gwaslab 3.4.37__py3-none-any.whl → 3.4.39__py3-none-any.whl

gwaslab/bd_common_data.py

@@ -280,17 +280,20 @@ def gtf_to_protein_coding(gtfpath,log=Log(),verbose=True):
     protein_coding_path = gtfpath[:-6]+"protein_coding.gtf.gz"
     # if not existing, extract protein coding records and output to a new file
     if not path.isfile(protein_coding_path):
+        
         # get gene list
-        if verbose: log.write(" - Extracting protein_coding genes from {}".format(gtfpath))
+        log.write(" - Extracting protein_coding 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") & (gtf["gene_biotype"]=="protein_coding"),"gene_id"].values
-        if verbose: log.write(" - Loaded {} protein_coding genes.".format(len(gene_list)))
+        log.write(" - Loaded {} protein_coding 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)
-        if verbose: log.write(" - Extracted records are saved to : {} ".format(protein_coding_path))
+        
+        log.write(" - Extracted records are saved to : {} ".format(protein_coding_path),verbose=verbose)
         gtf_raw.to_csv(protein_coding_path, header=None, index=None, sep="\t")
 
     return protein_coding_path

gwaslab/bd_download.py

@@ -106,7 +106,7 @@ def check_available_ref(log=Log(),verbose=True):
     Check available reference files for gwaslab.
     Return a dictionary of available reference files.
     '''
-    if verbose : log.write("Start to check available reference files...")
+    log.write("Start to check available reference files...", verbose=verbose)
     #ref_path = path.dirname(__file__) + '/data/reference.json'
     ref_path = options.paths["reference"]
     if not path.exists(ref_path):
@@ -115,11 +115,11 @@ def check_available_ref(log=Log(),verbose=True):
     dicts = json.load(open(ref_path))
     if dicts is not None:
         for key,value in dicts.items():
-            if verbose :log.write(" -",key," : ",value)
+            log.write(" -",key," : ",value, verbose=verbose)
         return dicts
     else:
-        if verbose :log.write(" -No available reference files.")
-    if verbose :log.write("Finished checking available reference files...")
+        log.write(" -No available reference files.", verbose=verbose)
+    log.write("Finished checking available reference files...", verbose=verbose)
     return {}
 
 def update_available_ref(log=Log()):
@@ -167,8 +167,8 @@ def get_path(name,log=Log(),verbose=True):
     #config_path =  path.dirname(__file__) + '/data/config.json'
     config_path = options.paths["config"]
     if not path.exists(config_path):
-        if verbose : log.write("Config file not exists...")
-        if verbose : log.write("Created new config file...")
+        log.write("Config file not exists...", verbose=verbose)
+        log.write("Created new config file...", verbose=verbose)
         initiate_config()      
     else:
         try:
@@ -176,9 +176,9 @@ def get_path(name,log=Log(),verbose=True):
             if path.exists(dicts[name]):
                 return dicts[name]
             else:
-                if verbose : log.write("File not exist.")
+                log.write("File not exist.", verbose=verbose)
         except:
-            if verbose : log.write("No records in config file. Please download first.")
+            log.write("No records in config file. Please download first.", verbose=verbose)
     return False
 
 ##################################################################################
@@ -277,7 +277,7 @@ def check_file_integrity(local_path, md5sum,log):
         log.write(" -MD5 verified.")
         return 1
     else:
-        log.write("WARNING: -MD5 VERIFICATION FAILED !")
+        log.warning("-MD5 VERIFICATION FAILED!")
         return 0
 
 def remove_file(name,log=Log()):

gwaslab/bd_get_hapmap3.py

@@ -1,6 +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
+
 #A unique identifier (e.g., the rs number)
 #Allele 1 (effect allele)
 #Allele 2 (non-effect allele)
@@ -8,30 +12,60 @@ from gwaslab.g_Log import Log
 #A P-value
 #A signed summary statistic (beta, OR, log odds, Z-score, etc)
 
