/HI_strains.txt',
"force_include_all": False,
"max_global": True, # sample as evenly as possible from different geographic regions
"cds": [11, None], # define the translation start in 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
"clade_designations": {
"1A": [(90, "K"), (73, "L"), (180, "K"), (604, "S")],
"1B": [(90, "K"), (73, "P"), (180, "K")],
},
"html_vars": {
"coloring": "lbi, dfreq, region, date",
"gtplaceholder": "HA1 positions...",
"freqdefault": "1A, 1B",
},
"js_vars": {"LBItau": 0.0005, "LBItime_window": 0.5, "dfreq_dn": 2},
}
)
class BVic_filter(flu_filter):
def __init__(self, min_length=987, **kwargs):
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H1N1pdm',
'alignment_file':'data/H1N1pdm_gisaid_epiflu_sequence.fasta',
'outgroup':'A/Swine/Indiana/P12439/00',
#'force_include':'source-data/HI_strains.txt',
'force_include_all':False,
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'clade_designations': {
'2':[(142, 'N'), (151 ,'A'), (200, 'S'), (48,'D'), (189,'N'), (203,'T')],
'3':[(151 ,'T'), (200, 'P')],
'4':[(142, 'D'), (151 ,'A'), (200, 'S')],
'5':[(104, 'N'), (222, 'K'), (233, 'V'), (266, 'L')],
'6':[(202,'T'), (114, 'N'), (214, 'A')],
'6c':[(251,'I'), (114, 'N'), (214, 'A'), (300,'E')],
'6b':[(180,'Q'), (273, 'T'), (214, 'A'), (300,'E')],
'7':[(160,'G'), (114, 'D'), (214, 'T')],
'8':[(203,'T'), (289,'A')],
},
'html_vars': {'coloring': 'ep, ne, rb, lbi, dfreq, region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '6b, 6c'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
})
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':
'H10',
'alignment_file':
'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H10_gisaid_epiflu_sequence.fasta',
'outgroup':
'A/mallard-duck/ALB/302/1977',
#'force_include':'H10_HI_strains.txt',
'force_include_all':
True,
'date_spec':
'year',
'max_global':
True, # sample as evenly as possible from different geographic regions
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
''''clade_designations': {
'1A': [('HA1', 75,'K'), ('HA1', 58, 'L'), ('HA1', 165, 'K')],
'1B': [('HA1', 75,'K'), ('HA1', 58, 'P'), ('HA1', 165, 'K')],
'117V': [('HA1', 75,'K'), ('HA1', 58, 'L'), ('HA1', 165, 'K'), ('HA1', 129, 'D'), ('HA1', 117, 'V')]
},'''
'auspice_prefix':
'H10_',
'HI_fname':
'H10_HI_titers.txt',
'html_vars': {
'coloring': 'lbi, dfreq, region, date, cHI, HI_dist',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '1A, 1B'
},
'js_vars': {
'LBItau': 0.0005,
'LBItime_window': 0.5,
'dfreq_dn': 2
},
'layout':
'auspice',
})
from Bio.Seq import Seq
from Bio.Align import MultipleSeqAlignment
import numpy as np
from itertools import izip
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'Zika',
'fasta_fields':{0:'strain', 2:'accession', 3:'date', 5:'country', 5:'region', 8:'db', 10:'authors'},
# 0 1 2 3 4 5 6 7 8 9 10
#>BeH818995|zika|KU365777|2015-XX-XX|south_america|brazil|?|?|genbank|genome|Azevedo et al
'alignment_file':'data/zika.fasta',
'outgroup':'H/PF/2013',
'aggregate_regions':[('global', None)],
'force_include_all':False,
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'min_mutation_frequency':0.499,
'min_genotype_frequency':0.499,
'html_vars': {'coloring': 'lbi, dfreq, region, date',
'gtplaceholder': 'Genomic positions...',
'freqdefault': ''},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
})
class zika_filter(virus_filter):
def __init__(self,min_length = 987, **kwargs):
'''
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':
'H7',
'alignment_file':
'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H7_gisaid_epiflu_sequence.fasta',
