def heatmap_page():
logger.info("In heatmap, request.form is:", pf(request.form))
logger.info(request.url)
start_vars = request.form
temp_uuid = uuid.uuid4()
traits = [trait.strip() for trait in start_vars['trait_list'].split(',')]
if traits[0] != "":
version = "v5"
key = "heatmap:{}:".format(version) + json.dumps(start_vars,
sort_keys=True)
logger.info("key is:", pf(key))
with Bench("Loading cache"):
result = Redis.get(key)
if result:
logger.info("Cache hit!!!")
with Bench("Loading results"):
result = pickle.loads(result)
else:
logger.info("Cache miss!!!")
template_vars = heatmap.Heatmap(request.form, temp_uuid)
template_vars.js_data = json.dumps(template_vars.js_data,
default=json_default_handler,
indent=" ")
result = template_vars.__dict__
for item in list(template_vars.__dict__.keys()):
logger.info(" ---**--- {}: {}".format(
type(template_vars.__dict__[item]), item))
pickled_result = pickle.dumps(result, pickle.HIGHEST_PROTOCOL)
logger.info("pickled result length:", len(pickled_result))
Redis.set(key, pickled_result)
Redis.expire(key, 60 * 60)
with Bench("Rendering template"):
rendered_template = render_template("heatmap.html", **result)
else:
rendered_template = render_template("empty_collection.html",
**{'tool': 'Heatmap'})
return rendered_template
def create_datasets_list():
if USE_REDIS:
key = "all_datasets"
result = Redis.get(key)
if result:
logger.debug("Redis cache hit")
datasets = pickle.loads(result)
if result is None:
datasets = list()
with Bench("Creating DataSets object"):
type_dict = {'Publish': 'PublishFreeze',
'ProbeSet': 'ProbeSetFreeze',
'Geno': 'GenoFreeze'}
for dataset_type in type_dict:
query = "SELECT Name FROM {}".format(type_dict[dataset_type])
for result in fetchall(query):
#The query at the beginning of this function isn't
#necessary here, but still would rather just reuse
#it logger.debug("type: {}\tname:
#{}".format(dataset_type, result.Name))
dataset = create_dataset(result.Name, dataset_type)
datasets.append(dataset)
if USE_REDIS:
Redis.set(key, pickle.dumps(datasets, pickle.HIGHEST_PROTOCOL))
Redis.expire(key, 60*60)
return datasets
def search_page():
logger.info("in search_page")
logger.info(request.url)
result = None
if USE_REDIS:
with Bench("Trying Redis cache"):
key = "search_results:v1:" + \
json.dumps(request.args, sort_keys=True)
logger.debug("key is:", pf(key))
result = Redis.get(key)
if result:
logger.info("Redis cache hit on search results!")
result = pickle.loads(result)
else:
logger.info("Skipping Redis cache (USE_REDIS=False)")
logger.info("request.args is", request.args)
the_search = SearchResultPage(request.args)
result = the_search.__dict__
valid_search = result['search_term_exists']
if USE_REDIS and valid_search:
Redis.set(key, pickle.dumps(result, pickle.HIGHEST_PROTOCOL))
Redis.expire(key, 60 * 60)
if valid_search:
return render_template("search_result_page.html", **result)
else:
return render_template("search_error.html")
def quick_search(self):
#search_terms = ""
#for term in self.search_terms.split():
# search_terms += '+{} '.format(term)
search_terms = ' '.join('+{}'.format(escape(term))
for term in self.search_terms.split())
print("search_terms are:", search_terms)
query = """ SELECT table_name, the_key, result_fields
FROM QuickSearch
WHERE MATCH (terms)
AGAINST ('{}' IN BOOLEAN MODE) """.format(
search_terms)
with Bench("Doing QuickSearch Query: "):
dbresults = g.db.execute(query, no_parameters=True).fetchall()
#print("results: ", pf(results))
self.results = collections.defaultdict(list)
type_dict = {
'PublishXRef': 'phenotype',
'ProbeSetXRef': 'mrna_assay',
'GenoXRef': 'genotype'
}
self.species_groups = {}
for dbresult in dbresults:
this_result = {}
this_result['table_name'] = dbresult.table_name
if self.trait_type == type_dict[
dbresult.table_name] or self.trait_type == 'all':
this_result['key'] = dbresult.the_key
this_result['result_fields'] = json.loads(
dbresult.result_fields)
this_species = this_result['result_fields']['species']
this_group = this_result['result_fields']['group_name']
if this_species not in self.species_groups:
self.species_groups[this_species] = {}
if type_dict[dbresult.table_name] not in self.species_groups[
this_species]:
self.species_groups[this_species][type_dict[
dbresult.table_name]] = []
if this_group not in self.species_groups[this_species][
type_dict[dbresult.table_name]]:
self.species_groups[this_species][type_dict[
dbresult.table_name]].append(this_group)
#if type_dict[dbresult.table_name] not in self.species_groups:
# self.species_groups[type_dict[dbresult.table_name]] = {}
#if this_species not in self.species_groups[type_dict[dbresult.table_name]]:
# self.species_groups[type_dict[dbresult.table_name]][this_species] = []
#if this_group not in self.species_groups[type_dict[dbresult.table_name]][this_species]:
# self.species_groups[type_dict[dbresult.table_name]][this_species].append(this_group)
self.results[type_dict[dbresult.table_name]].append(
this_result)
import redis
Redis = redis.Redis()
def gn_server(path):
"""Return JSON record by calling GN_SERVER
"""
with Bench("GN_SERVER", LOG_SQL):
res = urllib2.urlopen(GN_SERVER_URL + path)
rest = res.read()
res2 = json.loads(rest)
logger.debug(res2)
return res2
def fetchall(query):
"""Return row iterator by calling SQL directly (the
original fetchall, but with logging)
"""
with Bench("SQL", LOG_SQL):
def helper(query):
res = g.db.execute(query)
return res.fetchall()
return logger.sql(query, helper)
def fetchone(query):
"""Return tuple containing one row by calling SQL directly (the
original fetchone, but with logging)
"""
with Bench("SQL", LOG_SQL):
def helper(query):
res = g.db.execute(query)
return res.fetchone()
return logger.sql(query, helper)
def search_page():
print("in search_page")
if 'info_database' in request.args:
print("Going to sharing_info_page")
template_vars = sharing_info_page()
if template_vars.redirect_url:
print("Going to redirect")
return flask.redirect(template_vars.redirect_url)
else:
return render_template("data_sharing.html",
**template_vars.__dict__)
else:
key = "search_results:v1:" + json.dumps(request.args, sort_keys=True)
print("key is:", pf(key))
with Bench("Loading cache"):
result = Redis.get(key)
if result:
print("Cache hit!!!")
with Bench("Loading results"):
result = pickle.loads(result)
else:
print("calling search_results.SearchResultPage")
print("request.args is", request.args)
the_search = search_results.SearchResultPage(request.args)
result = the_search.__dict__
print("result: ", pf(result))
Redis.set(key, pickle.dumps(result, pickle.HIGHEST_PROTOCOL))
Redis.expire(key, 60 * 60)
if result['quick']:
return render_template("quick_search.html", **result)
elif result['search_term_exists']:
return render_template("search_result_page.html", **result)
else:
return render_template("search_error.html")
def search_page():
logger.info("in search_page")
if 'info_database' in request.args:
logger.info("Going to sharing_info_page")
template_vars = sharing_info_page()
if template_vars.redirect_url:
logger.info("Going to redirect")
return flask.redirect(template_vars.redirect_url)
else:
return render_template("data_sharing.html",
**template_vars.__dict__)
else:
result = None
if USE_REDIS:
with Bench("Trying Redis cache"):
key = "search_results:v1:" + json.dumps(request.args,
sort_keys=True)
logger.debug("key is:", pf(key))
result = Redis.get(key)
if result:
logger.info("Redis cache hit on search results!")
