gwaslab 3.4.44__py3-none-any.whl → 3.4.46__py3-none-any.whl

gwaslab/__init__.py

@@ -44,4 +44,5 @@ 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.io_read_tabular import _read_tabular as read_tabular
+from gwaslab.util_in_meta import meta_analyze

gwaslab/bd_common_data.py

@@ -298,6 +298,28 @@ def gtf_to_protein_coding(gtfpath,log=Log(),verbose=True):
 
     return protein_coding_path
 
+def gtf_to_all_gene(gtfpath,log=Log(),verbose=True):
+    all_gene_path = gtfpath[:-6]+"all_genes.gtf.gz"
+    # if not existing, extract protein coding records and output to a new file
+    if not path.isfile(all_gene_path):
+        
+        # get gene list
+        log.write(" - Extracting genes from {}".format(gtfpath),verbose=verbose)
+        gtf = read_gtf(gtfpath,usecols=["feature","gene_biotype","gene_id","gene_name"])
+        gene_list = gtf.loc[gtf["feature"]=="gene","gene_id"].values
+        log.write(" - Loaded {} genes.".format(len(gene_list)),verbose=verbose)
+        
+        # extract entry using csv
+        gtf_raw = pd.read_csv(gtfpath,sep="\t",header=None,comment="#",dtype="string")
+        gtf_raw["_gene_id"] = gtf_raw[8].str.extract(r'gene_id "([\w\.-]+)"')
+        gtf_raw = gtf_raw.loc[ gtf_raw["_gene_id"].isin(gene_list) ,:]
+        gtf_raw = gtf_raw.drop("_gene_id",axis=1)
+        
+        log.write(" - Extracted records are saved to : {} ".format(all_gene_path),verbose=verbose)
+        gtf_raw.to_csv(all_gene_path, header=None, index=None, sep="\t")
+
+    return all_gene_path
+
 ####################################################################################################################   
 # From BioPython: https://github.com/biopython/biopython/blob/c5a6b1374267d769b19c1022b4b45472316e78b4/Bio/Seq.py#L36
 def _maketrans(complement_mapping):

gwaslab/g_Sumstats.py

@@ -121,6 +121,7 @@ class Sumstats():
              snpr2=None,
              status=None,
              other=[],
+             usekeys=None,
              direction=None,
              verbose=True,
              study="Study_1",
@@ -200,6 +201,7 @@ class Sumstats():
           trait=trait,
           status=status,
           other=other,
+          usekeys=usekeys,
           verbose=verbose,
           readargs=readargs,
           log=self.log)

gwaslab/g_SumstatsPair.py

@@ -139,7 +139,7 @@ class SumstatsPair( ):
         self.clumps["clumps"], self.clumps["plink_log"] = _clump(self.data, log=self.log, p="P_1",mlog10p="MLOG10P_1", study = self.study_name, **kwargs)
 
     def to_coloc(self,**kwargs):
-        self.to_finemapping_file_path, self.plink_log = tofinemapping(self.data,study=self.study_name,suffixes=self.suffixes,log=self.log,**kwargs)
+        self.to_finemapping_file_path, output_file_list, self.plink_log = tofinemapping(self.data,study=self.study_name,suffixes=self.suffixes,log=self.log,**kwargs)
 
     def run_coloc_susie(self,**kwargs):
 

gwaslab/g_vchange_status.py

@@ -1,13 +1,15 @@
 import pandas as pd
 
+CATEGORIES = {str(j+i) for j in [1900000,3800000,9700000,9800000,9900000] for i in range(0,100000)}
+
 def vchange_status(status,digit,before,after):
     dic={}
     for i in range(len(before)):
         dic[before[i]]=after[i]
     if digit>1:
-        return status.str[:digit-1]+status.str[digit-1].replace(dic)+status.str[digit:]
+        return pd.Categorical(status.str[:digit-1]+status.str[digit-1].replace(dic)+status.str[digit:],categories=CATEGORIES)
     else:
-        return status.str[digit-1].replace(dic)+status.str[digit:]
+        return pd.Categorical(status.str[digit-1].replace(dic)+status.str[digit:],categories=CATEGORIES)
 
 def copy_status(from_status,to_status, digit):
     if digit>1:

gwaslab/g_version.py

@@ -15,8 +15,8 @@ def _get_version():
 def gwaslab_info():
     # version meta information
     dic={
-   "version":"3.4.44",
-   "release_date":"20240424"
+   "version":"3.4.46",
+   "release_date":"20240624"
     }
     return dic   
 

gwaslab/hm_harmonize_sumstats.py

@@ -355,7 +355,11 @@ def oldcheckref(sumstats,ref_seq,chrom="CHR",pos="POS",ea="EA",nea="NEA",status=
     
     log.write("\n",end="",show_time=False,verbose=verbose) 
         
-    sumstats[status] = sumstats[status].astype("string")
+    CATEGORIES = {str(j+i) for j in [1900000,3800000,9700000,9800000,9900000] for i in range(0,100000)}
+    sumstats[status] = pd.Categorical(sumstats[status],categories=CATEGORIES)
+    #sumstats[status] = sumstats[status].astype("string")
+
+
     available_to_check =sum( (~sumstats[pos].isna()) & (~sumstats[nea].isna()) & (~sumstats[ea].isna()))
     status_0=sum(sumstats["STATUS"].str.match("\w\w\w\w\w[0]\w", case=False, flags=0, na=False))
     status_3=sum(sumstats["STATUS"].str.match("\w\w\w\w\w[3]\w", case=False, flags=0, na=False))
@@ -669,9 +673,11 @@ def checkref(sumstats,ref_seq,chrom="CHR",pos="POS",ea="EA",nea="NEA",status="ST
         sumstats_to_check = sumstats.loc[to_check_ref,[chrom,pos,ea,nea,status]]
         sumstats.loc[to_check_ref,status] = check_status(sumstats_to_check, all_records_dict, log=log, verbose=verbose)
         log.write(" -Finished checking records", verbose=verbose) 
- 
-    sumstats[status] = sumstats[status].astype("string")
-        
+    
+    CATEGORIES = {str(j+i) for j in [1900000,3800000,9700000,9800000,9900000] for i in range(0,100000)}
+    sumstats[status] = pd.Categorical(sumstats[status],categories=CATEGORIES)
+    #sumstats[status] = sumstats[status].astype("string")
+
     available_to_check =sum( (~sumstats[pos].isna()) & (~sumstats[nea].isna()) & (~sumstats[ea].isna()))
     status_0=sum(sumstats["STATUS"].str.match("\w\w\w\w\w[0]\w", case=False, flags=0, na=False))
     status_3=sum(sumstats["STATUS"].str.match("\w\w\w\w\w[3]\w", case=False, flags=0, na=False))
@@ -700,6 +706,7 @@ def checkref(sumstats,ref_seq,chrom="CHR",pos="POS",ea="EA",nea="NEA",status="ST
     if remove is True:
         sumstats = sumstats.loc[~sumstats["STATUS"].str.match("\w\w\w\w\w[8]\w"),:]
         log.write(" -Variants not on given reference sequence were removed.",verbose=verbose)
+
     
     finished(log, verbose, _end_line)
     return sumstats
@@ -861,8 +868,9 @@ def parallelizeassignrsid(sumstats, path, ref_mode="vcf",snpid="SNPID",rsid="rsI
         if is_enough_info == False: return sumstats
         ############################################################################################
         
-        standardized_normalized = sumstats["STATUS"].str.match("\w\w\w[0][01234]\w\w", case=False, flags=0, na=False)
-        
+        #standardized_normalized = sumstats["STATUS"].str.match("\w\w\w[0][01234]\w\w", case=False, flags=0, na=False)
+        standardized_normalized = sumstats["STATUS"] == sumstats["STATUS"]
+
         if rsid not in sumstats.columns:
             sumstats[rsid]=pd.Series(dtype="string")
             

gwaslab/io_preformat_input.py

@@ -55,6 +55,7 @@ def preformat(sumstats,
           trait=None,
           build=None,
           other=[],
+          usekeys=None,
           verbose=False,
           readargs=None,
           log=None):
@@ -65,6 +66,11 @@ def preformat(sumstats,
     dtype_dictionary ={}    
     
  #######################################################################################################################################################
+    # workflow: 
+    # 1. formatbook
+    # 2. user specified header
+    # 3. usekeys
+    
     if fmt is not None:
         # loading format parameters
         log.write("Start to load format from formatbook....",verbose=verbose)
@@ -129,6 +135,8 @@ def preformat(sumstats,
         
         ################################################
         for key,value in rename_dictionary.items():
+            # check avaiable keys  key->raw header
+            # usecols : a list of raw headers to load from file/DataFrame 
             if key in raw_cols:
                 usecols.append(key)
             if value in ["EA","NEA"]:
@@ -137,7 +145,7 @@ def preformat(sumstats,
                 dtype_dictionary[value]="string"     
     
     except ValueError:
-        raise ValueError("Please input a path or a pd.DataFrame, and make sure the columns you specified are in the file.")
+        raise ValueError("Please input a path or a pd.DataFrame, and make sure the separator is correct and the columns you specified are in the file.")
         
