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

gwaslab/{util_ex_run_clumping.py → util/util_ex_run_clumping.py}

@@ -3,12 +3,12 @@ import numpy as np
 import os
 import pandas as pd
 from gwaslab.g_Log import Log
-from gwaslab.qc_fix_sumstats import start_to
-from gwaslab.qc_fix_sumstats import finished
-from gwaslab.util_ex_process_ref import _process_plink_input_files
+from gwaslab.qc.qc_fix_sumstats import start_to
+from gwaslab.qc.qc_fix_sumstats import finished
+from gwaslab.util.util_ex_process_ref import _process_plink_input_files
 from gwaslab.g_version import _checking_plink_version
 
-def _clump(insumstats, vcf=None, scaled=False, out="clumping_plink2", 
+def _clump(gls, vcf=None, scaled=False, out="clumping_plink2", 
            p="P",mlog10p="MLOG10P", overwrite=False, study=None, bfile=None, pfile=None,
            n_cores=1, memory=None, chrom=None, clump_p1=5e-8, clump_p2=5e-8, clump_r2=0.01, clump_kb=250,
            log=Log(),verbose=True,plink="plink",plink2="plink2"):
@@ -18,8 +18,16 @@ def _clump(insumstats, vcf=None, scaled=False, out="clumping_plink2",
     _start_cols =["SNPID","CHR","POS"]
     _start_function = ".clump()"
     _must_args ={}
+    
+    if out is None:
+        out = f"./{study}_clumpping".lstrip('/')
+    else:
+        out = out.lstrip('/')
+    sumstats_id = gls.id
+    sumstats = gls.data
+    gls.offload()
 
-    is_enough_info = start_to(sumstats=insumstats,
+    is_enough_info = start_to(sumstats=sumstats,
                             log=log,
                             verbose=verbose,
                             start_line=_start_line,
@@ -42,11 +50,18 @@ def _clump(insumstats, vcf=None, scaled=False, out="clumping_plink2",
         clump_log10_p2=-np.log10(clump_p2)
         log.write("  -clump_log10_p1 : {}...".format(clump_log10_p1),verbose=verbose)
         log.write("  -clump_log10_p2 : {}...".format(clump_log10_p2),verbose=verbose)
-        sumstats = insumstats.loc[insumstats[mlog10p]>min(clump_log10_p1,clump_log10_p2),:].copy()
+        sumstats = sumstats.loc[sumstats[mlog10p]>min(clump_log10_p1,clump_log10_p2),:].copy()
     # extract lead variants
     else:
         log.write(" -Clumping will be performed using {}".format(p),verbose=verbose)
-        sumstats = insumstats.loc[insumstats[p]<max(clump_p1,clump_p2),:].copy()
+        sumstats = sumstats.loc[sumstats[p]<max(clump_p1,clump_p2),:].copy()
+
+    if len(sumstats)==0:
+        log.write(" -No significant variants after filtering.")
+        finished(log=log, verbose=verbose, end_line=_end_line)
+        gls.reload()
+        return pd.DataFrame(), pd.DataFrame(), ""
+    
     log.write(" -Significant variants on CHR: ",list(sumstats["CHR"].unique()),verbose=verbose)
     
     plink_log=""
@@ -88,9 +103,9 @@ def _clump(insumstats, vcf=None, scaled=False, out="clumping_plink2",
             is_avaialable_variant = (sumstats["CHR"]==i) & (is_on_both)
 
             if scaled == True:
-                sumstats.loc[is_avaialable_variant,["SNPID",mlog10p]].to_csv("_gwaslab_tmp.{}.SNPIDP".format(i),index=False,sep="\t")
+                sumstats.loc[is_avaialable_variant,["SNPID",mlog10p]].to_csv("{}_gwaslab_tmp.{}.{}.SNPIDP".format(out, sumstats_id, i),index=False,sep="\t")
             else:
-                sumstats.loc[is_avaialable_variant,["SNPID",p]].to_csv("_gwaslab_tmp.{}.SNPIDP".format(i),index=False,sep="\t")
+                sumstats.loc[is_avaialable_variant,["SNPID",p]].to_csv("{}_gwaslab_tmp.{}.{}.SNPIDP".format(out, sumstats_id,i),index=False,sep="\t")
         except:
             log.write(" -Not available for: {}...".format(i),verbose=verbose)
         
