Built on 2026-02-24 V008

saeidamiri1 · saeidamiri1 · commit 36121f8be730 · 2026-02-24T10:47:28.000-05:00
diff --git a/.DS_Store b/.DS_Store
diff --git a/segpy/CHANGES.txt b/segpy/CHANGES.txt
@@ -1,3 +1,5 @@
+v0.0.8, 2026-02-22
+ * Correct issue in sample id. 
 v0.0.5, 2025-09-12
  * Correct issue in case-control. 
 v0.0.6, 2024-12-12
diff --git a/segpy/segpy/segrun/segrun_family_wise_whole.py b/segpy/segpy/segrun/segrun_family_wise_whole.py
@@ -83,90 +83,95 @@ def sample_retrieve(mt, ped, outfolder):
     ##### list of sample in the affected and non-affected family
     glb_aff=[ x for x in ped.loc[ped.loc[:,'phenotype']==2,'individualid']]
     glb_naf=[ x for x in ped.loc[ped.loc[:,'phenotype']==1,'individualid']]
-    ##### list of family
-    #################################################### Global affected
-    glb_aff_sam = hl.literal(hl.set(glb_aff))
-    glb_aff_sam_mt=mt.filter_cols(glb_aff_sam.contains(mt.s))
-    # fam_aff_mt.count()
-    ## wildtype 
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_r= glb_aff)
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_wild = hl.agg.sum(glb_aff_sam_mt.wild))
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_wild_c = hl.agg.collect(glb_aff_sam_mt.wild))
-    # no call
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_ncl = hl.agg.sum(glb_aff_sam_mt.ncl))
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_ncl_c = hl.agg.collect(glb_aff_sam_mt.ncl))
-    # variant 
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_vrt = hl.agg.sum(glb_aff_sam_mt.vrt))
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_vrt_c = hl.agg.collect(glb_aff_sam_mt.vrt))
-    # hom_var: contains identical alternate alleles
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_homv = hl.agg.sum(glb_aff_sam_mt.homv))
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_homv_c = hl.agg.collect(glb_aff_sam_mt.homv))
-    # altaf: contains  ALT allele frequency   
-    glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_altaf = (hl.agg.call_stats(glb_aff_sam_mt.GT, glb_aff_sam_mt.alleles).AF[1]))
-    # listt2=[]
-    # name2=f'{outfolder}/samp/glb_aff.csv'
-    listt2=['glb_aff_r','glb_aff_wild','glb_aff_wild_c','glb_aff_ncl','glb_aff_ncl_c','glb_aff_vrt','glb_aff_vrt_c', 'glb_aff_homv', 'glb_aff_homv_c','glb_aff_altaf']
-    df3=glb_aff_sam_mt.rows().select(*listt2).to_spark()
     udf_i = udf(lambda x: np.where(x)[0].tolist(), ArrayType(IntegerType()))
-    df4=df3.select('glb_aff_r','glb_aff_wild','glb_aff_wild_c','glb_aff_ncl','glb_aff_ncl_c','glb_aff_vrt','glb_aff_vrt_c', 'glb_aff_homv', 'glb_aff_homv_c','glb_aff_altaf',udf_i('glb_aff_wild_c').alias('glb_aff_wild_c2'),udf_i('glb_aff_ncl_c').alias('glb_aff_ncl_c2'),udf_i('glb_aff_vrt_c').alias('glb_aff_vrt_c2'),udf_i('glb_aff_homv_c').alias('glb_aff_homv_c2'))
-    del df3
     udf_2b = udf(lambda x,ref: [x[i] for i in ref])
-    df5=df4.select('glb_aff_wild',udf_2b('glb_aff_r', 'glb_aff_wild_c2').alias('glb_aff_wild_s'),'glb_aff_ncl',udf_2b('glb_aff_r', 'glb_aff_ncl_c2').alias('glb_aff_ncl_s'),'glb_aff_vrt', udf_2b('glb_aff_r', 'glb_aff_vrt_c2').alias('glb_aff_vrt_s'),'glb_aff_homv', udf_2b('glb_aff_r', 'glb_aff_homv_c2').alias('glb_aff_homv_s'),'glb_aff_altaf')
     str_udf = F.udf(str_list, T.StringType())