     ###################################################################################################################################################
     ## check columns/datatype to use 
@@ -276,6 +284,19 @@ def preformat(sumstats,
         else:
             study = raw_cols[9]
             usecols =  usecols + [study]
+
+    if usekeys is not None:
+    # extract only specified keys
+        usecols_new =[]
+        for i in usekeys:
+            for k, v in rename_dictionary.items():
+                if i == v:
+                    usecols_new.append(k)
+        usecols_valid =[]
+        for i in usecols_new:
+            if i in usecols:
+                usecols_valid.append(i)
+        usecols = usecols_valid
  #loading data ##########################################################################################################
     
     try:

gwaslab/qc_fix_sumstats.py

@@ -1061,6 +1061,13 @@ def check_range(sumstats, var_range, header, coltocheck, cols_to_check, log, ver
             if sum(is_low_p) >0:
                 log.warning("Extremely low P detected (P=0 or P < minimum positive value of float64) : {}".format(sum(is_low_p)))
                 log.warning("Please consider using MLOG10P instead.")
+        
+        if header=="INFO":
+            is_high_info =  sumstats["INFO"]>1 
+            if sum(is_high_info) >0:
+                log.warning("High INFO detected (INFO>1) : {}".format(sum(is_high_info)))
+                log.warning("max(INFO): {}".format(sumstats["INFO"].max()))
+                log.warning("Please check if this is as expected.")
 
         if sum(~is_valid)>0:
             try:
@@ -1102,7 +1109,7 @@ def sanitycheckstats(sumstats,
                      HR=(-100,100),
                      HR_95L=(0,float("Inf")),
                      HR_95U=(0,float("Inf")),
-                     info=(0,1),
+                     info=(0,2),
                      float_tolerence = 1e-7,
                      verbose=True,
                      log=Log()):

gwaslab/util_in_filter_value.py

@@ -10,6 +10,7 @@ from gwaslab.g_vchange_status import vchange_status
 from gwaslab.qc_fix_sumstats import sortcoordinate
 from gwaslab.qc_fix_sumstats import start_to
 from gwaslab.qc_fix_sumstats import finished
+from gwaslab.qc_fix_sumstats import _process_build
 from gwaslab.hm_harmonize_sumstats import is_palindromic
 
 import gc
@@ -430,8 +431,43 @@ def _filter_snp(sumstats, mode="in", ea="EA",nea="NEA", log=Log(),verbose=True):
     log.write("Finished filtering SNPs.",verbose=verbose)
     return snp
 
-def _exclude_hla(sumstats, chrom="CHR", pos="POS", lower=25000000 ,upper=34000000 ,log=Log(), verbose=True):
-    
+def _exclude_hla(sumstats, chrom="CHR", pos="POS", lower=None ,upper=None, build=None, mode="xmhc", log=Log(), verbose=True):
+    
+    if build is not None:
+        build = _process_build(build = build,log = log,verbose = verbose)
+        # xMHC : HIST1H2AA ~ 7.6mb ~ RPL12P1
+        # reference: Horton, R., Wilming, L., Rand, V., Lovering, R. C., Bruford, E. A., Khodiyar, V. K., ... & Beck, S. (2004). Gene map of the extended human MHC. Nature Reviews Genetics, 5(12), 889-899.
+        # hg38:  25,726,063 ~ 33,400,644
+        # hg19 : 25,726,291 ~ 33,368,421
+
+        # HLA : GABBR1 ~ 3.78mb ~ KIFC1
+        # reference: Shiina, T., Hosomichi, K., Inoko, H., & Kulski, J. K. (2009). The HLA genomic loci map: expression, interaction, diversity and disease. Journal of human genetics, 54(1), 15-39. 
+        # hg38:  29,602,238 ~ 33,409,896
+        # hg19:  29,570,015 ~ 33,377,673
+
+        if build == "19":
+            if mode =="xmhc":
+                lower=25000000
+                upper=34000000
+            if mode =="hla" or mode =="mhc":
+                lower=29500000
+                upper=33500000
+        if build == "38":
+            if mode =="xmhc":
+                lower=25000000
+                upper=34000000
+            if mode =="hla" or mode =="mhc":
+                lower=29500000
+                upper=33500000
+    else:
+        # -> 25,000,000 ~ 34,000,000
+        if mode =="xmhc":
+            lower=25000000
+            upper=34000000
+        if mode =="hla" or mode =="mhc":
+            lower=29500000
+            upper=33500000
+        
     raw_len = len(sumstats)
     
     if str(sumstats[chrom].dtype) == "string":

gwaslab/util_in_get_sig.py

@@ -11,6 +11,7 @@ from gwaslab.bd_common_data import get_chr_to_number
 from gwaslab.bd_common_data import get_number_to_chr
 from gwaslab.bd_common_data import get_chr_to_NC
 from gwaslab.bd_common_data import gtf_to_protein_coding
+from gwaslab.bd_common_data import gtf_to_all_gene
 from gwaslab.bd_download import check_and_download
 from gwaslab.util_ex_gwascatalog import gwascatalog_trait
 from gwaslab.qc_fix_sumstats import check_dataframe_shape
@@ -38,6 +39,7 @@ def getsig(insumstats,
            wc_correction=False,
            build="19",
            source="ensembl",
+           gtf_path=None,
            verbose=True):
     """
     Extract the lead variants using a sliding window. P or MLOG10P will be used and converted to SCALEDP for sorting. 
@@ -172,6 +174,7 @@ def getsig(insumstats,
                xymt=xymt,
                build=build,
                source=source,
+               gtf_path=gtf_path,
                verbose=verbose)
         
     # drop internal id
@@ -253,6 +256,7 @@ def annogene(
            xymt=["X","Y","MT"],
            build="19",
            source="ensembl",
+           gtf_path=None,
            verbose=True):
     
     log.write("Start to annotate variants with nearest gene name(s)...", verbose=verbose)
@@ -267,8 +271,13 @@ def annogene(
             #| gzip >Homo_sapiens.GRCh37.75.processed.chr.gtf.gz     
             
