def run():
params = read_run_params()
run = params["current_run"]
out_home = params["container"] + "output/"
out_dir = out_home + run + "/"
##### generate genome wide variants
if params["source"] == "alignment_all":
df = run_alignment_analysis(params, "alignment_all")
variant_screener.genomewide_mutations(df, out_dir, run)
elif params["source"] == "alignment_current":
df = run_alignment_analysis(params, "alignment_current")
variant_screener.genomewide_mutations(df, out_dir, run)
def run():
params = read_run_params()
run = params["current_run"]
out_home = params["container"] + "output/"
out_dir = out_home + run + "/"
##### preprare for variant calling
df_muttable = pd.read_excel(out_dir + "1_genomic_mutations_" + run +
".xlsx")
if params["source"] == "alignment_current":
df_muttable_prev = pd.read_excel(
out_home + "/previous_genomic_table/1_genomic_mutations_all.xlsx")
df_muttable = df_muttable.append(df_muttable_prev, ignore_index=True)
df_muttable.drop_duplicates("strain", inplace=True)
df_muttable.to_excel(out_dir + "1_genomic_mutations_all.xlsx",
index=False)
df_muttable.to_excel(
out_home + "/previous_genomic_table/1_genomic_mutations_all_" +
run + ".xlsx",
index=False)
df_muttable.nucleotide_change = df_muttable.nucleotide_change.apply(
ast.literal_eval)
df_muttable.nt_aa_pair = df_muttable.nt_aa_pair.apply(ast.literal_eval)
# #### generate per variant summary with pangolin
db_pangolin = params[
"container"] + "pangolin_analysis/pangolin_lineage_assignment_for_pipeline_" + run + ".xlsx"
db = out_dir + "/database/5_strains_run_group_analysis_table_with_samplesheet.csv"
variant_screener.variant_screener_per_variant_summary_with_pangolin(
df_muttable, db, db_pangolin, out_dir, run)
print("check...")
print(df_muttable.head())
# generate_snp_table
log_msg("generating snp table for s protein..")
df_muttable.columns = [
"strain", "total_mutations", "nucleotide_change", "nt_aa_pair",
"deletions"
]
mutation.generate_snp_table(df_muttable, db, out_dir, run)
variant_screener.variant_screener_summary_pangolin(df_muttable, out_dir,
run)
def get_combine_df():
params = read_run_params()
all_strains = []
nta_dir = params["container"]+"input_alignment/"
nta_files = params["nta_group_v1"]
for nta_group in sorted(nta_files) :
log_msg("run group is - "+ nta_group)
align_file = nta_files[nta_group].split(",")[0]
adj = int(nta_files[nta_group].split(",")[1])
if "reference" in nta_group:
all_strains.extend(genomicSequenceFromAlignment(nta_dir+align_file,reference=True))
else:
all_strains.extend(genomicSequenceFromAlignment(nta_dir+align_file,adjustment=adj))
df = pd.DataFrame(all_strains)
df = filterMainAlignment(df,"cds")
return df
import pandas as pd
import numpy as np
from datetime import timedelta
import gen_utils.gen_covid as covid
from gen_utils.gen_io import read_run_params,log_msg
import sys
params = read_run_params()
run = params["current_run"]
out_dir = params["container"]+"output/"+run+"/"
df = pd.read_csv(out_dir+"4_mcov_strain_variant_map_covid_pangolin_db_input_"+run+".csv")
df = df[df.quality=="HQ"]
start_date = sys.argv[1]
end_date = sys.argv[2]
dfs=[]
for voi in covid.covid_variants.pangolin:
print(voi)
###take unique patients with variant
keep_mrns_variant = np.unique(df[df.variant==voi]["MRN"])
df_mrns = df[df.MRN.isin(keep_mrns_variant)]
df_mrns = df_mrns[df_mrns.variant==voi] ###important step--remove non b117 variant
df_mrns.sort_values("COLLECTION_DT",inplace=True)
df_mrns.drop_duplicates("MRN",keep="first",inplace=True)
keep_mrns_not_variant = np.unique(df[df.variant!=voi]["MRN"])
df_mrns_not_variant = df[df.MRN.isin(keep_mrns_not_variant)]
df_mrns_not_variant = df_mrns_not_variant[df_mrns_not_variant.variant!=voi]
df_mrns_not_variant.sort_values("COLLECTION_DT",inplace=True)
df_mrns_not_variant.drop_duplicates("MRN",keep="first",inplace=True)
def getcon():
params = read_run_params()
SQLALCHEMY_DATABASE_URI = "mysql+pymysql://" + params["dbcred"]
sqlEngine = sqlalchemy.create_engine(SQLALCHEMY_DATABASE_URI, echo=False)
dbConnection = sqlEngine.connect()
return dbConnection