-    df6=df5.select('glb_aff_wild',str_udf('glb_aff_wild_s').alias('glb_aff_wild_samp'),'glb_aff_ncl',str_udf('glb_aff_ncl_s').alias('glb_aff_ncl_samp'),'glb_aff_vrt', str_udf('glb_aff_vrt_s').alias('glb_aff_vrt_samp'),'glb_aff_homv',str_udf('glb_aff_homv_s').alias('glb_aff_homv_samp'),'glb_aff_altaf')
-    del df5
-    name_glb_csv=f'{outfolder}/samp/glb_affcsv'
-    df6.repartition(1).write.format("csv").mode('overwrite').option("sep","\t").option("header", "true").save(name_glb_csv)
-    del df6
-    cmd_glb_aff0=f'cd {outfolder}/samp/glb_affcsv ; find . -type f -name \""*.csv"\" -exec mv {{}} ../glb_aff_out \; ; rm -r  ../glb_affcsv'
-    os.system(cmd_glb_aff0)  
-    cmd_prune_glb=f'cd {outfolder}/samp;' + ' sed -i glb_aff_out -e \"s/\[\]/\[\\"\\"\]/g ; s/\[\'/\[\\"/g ;  s/\'\]/\\"\]/g ;  s/\'/\\"/g ; s/\[\]/\[\"\"\]/g \" '
-    os.system(cmd_prune_glb)
-    cmd_prune_glb_mv=f'mv {outfolder}/samp/glb_aff_out {outfolder}/glb_aff_out'
-    os.system(cmd_prune_glb_mv)
+    ##### list of family
+    #################################################### Global affected
+    if len(glb_aff) > 0:
+        glb_aff_sam = hl.literal(hl.set(glb_aff))
+        glb_aff_sam_mt=mt.filter_cols(glb_aff_sam.contains(mt.s))
+        # fam_aff_mt.count()
+        ## wildtype 
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_r= glb_aff)
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_wild = hl.agg.sum(glb_aff_sam_mt.wild))
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_wild_c = hl.agg.collect(glb_aff_sam_mt.wild))
+        # no call
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_ncl = hl.agg.sum(glb_aff_sam_mt.ncl))
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_ncl_c = hl.agg.collect(glb_aff_sam_mt.ncl))
+        # variant 
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_vrt = hl.agg.sum(glb_aff_sam_mt.vrt))
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_vrt_c = hl.agg.collect(glb_aff_sam_mt.vrt))
+        # hom_var: contains identical alternate alleles
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_homv = hl.agg.sum(glb_aff_sam_mt.homv))
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_homv_c = hl.agg.collect(glb_aff_sam_mt.homv))
+        # altaf: contains  ALT allele frequency   
+        glb_aff_sam_mt = glb_aff_sam_mt.annotate_rows(glb_aff_altaf = (hl.agg.call_stats(glb_aff_sam_mt.GT, glb_aff_sam_mt.alleles).AF[1]))
+        # listt2=[]
+        # name2=f'{outfolder}/samp/glb_aff.csv'
+        listt2=['glb_aff_r','glb_aff_wild','glb_aff_wild_c','glb_aff_ncl','glb_aff_ncl_c','glb_aff_vrt','glb_aff_vrt_c', 'glb_aff_homv', 'glb_aff_homv_c','glb_aff_altaf']
+        df3=glb_aff_sam_mt.rows().select(*listt2).to_spark()
+        udf_i = udf(lambda x: np.where(x)[0].tolist(), ArrayType(IntegerType()))
+        df4=df3.select('glb_aff_r','glb_aff_wild','glb_aff_wild_c','glb_aff_ncl','glb_aff_ncl_c','glb_aff_vrt','glb_aff_vrt_c', 'glb_aff_homv', 'glb_aff_homv_c','glb_aff_altaf',udf_i('glb_aff_wild_c').alias('glb_aff_wild_c2'),udf_i('glb_aff_ncl_c').alias('glb_aff_ncl_c2'),udf_i('glb_aff_vrt_c').alias('glb_aff_vrt_c2'),udf_i('glb_aff_homv_c').alias('glb_aff_homv_c2'))
+        del df3
+        udf_2b = udf(lambda x,ref: [x[i] for i in ref])