result = pickle.loads(result)
else:
logger.info("Skipping Redis cache (USE_REDIS=False)")
logger.info("request.args is", request.args)
the_search = search_results.SearchResultPage(request.args)
result = the_search.__dict__
logger.debugf("result", result)
if USE_REDIS:
Redis.set(key, pickle.dumps(result, pickle.HIGHEST_PROTOCOL))
Redis.expire(key, 60 * 60)
if result['search_term_exists']:
return render_template("search_result_page.html", **result)
else:
return render_template("search_error.html")
def __init__(self, kw):
self.type = kw['type']
self.terms = kw['terms']
if self.type == "gene":
sql = """
SELECT
Species.`Name` AS species_name,
InbredSet.`Name` AS inbredset_name,
Tissue.`Name` AS tissue_name,
ProbeSetFreeze.Name AS probesetfreeze_name,
ProbeSet.Name AS probeset_name,
ProbeSet.Symbol AS probeset_symbol,
ProbeSet.`description` AS probeset_description,
ProbeSet.Chr AS chr,
ProbeSet.Mb AS mb,
ProbeSetXRef.Mean AS mean,
ProbeSetXRef.LRS AS lrs,
ProbeSetXRef.`Locus` AS locus,
ProbeSetXRef.`pValue` AS pvalue,
ProbeSetXRef.`additive` AS additive
FROM Species, InbredSet, ProbeSetXRef, ProbeSet, ProbeFreeze, ProbeSetFreeze, Tissue
WHERE InbredSet.`SpeciesId`=Species.`Id`
AND ProbeFreeze.InbredSetId=InbredSet.`Id`
AND ProbeFreeze.`TissueId`=Tissue.`Id`
AND ProbeSetFreeze.ProbeFreezeId=ProbeFreeze.Id
AND ( MATCH (ProbeSet.Name,ProbeSet.description,ProbeSet.symbol,alias,GenbankId, UniGeneId, Probe_Target_Description) AGAINST ('%s' IN BOOLEAN MODE) )
AND ProbeSet.Id = ProbeSetXRef.ProbeSetId
AND ProbeSetXRef.ProbeSetFreezeId=ProbeSetFreeze.Id
AND ProbeSetFreeze.confidentiality < 1
AND ProbeSetFreeze.public > 0
ORDER BY species_name, inbredset_name, tissue_name, probesetfreeze_name, probeset_name
LIMIT 6000
""" % (self.terms)
with Bench("Running query"):
logger.sql(sql)
re = g.db.execute(sql).fetchall()
self.trait_list = []
with Bench("Creating trait objects"):
for line in re:
dataset = create_dataset(line[3],
"ProbeSet",
get_samplelist=False)
trait_id = line[4]
#with Bench("Building trait object"):
this_trait = GeneralTrait(dataset=dataset,
name=trait_id,
get_qtl_info=True,
get_sample_info=False)
self.trait_list.append(this_trait)
elif self.type == "phenotype":
sql = """
SELECT
Species.`Name`,
InbredSet.`Name`,
PublishFreeze.`Name`,
PublishXRef.`Id`,
Phenotype.`Post_publication_description`,
Publication.`Authors`,
Publication.`Year`,
PublishXRef.`LRS`,
PublishXRef.`Locus`,
PublishXRef.`additive`
FROM Species,InbredSet,PublishFreeze,PublishXRef,Phenotype,Publication
WHERE PublishXRef.`InbredSetId`=InbredSet.`Id`
AND PublishFreeze.`InbredSetId`=InbredSet.`Id`
AND InbredSet.`SpeciesId`=Species.`Id`
AND PublishXRef.`PhenotypeId`=Phenotype.`Id`
AND PublishXRef.`PublicationId`=Publication.`Id`
AND (Phenotype.Post_publication_description REGEXP "[[:<:]]%s[[:>:]]"
OR Phenotype.Pre_publication_description REGEXP "[[:<:]]%s[[:>:]]"
OR Phenotype.Pre_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]"
OR Phenotype.Post_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]"
OR Phenotype.Lab_code REGEXP "[[:<:]]%s[[:>:]]"
OR Publication.PubMed_ID REGEXP "[[:<:]]%s[[:>:]]"
OR Publication.Abstract REGEXP "[[:<:]]%s[[:>:]]"
OR Publication.Title REGEXP "[[:<:]]%s[[:>:]]"
OR Publication.Authors REGEXP "[[:<:]]%s[[:>:]]"
OR PublishXRef.Id REGEXP "[[:<:]]%s[[:>:]]")
ORDER BY Species.`Name`, InbredSet.`Name`, PublishXRef.`Id`
LIMIT 6000
""" % (self.terms, self.terms, self.terms, self.terms,
self.terms, self.terms, self.terms, self.terms,
self.terms, self.terms)
logger.sql(sql)
re = g.db.execute(sql).fetchall()
self.trait_list = []
with Bench("Creating trait objects"):
for line in re:
dataset = create_dataset(line[2], "Publish")
trait_id = line[3]
this_trait = GeneralTrait(dataset=dataset,
name=trait_id,
get_qtl_info=True,
get_sample_info=False)
self.trait_list.append(this_trait)
def __init__(self, start_vars, temp_uuid):
helper_functions.get_species_dataset_trait(self, start_vars)
#tempdata = temp_data.TempData(temp_uuid)
self.temp_uuid = temp_uuid #needed to pass temp_uuid to gn1 mapping code (marker_regression_gn1.py)
self.json_data = {}
self.json_data['lodnames'] = ['lod.hk']
self.samples = [] # Want only ones with values
self.vals = []
for sample in self.dataset.group.samplelist:
value = start_vars['value:' + sample]
self.samples.append(str(sample))
self.vals.append(value)
self.mapping_method = start_vars['method']
if start_vars['manhattan_plot'] == "true":
self.manhattan_plot = True
else:
self.manhattan_plot = False
self.maf = start_vars['maf'] # Minor allele frequency
self.suggestive = ""
self.significant = ""
self.pair_scan = False # Initializing this since it is checked in views to determine which template to use
self.score_type = "LRS" #ZS: LRS or LOD
self.mapping_scale = "physic"
self.bootstrap_results = []
#ZS: This is passed to GN1 code for single chr mapping
self.selected_chr = -1
if "selected_chr" in start_vars:
if int(
start_vars['selected_chr']
) != -1: #ZS: Needs to be -1 if showing full map; there's probably a better way to fix this
self.selected_chr = int(start_vars['selected_chr']) + 1
else:
self.selected_chr = int(start_vars['selected_chr'])
if "startMb" in start_vars:
self.startMb = start_vars['startMb']
if "endMb" in start_vars:
self.endMb = start_vars['endMb']
if "graphWidth" in start_vars:
self.graphWidth = start_vars['graphWidth']
if "lrsMax" in start_vars:
self.lrsMax = start_vars['lrsMax']
if "haplotypeAnalystCheck" in start_vars:
self.haplotypeAnalystCheck = start_vars['haplotypeAnalystCheck']
if "startMb" in start_vars: #ZS: This is to ensure showGenes, Legend, etc are checked the first time you open the mapping page, since startMb will only not be set during the first load
if "permCheck" in start_vars:
self.permCheck = "ON"
else:
self.permCheck = False
self.num_perm = int(start_vars['num_perm'])
self.LRSCheck = start_vars['LRSCheck']
if "showSNP" in start_vars:
self.showSNP = start_vars['showSNP']
else:
self.showSNP = False
if "showGenes" in start_vars:
self.showGenes = start_vars['showGenes']
else:
self.showGenes = False
if "viewLegend" in start_vars:
self.viewLegend = start_vars['viewLegend']
else:
self.viewLegend = False
else:
try:
if int(start_vars['num_perm']) > 0:
self.num_perm = int(start_vars['num_perm'])
else:
self.num_perm = 0
except:
self.num_perm = 0
self.LRSCheck = self.score_type
self.permCheck = "ON"
self.showSNP = "ON"
self.showGenes = "ON"
self.viewLegend = "ON"
self.dataset.group.get_markers()
if self.mapping_method == "gemma":
self.score_type = "LOD"
self.manhattan_plot = True
with Bench("Running GEMMA"):
included_markers, p_values = gemma_mapping.run_gemma(
self.dataset, self.samples, self.vals)
with Bench("Getting markers from csv"):
marker_obs = get_markers_from_csv(included_markers, p_values,
self.dataset.group.name)
results = marker_obs
elif self.mapping_method == "rqtl_plink":
results = self.run_rqtl_plink()
elif self.mapping_method == "rqtl_geno":
self.score_type = "LOD"
self.mapping_scale = "morgan"
self.control_marker = start_vars['control_marker']
self.do_control = start_vars['do_control']
self.method = start_vars['mapmethod_rqtl_geno']
self.model = start_vars['mapmodel_rqtl_geno']
if start_vars['pair_scan'] == "true":
self.pair_scan = True
results = self.run_rqtl_geno()
elif self.mapping_method == "reaper":
if "startMb" in start_vars: #ZS: Check if first time page loaded, so it can default to ON
if "additiveCheck" in start_vars:
self.additiveCheck = start_vars['additiveCheck']
else:
self.additiveCheck = False
if "bootCheck" in start_vars:
self.bootCheck = "ON"
else:
self.bootCheck = False
self.num_bootstrap = int(start_vars['num_bootstrap'])
else:
self.additiveCheck = "ON"
try:
if int(start_vars['num_bootstrap']) > 0:
self.bootCheck = "ON"
self.num_bootstrap = int(start_vars['num_bootstrap'])
else:
self.bootCheck = False
self.num_bootstrap = 0
except:
self.bootCheck = False
self.num_bootstrap = 0
self.control_marker = start_vars['control_marker']
self.do_control = start_vars['do_control']
results = self.gen_reaper_results()
elif self.mapping_method == "plink":
results = self.run_plink()
elif self.mapping_method == "pylmm":
print("RUNNING PYLMM")
if self.num_perm > 0:
self.run_permutations(str(temp_uuid))
results = self.gen_data(str(temp_uuid))
else:
print("RUNNING NOTHING")
if self.pair_scan == True:
self.qtl_results = []
highest_chr = 1 #This is needed in order to convert the highest chr to X/Y
for marker in results:
if marker['chr1'] > 0 or marker['chr1'] == "X" or marker[
'chr1'] == "X/Y":
if marker['chr1'] > highest_chr or marker[
'chr1'] == "X" or marker['chr1'] == "X/Y":
highest_chr = marker['chr1']
if 'lod_score' in marker.keys():
self.qtl_results.append(marker)
for qtl in enumerate(self.qtl_results):
self.json_data['chr1'].append(str(qtl['chr1']))
self.json_data['chr2'].append(str(qtl['chr2']))
self.json_data['Mb'].append(qtl['Mb'])
self.json_data['markernames'].append(qtl['name'])
self.js_data = dict(
json_data=self.json_data,
this_trait=self.this_trait.name,
data_set=self.dataset.name,
maf=self.maf,
manhattan_plot=self.manhattan_plot,
mapping_scale=self.mapping_scale,
qtl_results=self.qtl_results,
)
else:
self.cutoff = 2
self.qtl_results = []
highest_chr = 1 #This is needed in order to convert the highest chr to X/Y
for marker in results:
if marker['chr'] > 0 or marker['chr'] == "X" or marker[
'chr'] == "X/Y":
if marker['chr'] > highest_chr or marker[
'chr'] == "X" or marker['chr'] == "X/Y":
highest_chr = marker['chr']
if ('lod_score' in marker.keys()) or ('lrs_value'
in marker.keys()):
self.qtl_results.append(marker)
self.trimmed_markers = trim_markers_for_table(results)
