def make_config(params):
return {
"dir": "ebola",
"file_prefix": "ebola",
"input_paths": ["../../fauna/data/ebola.fasta"],
"header_fields": {0:'strain', 2:'accession', 3:'date', 4:'region', 5:'country', 6:'division', 8:'db', 10:'authors', 11:'url'},
"filters": (
("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
("Restrict Date Range", lambda s: s.attributes['date'] >= datetime(2012,01,1).date()),
("Restrict Date Range", lambda s: s.attributes['date'] <= datetime(2018,01,1).date()),
),
"subsample": {
"category": lambda x:(x.attributes['region'], x.attributes['date'].year, x.attributes['date'].month),
"threshold": params.viruses_per_month,
"priority": lambda x:x.id in forced_strains
},
"colors": ["country", "division"], # essential. Maybe False.
"color_defs": ["./colors.tsv"],
"lat_longs": ["country", "division"], # essential. Maybe False.
"reference": {
"path": "metadata/ebola_outgroup.gb",
"metadata": {
'strain': "reference", "accession": "KR075003", "date": "2014-XX-XX",
'host': "human", 'country': "Liberia"
},
"include": 0,
"genes": ['NP', 'VP35', 'VP40', 'GP', 'sGP', 'VP30', 'VP24', 'L']
}
}
def make_config(serotype, params):
if params.file_prefix is not None:
file_prefix = params.file_prefix
else:
file_prefix = "dengue_%s" % serotype
if params.sequences is not None:
input_paths = [params.sequences]
elif os.path.isfile("../../../fauna/data/dengue_%s.fasta"%serotype): #is file: # Look for a serotype-specific fasta
input_paths = ["../../../fauna/data/dengue_%s.fasta"%serotype]
else: # If it doesn't exist, try to pull serotype-specific sequences out of the all-serotype fasta (warn the user of this behavior)
input_paths = [select_serotype('../../../fauna/data/dengue_all.fasta', '../../../fauna/data/', serotype)]
print('WARNING: Did not find serotype-specific fasta file.\nPulled sequences with serotype %s from all-serotype fasta file %s\nWrote these to file %s'%(serotype, '../fauna/data/dengue.fasta', input_paths))
years_back = params.years_back
time_interval = [datetime.today().date(), (datetime.today() - timedelta(days=365.25 * years_back)).date()]
if params.titers is not None:
if not os.path.isfile(params.titers):
params.titers = '../../../fauna/data/%s'%params.titers
titer_values, strains, sources = TiterCollection.load_from_file(params.titers)
else:
titer_values, strains, sources = None, None, None
force_include = sanofi_vaccine_strains.values()
config = {
"dir": "dengue",
"lineage": serotype,
"title": "Real-time tracking of dengue evolution",
"maintainer": ["Sidney Bell", "http://bedford.io/team/sidney-bell/"],
"file_prefix": file_prefix,
"input_paths": input_paths,
"header_fields": {0:'strain', 1:'accession', 2:'date', 3:'region', 4:'country',
5:'division', 6: 'location', 7: 'authors', 8: 'url'},
"filters": (("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
("Bad Region", lambda s: any([
s.attributes['region'] not in ['', ' ', '?'],
s.attributes['accession'] in force_include,
s.attributes['strain'] in force_include
]))),
"subsample": dengue_subsampling(params, years_back, titer_values,
force_include),
"add_urls": {
"prefix": "https://www.ncbi.nlm.nih.gov/nuccore/%s",
"attr": "accession" },
"colors": ["authors", "region", "country"],
"lat_longs": ["region", "country"],
"auspice_filters": ["authors", "region", "country"],
"reference": references[serotype],
"time_interval": time_interval,
"titers": titer_values,
"strains": params.strains,
"sources": sources
}
return config
def make_config(serotype, params):
config = {
"dir":
"dengue",
"file_prefix":
"dengue_%s" % serotype,
"input_paths":
None,
"header_fields": {
0: 'strain',
1: 'accession',
2: 'date',
3: 'region',
4: 'country',
5: 'division',
6: 'location',
7: 'authors',
8: 'url'
},
"filters": (
("Dropped Strains",
lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
# ("Sequence Length", lambda s: len(s.seq)>=5000),
("Bad Region", lambda s: s.attributes['region'] not in ['', '?'])),
### Make subsampling serotype specific?? Probably not?
"subsample": {
"category":
lambda x: (x.attributes['region'], x.attributes['date'].year, x.