             #gtf_path = check_and_download("ensembl_hg19_gtf_protein_coding")
-            gtf_path = check_and_download("ensembl_hg19_gtf")
-            gtf_path = gtf_to_protein_coding(gtf_path,log=log,verbose=verbose)
+            if gtf_path is None:
+                gtf_path = check_and_download("ensembl_hg19_gtf")
+                gtf_path = gtf_to_protein_coding(gtf_path,log=log,verbose=verbose)
+            else:
+                log.write(" -Using user-provided gtf:{}".format(gtf_path))
+                gtf_path = gtf_to_all_gene(gtf_path,log=log,verbose=verbose)
+
             gtf_db_path = gtf_path[:-2]+"db"
             
             data = Genome(
@@ -283,8 +292,13 @@ def annogene(
         elif build=="38":
             log.write(" -Assigning Gene name using ensembl_hg38_gtf for protein coding genes", verbose=verbose)
             #gtf_path = check_and_download("ensembl_hg38_gtf_protein_coding")
-            gtf_path = check_and_download("ensembl_hg38_gtf")
-            gtf_path = gtf_to_protein_coding(gtf_path,log=log,verbose=verbose)
+            if gtf_path is None:
+                gtf_path = check_and_download("ensembl_hg38_gtf")
+                gtf_path = gtf_to_protein_coding(gtf_path,log=log,verbose=verbose)
+            else:
+                log.write(" -Using user-provided gtf:{}".format(gtf_path))
+                gtf_path = gtf_to_all_gene(gtf_path,log=log,verbose=verbose)
+            
             gtf_db_path = gtf_path[:-2]+"db"
             data = Genome(
                 reference_name='GRCh38',
@@ -300,8 +314,13 @@ def annogene(
         if build=="19":
             log.write(" -Assigning Gene name using NCBI refseq latest GRCh37 for protein coding genes", verbose=verbose)
             #gtf_path = check_and_download("refseq_hg19_gtf_protein_coding")
-            gtf_path = check_and_download("refseq_hg19_gtf")
-            gtf_path = gtf_to_protein_coding(gtf_path,log=log,verbose=verbose)
+            if gtf_path is None:
+                gtf_path = check_and_download("refseq_hg19_gtf")
+                gtf_path = gtf_to_protein_coding(gtf_path,log=log,verbose=verbose)
+            else:
+                log.write(" -Using user-provided gtf:{}".format(gtf_path))
+                gtf_path = gtf_to_all_gene(gtf_path,log=log,verbose=verbose)
+            
             gtf_db_path = gtf_path[:-2]+"db"
             data = Genome(
                 reference_name='GRCh37',
@@ -315,8 +334,13 @@ def annogene(
         elif build=="38":
             log.write(" -Assigning Gene name using NCBI refseq latest GRCh38 for protein coding genes", verbose=verbose)
             #gtf_path = check_and_download("refseq_hg38_gtf_protein_coding")
-            gtf_path = check_and_download("refseq_hg38_gtf")
-            gtf_path = gtf_to_protein_coding(gtf_path,log=log,verbose=verbose)
+            if gtf_path is None:
+                gtf_path = check_and_download("refseq_hg38_gtf")
+                gtf_path = gtf_to_protein_coding(gtf_path,log=log,verbose=verbose)
+            else:
+                log.write(" -Using user-provided gtf:{}".format(gtf_path))
+                gtf_path = gtf_to_all_gene(gtf_path,log=log,verbose=verbose)
+            
             gtf_db_path = gtf_path[:-2]+"db"
             data = Genome(
                 reference_name='GRCh38',

