gwaslab 3.6.5__py3-none-any.whl → 3.6.7__py3-none-any.whl

gwaslab/__init__.py

@@ -3,51 +3,61 @@ from gwaslab.g_Sumstats_polars import Sumstatsp
 from gwaslab.g_SumstatsT import SumstatsT
 from gwaslab.g_SumstatsPair import SumstatsPair
 from gwaslab.g_SumstatsMulti import SumstatsMulti
-from gwaslab.util_in_convert_h2 import h2_obs_to_liab
-from gwaslab.util_in_convert_h2 import _get_per_snp_r2
-from gwaslab.util_in_convert_h2 import h2_se_to_p
-from gwaslab.viz_plot_compare_effect import compare_effect
-from gwaslab.io_read_ldsc import read_ldsc
-from gwaslab.io_read_ldsc import read_popcorn
-from gwaslab.viz_plot_forestplot import plot_forest
-from gwaslab.viz_plot_miamiplot import plot_miami
-from gwaslab.viz_plot_miamiplot2 import plot_miami2
-from gwaslab.viz_plot_rg_heatmap import plot_rg
-from gwaslab.viz_plot_stackedregional import plot_stacked_mqq
-from gwaslab.util_ex_gwascatalog import gwascatalog_trait
-from gwaslab.bd_common_data import get_NC_to_chr
-from gwaslab.bd_common_data import get_NC_to_number
-from gwaslab.bd_common_data import get_chr_to_NC
-from gwaslab.bd_common_data import get_number_to_NC
-from gwaslab.bd_common_data import get_chr_list
-from gwaslab.bd_common_data import get_number_to_chr
-from gwaslab.bd_common_data import get_chr_to_number
-from gwaslab.bd_common_data import get_high_ld
-from gwaslab.bd_common_data import get_format_dict
-from gwaslab.bd_common_data import get_formats_list
-from gwaslab.bd_download import update_formatbook
-from gwaslab.bd_download import list_formats
-from gwaslab.bd_download import check_format
-from gwaslab.bd_download import check_available_ref
-from gwaslab.bd_download import update_available_ref
-from gwaslab.bd_download import check_downloaded_ref
-from gwaslab.bd_download import download_ref
-from gwaslab.bd_download import check_available_ref
-from gwaslab.bd_download import remove_file
-from gwaslab.bd_download import get_path
-from gwaslab.bd_download import update_record
-from gwaslab.io_to_pickle import dump_pickle
-from gwaslab.io_to_pickle import load_pickle
-from gwaslab.bd_config import options
+from gwaslab.g_SumstatsSet import SumstatsSet
 from gwaslab.g_version import _show_version as show_version
-from gwaslab.util_in_calculate_power import get_power
-from gwaslab.util_in_calculate_power import get_beta
-from gwaslab.viz_plot_trumpetplot import plot_power
-from gwaslab.viz_plot_trumpetplot import plot_power_x
-from gwaslab.util_ex_process_h5 import process_vcf_to_hfd5
-from gwaslab.util_ex_run_susie import _run_susie_rss as run_susie_rss
-from gwaslab.io_read_tabular import _read_tabular as read_tabular
-from gwaslab.util_in_meta import meta_analyze
-from gwaslab.viz_plot_scatter_with_reg import scatter
-from gwaslab.util_in_fill_data import rank_based_int
-from gwaslab.g_SumstatsSet import SumstatsSet
+
+from gwaslab.util.util_in_convert_h2 import h2_obs_to_liab
+from gwaslab.util.util_in_convert_h2 import _get_per_snp_r2
+from gwaslab.util.util_in_convert_h2 import h2_se_to_p
+from gwaslab.util.util_in_calculate_power import get_power
+from gwaslab.util.util_in_calculate_power import get_beta
+from gwaslab.util.util_ex_gwascatalog import gwascatalog_trait
+from gwaslab.util.util_ex_process_h5 import process_vcf_to_hfd5
+from gwaslab.util.util_ex_run_susie import _run_susie_rss as run_susie_rss
+from gwaslab.util.util_in_meta import meta_analyze
+from gwaslab.util.util_in_fill_data import rank_based_int
+
+from gwaslab.io.io_read_ldsc import read_ldsc
+from gwaslab.io.io_read_ldsc import read_popcorn
+from gwaslab.io.io_to_pickle import dump_pickle
+from gwaslab.io.io_to_pickle import load_pickle
+from gwaslab.io.io_read_tabular import _read_tabular as read_tabular
+
+from gwaslab.viz.viz_plot_compare_effect import compare_effect
+from gwaslab.viz.viz_plot_forestplot import plot_forest
+from gwaslab.viz.viz_plot_miamiplot import plot_miami
+from gwaslab.viz.viz_plot_miamiplot2 import plot_miami2
+from gwaslab.viz.viz_plot_rg_heatmap import plot_rg
+from gwaslab.viz.viz_plot_stackedregional import plot_stacked_mqq
+from gwaslab.viz.viz_plot_trumpetplot import plot_power
+from gwaslab.viz.viz_plot_trumpetplot import plot_power_x
+from gwaslab.viz.viz_plot_scatter_with_reg import scatter
+
+from gwaslab.bd.bd_common_data import get_NC_to_chr
+from gwaslab.bd.bd_common_data import get_NC_to_number
+from gwaslab.bd.bd_common_data import get_chr_to_NC
+from gwaslab.bd.bd_common_data import get_number_to_NC
+from gwaslab.bd.bd_common_data import get_chr_list
+from gwaslab.bd.bd_common_data import get_number_to_chr
+from gwaslab.bd.bd_common_data import get_chr_to_number
+from gwaslab.bd.bd_common_data import get_high_ld
+from gwaslab.bd.bd_common_data import get_format_dict
+from gwaslab.bd.bd_common_data import get_formats_list
+from gwaslab.bd.bd_download import update_formatbook
+from gwaslab.bd.bd_download import list_formats
+from gwaslab.bd.bd_download import check_format
+from gwaslab.bd.bd_download import check_available_ref
+from gwaslab.bd.bd_download import update_available_ref
+from gwaslab.bd.bd_download import check_downloaded_ref
+from gwaslab.bd.bd_download import download_ref
+from gwaslab.bd.bd_download import check_available_ref
+from gwaslab.bd.bd_download import remove_file
+from gwaslab.bd.bd_download import get_path
+from gwaslab.bd.bd_download import update_record
+from gwaslab.bd.bd_config import options
+
+
+
+
+
+