attributes['date'].month),
"threshold":
3
},
"add_urls": {
"prefix": "https://www.ncbi.nlm.nih.gov/nuccore/%s",
"attr": "accession"
},
"colors": ["region"],
"color_defs": ["./colors.tsv"],
"lat_longs": ["region"],
"lat_long_defs":
'../../fauna/source-data/geo_lat_long.tsv',
"reference":
references[serotype]
}
if os.path.isfile(
"../../fauna/data/dengue_%s.fasta" %
serotype): #is file: # Look for a serotype-specific fasta
config["input_paths"] = ["../../fauna/data/dengue_%s.fasta" % serotype]
else: # If it doesn't exist, try to pull serotype-specific sequences out of the all-serotype fasta (warn the user of this behavior)
config["input_paths"] = select_serotype(
'../fauna/data/dengue_all.fasta', '../fauna/data/', serotype)
print(
'WARNING: Did not find serotype-specific fasta file.\nPulled sequences with serotype %s from all-serotype fasta file %s\nWrote these to file %s'
% (serotype, '../fauna/data/dengue.fasta', config["input_paths"]))
return config
def make_config(serotype, params):
if params.file_prefix is not None:
file_prefix = params.file_prefix
else:
file_prefix = "dengue_%s" % serotype
if params.sequences is not None:
input_paths = [params.sequences]
elif os.path.isfile("../../fauna/data/dengue_%s.fasta"%serotype): #is file: # Look for a serotype-specific fasta
input_paths = ["../../fauna/data/dengue_%s.fasta"%serotype]
else: # If it doesn't exist, try to pull serotype-specific sequences out of the all-serotype fasta (warn the user of this behavior)
input_paths = [select_serotype('../fauna/data/dengue_all.fasta', '../fauna/data/', serotype)]
print('WARNING: Did not find serotype-specific fasta file.\nPulled sequences with serotype %s from all-serotype fasta file %s\nWrote these to file %s'%(serotype, '../fauna/data/dengue.fasta', input_paths))
years_back = params.years_back
time_interval = [datetime.today().date(), (datetime.today() - timedelta(days=365.25 * years_back)).date()]
if params.titers is not None:
if not os.path.isfile(params.titers):
params.titers = '../../fauna/data/%s'%params.titers
titer_values, strains, sources = TiterModel.load_from_file(params.titers)
else:
titer_values, strains, sources = None, None, None
config = {
"dir": "dengue",
"lineage": serotype,
"title": "Genomic Epidemiology of Dengue Virus",
"maintainer": ["@sidneymbell", "https://twitter.com/sidneymbell"],
"file_prefix": file_prefix,
"input_paths": input_paths,
"header_fields": {0:'strain', 1:'accession', 2:'date', 3:'region', 4:'country',
5:'division', 6: 'location', 7: 'authors', 8: 'url'},
"filters": (("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
# ("Sequence Length", lambda s: len(s.seq)>=5000),
("Bad Region", lambda s: s.attributes['region'] not in ['', ' ', '?'])),
"subsample": dengue_subsampling(params, years_back, titer_values),
"add_urls": {
"prefix": "https://www.ncbi.nlm.nih.gov/nuccore/%s",
"attr": "accession" },
"colors": ["region"],
"color_defs": "./colors.tsv",
"lat_longs": ["region"],
"lat_long_defs": '../../fauna/source-data/geo_lat_long.tsv',
"reference": references[serotype],
"time_interval": time_interval,
"titers": titer_values,
"sources": sources
}
return config
def make_config(params):
dropped_strains = [
"temara.MOR/24.03", "Mvs/Toulon.FRA/08.07" # clock is off
]
filters = (
("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
("Restrict Date Range", lambda s: s.attributes['date'] >= datetime(1950,01,1).date()),
("Restrict Date Range", lambda s: s.attributes['date'] <= datetime(2020,01,1).date()),
("Sequence Length", lambda s: len(s.seq)>=5000),
("Number Ns", lambda s: s.seq.count('N')<=3000)
)
config = {
"dir": "measles",
"file_prefix": "measles",
"title": "Real-time tracking of measles virus evolution",
"maintainer": ["Trevor Bedford", "http://bedford.io/team/trevor-bedford/"],
"input_paths": ["../../../fauna/data/measles.fasta"],
"header_fields": {0:'strain', 2:'accession', 3:'date', 4:'region', 5:'country',
6:'division', 8:'db', 10:'authors', 11:'url', 12:'title',