'outgroup':
'A/equine/Prague/2/1956',
#'force_include':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H7_HI_strains.txt',
'force_include_all':
False,
'date_spec':
'year',
'max_global':
True, # sample as evenly as possible from different geographic regions
'cds': [0, None], # define the translation start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
''''clade_designations': {
'2': [('HA1', 48,'K'), ('HA1', 108, 'A'), ('HA1', 150, 'S')],
'3': [('HA1', 48,'R'), ('HA1', 108, 'P'), ('HA1', 150, 'I')],
'3a': [('HA1', 37,'A'), ('HA1', 298, 'E'), ('HA1', 48,'R'), ('HA1', 105, 'P'), ('HA1', 150, 'I')],
'172Q': [('HA1', 48,'R'), ('HA1', 108, 'P'), ('HA1', 150, 'I'), ('HA1', 116, 'K'), ('HA1', 172, 'Q')]
},'''
'auspice_prefix':
'H7_',
#'HI_fname':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H7_HI_titers.txt',
'html_vars': {
'coloring': 'region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': ''
},
'js_vars': {
'LBItau': 0.0005,
'LBItime_window': 0.5,
'dfreq_dn': 2
},
'layout':
'auspice',
})
receptor_binding_sites = [159, 169, 170, 172, 173, 203, 207]
virus_config.update(
{
# data source and sequence parsing/cleaning/processing
"virus": "Yam",
"alignment_file": "data/Yam_gisaid_epiflu_sequence.fasta",
"outgroup": "B/Singapore/11/94",
#'force_include':'source-data/HI_strains.txt',
"force_include_all": False,
"max_global": True, # sample as evenly as possible from different geographic regions
"cds": [11, None], # define the translation start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
"clade_designations": {
"2": [("HA1", 48, "K"), ("HA1", 108, "A"), ("HA1", 150, "S")],
"3": [("HA1", 48, "R"), ("HA1", 108, "P"), ("HA1", 150, "I")],
"3a": [("HA1", 37, "A"), ("HA1", 298, "E"), ("HA1", 48, "R"), ("HA1", 105, "P"), ("HA1", 150, "I")],
},
"html_vars": {
"coloring": "lbi, dfreq, region, date",
"gtplaceholder": "HA1 positions...",
"freqdefault": "2, 3, 3a",
},
"js_vars": {"LBItau": 0.0005, "LBItime_window": 0.5, "dfreq_dn": 2},
}
)
class BYam_filter(flu_filter):
import numpy as np
from itertools import izip
path_to_augur = './' + '/'.join(sys.argv[0].split('/')[:-2])
std_outgroup_file_blast = path_to_augur + '/source-data/outgroups.fasta'
std_outgroup_file_nuc = path_to_augur + '/source-data/outgroups_nucleotides_unspliced.fasta'
no_raxml_threshold = 15000
virus_config.update({
# data source and sequence parsing/cleaning/processing
'fasta_fields': {
0: 'strain',
1: 'isolate_id',
2: 'date',
3: 'subtype',
4: 'country',
5: 'region',
7: 'host',
6: 'passage'
},
'cds': [0, None], # define the HA start i n 0 numbering
'verbose': 3
})
def get_date(strain):
from datetime import datetime
date_str = strain.split('|')[2]
try:
collection_date = datetime.strptime(date_str, '%Y-%m-%d')
return collection_date.strftime('%Y-%m-%d')
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H4',
'alignment_file':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H4_gisaid_epiflu_sequence.fasta',
'outgroup':'A/Duck/Czechoslovakia/1956',
#'force_include':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H4_HI_strains.txt',
'force_include_all':True,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
"""
'clade_designations': {
'2': [('HA1', 125, 'N'), ('HA1', 134 ,'A'), ('HA1', 183, 'S'), ('HA1', 31,'D'), ('HA1', 172,'N'), ('HA1', 186,'T')],
'3': [('HA1', 134 ,'T'), ('HA1', 183, 'P')],
'4': [('HA1', 125, 'D'), ('HA1', 134 ,'A'), ('HA1', 183, 'S')],
'5': [('HA1', 87, 'N'), ('HA1', 205, 'K'), ('HA1', 216, 'V'), ('HA1', 149, 'L')],
'6': [('HA1', 185,'T'), ('HA1', 97, 'N'), ('HA1', 197, 'A')],