@@ -102,7 +117,7 @@ def _clump(insumstats, vcf=None, scaled=False, out="clumping_plink2",
     for i in sumstats["CHR"].unique():
         chrom = i
         # temp file  
-        clump = "_gwaslab_tmp.{}.SNPIDP".format(chrom)
+        clump = "{}_gwaslab_tmp.{}.{}.SNPIDP".format(out,sumstats_id,chrom)
         # output prefix
         out_single_chr= out + ".{}".format(chrom)
         
@@ -173,10 +188,10 @@ def _clump(insumstats, vcf=None, scaled=False, out="clumping_plink2",
         os.remove(clump)
     
     results = results.sort_values(by=["#CHROM","POS"]).rename(columns={"#CHROM":"CHR","ID":"SNPID"})
-    log.write("Finished clumping.",verbose=verbose)
-    results_sumstats = insumstats.loc[insumstats["SNPID"].isin(results["SNPID"]),:].copy()
+    results_sumstats = sumstats.loc[sumstats["SNPID"].isin(results["SNPID"]),:].copy()
     finished(log=log, verbose=verbose, end_line=_end_line)
-
+    gls.reload()
+    
     return results_sumstats, results, plink_log
 
 

gwaslab/{util_ex_run_coloc.py → util/util_ex_run_coloc.py}

@@ -6,10 +6,12 @@ import numpy as np
 from gwaslab.g_Log import Log
 from gwaslab.g_version import _checking_r_version
 from gwaslab.g_version import _check_susie_version
-from gwaslab.qc_fix_sumstats import start_to
-from gwaslab.qc_fix_sumstats import finished
+from gwaslab.qc.qc_fix_sumstats import start_to
+from gwaslab.qc.qc_fix_sumstats import finished
 
-def _run_coloc_susie(filepath, r="Rscript",
+def _run_coloc_susie(glsp,
+                     filepath, 
+                     r="Rscript",
                      types=None, ns=None, 
                      fillldna=True, delete=False, 
                      coloc_args="", 
@@ -17,10 +19,18 @@ def _run_coloc_susie(filepath, r="Rscript",
                      ncols=None,
                      d1_args="",
                      d2_args="",
+                     out=None,
                      log=Log(), 
                      verbose=True):
     
-    log.write(" Start to run coloc.susie from command line:", verbose=verbose)
+    log.write("Start to run coloc.susie from command line:", verbose=verbose)
+
+    if filepath is None:
+        log.write(" -File path is None.", verbose=verbose)
+        log.write("Finished finemapping using SuSieR.", verbose=verbose)
+        return pd.DataFrame()
+    
+    glsp.offload()
 
     if types is None:
         types = ("cc","cc")
@@ -31,11 +41,6 @@ def _run_coloc_susie(filepath, r="Rscript",
             ns = ncols
     log.write(" -Ns: {} and {}".format(ns[0],ns[1]), verbose=verbose)
 