13: 'journal', 14: 'paper_url'},
"filters": filters,
"subsample": {
"threshold": params.viruses_per_month,
"category": lambda x:(x.attributes['date'].year, x.attributes['date'].month, x.attributes['country'])
},
"colors": ["authors", "country", "region"],
"color_defs": ["./colors.tsv"],
"lat_longs": ["country", "region"],
"auspice_filters": ["authors", "region", "country"],
"reference": {
"path": "measles-reference.gb",
"metadata": {
'strain': "Ichinose-B95a", "accession": "NC_001498.1", "date": "XXXX-XX-XX",
'host': "human", 'country': "Unknown", 'region': "Unknown"
},
"include": 0,
"genes": ['N', 'P', 'V', 'C', 'M', 'F', 'H', 'L']
}
}
return config
"input_paths": ["./data/mahar_RHDV.edit.fasta"],
#>AUS/ACT/BLMT-3/2015|blmt-3|RHDV|MF421563.1|RHDV1_G2|2015-06-18|Australia|ACT|Mahar et al|Monitoring the init
"header_fields": {
0: 'strain',
1: 'isolate',
4: 'rhdv_strain',
5: 'date',
6: 'country',
7: 'state',
8: 'authors',
10: 'journal',
9: 'title'
},
"filters":
(("Dropped Strains",
lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
# ("Restrict Date Range", lambda s: s.attributes['date'] >= datetime(2012,01,1).date()),
# ("Restrict Date Range", lambda s: s.attributes['date'] <= datetime(2018,01,1).date()),
#("Sequence Length", lambda s: len(s.seq)>=10000),
),
"subsample": {
"category":
lambda x: (x.attributes['date'].year, x.attributes['date'].month),
},
"colors": ["state", "authors", "rhdv_strain"],
# "color_defs": ["./colors.tsv"],
"lat_longs": ["isolate"],
"lat_long_defs":
"./RHDV2_coords.edit.txt",
"auspice_filters": ["state", "authors", "rhdv_strain"],
"reference": {
def make_config(serotype, params):
if params.file_prefix is not None:
file_prefix = params.file_prefix
else:
file_prefix = "dengue_%s" % serotype
if params.sequences is not None:
input_paths = [params.sequences]
elif os.path.isfile(
"../../../fauna/data/dengue_%s.fasta" %
serotype): #is file: # Look for a serotype-specific fasta
input_paths = ["../../../fauna/data/dengue_%s.fasta" % serotype]
else: # If it doesn't exist, try to pull serotype-specific sequences out of the all-serotype fasta (warn the user of this behavior)
input_paths = [
select_serotype('../../../fauna/data/dengue_all.fasta',
'../../../fauna/data/', serotype)
]
print(
'WARNING: Did not find serotype-specific fasta file.\nPulled sequences with serotype %s from all-serotype fasta file %s\nWrote these to file %s'
% (serotype, '../fauna/data/dengue.fasta', input_paths))
years_back = params.years_back
time_interval = [
datetime.today().date(),
(datetime.today() - timedelta(days=365.25 * years_back)).date()
]
if params.titers is not None:
if not os.path.isfile(params.titers):
params.titers = '../../../fauna/data/%s' % params.titers
titer_values, strains, sources = TiterCollection.load_from_file(
params.titers)
else:
titer_values, strains, sources = None, None, None
force_include = sanofi_vaccine_strains.values()
config = {
"dir":
"dengue",
"lineage":
serotype,
"title":
"Real-time tracking of dengue evolution",
"maintainer": ["Sidney Bell", "http://bedford.io/team/sidney-bell/"],
"file_prefix":
file_prefix,
"input_paths":
input_paths,
"header_fields": {
0: 'strain',
1: 'accession',
2: 'date',
3: 'region',
4: 'country',
5: 'division',
6: 'location',
7: 'authors',
8: 'url'
},
"filters":
(("Dropped Strains",
lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
("Bad Region", lambda s: any([
s.attributes['region'] not in ['', ' ', '?'], s.attributes[
'accession'] in force_include, s.attributes['strain'] in
force_include
]))),
"subsample":
dengue_subsampling(params, years_back, titer_values, force_include),
"add_urls": {
"prefix": "https://www.ncbi.nlm.nih.gov/nuccore/%s",
"attr": "accession"
},
"colors": ["authors", "region", "country"],
"lat_longs": ["region", "country"],
"auspice_filters": ["authors", "region", "country"],
"reference":
references[serotype],
"time_interval":
time_interval,
"titers":
titer_values,
"strains":