'6c':[('HA1', 234,'I'), ('HA1', 97, 'N'), ('HA1', 197, 'A'), ('HA1', 283,'E')],
'6b':[('HA1', 163,'Q'), ('HA1', 256, 'T'), ('HA1', 197, 'A'), ('HA1', 283,'E')],
'7': [('HA1', 143,'G'), ('HA1', 97, 'D'), ('HA1', 197, 'T')],
'8': [('HA1', 186,'T'), ('HA1', 272,'A')],
'84N':[('HA1', 163,'Q'), ('HA1', 256, 'T'), ('HA1', 197, 'A'), ('HA1', 283,'E'), ('SigPep', 13, 'T'), ('HA1', 84, 'N')]
},
"""
#'HI_fname':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H4_HI_titers.txt',
'auspice_prefix':'H4_',
'html_vars': {'coloring': 'region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': ''},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
'layout':'auspice',
})
from Bio.Seq import Seq
from Bio.Align import MultipleSeqAlignment
import numpy as np
from itertools import izip
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'Zika',
'fasta_fields':{0:'strain', 2:'accession', 3:'date', 5:'country', 5:'region', 8:'db', 10:'authors'},
# 0 1 2 3 4 5 6 7 8 9 10
#>BeH818995|Zika|KU365777|2015-07-21|SouthAmerica|Brazil|Para|Belem|Genbank|Genome|Azevedo et al|?|
'alignment_file':'data/Zika.fasta',
'outgroup':'H/PF/2013',
'aggregate_regions':[('global', None)],
'force_include_all':False,
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'min_mutation_frequency':0.499,
'min_genotype_frequency':0.499,
'html_vars': {'coloring': 'lbi, dfreq, region, date',
'gtplaceholder': 'Genomic positions...',
'freqdefault': ''},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
})
class zika_filter(virus_filter):
def __init__(self,min_length = 987, **kwargs):
'''
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H3N2',
'alignment_file': 'data/H3N2_IRD_sequence_october_clean.fasta',
# data/H3N2_gisaid_epiflu_sequence.fasta # data/H3N2_IRD_sequence_clean.fasta
'fasta_fields': {0: 'strain', 1: 'isolate_id', 3: 'passage', 5: 'date', 7: 'lab', 8: "accession"},
#'alignment_file':'data/H3N2_gisaid_epiflu_sequence.fasta',
'outgroup':'A/Beijing/32/1992',
'force_include':'data/H3N2_HI_strains.txt',
'force_include_all':False,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA1 start i n 0 numbering
'n_iqd':5,
'min_mutation_frequency':0.01,
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at HA1 start, adding sp to obtain numbering from methionine
'clade_designations': { "3c3.a":[('HA1', 128,'A'), ('HA1',142,'G'), ('HA1',159,'S')],
"3c3": [('HA1', 128,'A'), ('HA1',142,'G'), ('HA1',159,'F')],
"3c2.a": [('HA1', 144,'S'), ('HA1',159,'Y'), ('HA1',225,'D'), ('HA1', 311,'H'), ('HA2', 160,'N')],
"3c2": [('HA1', 144,'N'), ('HA1',159,'F'), ('HA1',225,'N'), ('HA2', 160,'N'), ('HA1', 142, 'R')],
"3c3.b": [('HA1', 83,'R'), ('HA1',261,'Q'), ('HA1',62,'K'), ('HA1', 122,'D')]
},
'epitope_masks_fname':'source-data/H3N2_epitope_masks.tsv',
'epitope_mask_version':'wolf',
'HI_fname':'data/H3N2_HI_titers.txt',
'html_vars': {'coloring': 'ep, ne, rb, lbi, dfreq, region, date, cHI, HI_dist',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '3c2.a, 3c3.a, 3c3.b'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
'excluded_tables': ['NIMR_Sep2012_08.csv'], #, 'nimr-sep-2010-table8', 'nimr-sep-2010-table8','NIMR_Sep2012_11.csv'],
'layout':'auspice',
'min_aamuts': 1,
# 'predictors': ['dfreq', 'cHI'] # estimate
'predictors': { 'dfreq': [2.50, 2.84], 'cHI': [1.68, 0.45] } # fix predictor: [value, std deviation]
})
from process import process, virus_config
from Bio import SeqIO, AlignIO
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
from Bio.Align import MultipleSeqAlignment
import numpy as np
from itertools import izip
path_to_augur = './' + '/'.join(sys.argv[0].split('/')[:-2])