-    if filepath is None:
-        log.write(" -File path is None.", verbose=verbose)
-        log.write("Finished finemapping using SuSieR.", verbose=verbose)
-        return pd.DataFrame()
-        
     filelist = pd.read_csv(filepath,sep="\t")
     r_log=""
     # write R script
@@ -49,7 +54,12 @@ def _run_coloc_susie(filepath, r="Rscript",
         study = row["STUDY"]
         ld_r_matrix = row["LD_R_MATRIX"]
         sumstats = row["LOCUS_SUMSTATS"]
-        output_prefix = sumstats.replace(".sumstats.gz","")
+
+        if out is None:
+            output_prefix = sumstats.replace(".sumstats.gz","")
+        else:
+            output_prefix = os.path.join(out, os.path.basename(sumstats.replace(".sumstats.gz","")))
+        
         log.write(" -Running for: {} - {}".format(row["SNPID"],row["STUDY"] ), verbose=verbose)
         log.write("  -Locus sumstats:{}".format(sumstats), verbose=verbose)
         log.write("  -LD r matrix:{}".format(ld_r_matrix), verbose=verbose)
@@ -141,5 +151,7 @@ def _run_coloc_susie(filepath, r="Rscript",
         except subprocess.CalledProcessError as e:
             log.write(e.output)
             os.remove("_{}_{}_gwaslab_coloc_susie_temp.R".format(study,row["SNPID"]))
+    
     log.write("Finished clocalization using coloc and SuSiE.", verbose=verbose)
+    glsp.reload()
     return locus_pip_cs

gwaslab/{util_ex_run_hyprcoloc.py → util/util_ex_run_hyprcoloc.py}

@@ -6,10 +6,10 @@ import numpy as np
 from gwaslab.g_Log import Log
 from gwaslab.g_version import _checking_r_version
 from gwaslab.g_version import _check_susie_version
-from gwaslab.qc_fix_sumstats import start_to
-from gwaslab.qc_fix_sumstats import finished
-from gwaslab.util_ex_calculate_ldmatrix import _extract_variants_in_locus
-from gwaslab.util_in_get_sig import getsig
+from gwaslab.qc.qc_fix_sumstats import start_to
+from gwaslab.qc.qc_fix_sumstats import finished
+from gwaslab.util.util_ex_calculate_ldmatrix import _extract_variants_in_locus
+from gwaslab.util.util_in_get_sig import getsig
 
 def _run_hyprcoloc(  sumstats_multi, 
                      r="Rscript",

gwaslab/{util_ex_run_magma.py → util/util_ex_run_magma.py}

@@ -4,9 +4,9 @@ import gc
 import pandas as pd
 import numpy as np
 from gwaslab.g_Log import Log
-from gwaslab.util_in_filter_value import _exclude_hla
+from gwaslab.util.util_in_filter_value import _exclude_hla
 
-def _run_magma(sumstats, 
+def _run_magma(gls, 
                 magma="magma",
                 study="Study1",
                 exclude_hla=True,
@@ -15,7 +15,7 @@ def _run_magma(sumstats,
                 ref=None,
                 ncbi=None,
                 set_annot=None,
-                out="./",
+                out=None,
                 delete=True, 
                 ncol="N",
                 build="19",
@@ -24,33 +24,42 @@ def _run_magma(sumstats,
     
     log.write(" Start to run magma from command line:", verbose=verbose)
 
+    sumstats = gls.data
+    gls.offload() 
     if exclude_hla==True:
         sumstats = _exclude_hla(sumstats, build =build)
+    
+    if out is None:
+        out = os.path.join("./", study)
+    else:
+        out = os.path.join(out, study)
 
-    snploc="{}{}.rsid.chr.pos.tsv".format(out,study)
-    pval="{}{}.rsid.p.n.tsv".format(out, study)
+    snploc="{}.rsid.chr.pos.tsv".format(out)
+    pval="{}.rsid.p.n.tsv".format(out)
 
     log.write(f" -writing temp file for --snp-loc:{snploc}", verbose=verbose)
-    sumstats.dropna()[[id_to_use,"CHR","POS"]].rename(columns={id_to_use:"SNP"}).to_csv("{}{}.rsid.chr.pos.tsv".format(out,study),index=None, sep="\t")
+    sumstats.dropna()[[id_to_use,"CHR","POS"]].rename(columns={id_to_use:"SNP"}).to_csv("{}.rsid.chr.pos.tsv".format(out),index=None, sep="\t")
     