params.strains,
"sources":
sources
}
return config
def make_config(lineage, resolution, params):
years_back = int(re.search("(\d+)", resolution).groups()[0])
time_interval = [
datetime.strptime(x, '%Y-%m-%d').date() for x in [
"{:%Y-%m-%d}".format(datetime.today()), "{:%Y-%m-%d}".format(
datetime.today() - timedelta(days=365.25 * years_back))
]
]
reference_cutoff = date(year=time_interval[0].year - 3, month=1, day=1)
return {
"dir":
"flu",
"file_prefix":
"flu_{}".format(lineage),
"segments":
params.segments,
"resolution":
resolution,
"lineage":
lineage,
"input_paths": [
"../../fauna/data/{}_{}.fasta".format(lineage, segment)
for segment in params.segments
],
# 0 1 2 3 4 5 6 7 8 9 10 11
# >A/Galicia/RR9542/2012|flu|EPI376225|2012-02-23|europe|spain|galicia|galicia|unpassaged|instituto_de_salud_carlos_iii|47y|female
"header_fields": {
0: 'strain',
2: 'isolate_id',
3: 'date',
4: 'region',
5: 'country',
6: 'division',
8: 'passage',
9: 'lab',
10: 'age',
11: 'gender'
},
"filters": (
("Time Interval", lambda s:
(s.attributes['date'] <= time_interval[0] and s.attributes['date']
>= time_interval[1]) or (s.name in reference_viruses[
lineage] and s.attributes['date'] > reference_cutoff)),
("Sequence Length", lambda s: len(s.seq) >= 900),
# what's the order of evaluation here I wonder?
("Dropped Strains",
lambda s: s.id not in [fix_names(x) for x in outliers[lineage]]),
("Bad geo info", lambda s: s.attributes["country"] != "?" and s.
attributes["region"] != "?"),
),
"subsample":
flu_subsampling(params, years_back,
"../../fauna/data/{}_crick_hi".format(lineage)),
"colors": ["region"],
"color_defs": ["colors.flu.tsv"],
"lat_longs": ["country", "region"],
"lat_long_defs":
'../../fauna/source-data/geo_lat_long.tsv',
"references":
{seg: reference_maps[lineage][seg]
for seg in params.segments},
"regions":
regions,
"time_interval":
time_interval,
}
def make_config(lineage, resolution, params):
years_back = int(re.search("(\d+)", resolution).groups()[0])
if params.time_interval:
time_interval = sorted([datetime.strptime(x, '%Y-%m-%d').date() for x in params.time_interval], reverse=True)
else:
time_interval = [datetime.today().date(), (datetime.today() - timedelta(days=365.25 * years_back)).date()]
reference_cutoff = date(year = time_interval[1].year - 4, month=1, day=1)
# Load and prepare outliers for the given lineage.
with open("metadata/%s_outliers.txt" % lineage, "r") as fh:
outliers = [outlier.rstrip() for outlier in fh]
fixed_outliers = [fix_names(x) for x in outliers]
fixed_references = [fix_names(x) for x in reference_viruses[lineage]]
if params.titers is not None:
titer_values, strains, sources = TiterCollection.load_from_file(params.titers)
else:
titer_values = None
if params.sequences is not None:
input_paths = params.sequences
else:
input_paths = ["../../../fauna/data/{}_{}.fasta".format(lineage, segment) for segment in params.segments]
if params.file_prefix:
file_prefix = params.file_prefix
else:
file_prefix = "flu_seasonal_{}_{}_{}".format(lineage, params.segments[0], resolution) # flu_seasonal_h3n2_ha_6y
config = {
"dir": "flu",
"file_prefix": file_prefix,
"title": make_title(lineage, resolution),
"maintainer": ["Trevor Bedford and Barney Potter", "http://bedford.io/"],
"auspice_filters": ["clade_membership", "region", "country"],
"segments": params.segments,
"ensure_all_segments": params.ensure_all_segments,
"lineage": lineage,
"resolution": resolution,
"input_paths": input_paths,
# 0 1 2 3 4 5 6 7 8 9 10 11
# >A/Galicia/RR9542/2012|flu|EPI376225|2012-02-23|europe|spain|galicia|galicia|unpassaged|instituto_de_salud_carlos_iii|47y|female
"header_fields": {
0:'strain', 2:'isolate_id', 3:'date',
4:'region', 5:'country', 6:'division',
8:'passage', 9:'authors', 10:'age',
11:'gender'
},
"filters": (
("Time Interval", lambda s:
(s.attributes['date']<=time_interval[0] and s.attributes['date']>=time_interval[1]) or
(s.name in fixed_references and s.attributes['date']>reference_cutoff)