std_outgroup_file_blast = path_to_augur+'/source-data/outgroups.fasta'
std_outgroup_file_nuc = path_to_augur+'/source-data/outgroups_nucleotides_unspliced.fasta'
no_raxml_threshold = 15000
virus_config.update({
# data source and sequence parsing/cleaning/processing
'fasta_fields':{0:'strain', 1:'isolate_id', 2:'date', 3:'subtype', 4:'country', 5:'region', 7:'host', 6:'passage'},
'cds':[0,None], # define the HA start i n 0 numbering
'verbose':3
})
def get_date(strain):
from datetime import datetime
date_str = strain.split('|')[2]
try:
collection_date = datetime.strptime(date_str, '%Y-%m-%d')
return collection_date.strftime('%Y-%m-%d')
except:
collection_date = datetime.strptime(date_str[:4], '%Y')
return collection_date.strftime('%Y-%m-%d')
class mutation_tree(process, flu_filter, tree_refine, virus_clean):
"""docstring for mutation_tree"""
receptor_binding_sites = [159,169,170,172,173,203,207]
'''
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H7',
'alignment_file':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H7_gisaid_epiflu_sequence.fasta',
'outgroup':'A/equine/Prague/2/1956',
#'force_include':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H7_HI_strains.txt',
'force_include_all':False,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the translation start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
''''clade_designations': {
'2': [('HA1', 48,'K'), ('HA1', 108, 'A'), ('HA1', 150, 'S')],
'3': [('HA1', 48,'R'), ('HA1', 108, 'P'), ('HA1', 150, 'I')],
'3a': [('HA1', 37,'A'), ('HA1', 298, 'E'), ('HA1', 48,'R'), ('HA1', 105, 'P'), ('HA1', 150, 'I')],
'172Q': [('HA1', 48,'R'), ('HA1', 108, 'P'), ('HA1', 150, 'I'), ('HA1', 116, 'K'), ('HA1', 172, 'Q')]
},'''
'auspice_prefix':'H7_',
#'HI_fname':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H7_HI_titers.txt',
'html_vars': {'coloring': 'region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': ''},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
'layout':'auspice',
})
class H7_filter(flu_filter):
epitope_mask = np.fromstring(sp*"0"+"0000000000000000000000000000000000000000000011111011011001010011000100000001001011110011100110101000001100000100000001000110101011111101011010111110001010011111000101011011111111010010001111101110111001010001110011111111000000111110000000101010101110000000000011100100000001011011100000000000001001011000110111111000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000", dtype='S1')
receptor_binding_sites = map(lambda x:x+sp-1, [145, 155, 156, 158, 159, 189, 193])
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H3N2',
'alignment_file':'data/H3N2_gisaid_epiflu_sequence.fasta',
'outgroup':'A/Beijing/32/1992',
#'force_include':'source-data/HI_strains.txt',
'force_include_all':False,
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA1 start i n 0 numbering
'n_iqd':6,
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at HA1 start, adding sp to obtain numbering from methionine
'clade_designations': { "3c3.a":[(128+sp,'A'), (142+sp,'G'), (159+sp,'S')],
"3c3": [(128+sp,'A'), (142+sp,'G'), (159+sp,'F')],
"3c2.a": [(144+sp,'S'), (159+sp,'Y'), (225+sp,'D'), (311+sp,'H'), (489+sp,'N')],
"3c2": [(144+sp,'N'), (159+sp,'F'), (225+sp,'N'), (489+sp,'N'), (142+sp, 'R')],
"3c3.b": [(83+sp,'R'), (261+sp,'Q'), (62+sp,'K'), (122+sp,'D')]
},
'html_vars': {'coloring': 'ep, ne, rb, lbi, dfreq, region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '3c2.a, 3c3.a'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
})
class H3N2_filter(flu_filter):
def __init__(self,min_length = 987, **kwargs):