gwaslab/{bd_common_data.py → bd/bd_common_data.py}

@@ -4,14 +4,15 @@ import tarfile
 import requests
 import pandas as pd
 from os import path
+from pathlib import Path
 from pyensembl import Genome
 from gtfparse import read_gtf
 # read_gtf -> v1.3.0
 from gwaslab.g_Log import Log
-from gwaslab.bd_download import download_ref
-from gwaslab.bd_download import check_and_download
-from gwaslab.bd_download import update_formatbook
-from gwaslab.bd_config import options
+from gwaslab.bd.bd_download import download_ref
+from gwaslab.bd.bd_download import check_and_download
+from gwaslab.bd.bd_download import update_formatbook
+from gwaslab.bd.bd_config import options
 
 #hard-coded data
 def get_chr_to_NC(build,inverse=False):
@@ -188,9 +189,11 @@ def get_number_to_chr(in_chr=False,xymt=["X","Y","MT"],xymt_num=[23,24,25],prefi
 ###################################################################################################################    
 def get_high_ld(build="19"):
     if build=="19":
-        data_path =  path.dirname(__file__) + '/data/high_ld/high_ld_hla_hg19.bed.gz'
+        #data_path =  path.dirname(__file__) + '/data/high_ld/high_ld_hla_hg19.bed.gz'
+        data_path = path.join( Path(__file__).parents[1], "data","high_ld","high_ld_hla_hg19.bed.gz")
     elif build=="38":
-        data_path =  path.dirname(__file__) + '/data/high_ld/high_ld_hla_hg38.bed.gz'
+        #data_path =  path.dirname(__file__) + '/data/high_ld/high_ld_hla_hg38.bed.gz'
+        data_path = path.join( Path(__file__).parents[1], "data","high_ld","high_ld_hla_hg38.bed.gz")
     return data_path
 
 def get_format_dict(fmt,inverse=False):
@@ -347,9 +350,7 @@ def _inch_to_point(inch):
     #points: 1/72 inch
     return inch*72
         
-        
-        
-        
+NA_STRINGS=["na","NA","Na","Nan","NaN","<NA>","null","NULL","#N/A","#VALUE!","N/A","n/a","missing",""]        
         
         
         

gwaslab/bd/bd_config.py

@@ -0,0 +1,28 @@
+from os import path
+from pathlib import Path
+
+class Options_dic:
+    def __init__(self,path_dic):
+        self.paths = path_dic
+        self.default = path_dic.copy()
+    def set_option(self,key,path):
+        self.paths[key] = path
+    def reset_option(self):
+        self.paths = self.default.copy()
+
+#default_dic={
+#    "config": path.dirname(__file__) + "/data/config.json",
+#    "reference": path.dirname(__file__) + "/data/reference.json",
+#    "formatbook": path.dirname(__file__) + "/data/formatbook.json",
+#    "data_directory": path.expanduser('~') + "/.gwaslab/"
+#}
+
+default_dic={
+    "config": path.join(Path(__file__).parents[1], "data","config.json"),
+    "reference": path.join(Path(__file__).parents[1], "data","reference.json"),
+    "formatbook": path.join(Path(__file__).parents[1], "data","formatbook.json"),
+    "data_directory": path.expanduser('~') + "/.gwaslab/"
+}
+
+
+options = Options_dic(default_dic)

gwaslab/{bd_download.py → bd/bd_download.py}

@@ -6,7 +6,7 @@ import requests
 import shutil
 import hashlib
 from gwaslab.g_Log import Log
-from gwaslab.bd_config import options
+from gwaslab.bd.bd_config import options
 import re
 from gwaslab.g_version import _get_version
 #### config ##############################################################################################

gwaslab/{bd_get_hapmap3.py → bd/bd_get_hapmap3.py}

@@ -1,9 +1,10 @@
 import pandas as pd
 from os import path
 from gwaslab.g_Log import Log
-from gwaslab.qc_fix_sumstats import start_to
-from gwaslab.qc_fix_sumstats import skipped
-from gwaslab.qc_fix_sumstats import finished
+from gwaslab.qc.qc_fix_sumstats import start_to
+from gwaslab.qc.qc_fix_sumstats import skipped
+from gwaslab.qc.qc_fix_sumstats import finished
+from pathlib import Path
 