),
("invalid chars", lambda s: sum([s.seq.count(c) for c in "EFIJKLOPQXYZ"])==0),
("Sequence Length", lambda s: len(s.seq)>=900),
# what's the order of evaluation here I wonder?
("Dropped Strains", lambda s: s.id not in fixed_outliers),
("Bad geo info", lambda s: s.attributes["country"]!= "?" and s.attributes["region"]!= "?" ),
),
"subsample": flu_subsampling(params, years_back, titer_values),
"colors": ["region", "country"],
"color_defs": ["colors.tsv"],
"lat_longs": ["country", "region"],
"references": {seg:reference_maps[lineage][seg] for seg in params.segments},
"regions": regions,
"time_interval": time_interval,
"strains": params.strains,
"titers": titer_values
}
## VACCINES
if lineage in vaccine_choices:
config["vaccine_choices"] = vaccine_choices[lineage]
else:
print("WARNING. vaccine_choices are undefined for this lineage")
## LBI
try:
config["LBI_params"] = LBI_params[resolution]
except:
print("WARNING. LBI parameters are undefined for this resolution")
## FREQUENCIES
try:
config["frequency_params"] = frequency_params[resolution]
except:
print("WARNING. Frequency parameters are undefined for this resolution")
return config;
def make_config(params):
if params.geo == "global":
file_prefix = "mumps_global"
if params.viruses_per_month == 0:
viruses_per_month = 3
else:
viruses_per_month = params.viruses_per_month
dropped_strains = [
"WA0268502_buccal/Washington.USA/16", # not yet released
"Split.CRO/05.11/G", # retracted sequence
"9218/Zg98", # retracted sequence
"Zagreb.HRV/28.12/G", # retracted sequence
"Du/CRO05" # retracted sequence
]
colors = ["authors", "region", "country", "MuV_genotype"]
lat_longs = ["country", "region"]
auspice_filters = ["authors", "region", "country", "MuV_genotype"]
filters = (
("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
("Restrict Date Range", lambda s: s.attributes['date'] >= datetime(1950,01,1).date()),
("Restrict Date Range", lambda s: s.attributes['date'] <= datetime(2020,01,1).date()),
("Sequence Length", lambda s: len(s.seq)>=5000),
("Number Ns", lambda s: s.seq.count('N')<=3000)
)
elif params.geo == "na":
file_prefix = "mumps_na"
if params.viruses_per_month == 0:
viruses_per_month = 100
else:
viruses_per_month = params.viruses_per_month
dropped_strains = [
"Ontario.CAN/13.10/G", "Ontario.CAN/04.10/G", "Massachusetts.USA/37.16/1/G", "BritishColumbia.CAN/50.16/H",
"BritishColumbia.CAN/22.16/1/G", "Mass.USA/4.10",
"Virginia.USA/10.12/H", "BritishColumbia.CAN/33.16/3/G",
"BritishColumbia.CAN/33.16/1/G", "BritishColumbia.CAN/9.17/A",
"BritishColumbia.CAN/28.16/3/G",
# all below are true strains, but group outside NA outbreak clade
"WA0268502_buccal/Washington.USA/16", # not yet released
"Washington.USA/2017217/8.17/3/G", # outlier. MRCA with other NA strains of 1990
"BritishColumbia.CAN/34.16/2/F", #MuV genotype F. MRCA of 1943 (!)