gwaslab/util_in_meta.py

@@ -0,0 +1,234 @@
+
+import pandas as pd
+import numpy as np
+from scipy.stats.distributions import chi2
+from scipy.stats import norm
+from gwaslab.g_Log import Log
+from gwaslab.io_to_pickle import load_data_from_pickle
+from gwaslab.g_Sumstats import Sumstats
+import gc
+
+def meta_analyze(sumstats_list,random_effects=False, match_allele=True, log=Log()):
+    
+    ###########################################################################
+    columns=["SNPID","CHR","POS","EA","NEA"]
+    results_df = pd.DataFrame(columns=columns)
+
+    log.write("Start to perform meta-analysis...")
+    log.write(" -Datasets:")
+    for index,sumstats_path in enumerate(sumstats_list):
+        if isinstance(sumstats_path, pd.DataFrame):
+            log.write("  -Sumstats #{}: {} ".format(index, sumstats_path))
+        elif isinstance(sumstats_path, Sumstats):
+            log.write("  -Sumstats #{}: {} ".format(index, sumstats_path))
+        else:
+            log.write("  -Sumstats #{}: {} ".format(index, sumstats_path))
+    
+    
+    # extract all variants information
+    log.write(" -Iterating through {} datasets to determine variant list...".format(len(sumstats_list)))
+    
+    for index,sumstats_path in enumerate(sumstats_list):
+        sumstats = get_sumstats(sumstats_path,usekeys=["SNPID","CHR","POS","EA","NEA"])
+        new_rows = sumstats.loc[~sumstats["SNPID"].isin(results_df["SNPID"]),["SNPID","CHR","POS","EA","NEA"]]
+        log.write("  -Sumstats #{}: {} new variants (out of {}) are being added to analysis...".format(index, len(new_rows),len(sumstats)))
+        
+        if len(new_rows)>0:
+            if len(results_df) == 0:
+                results_df = new_rows
+            else:
+                results_df = pd.concat([results_df, new_rows],ignore_index=True)
+        del sumstats
+        del new_rows
+        gc.collect()
+    
+    
+    
+    ###########################################################################
+    log.write(" -Initiating result DataFrame...")
+    columns=["SNPID","CHR","POS","EA","NEA","_BETAW_SUM","_EA_N","_NEA_N","_BETA2W_SUM","_W_SUM","EAF","N","DIRECTION","BETA","SE","DOF"]
+    results_df = results_df.set_index("SNPID")
+    results_df["N"] = 0 
+    results_df["_BETAW_SUM"] = 0.0  
+    results_df["_BETA2W_SUM"] = 0.0  
+    results_df["_W_SUM"] = 0.0 
+    results_df["_W2_SUM"] = 0.0
+    results_df["_EA_N"] = 0.0
+    results_df["_NEA_N"] = 0.0 
+    results_df["N"] = 0 
+    results_df["DIRECTION"] = ""
+    results_df["BETA"] = 0.0 
+    results_df["SE"] = 0.0 
+    results_df["DOF"] = -1
+    
+    dtype_dict ={
+        "_BETAW_SUM":"float64",
+        "_EA_N":"float64",
+        "_NEA_N":"float64",
+        "_BETA2W_SUM":"float64",
+        "_W_SUM":"float64",
+        "BETA":"float64",
+        "SE":"float64",
+        "N":"Int64",
+        "DOF":"Int64"
+    }
+    results_df=results_df.astype(dtype_dict)
+    ###########################################################################
+    
+    log.write(" -Iterating through {} datasets to compute statistics for fixed-effect model...".format(len(sumstats_list)))
+    for index,sumstats_path in enumerate(sumstats_list):
+        to_use_sumstats = process_sumstats(sumstats_path, 
+                                           results_df[["EA","NEA"]],
+                                           index=index,
+                                           match_allele=match_allele,)
+        sumstats_index = to_use_sumstats.index
+        results_df_not_in_sumstat_index = results_df.index[~results_df.index.isin(to_use_sumstats.index)]
+        
+        # N and DOF
+        results_df.loc[sumstats_index, "N"]         += to_use_sumstats["N"]
+        results_df.loc[sumstats_index, "DOF"]       += 1        
+        
+        # BEAT and SE
+        results_df.loc[sumstats_index,"_BETA2W_SUM"] += to_use_sumstats["BETA"]**2 *(1/(to_use_sumstats["SE"]**2))
+        results_df.loc[sumstats_index,"_BETAW_SUM"]  += to_use_sumstats["BETA"]*(1/(to_use_sumstats["SE"]**2))
+        results_df.loc[sumstats_index,"_W_SUM"]      += 1/(to_use_sumstats["SE"]**2)  
+        results_df.loc[sumstats_index,"_W2_SUM"]     += results_df.loc[sumstats_index,"_W_SUM"]**2  
+        
+        # EAF
+        results_df.loc[sumstats_index,"_EA_N"] += to_use_sumstats["N"]*to_use_sumstats["EAF"]
+        results_df.loc[sumstats_index,"_NEA_N"]  += to_use_sumstats["N"]*(1 - to_use_sumstats["EAF"])  
+
+        # DIRECTION
+        beta_index = to_use_sumstats[to_use_sumstats["BETA"]>0].index
+        results_df.loc[beta_index, "DIRECTION"] += "+"
+        beta_index = to_use_sumstats[to_use_sumstats["BETA"]==0].index
+        results_df.loc[beta_index, "DIRECTION"] += "0"
+        beta_index = to_use_sumstats[to_use_sumstats["BETA"]<0].index
+        results_df.loc[beta_index, "DIRECTION"] += "-"
+        results_df.loc[results_df_not_in_sumstat_index, "DIRECTION"] += "?"
+        
+        del to_use_sumstats
+        gc.collect()
+
+    ############################################################################## 
+    # fixed - effect statistics
+    results_df["BETA"] = results_df["_BETAW_SUM"] / results_df["_W_SUM"]
+    results_df["EAF"] = results_df["_EA_N"] / (results_df["_EA_N"] + results_df["_NEA_N"])
+    results_df["SE"] = np.sqrt(1/results_df["_W_SUM"])
+    results_df["Z"] = results_df["BETA"] / results_df["SE"]
+    results_df["P"] = norm.sf(abs(results_df["Z"]))*2
+    results_df["Q"] = results_df["_BETA2W_SUM"] - (results_df["_BETAW_SUM"]**2 / results_df["_W_SUM"])
+    
+    for dof in results_df["DOF"].unique():
+        results_df_dof_index = results_df["DOF"] == dof
+        results_df.loc[results_df_dof_index,"P_HET"] = chi2.sf(results_df.loc[results_df_dof_index, "Q"].values,dof)
+        gc.collect()
+    
+    results_df["I2_HET"] = (results_df["Q"] - results_df["DOF"])/results_df["Q"]
+    results_df.loc[results_df["I2_HET"]<0, "I2_HET"] = 0
+    
+    results_df=results_df.drop(columns=["_EA_N","_NEA_N"])
+    gc.collect()
+
+    ###########################################################################
+    if random_effects==True:        
+        log.write(" -Iterating through {} datasets to compute statistics for random-effects model...".format(len(sumstats_list)))
+        results_df["_R2"] = (results_df["Q"] - results_df["DOF"])/(results_df["_W_SUM"] - (results_df["_W2_SUM"]/results_df["_W_SUM"]))
+        results_df.loc[results_df["_R2"]<0, "_R2"] = 0
+        variant_index_random = results_df[results_df["_R2"]>0].index
+
+        results_df["_BETAW_SUM_R"] = 0.0  
+        results_df["_W_SUM_R"] = 0.0
+        results_df["BETA_RANDOM"] = results_df["BETA"]
+        results_df["SE_RANDOM"] = results_df["SE"]
+
+        for index,sumstats_path in enumerate(sumstats_list):
+            to_use_sumstats = process_sumstats(sumstats_path, 
+                                               results_df.loc[variant_index_random, ["EA","NEA"]], 
+                                               index=index,
+                                               match_allele=match_allele,
+                                               extract_index=variant_index_random)
+            
+            sumstats_index = to_use_sumstats.index
+            
+            # BEAT and SE
+            results_df.loc[sumstats_index,"_BETAW_SUM_R"]  += to_use_sumstats["BETA"]*(1/(to_use_sumstats["SE"]**2 + results_df.loc[sumstats_index,"_R2"]))
+            results_df.loc[sumstats_index,"_W_SUM_R"]      += 1/(to_use_sumstats["SE"]**2 + results_df.loc[sumstats_index,"_R2"])
+            
+            del to_use_sumstats
+            del sumstats_index
+            gc.collect()
+            
+        results_df.loc[variant_index_random,"BETA_RANDOM"] = results_df.loc[variant_index_random,"_BETAW_SUM_R"] / results_df.loc[variant_index_random,"_W_SUM_R"]
+        results_df.loc[variant_index_random,"SE_RANDOM"] = np.sqrt(1/results_df.loc[variant_index_random,"_W_SUM_R"])
+        results_df["Z_RANDOM"] = results_df["BETA_RANDOM"] / results_df["SE_RANDOM"]
+        results_df["P_RANDOM"] = norm.sf(abs(results_df["Z_RANDOM"]))*2
+        results_df = results_df.drop(columns=["_BETAW_SUM_R","_W_SUM_R"])
+
+        gc.collect()
+    ###########################################################################
+    results_df = results_df.drop(columns=["_BETAW_SUM","_BETA2W_SUM","_W_SUM","_R2","_W2_SUM"]).sort_values(by=["CHR","POS"])
+    gc.collect()
+    log.write("Finished meta-analysis successfully!")
+    
+    return results_df
+     
+def process_sumstats(sumstats_path, results_df, index, extract_index=None, match_allele=True, log=Log()):
+    
+    if extract_index is None:
+        extract_index = results_df.index
+        
+    sumstats = get_sumstats(sumstats_path)
+    
+    to_use_sumstats = sumstats.loc[sumstats["SNPID"].isin(extract_index.values),["SNPID","EA","NEA","BETA","N","SE","EAF"]]
+    
+    if len(to_use_sumstats)>0:
+        n_pre_dup = len(to_use_sumstats)
+        log.write("  -Processing {} variants from sumstats #{}".format(len(to_use_sumstats), index))
+        
+        to_use_sumstats = to_use_sumstats.drop_duplicates(subset="SNPID").set_index("SNPID")
+        n_post_dup = len(to_use_sumstats)
+        
+        if n_pre_dup - n_post_dup>0:
+            log.write("  -Dropping {} duplicated variants from sumstats #{}".format(n_pre_dup - n_post_dup, index))
+        
+        if match_allele==True:
+            sumstats_index = to_use_sumstats.index
+            # drop not matched
+            is_match = (to_use_sumstats.loc[sumstats_index,"EA"] == results_df.loc[sumstats_index, "EA"] )&(to_use_sumstats.loc[sumstats_index,"NEA"] == results_df.loc[sumstats_index, "NEA"])
+            is_flip = (to_use_sumstats.loc[sumstats_index,"EA"] == results_df.loc[sumstats_index, "NEA"])&( to_use_sumstats.loc[sumstats_index,"NEA"] == results_df.loc[sumstats_index, "EA"])
+            is_flip = is_flip | ((to_use_sumstats.loc[sumstats_index,"NEA"] == results_df.loc[sumstats_index, "EA"])&( to_use_sumstats.loc[sumstats_index,"EA"] == results_df.loc[sumstats_index, "NEA"])) 
+            is_to_use = is_match|is_flip
+            
+            if sum(~is_to_use)>0:
+                log.write("  -Dropping {} variants with unmatched alleles from sumstats #{}".format(sum(~is_to_use), index))
+            
+            to_use_sumstats.loc[is_flip[is_flip].index, "BETA"] =  -to_use_sumstats.loc[is_flip[is_flip].index, "BETA"] 
+            to_use_sumstats.loc[is_flip[is_flip].index, "EAF"]  = 1-to_use_sumstats.loc[is_flip[is_flip].index, "EAF"] 
+            to_use_sumstats = to_use_sumstats.loc[is_to_use[is_to_use].index,:]  
+    
+    gc.collect()
+
+    return to_use_sumstats
+
+def get_sumstats(input_path,usekeys=None):
+    if isinstance(input_path, tuple):
+        path = input_path[0]
+        path_args = input_path[1]
+    else:
+        path = input_path
+        path_args={}
+        
+    if isinstance(path, pd.DataFrame):
+        sumstats = Sumstats(path,fmt="auto",verbose=False,usekeys=usekeys,**path_args).data
+    elif isinstance(path, Sumstats):
+        sumstats = path.data
+        if usekeys is not None:
+            sumstats = sumstats[usekeys]
+    elif path[-6:] == "pickle":
+        sumstats = load_data_from_pickle(path)
+        if usekeys is not None:
+            sumstats = sumstats[usekeys]
+    else:
+        sumstats = Sumstats(path,fmt="auto",verbose=False,usekeys=usekeys,**path_args).data
+    return sumstats