receptor_binding_sites = [159,169,170,172,173,203,207]
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H10',
'alignment_file':'/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/src/data/H10_gisaid_epiflu_sequence.fasta',
'outgroup':'A/mallard-duck/ALB/302/1977',
#'force_include':'H10_HI_strains.txt',
'force_include_all':True,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
''''clade_designations': {
'1A': [('HA1', 75,'K'), ('HA1', 58, 'L'), ('HA1', 165, 'K')],
'1B': [('HA1', 75,'K'), ('HA1', 58, 'P'), ('HA1', 165, 'K')],
'117V': [('HA1', 75,'K'), ('HA1', 58, 'L'), ('HA1', 165, 'K'), ('HA1', 129, 'D'), ('HA1', 117, 'V')]
},'''
'auspice_prefix':'H10_',
'HI_fname':'H10_HI_titers.txt',
'html_vars': {'coloring': 'lbi, dfreq, region, date, cHI, HI_dist',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '1A, 1B'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
'layout':'auspice',
})
class H10_filter(flu_filter):
def __init__(self,min_length = 0, **kwargs):
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus': 'Yam',
'alignment_file': 'data/yam.fasta',
'outgroup': 'B/Singapore/11/94',
'force_include': 'data/yam_hi_strains.tsv',
'force_include_all': False,
'date_spec': 'year',
'max_global':
True, # sample as evenly as possible from different geographic regions
'cds': [11, None], # define the translation start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'clade_designations': {
'2': [('HA1', 48, 'K'), ('HA1', 108, 'A'), ('HA1', 150, 'S')],
'3': [('HA1', 48, 'R'), ('HA1', 108, 'P'), ('HA1', 150, 'I')],
'3a': [('HA1', 37, 'A'), ('HA1', 298, 'E'), ('HA1', 48, 'R'),
('HA1', 105, 'P'), ('HA1', 150, 'I')],
'172Q': [('HA1', 48, 'R'), ('HA1', 108, 'P'), ('HA1', 150, 'I'),
('HA1', 116, 'K'), ('HA1', 172, 'Q')]
},
'HI_fname': 'data/yam_hi_titers.tsv',
'html_vars': {
'coloring': 'lbi, dfreq, region, date, cHI, HI_dist',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '2, 3, 3a'
},
'js_vars': {
'LBItau': 0.0005,
'LBItime_window': 0.5,
'dfreq_dn': 2
},
'layout': 'auspice',
})
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H9',
'alignment_file':'/Users/yujiazhou/Documents/FluProject/augur/src/data/H9_gisaid_epiflu_sequence.fasta',
'outgroup':'A/duck/HongKong/147/1977',
#'force_include':'/Users/yujiazhou/Documents/FluProject/augur/src/data/H9_HI_strains.txt',
'force_include_all':False,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
#'max_globalh':True,
'cds':[0,None], # define the HA1 start i n 0 numbering
'n_iqd':5,
'min_mutation_frequency':0.01,
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at HA1 start, adding sp to obtain numbering from methionine
''''clade_designations': { "Y439":[('HA1',122,'F'), ('HA1',353,'P')],
"Korea":[('HA1',107,'M'), ('HA1',122,'F'), ('HA1',127,'R'), ('HA1',130,'K'), ('HA1',132,'L'), ('HA1',134,'L'), ('HA1',179,'D'), ('HA1',212,'I'), ('HA1',299,'T'), ('HA1',353,'P'), ('HA1',473,'K')],
"G1":[('HA1',353,'P'), ('HA1',473,'K')],
"Ck-Bei":[('HA1',107,'M'), ('HA1',299,'T'), ('HA1',473,'K')],
"G9":[('HA1',107,'M'), ('HA1',299,'T'), ('HA1',473,'K')],
"Y280":[('HA1',299,'T'), ('HA1',473,'K')]
},'''
#'epiope_masks_fname':'/Users/yujiazhou/Documents/FluProject/augur/source-data/H9_epitope_masks.tsv',
#'epitope_mask_version':'wolf',
#'HI_fname':'/Users/yujiazhou/Documents/FluProject/augur/src/data/H9_HI_titers.txt',
'auspice_prefix':'H9_',
'html_vars': {'coloring': 'ep, ne, rb, lbi, dfreq, region, date, cHI, host',
'gtplaceholder': 'HA1 positions...',
'freqdefault': 'Y439, Korea, G1, Ck-Bei, G9, Y280'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