"Massachusetts.USA/24.17/5/K", #MuV genotype K
"Massachusetts.USA/11.17/G" , "Massachusetts.USA/7.17/G", "Massachusetts.USA/9.17/G",
"Massachusetts.USA/10.17/G","Massachusetts.USA/10.17/2/G","Massachusetts.USA/7.17/2/G",
"Massachusetts.USA/13.17/G","Massachusetts.USA/12.17/G","Georgia.USA/2.17/G",
"Massachusetts.USA/5.17/G","Massachusetts.USA/18.17/G","Massachusetts.USA/22.17/7/G",
"Massachusetts.USA/23.17/2/G","Massachusetts.USA/19.17/2/G"
]
colors = ["authors", "country", "division", "MuV_genotype"]
lat_longs = ["country", "division"]
auspice_filters = ["authors", "country", "division", "MuV_genotype"]
filters = (
("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
("Restrict Date Range", lambda s: s.attributes['date'] >= datetime(2009,01,1).date()),
("Restrict Date Range", lambda s: s.attributes['date'] <= datetime(2020,01,1).date()),
("Sequence Length", lambda s: len(s.seq) >= 5000),
("Number Ns", lambda s: s.seq.count('N') <= 3000),
("Restrict Region", lambda s: s.attributes['region'] == 'north_america')
)
config = {
"dir": "mumps",
"file_prefix": file_prefix,
"title": "Real-time tracking of mumps virus evolution",
"maintainer": ["Louise Moncla", "http://bedford.io/team/louise-moncla/"],
"input_paths": ["../../../fauna/data/mumps.fasta"],
"header_fields": {0:'strain', 2:'accession', 3:'date', 4:'region', 5:'country',
6:'division', 8:'db', 10:'authors', 11:'url', 12:'title',
13: 'journal', 14: 'paper_url', 15: 'MuV_genotype'},
"filters": filters,
"subsample": {
"threshold": viruses_per_month,
"category": lambda x:(x.attributes['date'].year, x.attributes['date'].month, x.attributes['country'],x.attributes['MuV_genotype'])
},
"colors": colors,
"color_defs": ["./colors.tsv"],
"lat_longs": lat_longs,
"auspice_filters": auspice_filters,
"reference": {
"path": "mumps-reference.gb",
"metadata": {
'strain': "MuV/Gabon/13/2", "accession": "KM597072.1", "date": "2013-03-01",
'host': "human", 'country': "Gabon", 'region': "Gabon", 'MuV_genotype': "G"
},
"include": 0,
"genes": ['NC', 'P', 'V', 'I', 'M', 'F', 'SH', 'HN', 'L']
}
}
return config
def make_config(params):
return {
"dir":
"lassa",
"file_prefix":
"lassa",
"title":
"Real-time tracking of Lassa virus evolution",
"maintainer": ["Bedford Lab", "http://bedford.io/team/"],
"input_paths": [
"../../../flora/data/lassa_s.fasta",
"../../../flora/data/lassa_l.fasta",
],
"header_fields": {
0: 'strain',
1: 'accesion',
2: 'segment',
3: 'date',
4: 'region',
5: 'country',
6: 'host_species',
7: 'authors',
8: 'title',
9: 'journal',
10: 'paper_url'
},
"filters": (
("Dropped Strains",
lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
("Restrict Date Range for S segment", {
"s": lambda s: True,
"l": lambda s: True
}),
# ("Restrict Date Range", lambda s: s.attributes['date'] <= datetime(2018,01,1).date()),
("Sequence Length", {
"s": lambda s: len(s.seq) >= 2500,
"l": lambda s: len(s.seq) >= 5000,
})),
"subsample": {
"category":
lambda x: (x.attributes['country'], x.attributes['date'].year),
"threshold":
params.viruses_per_month,
"priority":