gwaslab/util_in_snphwe.py

@@ -0,0 +1,58 @@
+
+import numpy as np
+import pandas as pd
+
+def snphwe(obs_hets, obs_hom1, obs_hom2):
+    # Convert cpp code from (Jeremy McRae) to python  
+    # https://github.com/jeremymcrae/snphwe/blob/master/src/snp_hwe.cpp
+    #/* (original comments)
+    #// This code implements an exact SNP test of Hardy-Weinberg Equilibrium as
+    #// described in Wigginton, JE, Cutler, DJ, and Abecasis, GR (2005) A Note on
+    #// Exact Tests of Hardy-Weinberg Equilibrium. AJHG 76: 887-893
+    #//
+    #// Written by Jan Wigginton
+    #*/
+    
+    obs_homr = min(obs_hom1, obs_hom2)
+    obs_homc = max(obs_hom1, obs_hom2)
+    
+    rare = 2 * obs_homr + obs_hets
+    genotypes = obs_hets + obs_homc + obs_homr
+    
+    probs = np.array([0.0 for i in range(rare +1)])
+    
+    mid = rare * (2 * genotypes - rare) // (2 * genotypes)
+    
+    if mid % 2 != rare%2:
+        mid += 1
+        
+    probs[mid] = 1.0
+    
+    sum_p = 1 #probs[mid]
+    curr_homr = (rare - mid) // 2
+    curr_homc = genotypes - mid - curr_homr
+    
+    
+    for curr_hets in range(mid, 1, -2):
+        probs[curr_hets - 2] = probs[curr_hets] * curr_hets * (curr_hets - 1.0)/ (4.0 * (curr_homr + 1.0) * (curr_homc + 1.0))
+        sum_p+= probs[curr_hets - 2]
+        curr_homr += 1
+        curr_homc += 1
+    
+    curr_homr = (rare - mid) // 2
+    curr_homc = genotypes - mid - curr_homr
+    
+    for curr_hets in range(mid, rare-1, 2):
+        probs[curr_hets + 2] = probs[curr_hets] * 4.0 * curr_homr * curr_homc/ ((curr_hets + 2.0) * (curr_hets + 1.0))
+        sum_p += probs[curr_hets + 2]
+        curr_homr -= 1
+        curr_homc -= 1
+    
+    target = probs[obs_hets]
+    p_hwe = 0.0
+    
+    for p in probs:
+        if p <= target :
+            p_hwe += p / sum_p  
+    
+    return min(p_hwe,1)

gwaslab/viz_aux_chromatin.py

@@ -0,0 +1,111 @@
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+from gwaslab.g_Log import Log
+
+#STATE NO.	MNEMONIC	DESCRIPTION	COLOR NAME	COLOR CODE
+#1	TssA	Active TSS	Red	255,0,0
+#2	TssAFlnk	Flanking Active TSS	Orange Red	255,69,0
+#3	TxFlnk	Transcr. at gene 5' and 3'	LimeGreen	50,205,50
+#4	Tx	Strong transcription	Green	0,128,0
+#5	TxWk	Weak transcription	DarkGreen	0,100,0
+#6	EnhG	Genic enhancers	GreenYellow	194,225,5
+#7	Enh	Enhancers	Yellow	255,255,0
+#8	ZNF/Rpts	ZNF genes & repeats	Medium Aquamarine	102,205,170
+#9	Het	Heterochromatin	PaleTurquoise	138,145,208
+#10	TssBiv	Bivalent/Poised TSS	IndianRed	205,92,92
+#11	BivFlnk	Flanking Bivalent TSS/Enh	DarkSalmon	233,150,122
+#12	EnhBiv	Bivalent Enhancer	DarkKhaki	189,183,107
+#13	ReprPC	Repressed PolyComb	Silver	128,128,128
+#14	ReprPCWk	Weak Repressed PolyComb	Gainsboro	192,192,192
+#15	Quies	Quiescent/Low	White	255,255,255
+
+color_dict={
+    "E1": np.array([255,0,0]),
+    "E2": np.array([255,69,0]),
+    "E3": np.array([50,205,50]),
+    "E4": np.array([0,128,0]),
+    "E5": np.array([0,100,0]),
+    "E6": np.array([194,225,5]),
+    "E7": np.array([255,255,0]),
+    "E8": np.array([102,205,170]),
+    "E9": np.array([138,145,208]),
+    "E10":np.array([205,92,92]),
+    "E11":np.array([233,150,122]),
+    "E12":np.array([189,183,107]),
+    "E13":np.array([128,128,128]),
+    "E14":np.array([192,192,192]),
+    "E15":np.array([255,255,255])
+}
+
+color_dict_i={
+    1: np.array([255,0,0]),
+    2: np.array([255,69,0]),
+    3: np.array([50,205,50]),
+    4: np.array([0,128,0]),
+    5: np.array([0,100,0]),
+    6: np.array([194,225,5]),
+    7: np.array([255,255,0]),
+    8: np.array([102,205,170]),
+    9: np.array([138,145,208]),
+    10:np.array([205,92,92]),
+    11:np.array([233,150,122]),
+    12:np.array([189,183,107]),
+    13:np.array([128,128,128]),
+    14:np.array([192,192,192]),
+    15:np.array([255,255,255])
+}
+
+
+def _plot_chromatin_state(region_chromatin_files, 
+                          region_chromatin_labels,
+                          region, 
+                          fig, 
+                          ax,
+                          xlim_i,
+                          log=Log(),
+                          verbose=True):
+    '''
+    files : a list of numbers
+    '''    
+    target_chr = region[0]
+    target_start = region[1]
+    target_end = region[2]
+
+    offset_i = xlim_i[0] - region[1]
+
+    ax.set_ylim([-0.05,0.1*len(region_chromatin_files)-0.05])
+    ax.set_xlim([offset_i+target_start,offset_i+target_end])
+
+    px_for_01 = ax.transData.transform([0,0])[1] - ax.transData.transform([0,0.1])[1]
+
+    point=fig.dpi/72
+    points_for_01 = px_for_01*72 / fig.dpi
+
+    # each tissue
+    for i,file in enumerate(region_chromatin_files):
+        log.write(" -Loading : {}".format(file), verbose=verbose)
+        enh = pd.read_csv(file,sep="\t",header=None)
+        enh.columns=["ID","START","END","STATE"]
+        enh["CHR"] =  enh["ID"].str.extract(r"chr([0-9]+)").astype("float").astype("Int64")
+        enh["STATE_i"] =  enh["STATE"].str.extract(r"([0-9]+)_*").astype("float").astype("Int64")
+        enh_in_region = (enh["CHR"] == target_chr) & ((enh["END"] > target_start) & (enh["START"]<target_end))
+        df =enh.loc[enh_in_region,["STATE_i","START","END"]].sort_values("STATE_i",ascending=False)
+        log.write("  -Number of records in specified region: {}".format(len(df)), verbose=verbose)
+        # each block
+        for index, row in df.iterrows():
+            color=color_dict_i[row["STATE_i"]]
+            ax.plot([offset_i + row["START"] ,offset_i + row["END"]],
+                    [i*0.1,i*0.1],
+                    c=color/255,linewidth=points_for_01,solid_capstyle="butt")
+    
+    ## add stripe label
+    if len(region_chromatin_labels) == len(region_chromatin_files):
+        ax.set_yticks([i*0.1 for i in range(len(region_chromatin_labels))], 
+                      region_chromatin_labels)
+    else:
+        ax.set_yticks(ticks=[])
+    
+    ax.set_xticks(ticks=[])
+    ax.invert_yaxis()
+    return fig

gwaslab/viz_plot_compare_effect.py

@@ -75,7 +75,10 @@ def compare_effect(path1,
     if scaled == True:
         scaled1 = True
         scaled2 = True
-    
+    if is_q_mc=="fdr" or is_q_mc=="bon":
+        is_q = True
+    else:
+        raise ValueError("Please select either fdr or bon for is_q_mc.")
     if save_args is None:
         save_args = {"dpi":300,"facecolor":"white"}
     if reg_box is None:

gwaslab/viz_plot_mqqplot.py

@@ -133,6 +133,7 @@ def mqqplot(insumstats,
           anno_style="right",
           anno_fixed_arm_length=None,
           anno_source = "ensembl",
+          anno_gtf_path=None,
           anno_adjust=False,
           anno_max_iter=100,
           arm_offset=50,
@@ -816,6 +817,7 @@ def mqqplot(insumstats,
                                    log=log,
                                    build=build,
                                    source=anno_source,
+                                   gtf_path=anno_gtf_path,
                                    verbose=verbose).rename(columns={"GENE":"Annotation"})
         log.write("Finished extracting variants for annotation...",verbose=verbose)
 

