hapsb_ind(
iid,
chs=range(1, 23),
path_targets_prefix=f"{basepath}/hdf5",
h5_path1000g=
"/mnt/archgen/users/yilei/Data/1000G/1000g1240khdf5/all1240/chr",
meta_path_ref=
"/mnt/archgen/users/yilei/Data/1000G/1000g1240khdf5/all1240/meta_df_all.csv",
folder_out=f"{basepath}/hapRoh/",
prefix_out="",
e_model="readcount_contam",
p_model="SardHDF5",
post_model="Standard",
processes=args.processes,
delete=False,
output=True,
save=True,
save_fp=False,
n_ref=2504,
diploid_ref=True,
exclude_pops=[],
readcounts=True,
random_allele=False,
c=0.05,
roh_min_l_final=0.06,
roh_in=1,
roh_out=20,
roh_jump=300,
e_rate=err,
e_rate_ref=1e-3,
logfile=True,
combine=True,
file_result="_roh_full.csv")
hapsb_ind(
iid=iid,
chs=range(1, 23),
path_targets=path_target, # The path before the .ind, .snp, .geno
h5_path1000g='./Data/1000Genomes/HDF5/1240kHDF5/all1240int8/chr',
meta_path_ref='./Data/1000Genomes/Individuals/meta_df_all.csv',
folder_out="./Empirical/1240k/SA_Readcounts/IPK12_rep/",
prefix_out='',
e_model='haploid',
p_model='MosaicHDF5',
post_model='Standard',
processes=1,
delete=True,
output=True,
save=True,
save_fp=False,
n_ref=2504,
exclude_pops=[],
readcounts=False,
random_allele=True,
roh_in=1,
roh_out=20,
roh_jump=300,
e_rate=0.01,
e_rate_ref=0.0,
cutoff_post=0.999,
max_gap=0,
roh_min_l=0.01,
logfile=True,
combine=True,
file_result='_roh_full.csv')
hapsb_ind(
iid,
chs=range(1, 2),
path_targets=f"{outFolder}/data.h5",
h5_path1000g=path1000G,
meta_path_ref=
"/mnt/archgen/users/yilei/Data/1000G/1000g1240khdf5/all1240/meta_df_all.csv",
folder_out=f"{outFolder}/hapRoh/",
prefix_out="",
e_model="readcount_contam",
p_model="SardHDF5",
post_model="Standard",
processes=1,
delete=True,
output=True,
save=True,
save_fp=False,
c=con,
conPop=["CEU"],
n_ref=2504,
diploid_ref=True,
exclude_pops=["CHB"],
readcounts=True,
random_allele=False,
roh_in=1,
roh_out=20,
roh_jump=300,
e_rate=0.01,
e_rate_ref=1e-3,
cutoff_post=0.999,
max_gap=0.005,
logfile=False,
combine=True,
file_result="_roh_full.csv")
raise RuntimeError(f"Index {i} out of Range of High Coverage ancients.")
iid = df[id_col].values[i]
return iid
#########################################################
#########################################################
if __name__ == "__main__":
if len(sys.argv) < 2:
raise RuntimeError("Script needs argument (indiviual i)")
run_nr = int(sys.argv[1]) # The Parameter passed to the Python Script from outside
#df_anno = load_eigenstrat_anno(min_snps=400000)
#iid = get_iid_from_df(df_anno, run_nr, id_col="Instance ID")
#df_anno = load_meta_csv(path = "./Data/ReichLabEigenstrat/Raw/meta.v42_additional.csv",
# min_snps=400000)
df_anno = load_meta_csv(path = "./Data/ReichLabEigenstrat/Raw/meta.v42_old.csv",
min_snps=400000)
iid=get_iid_from_df(df_anno, run_nr, id_col="iid")
hapsb_ind(iid, chs=range(1, 23), processes=1, delete=False, output=True,
save=True, save_fp=False, n_ref=2504, exclude_pops=[],
e_model='haploid', p_model='EigenstratPacked', readcounts=False,
destroy_phase=True, post_model='Standard',
path_targets="./Data/ReichLabEigenstrat/Raw.v42.4/v42.4.1240K",
h5_path1000g='./Data/1000Genomes/HDF5/1240kHDF5/all1240int8/chr',
meta_path_ref='./Data/1000Genomes/Individuals/meta_df_all.csv',
base_out_folder='./Empirical/Eigenstrat/Reichall/v42_core/', prefix_out='',
roh_in=1, roh_out=20, roh_jump=300, e_rate=0.01, e_rate_ref=0.0, max_gap=0,
cutoff=0.999, l_cutoff=0.01, logfile=True, combine=True, file_name='_roh_full.csv')