     log.write(f" -writing temp file for --pval:{pval}", verbose=verbose)
-    sumstats.dropna()[[id_to_use,"P","N"]].rename(columns={id_to_use:"SNP"}).to_csv("{}{}.rsid.p.n.tsv".format(out,study),index=None, sep="\t")
+    sumstats.dropna()[[id_to_use,"P","N"]].rename(columns={id_to_use:"SNP"}).to_csv("{}.rsid.p.n.tsv".format(out),index=None, sep="\t")
     
     log.write(f" --annotate window: {window}", verbose=verbose)
     log.write(f" --gene-loc: {ncbi}", verbose=verbose)
     log.write(f" --bfile: {ref}", verbose=verbose)
     log.write(f" Output prefix: {out}", verbose=verbose)
-
+    
+    
+    
     bash_script=f'''#!/bin/bash
 
-{magma} --annotate window={window}  --snp-loc {snploc} --gene-loc {ncbi} --out {study}
+{magma} --annotate window={window}  --snp-loc {snploc} --gene-loc {ncbi} --out {out}
 
-{magma} --bfile {ref} --pval {pval} ncol={ncol} --gene-annot {study}.genes.annot --out {study}
+{magma} --bfile {ref} --pval {pval} ncol={ncol} --gene-annot {out}.genes.annot --out {out}
 '''
     
     if set_annot is not None:
         bash_script+=f'''
-{magma} --gene-results {study}.genes.raw --set-annot {set_annot} --out {study}
+{magma} --gene-results {out}.genes.raw --set-annot {set_annot} --out {out}
 '''
     log.write(f"Script: {bash_script}")
 
@@ -67,5 +76,6 @@ def _run_magma(sumstats,
         log.warning("ERROR!")
         log.write(e.output)
 
+    gls.reload() 
     log.write("Finished running magma.", verbose=verbose)
 

gwaslab/{util_ex_run_mesusie.py → util/util_ex_run_mesusie.py}

@@ -6,9 +6,9 @@ import numpy as np
 from gwaslab.g_Log import Log
 from gwaslab.g_version import _checking_r_version
 from gwaslab.g_version import _check_susie_version
-from gwaslab.qc_fix_sumstats import start_to
-from gwaslab.qc_fix_sumstats import finished
-from gwaslab.viz_plot_stackedregional import _sort_args
+from gwaslab.qc.qc_fix_sumstats import start_to
+from gwaslab.qc.qc_fix_sumstats import finished
+from gwaslab.viz.viz_plot_stackedregional import _sort_args
 
 def _run_mesusie(filepath, 
                  r="Rscript",

gwaslab/{util_ex_run_mtag.py → util/util_ex_run_mtag.py}

@@ -4,19 +4,22 @@ import gc
 import pandas as pd
 import numpy as np
 from gwaslab.g_Log import Log
+from gwaslab.bd.bd_path_manager import _path
 
 def _run_mtag(       sumstats_multi, 
-                     python="Rscript",
+                     python="python",
                      mtag="",
                      study="Group1",
+                     special_flags="",
+                     ld_ref_panel = None,
                      traits=None,
                      out_prefix=None,
-                     types=None, 
+                     perfect_gencov = False, 
+                     equal_h2 = False, 
+                     no_overlap = False, 
+                     fdr=False,
                      n_min=0,
-                     loci=None,
                      nstudy=2,
-                     windowsizekb=1000,
-                     build="99",
                      log=Log(), 
                      verbose=True):
     
@@ -49,16 +52,37 @@ def _run_mtag(       sumstats_multi,
              "N_{}".format( i+1)   :"n",
 