gwaslab/viz_plot_regionalplot.py

@@ -365,6 +365,10 @@ def  _plot_recombination_rate(sumstats,pos, region, ax1, rr_path, rr_chr_dict, r
 
     rc = rc.loc[(rc["Position(bp)"]<region[2]) & (rc["Position(bp)"]>region[1]),:]
     ax4.plot(rc_track_offset+rc["Position(bp)"],rc["Rate(cM/Mb)"],color="#5858FF",zorder=1)
+    
+    ax1.set_zorder(ax4.get_zorder()+1)
+    ax1.patch.set_visible(False)
+    
     if rr_ylabel:
         ax4.set_ylabel("Recombination rate(cM/Mb)")
     if rr_lim!="max":

gwaslab/viz_plot_stackedregional.py

@@ -22,6 +22,7 @@ from gwaslab.bd_common_data import get_number_to_chr
 from gwaslab.bd_common_data import get_recombination_rate
 from gwaslab.bd_common_data import get_gtf
 from gwaslab.viz_aux_reposition_text import adjust_text_position
+from gwaslab.viz_aux_chromatin import _plot_chromatin_state
 from gwaslab.viz_aux_quickfix import _quick_fix
 from gwaslab.viz_aux_quickfix import _get_largenumber
 from gwaslab.viz_aux_quickfix import _quick_add_tchrpos
@@ -37,15 +38,20 @@ from gwaslab.io_to_pickle import load_data_from_pickle
 from gwaslab.g_Sumstats import Sumstats
 from gwaslab.viz_aux_save_figure import save_figure
 from gwaslab.viz_plot_mqqplot import mqqplot
+import matplotlib.patches as patches
 
 def plot_stacked_mqq(objects,
                         vcfs=None,
                         mode="r",
                         mqqratio=3,
                         region=None,
+                        region_chromatin_height=0.1,
+                        region_chromatin_files = None,
+                        region_chromatin_labels= None,
                         titles= None,
                         title_pos=None,
                         title_args=None,
+                        #title_box = None,
                         gtf=None,
                         gene_track_height=0.5,
                         fig_args=None,
@@ -72,11 +78,11 @@ def plot_stacked_mqq(objects,
         fig_args = {"dpi":200}
     if region_lead_grid_line is None:
         region_lead_grid_line = {"alpha":0.5,"linewidth" : 2,"linestyle":"--","color":"#FF0000"}
-    if title_pos is None:
-        title_pos = [0.01,0.97]
-    if title_args is None:
-        title_args = {}
-    
+    if region_chromatin_files is None:
+        region_chromatin_files = []
+        region_chromatin_height = len(region_chromatin_files) * region_chromatin_height
+    if region_chromatin_labels is None:
+        region_chromatin_labels = []
     # create figure and axes ##################################################################################################################
     if mode=="r":
         if len(vcfs)==1:
@@ -84,9 +90,15 @@ def plot_stacked_mqq(objects,
         n_plot = len(sumstats_list)
         n_plot_plus_gene_track = n_plot + 1
 
+        if len(region_chromatin_files)>0 and mode=="r":
+            height_ratios = [1 for i in range(n_plot_plus_gene_track-1)]+[region_chromatin_height]+[gene_track_height]
+            n_plot_plus_gene_track +=1
+        else:
+            height_ratios = [1 for i in range(n_plot_plus_gene_track-1)]+[gene_track_height]
+        
         fig_args["figsize"] = [16,subplot_height*n_plot_plus_gene_track]
         fig, axes = plt.subplots(n_plot_plus_gene_track, 1, sharex=True, 
-                             gridspec_kw={'height_ratios': [1 for i in range(n_plot_plus_gene_track-1)]+[gene_track_height]},
+                             gridspec_kw={'height_ratios': height_ratios},
                              **fig_args)
         plt.subplots_adjust(hspace=region_hspace)
     elif mode=="m":
@@ -179,18 +191,58 @@ def plot_stacked_mqq(objects,
                             **mqq_args_for_each_plot[index]
                             )
             lead_variants_is[index] = (lead_i,lead_i2)
-    
+
+    if len(region_chromatin_files)>0 and mode=="r":
+        xlim_i = axes[-1].get_xlim()
+        fig = _plot_chromatin_state(     region_chromatin_files = region_chromatin_files, 
+                                         region_chromatin_labels = region_chromatin_labels,
+                                         region = region, 
+                                         fig = fig, 
+                                         ax = axes[-2],
+                                         xlim_i=xlim_i,
+                                         log=log,
+                                         verbose=verbose)    
     # adjust labels
     # drop labels for each plot 
     # set a common laebl for all plots
 
-    
-    if titles is not None:
+    #if title_box is None:
+    #    title_box = dict(boxstyle='square', facecolor='white', alpha=1.0, edgecolor="black")
+    #    title_box = {}
+
+    if title_args is None:
+        title_args = {}   
+    if titles is not None and mode=="r":    
+        if title_pos is None:
+            title_pos = [0.01,0.01]
         for index,title in enumerate(titles):
-            axes[index].text(title_pos[0], title_pos[1] , title, transform=axes[index].transAxes,ha="left", va='top',**title_args)
+            
+            current_text = axes[index].text(title_pos[0], title_pos[1] , title, transform=axes[index].transAxes,ha="left", va='bottom',zorder=999999, **title_args)
+            r = fig.canvas.get_renderer()
+            bb = current_text.get_window_extent(renderer=r).transformed(axes[index].transAxes.inverted())
+            width = bb.width
+            height = bb.height
+
+            rect = patches.Rectangle((0.0,0.0),
+                            height=height + 0.02*2,
+                            width=width + 0.01*2, 
+                            transform=axes[index].transAxes,
+                            linewidth=1, 
+                            edgecolor='black', 
+                            facecolor='white',
+                            alpha=1.0,
+                            zorder=99998)
+            axes[index].add_patch(rect)
+            rect.set(zorder=99998) 
+    else:
+        if title_pos is None:
+            title_pos = [0.01,0.97]
+        for index,title in enumerate(titles):
+            axes[index].text(title_pos[0], title_pos[1] , title, transform=axes[index].transAxes,ha="left", va='top',zorder=999999, **title_args)
+    
     ##########################################################################################################################################
     # draw the line for lead variants
-    _draw_grid_line_for_lead_variants(mode, lead_variants_is, n_plot, axes, region_lead_grid_line)
+    _draw_grid_line_for_lead_variants(mode, lead_variants_is, n_plot, axes, region_lead_grid_line,region_chromatin_files)
     
     ##########################################################################################################################################  
     _drop_old_y_labels(axes, n_plot)
@@ -208,12 +260,16 @@ def _drop_old_y_labels(axes, n_plot):
     for index in range(n_plot):
         axes[index].set_ylabel("")
 
-def _draw_grid_line_for_lead_variants(mode, lead_variants_is, n_plot, axes, region_lead_grid_line):
+def _draw_grid_line_for_lead_variants(mode, lead_variants_is, n_plot, axes, region_lead_grid_line,region_chromatin_files):
+    if len(region_chromatin_files)>0:
+        n_plot_and_track = n_plot+2
+    else:
+        n_plot_and_track = n_plot+1
     if mode=="r":
         for index, sig_is in lead_variants_is.items():
             for sig_i in sig_is:
                 if sig_i is not None:
-                    for each_axis_index in range(n_plot + 1):    
+                    for each_axis_index in range(n_plot_and_track):    
                         axes[each_axis_index].axvline(x=sig_i, zorder=2,**region_lead_grid_line)
 
 def _add_new_y_label(mode, fig, gene_track_height,n_plot,subplot_height ):