self.json_data['chr'] = []
self.json_data['pos'] = []
self.json_data['lod.hk'] = []
self.json_data['markernames'] = []
self.json_data['suggestive'] = self.suggestive
self.json_data['significant'] = self.significant
#Need to convert the QTL objects that qtl reaper returns into a json serializable dictionary
for index, qtl in enumerate(self.qtl_results):
#if index<40:
# print("lod score is:", qtl['lod_score'])
if qtl['chr'] == highest_chr and highest_chr != "X" and highest_chr != "X/Y":
#print("changing to X")
self.json_data['chr'].append("X")
else:
self.json_data['chr'].append(str(qtl['chr']))
self.json_data['pos'].append(qtl['Mb'])
if 'lrs_value' in qtl.keys():
self.json_data['lod.hk'].append(str(qtl['lrs_value']))
else:
self.json_data['lod.hk'].append(str(qtl['lod_score']))
self.json_data['markernames'].append(qtl['name'])
#Get chromosome lengths for drawing the interval map plot
chromosome_mb_lengths = {}
self.json_data['chrnames'] = []
for key in self.species.chromosomes.chromosomes.keys():
self.json_data['chrnames'].append([
self.species.chromosomes.chromosomes[key].name,
self.species.chromosomes.chromosomes[key].mb_length
])
chromosome_mb_lengths[
key] = self.species.chromosomes.chromosomes[key].mb_length
# print("json_data:", self.json_data)
self.js_data = dict(
result_score_type=self.score_type,
json_data=self.json_data,
this_trait=self.this_trait.name,
data_set=self.dataset.name,
maf=self.maf,
manhattan_plot=self.manhattan_plot,
mapping_scale=self.mapping_scale,
chromosomes=chromosome_mb_lengths,
qtl_results=self.qtl_results,
)
def mapping_results_page():
initial_start_vars = request.form
logger.info(request.url)
temp_uuid = initial_start_vars['temp_uuid']
wanted = ('trait_id', 'dataset', 'group', 'species', 'samples', 'vals',
'sample_vals', 'vals_hash', 'first_run', 'output_files',
'geno_db_exists', 'method', 'mapping_results_path',
'trimmed_markers', 'selected_chr', 'chromosomes',
'mapping_scale', 'plotScale', 'score_type', 'suggestive',
'significant', 'num_perm', 'permCheck', 'perm_strata',
'categorical_vars', 'perm_output', 'num_bootstrap', 'bootCheck',
'bootstrap_results', 'LRSCheck', 'covariates', 'maf', 'use_loco',
'manhattan_plot', 'color_scheme', 'manhattan_single_color',
'control_marker', 'do_control', 'genofile', 'genofile_string',
'pair_scan', 'startMb', 'endMb', 'graphWidth', 'lrsMax',
'additiveCheck', 'showSNP', 'showGenes', 'viewLegend',
'haplotypeAnalystCheck', 'mapmethod_rqtl_geno',
'mapmodel_rqtl_geno', 'temp_trait', 'n_samples', 'transform')
start_vars = {}
for key, value in list(initial_start_vars.items()):
if key in wanted:
start_vars[key] = value
version = "v3"
key = "mapping_results:{}:".format(version) + json.dumps(start_vars,
sort_keys=True)
with Bench("Loading cache"):
result = None # Just for testing
#result = Redis.get(key)
#logger.info("************************ Starting result *****************")
#logger.info("result is [{}]: {}".format(type(result), result))
#logger.info("************************ Ending result ********************")
if result:
logger.info("Cache hit!!!")
with Bench("Loading results"):
result = pickle.loads(result)
else:
logger.info("Cache miss!!!")
with Bench("Total time in RunMapping"):
try:
template_vars = run_mapping.RunMapping(start_vars, temp_uuid)
if template_vars.no_results:
rendered_template = render_template("mapping_error.html")
return rendered_template
except:
rendered_template = render_template("mapping_error.html")
return rendered_template
template_vars.js_data = json.dumps(template_vars.js_data,
default=json_default_handler,
indent=" ")
result = template_vars.__dict__
if result['pair_scan']:
with Bench("Rendering template"):
img_path = result['pair_scan_filename']
logger.info("img_path:", img_path)
initial_start_vars = request.form
logger.info("initial_start_vars:", initial_start_vars)
imgfile = open(TEMPDIR + img_path, 'rb')
imgdata = imgfile.read()
imgB64 = base64.b64encode(imgdata)
bytesarray = array.array('B', imgB64)
result['pair_scan_array'] = bytesarray
rendered_template = render_template(
"pair_scan_results.html", **result)
else:
gn1_template_vars = display_mapping_results.DisplayMappingResults(
result).__dict__
rendered_template = render_template("mapping_results.html",
**gn1_template_vars)
return rendered_template
def __init__(self, start_vars, temp_uuid):
helper_functions.get_species_dataset_trait(self, start_vars)
self.temp_uuid = temp_uuid #needed to pass temp_uuid to gn1 mapping code (marker_regression_gn1.py)
self.json_data = {}
self.json_data['lodnames'] = ['lod.hk']
self.samples = [] # Want only ones with values
self.vals = []
all_samples_ordered = self.dataset.group.all_samples_ordered()
primary_sample_names = list(all_samples_ordered)
for sample in self.dataset.group.samplelist:
# sample is actually the name of an individual
in_trait_data = False
for item in self.this_trait.data:
if self.this_trait.data[item].name == sample:
value = start_vars['value:' +
self.this_trait.data[item].name]
self.samples.append(self.this_trait.data[item].name)
self.vals.append(value)
in_trait_data = True
break
if not in_trait_data:
value = start_vars.get('value:' + sample)
if value:
self.samples.append(sample)
self.vals.append(value)
#ZS: Check if genotypes exist in the DB in order to create links for markers
if "geno_db_exists" in start_vars:
self.geno_db_exists = start_vars['geno_db_exists']
else:
try:
self.geno_db_exists = "True"
except:
self.geno_db_exists = "False"
self.mapping_method = start_vars['method']
if "results_path" in start_vars:
self.mapping_results_path = start_vars['results_path']
else:
mapping_results_filename = self.dataset.group.name + "_" + ''.join(
random.choice(string.ascii_uppercase + string.digits)
for _ in range(6))
self.mapping_results_path = "{}{}.csv".format(
webqtlConfig.GENERATED_IMAGE_DIR, mapping_results_filename)
if start_vars['manhattan_plot'] == "True":
self.manhattan_plot = True
else:
self.manhattan_plot = False
self.maf = start_vars['maf'] # Minor allele frequency
if "use_loco" in start_vars:
self.use_loco = start_vars['use_loco']
else:
self.use_loco = None
self.suggestive = ""
self.significant = ""
self.pair_scan = False # Initializing this since it is checked in views to determine which template to use
self.score_type = "LRS" #ZS: LRS or LOD
self.mapping_scale = "physic"
self.num_perm = 0
self.perm_output = []
self.bootstrap_results = []
self.covariates = start_vars[
'covariates'] if "covariates" in start_vars else None
#ZS: This is passed to GN1 code for single chr mapping
self.selected_chr = -1
if "selected_chr" in start_vars:
if int(
start_vars['selected_chr']
) != -1: #ZS: Needs to be -1 if showing full map; there's probably a better way to fix this
self.selected_chr = int(start_vars['selected_chr']) + 1
else:
self.selected_chr = int(start_vars['selected_chr'])
if "startMb" in start_vars:
self.startMb = start_vars['startMb']
if "endMb" in start_vars:
self.endMb = start_vars['endMb']
if "graphWidth" in start_vars:
self.graphWidth = start_vars['graphWidth']
if "lrsMax" in start_vars:
self.lrsMax = start_vars['lrsMax']
if "haplotypeAnalystCheck" in start_vars:
self.haplotypeAnalystCheck = start_vars['haplotypeAnalystCheck']
if "startMb" in start_vars: #ZS: This is to ensure showGenes, Legend, etc are checked the first time you open the mapping page, since startMb will only not be set during the first load
if "permCheck" in start_vars:
self.permCheck = "ON"
else:
self.permCheck = False
self.num_perm = int(start_vars['num_perm'])
self.LRSCheck = start_vars['LRSCheck']
if "showSNP" in start_vars:
self.showSNP = start_vars['showSNP']
else:
self.showSNP = False
if "showGenes" in start_vars:
self.showGenes = start_vars['showGenes']
else:
self.showGenes = False
if "viewLegend" in start_vars:
self.viewLegend = start_vars['viewLegend']
else:
self.viewLegend = False
else:
try:
if int(start_vars['num_perm']) > 0:
self.num_perm = int(start_vars['num_perm'])
except:
self.num_perm = 0
if self.num_perm > 0:
self.permCheck = "ON"
else:
self.permCheck = False
self.showSNP = "ON"
self.showGenes = "ON"
self.viewLegend = "ON"
if 'genofile' in start_vars:
if start_vars['genofile'] != "":
self.genofile_string = start_vars['genofile']
self.dataset.group.genofile = self.genofile_string.split(
":")[0]
self.dataset.group.get_markers()
if self.mapping_method == "gemma":
self.score_type = "-log(p)"
self.manhattan_plot = True
with Bench("Running GEMMA"):
marker_obs = gemma_mapping.run_gemma(self.dataset,
self.samples, self.vals,
self.covariates,
self.use_loco)
results = marker_obs
elif self.mapping_method == "rqtl_plink":
results = self.run_rqtl_plink()
elif self.mapping_method == "rqtl_geno":
self.score_type = "LOD"
self.mapping_scale = "morgan"
self.control_marker = start_vars['control_marker']
self.do_control = start_vars['do_control']
self.method = start_vars['mapmethod_rqtl_geno']
self.model = start_vars['mapmodel_rqtl_geno']
#if start_vars['pair_scan'] == "true":
# self.pair_scan = True
if self.permCheck and self.num_perm > 0:
self.perm_output, self.suggestive, self.significant, results = rqtl_mapping.run_rqtl_geno(
self.vals, self.dataset, self.method, self.model,
self.permCheck, self.num_perm, self.do_control,
self.control_marker, self.manhattan_plot, self.pair_scan)
else:
results = rqtl_mapping.run_rqtl_geno(
self.vals, self.dataset, self.method, self.model,
self.permCheck, self.num_perm, self.do_control,
self.control_marker, self.manhattan_plot, self.pair_scan)
elif self.mapping_method == "reaper":
if "startMb" in start_vars: #ZS: Check if first time page loaded, so it can default to ON
if "additiveCheck" in start_vars:
self.additiveCheck = start_vars['additiveCheck']
else:
self.additiveCheck = False
if "bootCheck" in start_vars:
self.bootCheck = "ON"
else:
self.bootCheck = False
self.num_bootstrap = int(start_vars['num_bootstrap'])
else:
self.additiveCheck = "ON"
try:
if int(start_vars['num_bootstrap']) > 0:
self.bootCheck = "ON"
self.num_bootstrap = int(start_vars['num_bootstrap'])
else:
self.bootCheck = False
self.num_bootstrap = 0
except:
self.bootCheck = False
self.num_bootstrap = 0
self.control_marker = start_vars['control_marker']
self.do_control = start_vars['do_control']
logger.info("Running qtlreaper")
results, self.json_data, self.perm_output, self.suggestive, self.significant, self.bootstrap_results = qtlreaper_mapping.gen_reaper_results(
self.this_trait, self.dataset, self.samples, self.vals,
self.json_data, self.num_perm, self.bootCheck,
self.num_bootstrap, self.do_control, self.control_marker,
self.manhattan_plot)
elif self.mapping_method == "plink":
self.score_type = "-log(p)"
self.manhattan_plot = True
results = plink_mapping.run_plink(self.this_trait, self.dataset,
self.species, self.vals,
self.maf)
#results = self.run_plink()
elif self.mapping_method == "pylmm":
logger.debug("RUNNING PYLMM")
if self.num_perm > 0:
self.run_permutations(str(temp_uuid))
results = self.gen_data(str(temp_uuid))
else:
logger.debug("RUNNING NOTHING")
if self.pair_scan == True:
self.qtl_results = []
highest_chr = 1 #This is needed in order to convert the highest chr to X/Y
for marker in results:
if marker['chr1'] > 0 or marker['chr1'] == "X" or marker[
'chr1'] == "X/Y":
if marker['chr1'] > highest_chr or marker[
'chr1'] == "X" or marker['chr1'] == "X/Y":
highest_chr = marker['chr1']
if 'lod_score' in marker.keys():
self.qtl_results.append(marker)
self.trimmed_markers = results
for qtl in enumerate(self.qtl_results):
self.json_data['chr1'].append(str(qtl['chr1']))
self.json_data['chr2'].append(str(qtl['chr2']))
self.json_data['Mb'].append(qtl['Mb'])
self.json_data['markernames'].append(qtl['name'])
self.js_data = dict(json_data=self.json_data,
this_trait=self.this_trait.name,
data_set=self.dataset.name,
maf=self.maf,
manhattan_plot=self.manhattan_plot,
mapping_scale=self.mapping_scale,
qtl_results=self.qtl_results)
else:
self.qtl_results = []
highest_chr = 1 #This is needed in order to convert the highest chr to X/Y
for marker in results:
if marker['chr'] > 0 or marker['chr'] == "X" or marker[
'chr'] == "X/Y":
if marker['chr'] > highest_chr or marker[
'chr'] == "X" or marker['chr'] == "X/Y":
highest_chr = marker['chr']
if ('lod_score' in marker.keys()) or ('lrs_value'
in marker.keys()):
self.qtl_results.append(marker)
with Bench("Exporting Results"):
export_mapping_results(self.dataset, self.this_trait,
self.qtl_results,
self.mapping_results_path,
self.mapping_scale, self.score_type)
with Bench("Trimming Markers for Figure"):
if len(self.qtl_results) > 30000:
self.qtl_results = trim_markers_for_figure(
self.qtl_results)
with Bench("Trimming Markers for Table"):
self.trimmed_markers = trim_markers_for_table(results)
if self.mapping_method != "gemma":
self.json_data['chr'] = []
self.json_data['pos'] = []
self.json_data['lod.hk'] = []
self.json_data['markernames'] = []
self.json_data['suggestive'] = self.suggestive
self.json_data['significant'] = self.significant
#Need to convert the QTL objects that qtl reaper returns into a json serializable dictionary
for index, qtl in enumerate(self.qtl_results):
#if index<40:
# logger.debug("lod score is:", qtl['lod_score'])
if qtl['chr'] == highest_chr and highest_chr != "X" and highest_chr != "X/Y":
#logger.debug("changing to X")
self.json_data['chr'].append("X")
else:
self.json_data['chr'].append(str(qtl['chr']))
self.json_data['pos'].append(qtl['Mb'])
if 'lrs_value' in qtl.keys():
self.json_data['lod.hk'].append(str(qtl['lrs_value']))
else:
self.json_data['lod.hk'].append(str(qtl['lod_score']))
self.json_data['markernames'].append(qtl['name'])
#Get chromosome lengths for drawing the interval map plot
chromosome_mb_lengths = {}
self.json_data['chrnames'] = []
for key in self.species.chromosomes.chromosomes.keys():
self.json_data['chrnames'].append([
self.species.chromosomes.chromosomes[key].name,
self.species.chromosomes.chromosomes[key].mb_length
])
chromosome_mb_lengths[
key] = self.species.chromosomes.chromosomes[
key].mb_length
self.js_data = dict(
result_score_type=self.score_type,
json_data=self.json_data,
this_trait=self.this_trait.name,
data_set=self.dataset.name,
maf=self.maf,
manhattan_plot=self.manhattan_plot,
mapping_scale=self.mapping_scale,
chromosomes=chromosome_mb_lengths,
qtl_results=self.qtl_results,
num_perm=self.num_perm,
perm_results=self.perm_output,
)
def __init__(self, start_vars, temp_uuid):
helper_functions.get_species_dataset_trait(self, start_vars)
self.temp_uuid = temp_uuid #needed to pass temp_uuid to gn1 mapping code (marker_regression_gn1.py)
#ZS: Needed to zoom in or remap temp traits like PCA traits
if "temp_trait" in start_vars and start_vars['temp_trait'] != "False":
self.temp_trait = "True"
self.group = self.dataset.group.name
self.json_data = {}
self.json_data['lodnames'] = ['lod.hk']
#ZS: Sometimes a group may have a genofile that only includes a subset of samples
genofile_samplelist = []
if 'genofile' in start_vars:
if start_vars['genofile'] != "":
self.genofile_string = start_vars['genofile']
self.dataset.group.genofile = self.genofile_string.split(
":")[0]
genofile_samplelist = get_genofile_samplelist(self.dataset)
all_samples_ordered = self.dataset.group.all_samples_ordered()
self.vals = []
self.samples = []
self.sample_vals = start_vars['sample_vals']
sample_val_dict = json.loads(self.sample_vals)
samples = sample_val_dict.keys()
if (len(genofile_samplelist) != 0):
for sample in genofile_samplelist:
self.samples.append(sample)
if sample in samples:
self.vals.append(sample_val_dict[sample])
else:
self.vals.append("x")
else:
for sample in self.dataset.group.samplelist:
if sample in samples:
self.vals.append(sample_val_dict[sample])
self.samples.append(sample)
if 'n_samples' in start_vars:
self.n_samples = start_vars['n_samples']
else:
self.n_samples = len([val for val in self.vals if val != "x"])
#ZS: Check if genotypes exist in the DB in order to create links for markers
self.geno_db_exists = geno_db_exists(self.dataset)
self.mapping_method = start_vars['method']
if "results_path" in start_vars:
self.mapping_results_path = start_vars['results_path']
else:
mapping_results_filename = self.dataset.group.name + "_" + ''.join(
random.choice(string.ascii_uppercase + string.digits)
for _ in range(6))
self.mapping_results_path = "{}{}.csv".format(
webqtlConfig.GENERATED_IMAGE_DIR, mapping_results_filename)
self.manhattan_plot = False
if 'manhattan_plot' in start_vars:
if start_vars['manhattan_plot'].lower() != "false":
self.color_scheme = "alternating"
if "color_scheme" in start_vars:
self.color_scheme = start_vars['color_scheme']
if self.color_scheme == "single":
self.manhattan_single_color = start_vars[
'manhattan_single_color']
self.manhattan_plot = True
self.maf = start_vars['maf'] # Minor allele frequency
if "use_loco" in start_vars:
self.use_loco = start_vars['use_loco']
else:
self.use_loco = None
self.suggestive = ""
self.significant = ""
self.pair_scan = False # Initializing this since it is checked in views to determine which template to use
if 'transform' in start_vars:
self.transform = start_vars['transform']
else:
self.transform = ""
self.score_type = "LRS" #ZS: LRS or LOD
self.mapping_scale = "physic"
if "mapping_scale" in start_vars:
self.mapping_scale = start_vars['mapping_scale']
self.num_perm = 0
self.perm_output = []
self.bootstrap_results = []
self.covariates = start_vars[
'covariates'] if "covariates" in start_vars else ""
self.categorical_vars = []
#ZS: This is passed to GN1 code for single chr mapping
self.selected_chr = -1
if "selected_chr" in start_vars:
if int(
start_vars['selected_chr']
) != -1: #ZS: Needs to be -1 if showing full map; there's probably a better way to fix this
self.selected_chr = int(start_vars['selected_chr']) + 1
else:
self.selected_chr = int(start_vars['selected_chr'])
if "startMb" in start_vars:
self.startMb = start_vars['startMb']
if "endMb" in start_vars:
self.endMb = start_vars['endMb']
if "graphWidth" in start_vars:
self.graphWidth = start_vars['graphWidth']
if "lrsMax" in start_vars:
self.lrsMax = start_vars['lrsMax']
if "haplotypeAnalystCheck" in start_vars:
self.haplotypeAnalystCheck = start_vars['haplotypeAnalystCheck']
if "startMb" in start_vars: #ZS: This is to ensure showGenes, Legend, etc are checked the first time you open the mapping page, since startMb will only not be set during the first load
if "permCheck" in start_vars:
self.permCheck = "ON"
else:
self.permCheck = False
self.num_perm = int(start_vars['num_perm'])
self.LRSCheck = start_vars['LRSCheck']
if "showSNP" in start_vars:
self.showSNP = start_vars['showSNP']
else:
self.showSNP = False
if "showGenes" in start_vars:
self.showGenes = start_vars['showGenes']
else:
self.showGenes = False
if "viewLegend" in start_vars:
self.viewLegend = start_vars['viewLegend']
else:
self.viewLegend = False
else:
try:
if int(start_vars['num_perm']) > 0:
self.num_perm = int(start_vars['num_perm'])
except:
self.num_perm = 0
if self.num_perm > 0:
self.permCheck = "ON"
else:
self.permCheck = False
self.showSNP = "ON"
self.showGenes = "ON"
self.viewLegend = "ON"
#self.dataset.group.get_markers()
if self.mapping_method == "gemma":
self.first_run = True
self.output_files = None
if 'output_files' in start_vars:
self.output_files = start_vars['output_files']