'excluded_tables': ['NIMR_Sep2012_08.csv'], #, 'nimr-sep-2010-table8', 'nimr-sep-2010-table8','NIMR_Sep2012_11.csv'],
'layout':'auspice',
'min_aamuts': 1,
# 'predictors': ['dfreq', 'cHI'] # estimate
'predictors': { 'dfreq': [2.50, 2.84], 'cHI': [1.68, 0.45] } # fix predictor: [value, std deviation]
})
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H3N2',
'alignment_file':'data/h3n2.fasta',
'outgroup':'A/Beijing/32/1992',
'force_include':'data/h3n2_hi_strains.tsv',
'force_include_all':False,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA1 start i n 0 numbering
'n_iqd':5,
'min_mutation_frequency':0.01,
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at HA1 start, adding sp to obtain numbering from methionine
'clade_designations': { "3c3.a":[('HA1',128,'A'), ('HA1',142,'G'), ('HA1',159,'S')],
"3c3": [('HA1',128,'A'), ('HA1',142,'G'), ('HA1',159,'F')],
"3c2.a": [('HA1',144,'S'), ('HA1',159,'Y'), ('HA1',225,'D'), ('HA1',311,'H'), ('HA2',160,'N')],
"171K": [('HA1',144,'S'), ('HA1',159,'Y'), ('HA1',171,'K'), ('HA1',225,'D'), ('HA1',311,'H'), ('HA2',77,'V'), ('HA2',155,'E'), ('HA2',160,'N')],
"3c2": [('HA1',144,'N'), ('HA1',159,'F'), ('HA1',225,'N'), ('HA2',160,'N'), ('HA1',142,'R')],
"3c3.b": [('HA1',83,'R'), ('HA1',261,'Q'), ('HA1',62,'K'), ('HA1',122,'D')]
},
'epitope_masks_fname':'source-data/H3N2_epitope_masks.tsv',
'epitope_mask_version':'wolf',
'HI_fname':'data/h3n2_hi_titers.tsv',
'html_vars': {'coloring': 'ep, ne, rb, lbi, dfreq, region, date, cHI, HI_dist',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '3c2.a, 3c3.a, 3c3.b'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
'excluded_tables': ['NIMR_Sep2012_08.csv'], #, 'nimr-sep-2010-table8', 'nimr-sep-2010-table8','NIMR_Sep2012_11.csv'],
'layout':'auspice',
'min_aamuts': 1,
# 'predictors': ['dfreq', 'cHI'] # estimate
'predictors': { 'dfreq': [2.50, 2.84], 'cHI': [1.68, 0.45] } # fix predictor: [value, std deviation]
})
170,173,174,177,206,207,210,211,212,214,216, #Sb
183,187,191,196,221,225,254,258,288, #Ca1
154,157,158,159,161,163,238,239,242,243, #Ca2
87, 88, 90, 91, 92, 95, 96, 98, 99, 100, 132, 139 #Cb
]
else '0' for pos in xrange(1,1725)])
receptor_binding_sites = [x-1 for x in [159,169,170,172,173,203,207]]
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H1N1',
'alignment_file':'data/H1N1_gisaid_epiflu_sequence.fasta',
'outgroup':'A/Tokyo/1/51',
'time_interval':(1990,2010),
#'force_include':'source-data/HI_strains.txt',
'force_include_all':False,
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
'clade_designations': {},
'auspice_prefix':'H1N1_',
})
class H1N1_filter(flu_filter):
def __init__(self,min_length = 987, **kwargs):
'''
parameters
min_length -- minimal length for a sequence to be acceptable
'''
flu_filter.__init__(self, **kwargs)
receptor_binding_sites = [159,169,170,172,173,203,207]
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'Vic',
'alignment_file':'data/vic.fasta',
'outgroup':'B/HongKong/02/1993',
'force_include':'data/vic_hi_strains.tsv',
'force_include_all':False,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'clade_designations': {
'1A': [('HA1', 75,'K'), ('HA1', 58, 'L'), ('HA1', 165, 'K')],
'1B': [('HA1', 75,'K'), ('HA1', 58, 'P'), ('HA1', 165, 'K')],
'117V': [('HA1', 75,'K'), ('HA1', 58, 'L'), ('HA1', 165, 'K'), ('HA1', 129, 'D'), ('HA1', 117, 'V')]
},
'HI_fname':'data/vic_hi_titers.tsv',
'html_vars': {'coloring': 'lbi, dfreq, region, date, cHI, HI_dist',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '1A, 1B'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
'layout':'auspice',