lambda x: x.id in forced_strains
},
"colors": ["country", "host_species"],
"color_defs": ["./colors.tsv"],
"lat_longs": ["country"],
"auspice_filters": ["country", "authors", "host_species"],
"references": {
# references are pinneo strain. Same as Kristian's Cell paper.
# Pinneo paper: http://jvi.asm.org/content/74/15/6992.long
# Cell paper: http://www.cell.com/cell/pdfExtended/S0092-8674(15)00897-1
"s": {
"path": "metadata/lassa_s.gb",
"metadata": {
'strain': "Nig08_04",
"accession": "GU481068",
"date": "2008-XX-XX",
'country': "nigeria",
'segment': 'S'
},
"include": 1,
"genes": ['NP', 'GPC']
},
"l": {
"path": "metadata/lassa_l.gb",
"metadata": {
'strain': "Pinneo-NIG-1969",
"accession": "KM822127",
"date": "1969-XX-XX",
'country': "nigeria",
'segment': 'L'
},
"include": 1,
"genes": ['Z', 'L']
},
}
}
from __future__ import print_function
import os, sys
sys.path.append('..') # we assume (and assert) that this script is running from the virus directory, i.e. inside H7N9 or zika
from base.prepare import prepare
from datetime import datetime
from base.utils import fix_names
import argparse
def collect_args():
parser = argparse.ArgumentParser(description = "Prepare fauna FASTA for analysis")
return parser.parse_args()
dropped_strains = []
filters = {
"dropped_strains": ("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
"canada_only": ("Canada only", lambda s: s.attributes['country'] == "canada"),
"exclude_BC": ("Exclude BC outbreak", lambda s: not s.attributes['accession'].startswith("BC_outbreak")),
"Mass_only": ("Massachusetts only", lambda s: s.attributes['accession'].startswith("Massachusetts_outbreak")),
"exclude_Mass": ("Exclude Massachusetts outbreak", lambda s: not s.attributes['accession'].startswith("Massachusetts_outbreak")),
"unknown_country": ("Exclude unknown countries", lambda s: not s.attributes['country'].startswith("unknown"))
}
def make_config(context):
config = {
"dir": "mumps",
"file_prefix": "mumps_%s"%context,
"title": "Mumps virus (context: {}).format(context)",
"maintainer": ["@LouiseHMoncla", "https://twitter.com/louisehmoncla"],
"input_paths": ["../../fauna/data/mumps.fasta"],
"header_fields": {0:'strain', 2:'accession', 3:'date', 4:'region', 5:'country',
def make_config(lineage, resolution, params):
years_back = int(re.search("(\d+)", resolution).groups()[0])
if params.time_interval:
time_interval = sorted([
datetime.strptime(x, '%Y-%m-%d').date()
for x in params.time_interval
],
reverse=True)
else:
time_interval = [
datetime.today().date(),
(datetime.today() - timedelta(days=365.25 * years_back)).date()
]
reference_cutoff = date(year=time_interval[1].year - 3, month=1, day=1)
fixed_outliers = [fix_names(x) for x in outliers[lineage]]
fixed_references = [fix_names(x) for x in reference_viruses[lineage]]
if params.titers is not None:
titer_values, strains, sources = TiterModel.load_from_file(
params.titers)
else:
titer_values = None
if params.sequences is not None:
input_paths = params.sequences
else:
input_paths = [
"../../fauna/data/{}_{}.fasta".format(lineage, segment)
for segment in params.segment
]
if params.file_prefix:
file_prefix = params.file_prefix
else:
file_prefix = "flu_{}_{}_{}".format(lineage, params.segment[0],
resolution)
return {
"dir":
"flu",
"file_prefix":
file_prefix,
"title":
make_title(lineage, resolution),
"maintainer": ["@trvrb", "https://twitter.com/trvrb"],
"segments":
params.segment,
"lineage":
lineage,
"input_paths":
input_paths,
# 0 1 2 3 4 5 6 7 8 9 10 11
# >A/Galicia/RR9542/2012|flu|EPI376225|2012-02-23|europe|spain|galicia|galicia|unpassaged|instituto_de_salud_carlos_iii|47y|female
"header_fields": {
0: 'strain',
2: 'isolate_id',
3: 'date',
4: 'region',
5: 'country',
6: 'division',
8: 'passage',
9: 'lab',
10: 'age',
11: 'gender'
},
"filters": (
("Time Interval", lambda s:
(s.attributes['date'] <= time_interval[0] and s.attributes['date']
>= time_interval[1]) or (s.name in fixed_references and s.
attributes['date'] > reference_cutoff)),
("Sequence Length", lambda s: len(s.seq) >= 900),
# what's the order of evaluation here I wonder?
("Dropped Strains", lambda s: s.id not in fixed_outliers),
("Bad geo info", lambda s: s.attributes["country"] != "?" and s.
attributes["region"] != "?"),
),
"subsample":
flu_subsampling(params, years_back, titer_values),
"colors": ["region"],
"color_defs": ["colors.flu.tsv"],
"lat_longs": ["country", "region"],
"lat_long_defs":
'../../fauna/source-data/geo_lat_long.tsv',
"references":
{seg: reference_maps[lineage][seg]
for seg in params.segment},
"regions":
regions,
"time_interval":
time_interval,
"strains":
params.strains,
"titers":
titer_values
}