if 'first_run' in start_vars: #ZS: check if first run so existing result files can be used if it isn't (for example zooming on a chromosome, etc)
self.first_run = False
self.score_type = "-logP"
self.manhattan_plot = True
with Bench("Running GEMMA"):
if self.use_loco == "True":
marker_obs, self.output_files = gemma_mapping.run_gemma(
self.this_trait, self.dataset, self.samples, self.vals,
self.covariates, self.use_loco, self.maf,
self.first_run, self.output_files)
else:
marker_obs, self.output_files = gemma_mapping.run_gemma(
self.this_trait, self.dataset, self.samples, self.vals,
self.covariates, self.use_loco, self.maf,
self.first_run, self.output_files)
results = marker_obs
elif self.mapping_method == "rqtl_plink":
results = self.run_rqtl_plink()
elif self.mapping_method == "rqtl_geno":
perm_strata = []
if "perm_strata" in start_vars and "categorical_vars" in start_vars:
self.categorical_vars = start_vars["categorical_vars"].split(
",")
if len(self.categorical_vars
) and start_vars["perm_strata"] == "True":
primary_samples = SampleList(dataset=self.dataset,
sample_names=self.samples,
this_trait=self.this_trait)
perm_strata = get_perm_strata(self.this_trait,
primary_samples,
self.categorical_vars,
self.samples)
self.score_type = "LOD"
self.control_marker = start_vars['control_marker']
self.do_control = start_vars['do_control']
if 'mapmethod_rqtl_geno' in start_vars:
self.method = start_vars['mapmethod_rqtl_geno']
else:
self.method = "em"
self.model = start_vars['mapmodel_rqtl_geno']
#if start_vars['pair_scan'] == "true":
# self.pair_scan = True
if self.permCheck and self.num_perm > 0:
self.perm_output, self.suggestive, self.significant, results = rqtl_mapping.run_rqtl_geno(
self.vals, self.samples, self.dataset, self.mapping_scale,
self.method, self.model, self.permCheck, self.num_perm,
perm_strata, self.do_control, self.control_marker,
self.manhattan_plot, self.pair_scan, self.covariates)
else:
results = rqtl_mapping.run_rqtl_geno(
self.vals, self.samples, self.dataset, self.mapping_scale,
self.method, self.model, self.permCheck, self.num_perm,
perm_strata, self.do_control, self.control_marker,
self.manhattan_plot, self.pair_scan, self.covariates)
elif self.mapping_method == "reaper":
if "startMb" in start_vars: #ZS: Check if first time page loaded, so it can default to ON
if "additiveCheck" in start_vars:
self.additiveCheck = start_vars['additiveCheck']
else:
self.additiveCheck = False
if "bootCheck" in start_vars:
self.bootCheck = "ON"
else:
self.bootCheck = False
self.num_bootstrap = int(start_vars['num_bootstrap'])
else:
self.additiveCheck = "ON"
try:
if int(start_vars['num_bootstrap']) > 0:
self.bootCheck = "ON"
self.num_bootstrap = int(start_vars['num_bootstrap'])
else:
self.bootCheck = False
self.num_bootstrap = 0
except:
self.bootCheck = False
self.num_bootstrap = 0
self.reaper_version = start_vars['reaper_version']
self.control_marker = start_vars['control_marker']
self.do_control = start_vars['do_control']
logger.info("Running qtlreaper")
if self.reaper_version == "new":
self.first_run = True
self.output_files = None
if 'first_run' in start_vars: #ZS: check if first run so existing result files can be used if it isn't (for example zooming on a chromosome, etc)
self.first_run = False
if 'output_files' in start_vars:
self.output_files = start_vars['output_files'].split(
",")
results, self.perm_output, self.suggestive, self.significant, self.bootstrap_results, self.output_files = qtlreaper_mapping.run_reaper(
self.this_trait, self.dataset, self.samples, self.vals,
self.json_data, self.num_perm, self.bootCheck,
self.num_bootstrap, self.do_control, self.control_marker,
self.manhattan_plot, self.first_run, self.output_files)
else:
results, self.json_data, self.perm_output, self.suggestive, self.significant, self.bootstrap_results = qtlreaper_mapping.run_original_reaper(
self.this_trait, self.dataset, self.samples, self.vals,
self.json_data, self.num_perm, self.bootCheck,
self.num_bootstrap, self.do_control, self.control_marker,
self.manhattan_plot)
elif self.mapping_method == "plink":
self.score_type = "-logP"
self.manhattan_plot = True
results = plink_mapping.run_plink(self.this_trait, self.dataset,
self.species, self.vals,
self.maf)
#results = self.run_plink()
else:
logger.debug("RUNNING NOTHING")
self.no_results = False
if len(results) == 0:
self.no_results = True
else:
if self.pair_scan == True:
self.qtl_results = []
highest_chr = 1 #This is needed in order to convert the highest chr to X/Y
for marker in results:
if marker['chr1'] > 0 or marker['chr1'] == "X" or marker[
'chr1'] == "X/Y":
if marker['chr1'] > highest_chr or marker[
'chr1'] == "X" or marker['chr1'] == "X/Y":
highest_chr = marker['chr1']
if 'lod_score' in list(marker.keys()):
self.qtl_results.append(marker)
self.trimmed_markers = results
for qtl in enumerate(self.qtl_results):
self.json_data['chr1'].append(str(qtl['chr1']))
self.json_data['chr2'].append(str(qtl['chr2']))
self.json_data['Mb'].append(qtl['Mb'])
self.json_data['markernames'].append(qtl['name'])
self.js_data = dict(json_data=self.json_data,
this_trait=self.this_trait.name,
data_set=self.dataset.name,
maf=self.maf,
manhattan_plot=self.manhattan_plot,
mapping_scale=self.mapping_scale,
qtl_results=self.qtl_results)
else:
self.qtl_results = []
self.results_for_browser = []
self.annotations_for_browser = []
highest_chr = 1 #This is needed in order to convert the highest chr to X/Y
for marker in results:
if 'Mb' in marker:
this_ps = marker['Mb'] * 1000000
else:
this_ps = marker['cM'] * 1000000
browser_marker = dict(chr=str(marker['chr']),
rs=marker['name'],
ps=this_ps,
url="/show_trait?trait_id=" +
marker['name'] + "&dataset=" +
self.dataset.group.name + "Geno")
if self.geno_db_exists == "True":
annot_marker = dict(name=str(marker['name']),
chr=str(marker['chr']),
rs=marker['name'],
pos=this_ps,
url="/show_trait?trait_id=" +
marker['name'] + "&dataset=" +
self.dataset.group.name + "Geno")
else:
annot_marker = dict(name=str(marker['name']),
chr=str(marker['chr']),
rs=marker['name'],
pos=this_ps)
if 'lrs_value' in marker and marker['lrs_value'] > 0:
browser_marker['p_wald'] = 10**-(marker['lrs_value'] /
4.61)
elif 'lod_score' in marker and marker['lod_score'] > 0:
browser_marker['p_wald'] = 10**-(marker['lod_score'])
else:
browser_marker['p_wald'] = 0
self.results_for_browser.append(browser_marker)
self.annotations_for_browser.append(annot_marker)
if str(marker['chr']) > '0' or str(
marker['chr']) == "X" or str(
marker['chr']) == "X/Y":
if str(marker['chr']) > str(highest_chr) or str(
marker['chr']) == "X" or str(
marker['chr']) == "X/Y":
highest_chr = marker['chr']
if ('lod_score'
in marker.keys()) or ('lrs_value'
in marker.keys()):
if 'Mb' in marker.keys():
marker['display_pos'] = "Chr" + str(
marker['chr']) + ": " + "{:.6f}".format(
marker['Mb'])
elif 'cM' in marker.keys():
marker['display_pos'] = "Chr" + str(
marker['chr']) + ": " + "{:.3f}".format(
marker['cM'])
else:
marker['display_pos'] = "N/A"
self.qtl_results.append(marker)
total_markers = len(self.qtl_results)
with Bench("Exporting Results"):
export_mapping_results(self.dataset, self.this_trait,
self.qtl_results,
self.mapping_results_path,
self.mapping_scale, self.score_type)
with Bench("Trimming Markers for Figure"):
if len(self.qtl_results) > 30000:
self.qtl_results = trim_markers_for_figure(
self.qtl_results)
self.results_for_browser = trim_markers_for_figure(
self.results_for_browser)
filtered_annotations = []
for marker in self.results_for_browser:
for annot_marker in self.annotations_for_browser:
if annot_marker['rs'] == marker['rs']:
filtered_annotations.append(annot_marker)
break
self.annotations_for_browser = filtered_annotations
browser_files = write_input_for_browser(
self.dataset, self.results_for_browser,
self.annotations_for_browser)
else:
browser_files = write_input_for_browser(
self.dataset, self.results_for_browser,
self.annotations_for_browser)
with Bench("Trimming Markers for Table"):
self.trimmed_markers = trim_markers_for_table(results)
chr_lengths = get_chr_lengths(self.mapping_scale,
self.mapping_method,
self.dataset, self.qtl_results)
#ZS: For zooming into genome browser, need to pass chromosome name instead of number
if self.dataset.group.species == "mouse":
if self.selected_chr == 20:
this_chr = "X"
else:
this_chr = str(self.selected_chr)
elif self.dataset.group.species == "rat":
if self.selected_chr == 21:
this_chr = "X"
else:
this_chr = str(self.selected_chr)
else:
if self.selected_chr == 22:
this_chr = "X"
elif self.selected_chr == 23:
this_chr = "Y"
else:
this_chr = str(self.selected_chr)
if self.mapping_method != "gemma":
if self.score_type == "LRS":
significant_for_browser = self.significant / 4.61
else:
significant_for_browser = self.significant
self.js_data = dict(
#result_score_type = self.score_type,
#this_trait = self.this_trait.name,
#data_set = self.dataset.name,
#maf = self.maf,
#manhattan_plot = self.manhattan_plot,
#mapping_scale = self.mapping_scale,
#chromosomes = chromosome_mb_lengths,
#qtl_results = self.qtl_results,
categorical_vars=self.categorical_vars,
chr_lengths=chr_lengths,
num_perm=self.num_perm,
perm_results=self.perm_output,
significant=significant_for_browser,
browser_files=browser_files,
selected_chr=this_chr,
total_markers=total_markers)
else:
self.js_data = dict(chr_lengths=chr_lengths,
browser_files=browser_files,
selected_chr=this_chr,
total_markers=total_markers)
def __init__(self, start_vars):
# get trait list from db (database name)
# calculate correlation with Base vector and targets
# Check parameters
assert('corr_type' in start_vars)
assert(is_str(start_vars['corr_type']))
assert('dataset' in start_vars)