         }
+        csv_path = _path(study = study,
+                    trait = traits_to_form_string[i],
+                    suffix="tsv.gz")
+
+        sumstats_multi.data[output_snp_info_cols+ output_stats_cols].rename(columns=rename_dict).to_csv(csv_path, index=None,sep="\t")
+        sumstats_paths.append(csv_path)
     
-        sumstats_multi[output_snp_info_cols+ output_stats_cols].rename(columns=rename_dict).to_csv("{}_{}.tsv.gz".format(study, traits_to_form_string[i]), index=None,sep="\t")
-        sumstats_paths.append("{}_{}.tsv.gz".format(study, traits_to_form_string[i]))
+    sumstats_multi.offload()
     
     python_log=""
     if out_prefix is None:
-        out_prefix = "./{study}_{nstudy}studies".format(study=study, nstudy=nstudy)
-    
+        out_prefix = _path(study=study, 
+                           nstudy = nstudy)
+        
+        #out_prefix = "./{study}_{nstudy}studies".format(study=study, nstudy=nstudy)
+    if ld_ref_panel is not None:
+        ld_ref_flag = "--ld_ref_panel {}".format(ld_ref_panel)
+    else:
+        ld_ref_flag=""
+
+    if perfect_gencov == True:
+        special_flags += "--perfect_gencov "
+    if equal_h2 == True:
+        special_flags += "--equal_h2 "
+    if no_overlap == True:
+        special_flags += "--no_overlap "
+    if fdr == True:
+        special_flags += "--fdr "
+
     script='''
-{python} {mtag} \
+{python} {mtag} {special_flags} {ld_ref_flag} \
 --sumstats {sumstats_paths_string} \
 --out {out_prefix} \
 --n_min {n_min} \
@@ -67,26 +91,34 @@ def _run_mtag(       sumstats_multi,
             python=python,
             n_min=n_min,
             mtag=mtag,
+            special_flags=special_flags,
             out_prefix=out_prefix,
+            ld_ref_flag=ld_ref_flag,
             sumstats_paths_string = ",".join(sumstats_paths)
         )
-    log.write(" MTAG script: {} ".format(script), verbose=verbose)
+    log.write("MTAG script: {} ".format(script), verbose=verbose)
 
-    
-    with open("_{}_gwaslab_mtag_temp.sh".format(study),"w") as file:
+    temp_script_path = _path(tmp=True,
+                             study=study,
+                             analysis="mtag", 
+                             suffix="sh"
+    )
+
+    with open(temp_script_path,"w") as file:
             file.write(script)
     
-    os.chmod("_{}_gwaslab_mtag_temp.sh".format(study), 0o700)   
-
-    script_run = "./_{}_gwaslab_mtag_temp.sh".format(study)
+    os.chmod(temp_script_path, 0o700)   
     
     try:
-        log.write(" Running MTAG from command line...", verbose=verbose)
-        output = subprocess.check_output(script_run, stderr=subprocess.STDOUT, shell=True,text=True)
+        log.write(" -Running MTAG from command line...", verbose=verbose)
+        output = subprocess.check_output(os.path.join(temp_script_path)
+                                         ,stderr=subprocess.STDOUT, shell=True,text=True)
         log.write(output)
         python_log+= output + "\n"
 
     except subprocess.CalledProcessError as e:
         log.write(e.output)
 
+    sumstats_multi.reload()
+    
     log.write("Finished MTAG.", verbose=verbose)

gwaslab/{util_ex_run_prscs.py → util/util_ex_run_prscs.py}

@@ -20,9 +20,9 @@ import os
 import sys
 import getopt
 
-import gwaslab.prscs_parse_genet as parse_genet
-import gwaslab.prscs_mcmc_gtb as mcmc_gtb
-import gwaslab.prscs_gigrnd as gigrnd
+import gwaslab.extension.prscs.prscs_parse_genet as parse_genet
+import gwaslab.extension.prscs.prscs_mcmc_gtb as mcmc_gtb
+import gwaslab.extension.prscs.prscs_gigrnd as gigrnd
 
 
 def _run_prscs(

gwaslab/{util_ex_run_scdrs.py → util/util_ex_run_scdrs.py}

@@ -5,7 +5,8 @@ import pandas as pd
 import numpy as np
 from gwaslab.g_Log import Log
 