})
class BVic_filter(flu_filter):
def __init__(self,min_length = 987, **kwargs):
from tree_refine import tree_refine
from virus_clean import virus_clean
from virus_filter import flu_filter
from collections import defaultdict
from process import process, virus_config
from Bio import SeqIO
from Bio.Seq import Seq
from Bio.Align import MultipleSeqAlignment
import numpy as np
from itertools import izip
std_outgroup_file = '/Users/yujiazhou/Documents/nextflu/H9_nextflu-master/augur/source-data/outgroups.fasta'
virus_config.update({
# data source and sequence parsing/cleaning/processing
'fasta_fields':{0:'strain', 1:'date', 2:'isolate_id', 3:'passage', 4:'subtype', 5:'ori_lab', 6:'sub_lab', 7:'submitter'},
'cds':[0,None], # define the HA start i n 0 numbering
'auspice_prefix':'H4_',
'verbose':3
})
class mutation_tree(process, flu_filter, tree_refine, virus_clean):
"""docstring for mutation_tree"""
def __init__(self, aln_fname, outgroup, outdir = './', formats = ['pdf','svg','png'], verbose = 0, **kwargs):
process.__init__(self, **kwargs)
flu_filter.__init__(self, alignment_file = aln_fname, **kwargs)
tree_refine.__init__(self, **kwargs)
virus_clean.__init__(self, **kwargs)
self.verbose = verbose
self.formats = formats
self.outdir = outdir.rstrip('/')+'/'
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'H1N1pdm',
'alignment_file':'data/H1N1pdm_gisaid_epiflu_sequence.fasta',
'outgroup':'A/Swine/Indiana/P12439/00',
'force_include':'data/H1N1pdm_HI_strains.txt',
'force_include_all':False,
'date_spec':'year',
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[0,None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'clade_designations': {
'2': [('HA1', 125, 'N'), ('HA1', 134 ,'A'), ('HA1', 183, 'S'), ('HA1', 31,'D'), ('HA1', 172,'N'), ('HA1', 186,'T')],
'3': [('HA1', 134 ,'T'), ('HA1', 183, 'P')],
'4': [('HA1', 125, 'D'), ('HA1', 134 ,'A'), ('HA1', 183, 'S')],
'5': [('HA1', 87, 'N'), ('HA1', 205, 'K'), ('HA1', 216, 'V'), ('HA1', 149, 'L')],
'6': [('HA1', 185,'T'), ('HA1', 97, 'N'), ('HA1', 197, 'A')],
'6c':[('HA1', 234,'I'), ('HA1', 97, 'N'), ('HA1', 197, 'A'), ('HA1', 283,'E')],
'6b':[('HA1', 163,'Q'), ('HA1', 256, 'T'), ('HA1', 197, 'A'), ('HA1', 283,'E')],
'7': [('HA1', 143,'G'), ('HA1', 97, 'D'), ('HA1', 197, 'T')],
'8': [('HA1', 186,'T'), ('HA1', 272,'A')],
'6b.1':[('HA1', 163,'Q'), ('HA1', 256, 'T'), ('HA1', 197, 'A'), ('HA1', 283, 'E'), ('SigPep', 13, 'T'), ('HA1', 84, 'N'), ('HA1', 162, 'N')],
'6b.2':[('HA1', 163,'Q'), ('HA1', 256, 'T'), ('HA1', 197, 'A'), ('HA1', 283, 'E'), ('HA2', 164, 'G'), ('HA1', 152, 'T'), ('HA2', 174, 'E')]
},
'HI_fname':'data/H1N1pdm_HI_titers.txt',
'html_vars': {'coloring': 'ep, ne, rb, lbi, dfreq, region, date, cHI, HI_dist',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '6b, 6c'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
'layout':'auspice',
})
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':
'H9',
'alignment_file':
'/Users/yujiazhou/Documents/FluProject/augur/src/data/H9_gisaid_epiflu_sequence.fasta',
'outgroup':
'A/duck/HongKong/147/1977',
#'force_include':'/Users/yujiazhou/Documents/FluProject/augur/src/data/H9_HI_strains.txt',
'force_include_all':
False,
'date_spec':
'year',
'max_global':
True, # sample as evenly as possible from different geographic regions
#'max_globalh':True,
'cds': [0, None], # define the HA1 start i n 0 numbering
'n_iqd':
5,
'min_mutation_frequency':
0.01,
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at HA1 start, adding sp to obtain numbering from methionine
''''clade_designations': { "Y439":[('HA1',122,'F'), ('HA1',353,'P')],