 #A unique identifier (e.g., the rs number)
 #Allele 1 (effect allele)
@@ -32,10 +33,12 @@ def gethapmap3(sumstats,rsid="rsID",chrom="CHR", pos="POS", ea="EA", nea="NEA",b
 
     ############################################################################################
     if build=="19":
-        data_path =  path.dirname(__file__) + '/data/hapmap3_SNPs/hapmap3_db150_hg19.snplist.gz'
+        #data_path =  path.dirname(__file__) + '/data/hapmap3_SNPs/hapmap3_db150_hg19.snplist.gz'
+        data_path = path.join( Path(__file__).parents[1], "data","hapmap3_SNPs","hapmap3_db150_hg19.snplist.gz")
     elif build=="38":
-        data_path =  path.dirname(__file__) + '/data/hapmap3_SNPs/hapmap3_db151_hg38.snplist.gz'
-    
+        #data_path =  path.dirname(__file__) + '/data/hapmap3_SNPs/hapmap3_db151_hg38.snplist.gz'
+        data_path = path.join( Path(__file__).parents[1], "data","hapmap3_SNPs","hapmap3_db151_hg38.snplist.gz")
+
     log.write(" -Loading Hapmap3 variants from built-in datasets...", verbose=verbose)
     
     if match_allele:

gwaslab/bd/bd_path_manager.py

@@ -0,0 +1,110 @@
+import os
+from gwaslab.g_Log import Log
+
+
+def _path( *args,
+                 out = None,
+                 directory = None,
+                 tmp = False,
+                 prefix=None,
+                 study = None,
+                 nstudy=None,
+                 trait = None,
+                 exposure = None,
+                 outcome = None,
+                 chrom = None,
+                 rsid = None,
+                 snpid = None,
+                 locus = None,
+                 loci = None, 
+                 analysis = None,
+                 mode = None,
+                 method = None,
+                 ancestry = None,
+                 population = None,
+                 sample_size = None,
+                 genotyping = None, 
+                 pid = None,
+                 build = None,
+                 suffix = None,
+                 log = Log(),
+                 verbose=True
+                 ):
+    '''
+    Create path for files generated by gwaslab.
+
+    If out is provided, out will be checked if it is a dir.
+    If not, out will be parsed into dirname and basename.
+
+    '''
+    out_basename = ""
+
+    if out is not None:
+        if os.path.isdir(out):
+            directory = out
+            log.write( "Directory detected: {}".format(directory), verbose=verbose)
+        else:
+            directory = os.path.dirname(out)
+            log.write( "Directory detected: {}".format(directory), verbose=verbose)
+            out_basename = os.path.basename(out)
+            log.write( "Basename detected: {}".format(out_basename), verbose=verbose)
+
+    if out_basename == "":
+        # create default path
+        ###############################################################################################################################################
+        path_list = []
+
+        # ordered components excluding directory, suffix
+        path_order = [
+            "prefix", "study", "nstudy", "trait", "exposure", "outcome", 
+            "chrom", "rsid", "snpid", "locus", "loci", "analysis", "mode_methods", 
+            "ancestry", "population","sample_size", "genotyping", "pid", "build"
+        ]
+        
+        # create default path
+        ###############################################################################################################################################
+        if tmp == True:
+            pid = id(path_list)
+        
+        ###############################################################################################################################################
+        all_args = locals()
+        for key,value in all_args.items():
+            if key in path_order:
+                if value is not None:
+                    if value !=False:
+                        path_list.append(value)
+
+        # merge path components
+        path_list = list(map(str, path_list))  + list(map(str, args))
+        path_list = list(map(lambda x: x.replace("_","-") , path_list))
+
+        if tmp == True:
+            path_list.insert(0, "_gwaslab")
+
+        log.write( "Path component detected: {}".format(path_list), verbose=verbose)
+
+        path = "_".join(path_list)
+    else:
+        # use user-provided path
+        path = out_basename
+    ###############################################################################################################################################
+
+    # add directory
+    if directory is not None:
+        path = os.path.join(directory, path)
+    else:
+        path = os.path.join("./", path)
+    ###############################################################################################################################################
+
+    # add file extension
+    if suffix is not None:
+        path = ".".join([path, suffix])
+    ###############################################################################################################################################
+
+    log.write( "Creating path: {}".format(path), verbose=verbose)
+
+    return path
+
+def _process_out(out):
+    out_dirname = os.path.dirname(out)
+    out_basename = os.path.base_name(out)