-def _run_scdrs( scdrs="scdrs",
+def _run_scdrs( gls,
+                scdrs="scdrs",
                 python="python",
                 study="Study1",
                 conda_env=None,
@@ -32,16 +33,21 @@ def _run_scdrs( scdrs="scdrs",
     
     log.write(" Start to run scDRS from command line:", verbose=verbose)
     
+    log.write(f" Output prefix: {out}", verbose=verbose)
+    gls.offload()
     trait = study
+    
     if out_file is None:
         out_file = f"./{trait}.gs"
+        out_file = os.path.join(out, out_file)
     if out_folder is None:
-        out_folder = f"./"
+        out_folder = out
+
     if conda_env is not None:
         conda_env_string = f"conda init bash\n conda activate {conda_env}\n"
     else:
         conda_env_string=""
-    log.write(f" Output prefix: {out}", verbose=verbose)
+    
 
     if group_analysis is not None:
         analysis_string = f"--group-analysis {group_analysis} "
@@ -104,5 +110,5 @@ def _run_scdrs( scdrs="scdrs",
     except subprocess.CalledProcessError as e:
         log.warning("ERROR!")
         log.write(e.output)
-
+    gls.reload()
     log.write("Finished running scDRS.", verbose=verbose)

gwaslab/{util_ex_run_susie.py → util/util_ex_run_susie.py}

@@ -6,22 +6,23 @@ import numpy as np
 from gwaslab.g_Log import Log
 from gwaslab.g_version import _checking_r_version
 from gwaslab.g_version import _check_susie_version
-from gwaslab.qc_fix_sumstats import start_to
-from gwaslab.qc_fix_sumstats import finished
+from gwaslab.qc.qc_fix_sumstats import start_to
+from gwaslab.qc.qc_fix_sumstats import finished
 
-def _run_susie_rss(filepath, 
+def _run_susie_rss(gls,
+                   filepath, 
                    r="Rscript", 
                    mode="bs",
-                   max_iter=100000,
-                   min_abs_corr=0.1,
-                   refine="TRUE",
+                   out=None,
+                   max_iter=100,
+                   min_abs_corr=0.5,
+                   refine="FALSE",
                    L=10,
                    fillldna=True, 
                    n=None, 
                    delete=False,  #if delete output file
                    susie_args="", 
                    log=Log(),
-                   main_sumstats=None,
                    verbose=True):
     ##start function with col checking##########################################################
     _start_line = "run finemapping using SuSieR from command line"
@@ -44,7 +45,9 @@ def _run_susie_rss(filepath,
         log.write(" -File path is None.")
         log.write("Finished finemapping using SuSieR.")
         return pd.DataFrame()
-        
+    
+    gls.offload()
+
     filelist = pd.read_csv(filepath,sep="\t")
     r_log=""
     # write R script
@@ -52,38 +55,49 @@ def _run_susie_rss(filepath,
 
     log = _checking_r_version(r, log)
     log = _check_susie_version(r,log)
-
+    
     for index, row in filelist.iterrows(): 
         gc.collect()
         study = row["STUDY"]
         ld_r_matrix = row["LD_R_MATRIX"] #ld matrix path
         sumstats = row["LOCUS_SUMSTATS"] #sumsttas path
-        output_prefix = sumstats.replace(".sumstats.gz","")
+        
+        # out: directory for output files
+        if out is None:
+            output_prefix = sumstats.replace(".sumstats.gz","")
+        else:
+            output_prefix = os.path.join(out, os.path.basename(sumstats.replace(".sumstats.gz","")))
+        
         log.write(" -Running for: {} - {}".format(row["SNPID"],row["STUDY"] ))
         log.write("  -Locus sumstats:{}".format(sumstats))
         log.write("  -LD r matrix:{}".format(ld_r_matrix))
         log.write("  -output_prefix:{}".format(output_prefix))
         