# assert('group' in start_vars) permitted to be empty?
assert('corr_sample_method' in start_vars)
assert('corr_samples_group' in start_vars)
assert('corr_dataset' in start_vars)
assert('corr_return_results' in start_vars)
if 'loc_chr' in start_vars:
assert('min_loc_mb' in start_vars)
assert('max_loc_mb' in start_vars)
with Bench("Doing correlations"):
if start_vars['dataset'] == "Temp":
self.dataset = data_set.create_dataset(dataset_name = "Temp", dataset_type = "Temp", group_name = start_vars['group'])
self.trait_id = start_vars['trait_id']
self.this_trait = create_trait(dataset=self.dataset,
name=self.trait_id,
cellid=None)
else:
helper_functions.get_species_dataset_trait(self, start_vars)
corr_samples_group = start_vars['corr_samples_group']
self.sample_data = {}
self.corr_type = start_vars['corr_type']
self.corr_method = start_vars['corr_sample_method']
self.min_expr = get_float(start_vars, 'min_expr')
self.p_range_lower = get_float(start_vars, 'p_range_lower', -1.0)
self.p_range_upper = get_float(start_vars, 'p_range_upper', 1.0)
if ('loc_chr' in start_vars and
'min_loc_mb' in start_vars and
'max_loc_mb' in start_vars):
self.location_type = get_string(start_vars, 'location_type')
self.location_chr = get_string(start_vars, 'loc_chr')
self.min_location_mb = get_int(start_vars, 'min_loc_mb')
self.max_location_mb = get_int(start_vars, 'max_loc_mb')
else:
self.location_type = self.location_chr = self.min_location_mb = self.max_location_mb = None
self.get_formatted_corr_type()
self.return_number = int(start_vars['corr_return_results'])
#The two if statements below append samples to the sample list based upon whether the user
#rselected Primary Samples Only, Other Samples Only, or All Samples
primary_samples = self.dataset.group.samplelist
if self.dataset.group.parlist != None:
primary_samples += self.dataset.group.parlist
if self.dataset.group.f1list != None:
primary_samples += self.dataset.group.f1list
#If either BXD/whatever Only or All Samples, append all of that group's samplelist
if corr_samples_group != 'samples_other':
self.process_samples(start_vars, primary_samples)
#If either Non-BXD/whatever or All Samples, get all samples from this_trait.data and
#exclude the primary samples (because they would have been added in the previous
#if statement if the user selected All Samples)
if corr_samples_group != 'samples_primary':
if corr_samples_group == 'samples_other':
primary_samples = [x for x in primary_samples if x not in (
self.dataset.group.parlist + self.dataset.group.f1list)]
self.process_samples(start_vars, list(self.this_trait.data.keys()), primary_samples)
self.target_dataset = data_set.create_dataset(start_vars['corr_dataset'])
self.target_dataset.get_trait_data(list(self.sample_data.keys()))
self.header_fields = get_header_fields(self.target_dataset.type, self.corr_method)
if self.target_dataset.type == "ProbeSet":
self.filter_cols = [7, 6]
elif self.target_dataset.type == "Publish":
self.filter_cols = [6, 0]
else:
self.filter_cols = [4, 0]
self.correlation_results = []
self.correlation_data = {}
if self.corr_type == "tissue":
self.trait_symbol_dict = self.dataset.retrieve_genes("Symbol")
tissue_corr_data = self.do_tissue_correlation_for_all_traits()
if tissue_corr_data != None:
for trait in list(tissue_corr_data.keys())[:self.return_number]:
self.get_sample_r_and_p_values(trait, self.target_dataset.trait_data[trait])
else:
for trait, values in list(self.target_dataset.trait_data.items()):
self.get_sample_r_and_p_values(trait, values)
elif self.corr_type == "lit":
self.trait_geneid_dict = self.dataset.retrieve_genes("GeneId")
lit_corr_data = self.do_lit_correlation_for_all_traits()
for trait in list(lit_corr_data.keys())[:self.return_number]:
self.get_sample_r_and_p_values(trait, self.target_dataset.trait_data[trait])
elif self.corr_type == "sample":
for trait, values in list(self.target_dataset.trait_data.items()):
self.get_sample_r_and_p_values(trait, values)
self.correlation_data = collections.OrderedDict(sorted(list(self.correlation_data.items()),
key=lambda t: -abs(t[1][0])))
#ZS: Convert min/max chromosome to an int for the location range option
range_chr_as_int = None
for order_id, chr_info in list(self.dataset.species.chromosomes.chromosomes.items()):
if 'loc_chr' in start_vars:
if chr_info.name == self.location_chr:
range_chr_as_int = order_id
for _trait_counter, trait in enumerate(list(self.correlation_data.keys())[:self.return_number]):
trait_object = create_trait(dataset=self.target_dataset, name=trait, get_qtl_info=True, get_sample_info=False)
if not trait_object:
continue
chr_as_int = 0
for order_id, chr_info in list(self.dataset.species.chromosomes.chromosomes.items()):
if self.location_type == "highest_lod":
if chr_info.name == trait_object.locus_chr:
chr_as_int = order_id
else:
if chr_info.name == trait_object.chr:
chr_as_int = order_id
if (float(self.correlation_data[trait][0]) >= self.p_range_lower and
float(self.correlation_data[trait][0]) <= self.p_range_upper):
if (self.target_dataset.type == "ProbeSet" or self.target_dataset.type == "Publish") and bool(trait_object.mean):
if (self.min_expr != None) and (float(trait_object.mean) < self.min_expr):
continue
if range_chr_as_int != None and (chr_as_int != range_chr_as_int):
continue
if self.location_type == "highest_lod":
if (self.min_location_mb != None) and (float(trait_object.locus_mb) < float(self.min_location_mb)):
continue
if (self.max_location_mb != None) and (float(trait_object.locus_mb) > float(self.max_location_mb)):
continue
else:
if (self.min_location_mb != None) and (float(trait_object.mb) < float(self.min_location_mb)):
continue
if (self.max_location_mb != None) and (float(trait_object.mb) > float(self.max_location_mb)):
continue
(trait_object.sample_r,
trait_object.sample_p,
trait_object.num_overlap) = self.correlation_data[trait]
# Set some sane defaults
trait_object.tissue_corr = 0
trait_object.tissue_pvalue = 0
trait_object.lit_corr = 0
if self.corr_type == "tissue" and tissue_corr_data != None:
trait_object.tissue_corr = tissue_corr_data[trait][1]
trait_object.tissue_pvalue = tissue_corr_data[trait][2]
elif self.corr_type == "lit":
trait_object.lit_corr = lit_corr_data[trait][1]
self.correlation_results.append(trait_object)
if self.corr_type != "lit" and self.dataset.type == "ProbeSet" and self.target_dataset.type == "ProbeSet":
self.do_lit_correlation_for_trait_list()
if self.corr_type != "tissue" and self.dataset.type == "ProbeSet" and self.target_dataset.type == "ProbeSet":
self.do_tissue_correlation_for_trait_list()
self.json_results = generate_corr_json(self.correlation_results, self.this_trait, self.dataset, self.target_dataset)
def __init__(self, kw):
assert ('type' in kw)
assert ('terms' in kw)
self.type = kw['type']
self.terms = kw['terms']
assert (is_str(self.type))
if self.type == "gene":
sql = """
SELECT
Species.`Name` AS species_name,
InbredSet.`Name` AS inbredset_name,
Tissue.`Name` AS tissue_name,
ProbeSetFreeze.Name AS probesetfreeze_name,
ProbeSet.Name AS probeset_name,
ProbeSet.Symbol AS probeset_symbol,
ProbeSet.`description` AS probeset_description,
ProbeSet.Chr AS chr,
ProbeSet.Mb AS mb,
ProbeSetXRef.Mean AS mean,
ProbeSetXRef.LRS AS lrs,
ProbeSetXRef.`Locus` AS locus,
ProbeSetXRef.`pValue` AS pvalue,
ProbeSetXRef.`additive` AS additive
FROM Species, InbredSet, ProbeSetXRef, ProbeSet, ProbeFreeze, ProbeSetFreeze, Tissue
WHERE InbredSet.`SpeciesId`=Species.`Id`
AND ProbeFreeze.InbredSetId=InbredSet.`Id`
AND ProbeFreeze.`TissueId`=Tissue.`Id`
AND ProbeSetFreeze.ProbeFreezeId=ProbeFreeze.Id