{gwaslab-3.4.44.dist-info → gwaslab-3.4.46.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gwaslab
-Version: 3.4.44
+Version: 3.4.46
 Summary: A collection of handy tools for GWAS SumStats
 Author-email: Yunye <yunye@gwaslab.com>
 Project-URL: Homepage, https://cloufield.github.io/gwaslab/
@@ -8,16 +8,16 @@ Project-URL: Github, https://github.com/Cloufield/gwaslab
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
-Requires-Python: <=3.10,>=3.9
+Requires-Python: <3.11,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: LICENSE_before_v3.4.39
 Requires-Dist: pandas !=1.5,>=1.3
-Requires-Dist: numpy >=1.21.2
-Requires-Dist: matplotlib !=3.7.2,>=3.5
+Requires-Dist: numpy <2,>=1.21.2
+Requires-Dist: matplotlib !=3.7.2,<3.9,>=3.5
 Requires-Dist: seaborn >=0.12
 Requires-Dist: scipy >=1.12
-Requires-Dist: pySAM <0.20,>=0.18.1
+Requires-Dist: pySAM ==0.22.1
 Requires-Dist: Biopython >=1.79
 Requires-Dist: adjustText <=0.8,>=0.7.3
 Requires-Dist: liftover >=1.1.13
@@ -51,7 +51,7 @@ Warning: Known issues of GWASLab are summarized in [https://cloufield.github.io/
 ### install via pip
 
 ```
-pip install gwaslab==3.4.43
+pip install gwaslab==3.4.45
 ```
 
 ```python
@@ -90,7 +90,7 @@ Create a Python 3.9 environment and install gwaslab using pip:
 ```
 conda env create -n gwaslab_test -c conda-forge python=3.9
 conda activate gwaslab
-pip install gwaslab==3.4.43
+pip install gwaslab==3.4.45
 ```
 
 or create a new environment using yml file [environment_3.4.40.yml](https://github.com/Cloufield/gwaslab/blob/main/environment_3.4.40.yml)

{gwaslab-3.4.44.dist-info → gwaslab-3.4.46.dist-info}/RECORD

@@ -1,22 +1,22 @@
-gwaslab/__init__.py,sha256=dFnrh4L620F5JirsSF98SmkuligA-fybIGdBF6r9Ims,2386
-gwaslab/bd_common_data.py,sha256=v98X3tdRNOVE2gCiSHkfyBb0pSIjTk5IFG8A725Oj3o,12639
+gwaslab/__init__.py,sha256=7TKJaODdpeuQKibL7gIEa4MtyQ0pmrU-vIHQ-Et27lQ,2433
+gwaslab/bd_common_data.py,sha256=qr6OMbBaTH2Smfu8347SO9NmF410tn8dq8pRGF5-OpY,13751
 gwaslab/bd_config.py,sha256=TP-r-DPhJD3XnRYZbw9bQHXaDIkiRgK8bG9HCt-UaLc,580
 gwaslab/bd_download.py,sha256=cDDk2C5IvjeAzvPvVYGTkI4Ss33DUtEDjGo8eAbQRvY,15663
 gwaslab/bd_get_hapmap3.py,sha256=asNjQYeGfQi8u3jnfenRvDdKMs5ptql5wpcUzqMlwUI,3937
 gwaslab/cache_manager.py,sha256=HOTnSkCOyGEPLRl90WT8D_6pAdI8d8AzenMIDGuCeWc,28113
 gwaslab/g_Log.py,sha256=C3Zv-_6c3C9ms8bgQ-ytplz22sjk7euqXYkWr9zNeAs,1573
 gwaslab/g_Phenotypes.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gwaslab/g_Sumstats.py,sha256=NOEQd00guGch_GIt5bHv1wcrAvETfChqzmtgm-nIx_I,35298
-gwaslab/g_SumstatsPair.py,sha256=tbgT-_1CqDEw22s4LbVJWF3ChELxz0gy1DEBzLc9ODU,8833
+gwaslab/g_Sumstats.py,sha256=TUcFQFyODS_-FYMdXDvrBijG4Qtfi1igIWM-eEgb0nc,35352
+gwaslab/g_SumstatsPair.py,sha256=20snPb4SlI6ftMGVjgxAuyxsxYRQF-GzzlBSnoB-3Lo,8851
 gwaslab/g_SumstatsT.py,sha256=u_DighLMnMxwTLnqm-B58pA0G6WXRj6pudPyKMVKjSU,2133
 gwaslab/g_Sumstats_summary.py,sha256=FECvvFXJVKaCX5dggBvvk9YvJ6AbdbcLfjltysX7wEE,6380
 gwaslab/g_meta.py,sha256=htWlgURWclm9R6UqFcX1a93WN27xny7lGUeyJZOtszQ,2583
-gwaslab/g_vchange_status.py,sha256=eX0jdIb6Spa07ZdpWNqUWqdVBWS0fuH2yrt4PDi3Res,1746
-gwaslab/g_version.py,sha256=44qNMttuGuAyDPPblc1z0V9R5lHo9z8x2_E6JuZ6eBE,1818
+gwaslab/g_vchange_status.py,sha256=jLoVzMJFhB5k_cJKzHuBNc2HZGBWydAunCNa0n_d54g,1923
+gwaslab/g_version.py,sha256=g2bR-qFeFvLADj57VXMT5dufwba2YGD86hfDHRYURfU,1818
 gwaslab/hm_casting.py,sha256=FqP4EQl83Q2OKLw004OgLIvUH795TVCGwziLk5jsHqY,11368
-gwaslab/hm_harmonize_sumstats.py,sha256=CADIG_KLsoq4y21wN0fyaaG2S4PDpKu96Y0of6b0TaU,78184
+gwaslab/hm_harmonize_sumstats.py,sha256=1hjUdle2DSKHGBp2BktfFqf-QHU_q2xWl_mPhiYc_ZA,78616
 gwaslab/hm_rsid_to_chrpos.py,sha256=ODWREO0jPN0RAfNzL5fRzSRANfhiksOvUVPuEsFZQqA,6552
-gwaslab/io_preformat_input.py,sha256=w62JLAr16Ru0EgUtBCEV2eXRO89OqhidQxwf2IPAM38,20014
+gwaslab/io_preformat_input.py,sha256=AZ43WGqVTzbo3XtClWhjRjsj6pBR9stw6JBL_TZ461U,20673
 gwaslab/io_read_ldsc.py,sha256=8S9n4imgl4d0WPms_GYld-6uUM5z7iWGiCA-M814kzY,12123
 gwaslab/io_read_tabular.py,sha256=EG-C6KhCutt4J4LlOMgXnqzJvU-EZXzVhMvaDFnHrMM,2380
 gwaslab/io_to_formats.py,sha256=QuGWdvnAamaZAuhymj-0SuNBaKz1maTTyH396gvVaO8,29229
@@ -28,7 +28,7 @@ gwaslab/ldsc_parse.py,sha256=MBnfgcWlV4oHp9MoDRh1mpilaHhAR15Af77hMFn4-5k,10564
 gwaslab/ldsc_regressions.py,sha256=yzbGjgNV7u-SWXNPsh9S8y9mK97Bim_Nmad9G9V18ZU,30078
 gwaslab/ldsc_sumstats.py,sha256=O0olsDxKlh1MJ1gAuEN1t40rxhajOEwOQ20ak7xoDrI,26245
 gwaslab/qc_check_datatype.py,sha256=kW68uk4dTLOU2b1dHoVat6n0loundDysAjIqxsXW28Q,3379
-gwaslab/qc_fix_sumstats.py,sha256=cpJibJ_77p4cg39R4zRunhOK2deIK4PfQA9wmYZgyqk,92745
+gwaslab/qc_fix_sumstats.py,sha256=-DQz5dPW6YXXVP-LV2Txa4lJrpZHhqAoKNny6IYAW18,93100