-def gethapmap3(sumstats,rsid="rsID",chrom="CHR", pos="POS", ea="EA", nea="NEA",build="19", verbose=True,log=Log()):
-    if verbose:log.write(" -Processing "+str(len(sumstats))+" raw variants...")
+def gethapmap3(sumstats,rsid="rsID",chrom="CHR", pos="POS", ea="EA", nea="NEA",build="19", verbose=True, match_allele= True, log=Log()):
+    ##start function with col checking##########################################################
+    _start_line = "extract HapMap3 SNPs"
+    _end_line = "extracting HapMap3 SNPs"
+    _start_cols =[]
+    _start_function = ".gethapmap3"
+    _must_args ={}
+
+    is_enough_info = start_to(sumstats=sumstats,
+                            log=log,
+                            verbose=verbose,
+                            start_line=_start_line,
+                            end_line=_end_line,
+                            start_cols=_start_cols,
+                            start_function=_start_function,
+                            **_must_args)
+    if is_enough_info == False: return None
 
+    ############################################################################################
     if build=="19":
         data_path =  path.dirname(__file__) + '/data/hapmap3_SNPs/hapmap3_db150_hg19.snplist.gz'
     elif build=="38":
         data_path =  path.dirname(__file__) + '/data/hapmap3_SNPs/hapmap3_db151_hg38.snplist.gz'
     
-    if verbose:log.write(" -Loading Hapmap3 variants data...")
-        
-    hapmap3_ref = pd.read_csv(data_path,sep="\s+",usecols=["#CHROM","POS","rsid"],dtype={"#CHROM":"string","POS":"string"})
+    log.write(" -Loading Hapmap3 variants from built-in datasets...", verbose=verbose)
+    
+    if match_allele:
+        additional_cols= ["A1","A2"]
+    else:
+        additional_cols=[]
+    hapmap3_ref = pd.read_csv(data_path,sep="\s+",usecols=["#CHROM","POS","rsid"]+additional_cols, dtype={"#CHROM":"string","POS":"string"})
+
     #rsid    A1      A2      #CHROM  POS
     #rs3094315       G       A       1       752566
+    
     if rsid in sumstats.columns:
         output = sumstats.loc[sumstats[rsid].isin(hapmap3_ref["rsid"].values),:].copy()
         return output
+    
     elif chrom in sumstats.columns and pos in sumstats.columns:
-        if verbose: log.write(" -Since rsID not in sumstats, chr:pos( build "+build+") will be used for matching...")
+        log.write(" -Since rsID not in sumstats, CHR:POS( build "+build+") will be used for matching...", verbose=verbose)
         sumstats   ["chr:pos"] = sumstats[chrom].astype("string")+":"+sumstats[pos].astype("string")
         hapmap3_ref["chr:pos"] = hapmap3_ref["#CHROM"]+":"+hapmap3_ref["POS"]
         hapmap3_ref = hapmap3_ref.rename(columns={"rsid":"rsID"})
-        output = pd.merge(sumstats,hapmap3_ref.loc[:,["chr:pos","rsID"]],left_on="chr:pos",right_on="chr:pos",how="inner",suffixes=('', '_hapmap3')).copy()
-        output = output.drop(columns="chr:pos")
-        if verbose: log.write(" -Raw input contains "+str(len(output))+" hapmaps variants based on chr:pos...")
+        output = pd.merge(sumstats,hapmap3_ref.loc[:,["chr:pos","rsID"]+additional_cols],left_on="chr:pos",right_on="chr:pos",how="inner",suffixes=('', '_hapmap3')).copy()
+        if match_allele:
+            log.write(" -Checking if alleles are same...")
+            is_matched = ((output[ea].astype("string") == output["A1"]) & (output[nea].astype("string") == output["A2"])) \
+                            | ((output[ea].astype("string") == output["A2"]) & (output[nea].astype("string") == output["A1"]))
+            log.write(" -Variants with macthed alleles: {}".format(sum(is_matched)))
+            output = output.loc[is_matched,:]
+        output = output.drop(columns=["chr:pos"]+additional_cols)
+        log.write(" -Raw input contains "+str(len(output))+" Hapmap3 variants based on CHR:POS...", verbose=verbose)
+        finished(log=log,verbose=verbose,end_line=_end_line)
         return output
     else:
         raise ValueError("Not enough information to match SNPs. Please check your sumstats...")