AND ( MATCH (ProbeSet.Name,ProbeSet.description,ProbeSet.symbol,alias,GenbankId, UniGeneId, Probe_Target_Description) AGAINST ('%s' IN BOOLEAN MODE) )
AND ProbeSet.Id = ProbeSetXRef.ProbeSetId
AND ProbeSetXRef.ProbeSetFreezeId=ProbeSetFreeze.Id
AND ProbeSetFreeze.confidentiality < 1
AND ProbeSetFreeze.public > 0
ORDER BY species_name, inbredset_name, tissue_name, probesetfreeze_name, probeset_name
LIMIT 6000
""" % (self.terms)
with Bench("Running query"):
logger.sql(sql)
re = g.db.execute(sql).fetchall()
self.trait_list = []
with Bench("Creating trait objects"):
for line in re:
this_trait = {}
this_trait['name'] = line[4]
this_trait['dataset'] = line[3]
this_trait['species'] = line[0]
this_trait['group'] = line[1]
this_trait['tissue'] = line[2]
this_trait['symbol'] = line[5]
this_trait['description'] = line[6]
this_trait['location_repr'] = 'N/A'
if (line[7] != "NULL"
and line[7] != "") and (line[8] != 0):
this_trait['location_repr'] = 'Chr%s: %.6f' % (
line[7], float(line[8]))
this_trait['mean'] = line[9]
this_trait['LRS_score_repr'] = "N/A"
if line[10] != "" and line[10] != None:
this_trait['LRS_score_repr'] = '%3.1f' % line[10]
this_trait['additive'] = "N/A"
if line[13] != "":
this_trait['additive'] = line[13]
#dataset = create_dataset(line[3], "ProbeSet", get_samplelist=False)
#trait_id = line[4]
#with Bench("Building trait object"):
#this_trait = GeneralTrait(dataset=dataset, name=trait_id, get_qtl_info=False, get_sample_info=False)
self.trait_list.append(this_trait)
elif self.type == "phenotype":
sql = """
SELECT
Species.`Name`,
InbredSet.`Name`,
PublishFreeze.`Name`,
PublishXRef.`Id`,
Phenotype.`Post_publication_description`,
Publication.`Authors`,
Publication.`Year`,
Publication.`PubMed_ID`,
PublishXRef.`LRS`,
PublishXRef.`additive`
FROM Species,InbredSet,PublishFreeze,PublishXRef,Phenotype,Publication
WHERE PublishXRef.`InbredSetId`=InbredSet.`Id`
AND PublishFreeze.`InbredSetId`=InbredSet.`Id`
AND InbredSet.`SpeciesId`=Species.`Id`
AND PublishXRef.`PhenotypeId`=Phenotype.`Id`
AND PublishXRef.`PublicationId`=Publication.`Id`
AND (Phenotype.Post_publication_description REGEXP "[[:<:]]%s[[:>:]]"
OR Phenotype.Pre_publication_description REGEXP "[[:<:]]%s[[:>:]]"
OR Phenotype.Pre_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]"
OR Phenotype.Post_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]"
OR Phenotype.Lab_code REGEXP "[[:<:]]%s[[:>:]]"
OR Publication.PubMed_ID REGEXP "[[:<:]]%s[[:>:]]"
OR Publication.Abstract REGEXP "[[:<:]]%s[[:>:]]"
OR Publication.Title REGEXP "[[:<:]]%s[[:>:]]"
OR Publication.Authors REGEXP "[[:<:]]%s[[:>:]]"
OR PublishXRef.Id REGEXP "[[:<:]]%s[[:>:]]")
ORDER BY Species.`Name`, InbredSet.`Name`, PublishXRef.`Id`
LIMIT 6000
""" % (self.terms, self.terms, self.terms, self.terms,
self.terms, self.terms, self.terms, self.terms,
self.terms, self.terms)
logger.sql(sql)
re = g.db.execute(sql).fetchall()
self.trait_list = []
with Bench("Creating trait objects"):
for line in re:
this_trait = {}
this_trait['name'] = line[3]
this_trait['dataset'] = line[2]
this_trait['species'] = line[0]
this_trait['group'] = line[1]
this_trait['description'] = line[4]
this_trait['authors'] = line[5]
this_trait['year'] = line[6]
if this_trait['year'].isdigit():
this_trait['pubmed_text'] = this_trait['year']
else:
this_trait['pubmed_text'] = "N/A"
if line[7] != "" and line[7] != None:
this_trait[
'pubmed_link'] = webqtlConfig.PUBMEDLINK_URL % line[
7]
else:
this_trait['pubmed_link'] = "N/A"
this_trait['LRS_score_repr'] = "N/A"
if line[8] != "" and line[8] != None:
this_trait['LRS_score_repr'] = '%3.1f' % line[8]
this_trait['additive'] = "N/A"
if line[9] != "":
this_trait['additive'] = line[9]
#dataset = create_dataset(line[2], "Publish")
#trait_id = line[3]
#this_trait = GeneralTrait(dataset=dataset, name=trait_id, get_qtl_info=True, get_sample_info=False)
self.trait_list.append(this_trait)
def __init__(self, kw):
assert('type' in kw)
assert('terms' in kw)
self.type = kw['type']
self.terms = kw['terms']
assert(is_str(self.type))
if self.type == "gene":
sql = """
SELECT
Species.`Name` AS species_name,
InbredSet.`Name` AS inbredset_name,
Tissue.`Name` AS tissue_name,
ProbeSetFreeze.Name AS probesetfreeze_name,
ProbeSetFreeze.FullName AS probesetfreeze_fullname,
ProbeSet.Name AS probeset_name,
ProbeSet.Symbol AS probeset_symbol,
CAST(ProbeSet.`description` AS BINARY) AS probeset_description,
ProbeSet.Chr AS chr,
ProbeSet.Mb AS mb,
ProbeSetXRef.Mean AS mean,
ProbeSetXRef.LRS AS lrs,
ProbeSetXRef.`Locus` AS locus,
ProbeSetXRef.`pValue` AS pvalue,
ProbeSetXRef.`additive` AS additive,
ProbeSetFreeze.Id AS probesetfreeze_id,
Geno.Chr as geno_chr,
Geno.Mb as geno_mb
FROM Species
INNER JOIN InbredSet ON InbredSet.`SpeciesId`=Species.`Id`
INNER JOIN ProbeFreeze ON ProbeFreeze.InbredSetId=InbredSet.`Id`
INNER JOIN Tissue ON ProbeFreeze.`TissueId`=Tissue.`Id`
INNER JOIN ProbeSetFreeze ON ProbeSetFreeze.ProbeFreezeId=ProbeFreeze.Id
INNER JOIN ProbeSetXRef ON ProbeSetXRef.ProbeSetFreezeId=ProbeSetFreeze.Id
INNER JOIN ProbeSet ON ProbeSet.Id = ProbeSetXRef.ProbeSetId
LEFT JOIN Geno ON ProbeSetXRef.Locus = Geno.Name AND Geno.SpeciesId = Species.Id
WHERE ( MATCH (ProbeSet.Name,ProbeSet.description,ProbeSet.symbol,ProbeSet.alias,ProbeSet.GenbankId, ProbeSet.UniGeneId, ProbeSet.Probe_Target_Description) AGAINST ('%s' IN BOOLEAN MODE) )
AND ProbeSetFreeze.confidentiality < 1
AND ProbeSetFreeze.public > 0
ORDER BY species_name, inbredset_name, tissue_name, probesetfreeze_name, probeset_name
LIMIT 6000
""" % (self.terms)
with Bench("Running query"):
logger.sql(sql)
re = g.db.execute(sql).fetchall()
trait_list = []
dataset_to_permissions = {}
with Bench("Creating trait objects"):
for i, line in enumerate(re):
this_trait = {}
this_trait['index'] = i + 1
this_trait['name'] = line[5]
this_trait['dataset'] = line[3]
this_trait['dataset_fullname'] = line[4]
this_trait['hmac'] = hmac.data_hmac('{}:{}'.format(line[5], line[3]))
this_trait['species'] = line[0]
this_trait['group'] = line[1]
this_trait['tissue'] = line[2]
this_trait['symbol'] = line[6]
if line[7]:
this_trait['description'] = line[7].decode('utf-8', 'replace')
else:
this_trait['description'] = "N/A"
this_trait['location_repr'] = 'N/A'
if (line[8] != "NULL" and line[8] != "") and (line[9] != 0):
this_trait['location_repr'] = 'Chr%s: %.6f' % (line[8], float(line[9]))
try:
this_trait['mean'] = '%.3f' % line[10]
except:
this_trait['mean'] = "N/A"
this_trait['LRS_score_repr'] = "N/A"
if line[11] != "" and line[11] != None:
this_trait['LRS_score_repr'] = '%3.1f' % line[11]
this_trait['additive'] = "N/A"
if line[14] != "" and line[14] != None:
this_trait['additive'] = '%.3f' % line[14]
this_trait['dataset_id'] = line[15]
this_trait['locus_chr'] = line[16]
this_trait['locus_mb'] = line[17]
dataset_ob = SimpleNamespace(id=this_trait["dataset_id"], type="ProbeSet",species=this_trait["species"])
if dataset_ob.id not in dataset_to_permissions:
permissions = check_resource_availability(dataset_ob)
dataset_to_permissions[dataset_ob.id] = permissions
else:
pemissions = dataset_to_permissions[dataset_ob.id]
if "view" not in permissions['data']:
continue
max_lrs_text = "N/A"
if this_trait['locus_chr'] != None and this_trait['locus_mb'] != None:
max_lrs_text = "Chr" + str(this_trait['locus_chr']) + ": " + str(this_trait['locus_mb'])
this_trait['max_lrs_text'] = max_lrs_text
trait_list.append(this_trait)
self.trait_count = len(trait_list)
self.trait_list = json.dumps(trait_list)
self.header_fields = ['Index',
'Record',
'Species',
'Group',
'Tissue',
'Dataset',
'Symbol',
'Description',
'Location',
'Mean',
'Max LRS',
'Max LRS Location',
'Additive Effect']
elif self.type == "phenotype":