         rscript='''
-        library(susieR)
-        
-        sumstats <- read.csv("{}",sep="\t")
-        
-        R <- as.matrix(read.csv("{}",sep="\t",header=FALSE))
-        {}
+library(susieR)
+
+sumstats <- read.csv("{}",sep="\t")
+
+R <- as.matrix(read.csv("{}",sep="\t",header=FALSE))
+{}
+
+n <- floor(mean(sumstats$N))
 
-        n <- floor(mean(sumstats$N))
+fitted_rss1 <- susie_rss({}, n = {}, R = R, max_iter = {}, min_abs_corr={}, refine = {}, L = {}{})
 
-        fitted_rss1 <- susie_rss({}, n = {}, R = R, max_iter = {}, min_abs_corr={}, refine = {}, L = {}{})
+susie_fitted_summary <- summary(fitted_rss1)
 
-        susie_fitted_summary <- summary(fitted_rss1)
+output <- susie_fitted_summary$vars
+output$SNPID <- sumstats$SNPID[susie_fitted_summary$vars$variable]
+output$LOCUS <- "{}"
+output$STUDY <- "{}"
 
-        output <- susie_fitted_summary$vars
-        output$SNPID <- sumstats$SNPID[susie_fitted_summary$vars$variable]
-        output$LOCUS <- "{}"
-        output$STUDY <- "{}"
+write.csv(output, "{}.pipcs", row.names = FALSE)
 
-        write.csv(output, "{}.pipcs", row.names = FALSE)
+png(filename="{}_diagnostic.png")
+diagnostic <- kriging_rss({}, R, n=n)
+diagnostic$plot
+dev.off()
         '''.format(sumstats, 
                    ld_r_matrix,
                     "R[is.na(R)] <- 0" if fillldna==True else "",
@@ -96,7 +110,9 @@ def _run_susie_rss(filepath,
                     susie_args, 
                     row["SNPID"],
                     row["STUDY"],
-                    output_prefix)
+                    output_prefix,
+                    output_prefix,
+                    "sumstats$Z" if mode=="z" else "sumstats$BETA/sumstats$SE")
         susier_line = "susie_rss({}, n = {}, R = R, max_iter = {}, min_abs_corr={}, refine = {}, L = {}{})".format("z= sumstats$Z," if mode=="z" else "bhat = sumstats$BETA,shat = sumstats$SE,",
                     n if n is not None else "n", 
                     max_iter,
@@ -106,7 +122,12 @@ def _run_susie_rss(filepath,
                     susie_args)
         log.write("  -SuSieR script: {}".format(susier_line))
         
+        # temporary R script path
         temp_r_path = "_{}_{}_{}_gwaslab_susie_temp.R".format(study,row["SNPID"],id(sumstats))
+        if out is not None:
+            temp_r_path = os.path.join(out, temp_r_path)
+        
+        
         log.write("  -Createing temp R script: {}".format(temp_r_path))
         with open(temp_r_path,"w") as file:
                 file.write(rscript)
@@ -140,8 +161,10 @@ def _run_susie_rss(filepath,
             os.remove(temp_r_path)
             log.write("  -Removing temp R script: {}".format(temp_r_path))
     