 gwaslab/run_script.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gwaslab/util_ex_calculate_ldmatrix.py,sha256=LpE__LoYRHLgVKlCHo6lYWlz9LEUVUDqYPEAP-Svbm0,14598
 gwaslab/util_ex_calculate_prs.py,sha256=5l1eiZs8YwIpEgp7i3IurP8n5KwQM5awbG9fWSm4iT4,9053
@@ -47,23 +47,26 @@ gwaslab/util_in_calculate_power.py,sha256=JfHJFg3tNF0f4NHgWlzVW2mSxCiP07mAHIyEfV
 gwaslab/util_in_convert_h2.py,sha256=a8Cbudt3xn9WP2bPc-7ysuowB-LYub8j8GeDXl7Lk7Q,6483
 gwaslab/util_in_correct_winnerscurse.py,sha256=Gp--yAQ8MMzdkWIvXP9C1BHVjZc-YzqHfYWhAj19w9w,2110
 gwaslab/util_in_fill_data.py,sha256=gdTwYA6FvBMnrtxAeL0lEj_Z0aGIoRNPScWDlJvZWeQ,14021
-gwaslab/util_in_filter_value.py,sha256=6yz3omukfqhmkfGZwGtr2BPQ6FcSTj4l6o7EhPMXRz0,22100
+gwaslab/util_in_filter_value.py,sha256=dY4X66N9A4MHCRHjPqLYFufMM91ggLRwUBf_nJYh8Lg,23605
 gwaslab/util_in_get_density.py,sha256=kpKXH69acMkeYVG5vs-VbJC3COhmuLBfYco-wuOxgjc,3934
-gwaslab/util_in_get_sig.py,sha256=atyBJZCWGUSgy-nvIR8_a_isseq1nKhzTaRVG2LbKQk,37762
+gwaslab/util_in_get_sig.py,sha256=9kq1GXacknO2YnVmsTli1GlPA728ASweTZ3UKm3Wszo,38783
+gwaslab/util_in_meta.py,sha256=5K9lIZcIgUy0AERqHy1GvMN2X6dp45JUUgopuDLgt4o,11284
+gwaslab/util_in_snphwe.py,sha256=-KpIDx6vn_nah6H55IkV2OyjXQVXV13XyBL069WE1wM,1751
 gwaslab/viz_aux_annotate_plot.py,sha256=R-1GT89E4NEBAMNTYzNawdi9rjQV5LCnODgnYOOKsys,32184
+gwaslab/viz_aux_chromatin.py,sha256=NzbFFpbwAMH-39F8z0qJaExw-JcKYcAlzyzbMkvFo5M,4002
 gwaslab/viz_aux_quickfix.py,sha256=Z6ZNEAUFuWVDTzH-qGreNGxPxJLCmqhXtBrvDOgo4g8,18308
 gwaslab/viz_aux_reposition_text.py,sha256=iRIP-Rkltlei068HekJcVubiqPrunBqvAoSQ1eHk04M,4304
 gwaslab/viz_aux_save_figure.py,sha256=nL-aoE8Kg06h7FgleGRBIZjhI-6w5gpn3E1HWMwBig8,2664
 gwaslab/viz_plot_compare_af.py,sha256=qtXW45-Sq_ugK8ZfqBYMpmf58SKi3lB3YyHnzn_akcE,5344
-gwaslab/viz_plot_compare_effect.py,sha256=8om3y6YQfnOk4FfkKSpKr2KqJcsMeCwQ6FRRKbDrm3U,49366
+gwaslab/viz_plot_compare_effect.py,sha256=iA74jMzh-G65U6BeXyQro08tPlJWpNyvtrjFsYHLvFM,49505
 gwaslab/viz_plot_forestplot.py,sha256=xgOnefh737CgdQxu5naVyRNBX1NQXPFKzf51fbh6afs,6771
 gwaslab/viz_plot_miamiplot.py,sha256=rCFEp7VNuVqeBBG3WRkmFAtFklbF79BvIQQYiSY70VY,31238
 gwaslab/viz_plot_miamiplot2.py,sha256=SWv82D8UBbREKsk8EoKth-2w68l6FbXyVLsb_E1hh8o,15882
-gwaslab/viz_plot_mqqplot.py,sha256=PzRWnm11whxww7ut-bzFkj1sbPc_c0OP7yRpIgYo2iQ,61739
+gwaslab/viz_plot_mqqplot.py,sha256=oVFiLe6Xv_-ryY8I36tGjU9StjM_ust72YSSfnZgaUg,61828
 gwaslab/viz_plot_qqplot.py,sha256=psQgVpP29686CEZkzQz0iRbApzqy7aE3GGiBcazVvNw,7247
-gwaslab/viz_plot_regionalplot.py,sha256=PBIWkNj2fj-dRLKQJNpM8wor5jya2anqix0-UYLE0Is,37901
+gwaslab/viz_plot_regionalplot.py,sha256=8u-5-yfy-UaXhaxVVz3Y5k2kBAoqzczUw1hyyD450iI,37983
 gwaslab/viz_plot_rg_heatmap.py,sha256=PidUsgOiEVt6MfBPCF3_yDhOEytZ-I1q-ZD6_0pFrV4,13713
-gwaslab/viz_plot_stackedregional.py,sha256=EAHz5SZGengZ_pxcOg62ZRimGRz6_goQlp9MLCwmeZc,11890
+gwaslab/viz_plot_stackedregional.py,sha256=yWxAJyqA3Kv9PUFTLzgbAu_hP7wi3_3bVVQlJECm8Gc,14687
 gwaslab/viz_plot_trumpetplot.py,sha256=ZHdc6WcVx0-oKoj88yglRkmB4bS9pOiEMcuwKW35Yvo,42672
 gwaslab/data/formatbook.json,sha256=N2nJs80HH98Rsu9FxaSvIQO9J5yIV97WEtAKjRqYwiY,38207
 gwaslab/data/reference.json,sha256=k8AvvgDsuLxzv-NCJHWvTUZ5q_DLAFxs1Th3jtL313k,11441
@@ -73,9 +76,9 @@ gwaslab/data/hapmap3_SNPs/hapmap3_db150_hg19.snplist.gz,sha256=qD9RsC5S2h6l-OdpW
 gwaslab/data/hapmap3_SNPs/hapmap3_db151_hg38.snplist.gz,sha256=Y8ZT2FIAhbhlgCJdE9qQVAiwnV_fcsPt72usBa7RSBM,10225828
 gwaslab/data/high_ld/high_ld_hla_hg19.bed.gz,sha256=R7IkssKu0L4WwkU9SrS84xCMdrkkKL0gnTNO_OKbG0Y,219
 gwaslab/data/high_ld/high_ld_hla_hg38.bed.gz,sha256=76CIU0pibDJ72Y6UY-TbIKE9gEPwTELAaIbCXyjm80Q,470
-gwaslab-3.4.44.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-gwaslab-3.4.44.dist-info/LICENSE_before_v3.4.39,sha256=GhLOU_1UDEKeOacYhsRN_m9u-eIuVTazSndZPeNcTZA,1066
-gwaslab-3.4.44.dist-info/METADATA,sha256=PJUO56s9S_nfVnZlRCYuSq-6BADrRxjcwjAqaAjJWc8,7764
-gwaslab-3.4.44.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-gwaslab-3.4.44.dist-info/top_level.txt,sha256=PyY6hWtrALpv2MAN3kjkIAzJNmmBTH5a2risz9KwH08,8
-gwaslab-3.4.44.dist-info/RECORD,,
+gwaslab-3.4.46.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+gwaslab-3.4.46.dist-info/LICENSE_before_v3.4.39,sha256=GhLOU_1UDEKeOacYhsRN_m9u-eIuVTazSndZPeNcTZA,1066
+gwaslab-3.4.46.dist-info/METADATA,sha256=aw5qahaxh7TAYCLNPdBO1FmHCWQk3mQcOlZohaGqorw,7765
+gwaslab-3.4.46.dist-info/WHEEL,sha256=cpQTJ5IWu9CdaPViMhC9YzF8gZuS5-vlfoFihTBC86A,91
+gwaslab-3.4.46.dist-info/top_level.txt,sha256=PyY6hWtrALpv2MAN3kjkIAzJNmmBTH5a2risz9KwH08,8
+gwaslab-3.4.46.dist-info/RECORD,,

{gwaslab-3.4.44.dist-info → gwaslab-3.4.46.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (70.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any