search_term = self.terms
group_clause = ""
if "_" in self.terms:
if len(self.terms.split("_")[0]) == 3:
search_term = self.terms.split("_")[1]
group_clause = "AND InbredSet.`InbredSetCode` = '{}'".format(self.terms.split("_")[0])
sql = """
SELECT
Species.`Name`,
InbredSet.`Name`,
PublishFreeze.`Name`,
PublishFreeze.`FullName`,
PublishXRef.`Id`,
CAST(Phenotype.`Pre_publication_description` AS BINARY),
CAST(Phenotype.`Post_publication_description` AS BINARY),
Publication.`Authors`,
Publication.`Year`,
Publication.`PubMed_ID`,
PublishXRef.`LRS`,
PublishXRef.`additive`,
InbredSet.`InbredSetCode`,
PublishXRef.`mean`
FROM Species,InbredSet,PublishFreeze,PublishXRef,Phenotype,Publication
WHERE PublishXRef.`InbredSetId`=InbredSet.`Id`
AND PublishFreeze.`InbredSetId`=InbredSet.`Id`
AND InbredSet.`SpeciesId`=Species.`Id`
{0}
AND PublishXRef.`PhenotypeId`=Phenotype.`Id`
AND PublishXRef.`PublicationId`=Publication.`Id`
AND (Phenotype.Post_publication_description REGEXP "[[:<:]]{1}[[:>:]]"
OR Phenotype.Pre_publication_description REGEXP "[[:<:]]{1}[[:>:]]"
OR Phenotype.Pre_publication_abbreviation REGEXP "[[:<:]]{1}[[:>:]]"
OR Phenotype.Post_publication_abbreviation REGEXP "[[:<:]]{1}[[:>:]]"
OR Phenotype.Lab_code REGEXP "[[:<:]]{1}[[:>:]]"
OR Publication.PubMed_ID REGEXP "[[:<:]]{1}[[:>:]]"
OR Publication.Abstract REGEXP "[[:<:]]{1}[[:>:]]"
OR Publication.Title REGEXP "[[:<:]]{1}[[:>:]]"
OR Publication.Authors REGEXP "[[:<:]]{1}[[:>:]]"
OR PublishXRef.Id REGEXP "[[:<:]]{1}[[:>:]]")
ORDER BY Species.`Name`, InbredSet.`Name`, PublishXRef.`Id`
LIMIT 6000
""".format(group_clause, search_term)
logger.sql(sql)
re = g.db.execute(sql).fetchall()
trait_list = []
with Bench("Creating trait objects"):
for i, line in enumerate(re):
this_trait = {}
this_trait['index'] = i + 1
this_trait['name'] = str(line[4])
if len(str(line[12])) == 3:
this_trait['display_name'] = str(line[12]) + "_" + this_trait['name']
else:
this_trait['display_name'] = this_trait['name']
this_trait['dataset'] = line[2]
this_trait['dataset_fullname'] = line[3]
this_trait['hmac'] = hmac.data_hmac('{}:{}'.format(line[4], line[2]))
this_trait['species'] = line[0]
this_trait['group'] = line[1]
if line[9] != None and line[6] != None:
this_trait['description'] = line[6].decode('utf-8', 'replace')
elif line[5] != None:
this_trait['description'] = line[5].decode('utf-8', 'replace')
else:
this_trait['description'] = "N/A"
if line[13] != None and line[13] != "":
this_trait['mean'] = line[13]
else:
this_trait['mean'] = "N/A"
this_trait['authors'] = line[7]
this_trait['year'] = line[8]
if this_trait['year'].isdigit():
this_trait['pubmed_text'] = this_trait['year']
else:
this_trait['pubmed_text'] = "N/A"
if line[9] != "" and line[9] != None:
this_trait['pubmed_link'] = webqtlConfig.PUBMEDLINK_URL % line[8]
else:
this_trait['pubmed_link'] = "N/A"
if line[12]:
this_trait['display_name'] = line[12] + "_" + str(this_trait['name'])
this_trait['LRS_score_repr'] = "N/A"
if line[10] != "" and line[10] != None:
this_trait['LRS_score_repr'] = '%3.1f' % line[10]
this_trait['additive'] = "N/A"
if line[11] != "" and line[11] != None:
this_trait['additive'] = '%.3f' % line[11]
this_trait['max_lrs_text'] = "N/A"
trait_ob = create_trait(dataset_name=this_trait['dataset'], name=this_trait['name'], get_qtl_info=True, get_sample_info=False)
if not trait_ob:
continue
if this_trait['dataset'] == this_trait['group'] + "Publish":
try:
if trait_ob.locus_chr != "" and trait_ob.locus_mb != "":
this_trait['max_lrs_text'] = "Chr" + str(trait_ob.locus_chr) + ": " + str(trait_ob.locus_mb)
except:
this_trait['max_lrs_text'] = "N/A"
trait_list.append(this_trait)
self.trait_count = len(trait_list)
self.trait_list = json.dumps(trait_list)
self.header_fields = ['Index',
'Species',
'Group',
'Record',
'Description',
'Authors',
'Year',
'Max LRS',
'Max LRS Location',
'Additive Effect']
def marker_regression_page():
initial_start_vars = request.form
logger.debug("Marker regression called with initial_start_vars:",
initial_start_vars.items())
temp_uuid = initial_start_vars['temp_uuid']
wanted = ('trait_id', 'dataset', 'method', 'trimmed_markers',
'selected_chr', 'chromosomes', 'mapping_scale', 'score_type',
'suggestive', 'significant', 'num_perm', 'permCheck',
'perm_output', 'num_bootstrap', 'bootCheck', 'bootstrap_results',
'LRSCheck', 'maf', 'manhattan_plot', 'control_marker',
'control_marker_db', 'do_control', 'genofile', 'pair_scan',
'startMb', 'endMb', 'graphWidth', 'lrsMax', 'additiveCheck',
'showSNP', 'showGenes', 'viewLegend', 'haplotypeAnalystCheck',
'mapmethod_rqtl_geno', 'mapmodel_rqtl_geno')
start_vars = {}
for key, value in initial_start_vars.iteritems():
if key in wanted or key.startswith(('value:')):
start_vars[key] = value
logger.debug("Marker regression called with start_vars:", start_vars)
version = "v3"
key = "marker_regression:{}:".format(version) + json.dumps(start_vars,
sort_keys=True)
logger.info("key is:", pf(key))
with Bench("Loading cache"):
result = None # Just for testing
#result = Redis.get(key)
#logger.info("************************ Starting result *****************")
#logger.info("result is [{}]: {}".format(type(result), result))
#logger.info("************************ Ending result ********************")
if result:
logger.info("Cache hit!!!")
with Bench("Loading results"):
result = pickle.loads(result)
else:
logger.info("Cache miss!!!")
with Bench("Total time in MarkerRegression"):
template_vars = marker_regression.MarkerRegression(
start_vars, temp_uuid)
if template_vars.mapping_method != "gemma" and template_vars.mapping_method != "plink":
template_vars.js_data = json.dumps(template_vars.js_data,
default=json_default_handler,
indent=" ")
result = template_vars.__dict__
if result['pair_scan']:
with Bench("Rendering template"):
img_path = result['pair_scan_filename']
logger.info("img_path:", img_path)
initial_start_vars = request.form
logger.info("initial_start_vars:", initial_start_vars)
imgfile = open(TEMPDIR + img_path, 'rb')
imgdata = imgfile.read()
imgB64 = imgdata.encode("base64")
bytesarray = array.array('B', imgB64)
result['pair_scan_array'] = bytesarray
rendered_template = render_template("pair_scan_results.html",
**result)
else:
#for item in template_vars.__dict__.keys():
# logger.info(" ---**--- {}: {}".format(type(template_vars.__dict__[item]), item))
gn1_template_vars = marker_regression_gn1.MarkerRegression(
result).__dict__
#pickled_result = pickle.dumps(result, pickle.HIGHEST_PROTOCOL)
#logger.info("pickled result length:", len(pickled_result))
#Redis.set(key, pickled_result)
#Redis.expire(key, 1*60)
with Bench("Rendering template"):
if (gn1_template_vars['mapping_method']
== "gemma") or (gn1_template_vars['mapping_method']
== "plink"):
gn1_template_vars.pop('qtlresults', None)
print("TEMPLATE KEYS:", list(gn1_template_vars.keys()))
rendered_template = render_template(
"marker_regression_gn1.html", **gn1_template_vars)
# with Bench("Rendering template"):
# if result['pair_scan'] == True:
# img_path = result['pair_scan_filename']
# logger.info("img_path:", img_path)
# initial_start_vars = request.form
# logger.info("initial_start_vars:", initial_start_vars)
# imgfile = open(TEMPDIR + '/' + img_path, 'rb')
# imgdata = imgfile.read()
# imgB64 = imgdata.encode("base64")
# bytesarray = array.array('B', imgB64)
# result['pair_scan_array'] = bytesarray
# rendered_template = render_template("pair_scan_results.html", **result)
# else:
# rendered_template = render_template("marker_regression.html", **result)
# rendered_template = render_template("marker_regression_gn1.html", **gn1_template_vars)
return rendered_template