+    gls.reload()
+
     locus_pip_cs = locus_pip_cs.rename(columns={"variable":"N_SNP","variable_prob":"PIP","cs":"CREDIBLE_SET_INDEX"})	
-    locus_pip_cs = pd.merge(locus_pip_cs, main_sumstats, on="SNPID",how="left")
+    locus_pip_cs = pd.merge(locus_pip_cs, gls.data[["SNPID","CHR","POS"]], on="SNPID",how="left")
     
     finished(log=log, verbose=verbose, end_line=_end_line)
     return locus_pip_cs

gwaslab/{util_in_fill_data.py → util/util_in_fill_data.py}

@@ -7,7 +7,7 @@ from gwaslab.g_Log import Log
 import gc
 #from gwaslab.qc_fix_sumstats import sortcolumn
 from gwaslab.g_version import _get_version
-from gwaslab.qc_check_datatype import check_datatype
+from gwaslab.qc.qc_check_datatype import check_datatype
 
 
 def filldata( 

gwaslab/{util_in_filter_value.py → util/util_in_filter_value.py}

@@ -1,17 +1,21 @@
 import re
-#import modin.pandas as pd
 import pandas as pd
 import numpy as np
 from os import path
-from gwaslab.bd_common_data import get_high_ld
-from gwaslab.bd_common_data import get_chr_to_number
+from pathlib import Path
+
 from gwaslab.g_Log import Log
 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
+
+from gwaslab.qc.qc_fix_sumstats import sortcoordinate
+from gwaslab.qc.qc_fix_sumstats import start_to
+from gwaslab.qc.qc_fix_sumstats import finished
+from gwaslab.qc.qc_fix_sumstats import _process_build
+
+from gwaslab.bd.bd_common_data import get_high_ld
+from gwaslab.bd.bd_common_data import get_chr_to_number
+
+from gwaslab.hm.hm_harmonize_sumstats import is_palindromic
 
 import gc
 def filtervalues(sumstats,expr,remove=False,verbose=True,log=Log()):
@@ -221,6 +225,8 @@ def inferbuild(sumstats,status="STATUS",chrom="CHR", pos="POS",
                ea="EA", nea="NEA",build="19",
                change_status=True, 
                verbose=True,log=Log()):
+    
+
     ##start function with col checking##########################################################
     _start_line = "infer genome build version using hapmap3 SNPs"
     _end_line = "inferring genome build version using hapmap3 SNPs"
@@ -241,8 +247,10 @@ def inferbuild(sumstats,status="STATUS",chrom="CHR", pos="POS",
 
     inferred_build="Unknown"
     log.write("Start to infer genome build version using hapmap3 SNPs...", verbose=verbose)    
-    data_path_19 =  path.dirname(__file__) + '/data/hapmap3_SNPs/hapmap3_db150_hg19.snplist.gz'    
-    data_path_38 =  path.dirname(__file__) + '/data/hapmap3_SNPs/hapmap3_db151_hg38.snplist.gz'    
+
+    data_path_19 = path.join( Path(__file__).parents[1], "data","hapmap3_SNPs","hapmap3_db150_hg19.snplist.gz")
+    data_path_38 = path.join( Path(__file__).parents[1], "data","hapmap3_SNPs","hapmap3_db151_hg38.snplist.gz")
+
     log.write(" -Loading Hapmap3 variants data...", verbose=verbose)        
     hapmap3_ref_19 = pd.read_csv(data_path_19,sep="\s+",usecols=["#CHROM","POS"],dtype={"#CHROM":"string","POS":"string"})
     hapmap3_ref_38 = pd.read_csv(data_path_38,sep="\s+",usecols=["#CHROM","POS"],dtype={"#CHROM":"string","POS":"string"})
@@ -266,7 +274,6 @@ def inferbuild(sumstats,status="STATUS",chrom="CHR", pos="POS",
         log.write(" -Since num_hg19 >> num_hg38, assigning genome build hg19...", verbose=verbose) 
         if change_status==True:
             sumstats[status] = vchange_status(sumstats[status],1,"9","1")
-            sumstats[status] = vchange_status(sumstats[status],2,"9","9")
         inferred_build="19"
     elif match_count_for_19 < match_count_for_38:
         log.write(" -Since num_hg19 << num_hg38, assigning genome build hg38...", verbose=verbose)