"Korea":[('HA1',107,'M'), ('HA1',122,'F'), ('HA1',127,'R'), ('HA1',130,'K'), ('HA1',132,'L'), ('HA1',134,'L'), ('HA1',179,'D'), ('HA1',212,'I'), ('HA1',299,'T'), ('HA1',353,'P'), ('HA1',473,'K')],
"G1":[('HA1',353,'P'), ('HA1',473,'K')],
"Ck-Bei":[('HA1',107,'M'), ('HA1',299,'T'), ('HA1',473,'K')],
"G9":[('HA1',107,'M'), ('HA1',299,'T'), ('HA1',473,'K')],
"Y280":[('HA1',299,'T'), ('HA1',473,'K')]
},'''
#'epiope_masks_fname':'/Users/yujiazhou/Documents/FluProject/augur/source-data/H9_epitope_masks.tsv',
#'epitope_mask_version':'wolf',
#'HI_fname':'/Users/yujiazhou/Documents/FluProject/augur/src/data/H9_HI_titers.txt',
'auspice_prefix':
'H9_',
'html_vars': {
'coloring': 'ep, ne, rb, lbi, dfreq, region, date, cHI, host',
'gtplaceholder': 'HA1 positions...',
'freqdefault': 'Y439, Korea, G1, Ck-Bei, G9, Y280'
},
'js_vars': {
'LBItau': 0.0005,
'LBItime_window': 0.5,
'dfreq_dn': 2
},
'excluded_tables': [
'NIMR_Sep2012_08.csv'
], #, 'nimr-sep-2010-table8', 'nimr-sep-2010-table8','NIMR_Sep2012_11.csv'],
'layout':
'auspice',
'min_aamuts':
1,
# 'predictors': ['dfreq', 'cHI'] # estimate
'predictors': {
'dfreq': [2.50, 2.84],
'cHI': [1.68, 0.45]
} # fix predictor: [value, std deviation]
})
else '0' for pos in xrange(1,1725)])
receptor_binding_sites = [159,169,170,172,173,203,207]
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus':'Yam',
'alignment_file':'data/Yam_gisaid_epiflu_sequence.fasta',
'outgroup':'B/Singapore/11/94',
#'force_include':'source-data/HI_strains.txt',
'force_include_all':False,
'max_global':True, # sample as evenly as possible from different geographic regions
'cds':[11,None], # define the translation start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'clade_designations': {
'2': [(63,'K'), (123, 'A'), (165, 'S')],
'3': [(63,'R'), (123, 'P'), (165, 'I')],
'3a': [(52,'A'), (313, 'E'), (63,'R'), (123, 'P'), (165, 'I')],
},
'html_vars': {'coloring': 'lbi, dfreq, region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '2, 3, 3a'},
'js_vars': {'LBItau': 0.0005, 'LBItime_window': 0.5, 'dfreq_dn':2},
})
class BYam_filter(flu_filter):
def __init__(self,min_length = 987, **kwargs):
'''
virus_config.update({
# data source and sequence parsing/cleaning/processing
'virus': 'H1N1pdm',
'alignment_file': 'data/H1N1pdm_gisaid_epiflu_sequence.fasta',
'outgroup': 'A/Swine/Indiana/P12439/00',
#'force_include':'source-data/HI_strains.txt',
'force_include_all': False,
'max_global':
True, # sample as evenly as possible from different geographic regions
'cds': [0, None], # define the HA start i n 0 numbering
# define relevant clades in canonical HA1 numbering (+1)
# numbering starting at methionine including the signal peptide
'clade_designations': {
'2': [('HA1', 125, 'N'), ('HA1', 134, 'A'), ('HA1', 183, 'S'),
('HA1', 31, 'D'), ('HA1', 172, 'N'), ('HA1', 186, 'T')],
'3': [('HA1', 134, 'T'), ('HA1', 183, 'P')],
'4': [('HA1', 125, 'D'), ('HA1', 134, 'A'), ('HA1', 183, 'S')],
'5': [('HA1', 87, 'N'), ('HA1', 205, 'K'), ('HA1', 216, 'V'),
('HA1', 149, 'L')],
'6': [('HA1', 185, 'T'), ('HA1', 97, 'N'), ('HA1', 197, 'A')],
'6c': [('HA1', 234, 'I'), ('HA1', 97, 'N'), ('HA1', 197, 'A'),
('HA1', 283, 'E')],
'6b': [('HA1', 163, 'Q'), ('HA1', 256, 'T'), ('HA1', 197, 'A'),
('HA1', 283, 'E')],
'7': [('HA1', 143, 'G'), ('HA1', 97, 'D'), ('HA1', 197, 'T')],
'8': [('HA1', 186, 'T'), ('HA1', 272, 'A')],
},
'html_vars': {
'coloring': 'ep, ne, rb, lbi, dfreq, region, date',
'gtplaceholder': 'HA1 positions...',
'freqdefault': '6b, 6c'
},
'js_vars': {
'LBItau': 0.0005,
'LBItime_window': 0.5,
'dfreq_dn': 2
},
})