+        df5=df4.select('glb_aff_wild',udf_2b('glb_aff_r', 'glb_aff_wild_c2').alias('glb_aff_wild_s'),'glb_aff_ncl',udf_2b('glb_aff_r', 'glb_aff_ncl_c2').alias('glb_aff_ncl_s'),'glb_aff_vrt', udf_2b('glb_aff_r', 'glb_aff_vrt_c2').alias('glb_aff_vrt_s'),'glb_aff_homv', udf_2b('glb_aff_r', 'glb_aff_homv_c2').alias('glb_aff_homv_s'),'glb_aff_altaf')
+        str_udf = F.udf(str_list, T.StringType())
+        df6=df5.select('glb_aff_wild',str_udf('glb_aff_wild_s').alias('glb_aff_wild_samp'),'glb_aff_ncl',str_udf('glb_aff_ncl_s').alias('glb_aff_ncl_samp'),'glb_aff_vrt', str_udf('glb_aff_vrt_s').alias('glb_aff_vrt_samp'),'glb_aff_homv',str_udf('glb_aff_homv_s').alias('glb_aff_homv_samp'),'glb_aff_altaf')
+        del df5
+        name_glb_csv=f'{outfolder}/samp/glb_affcsv'
+        df6.repartition(1).write.format("csv").mode('overwrite').option("sep","\t").option("header", "true").save(name_glb_csv)
+        del df6
+        cmd_glb_aff0=f'cd {outfolder}/samp/glb_affcsv ; find . -type f -name \""*.csv"\" -exec mv {{}} ../glb_aff_out \; ; rm -r  ../glb_affcsv'
+        os.system(cmd_glb_aff0)  
+        cmd_prune_glb=f'cd {outfolder}/samp;' + ' sed -i glb_aff_out -e \"s/\[\]/\[\\"\\"\]/g ; s/\[\'/\[\\"/g ;  s/\'\]/\\"\]/g ;  s/\'/\\"/g ; s/\[\]/\[\"\"\]/g \" '
+        os.system(cmd_prune_glb)
+        cmd_prune_glb_mv=f'mv {outfolder}/samp/glb_aff_out {outfolder}/glb_aff_out'
+        os.system(cmd_prune_glb_mv)
     # list_generated.append('glb_aff.csv')
     ##################################################### Global unaffected
     ##### generate global non-affected
-    glb_naf_sam = hl.literal(hl.set(glb_naf))
-    glb_naf_sam_mt=mt.filter_cols(glb_naf_sam.contains(mt.s))
-    # glb_naf_sam_mt.count()
-    ## wildtype 
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_r= glb_naf)
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_wild = hl.agg.sum(glb_naf_sam_mt.wild))
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_wild_c = hl.agg.collect(glb_naf_sam_mt.wild))
-    # no call
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_ncl = hl.agg.sum(glb_naf_sam_mt.ncl))
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_ncl_c = hl.agg.collect(glb_naf_sam_mt.ncl))
-    # variant 
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_vrt = hl.agg.sum(glb_naf_sam_mt.vrt))
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_vrt_c = hl.agg.collect(glb_naf_sam_mt.vrt))
-    # hom_var: contains identical alternate alleles
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_homv = hl.agg.sum(glb_naf_sam_mt.homv))
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_homv_c = hl.agg.collect(glb_naf_sam_mt.homv))
-    # altaf: contains  ALT allele frequency   
-    glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_altaf = (hl.agg.call_stats(glb_naf_sam_mt.GT, glb_naf_sam_mt.alleles).AF[1]))
-    # listt2=[]
-    # name2=f'{outfolder}/samp/glb_naf.csv'
-    listt2=['glb_naf_r','glb_naf_wild','glb_naf_wild_c','glb_naf_ncl','glb_naf_ncl_c','glb_naf_vrt','glb_naf_vrt_c', 'glb_naf_homv', 'glb_naf_homv_c','glb_naf_altaf']
-    # spark = SparkSession.builder.appName("myApp").getOrCreate()
-    df3=glb_naf_sam_mt.rows().select(*listt2).to_spark()
-    # udf_i = udf(lambda x: np.where(x)[0].tolist(), ArrayType(IntegerType()))
-    df4=df3.select('glb_naf_r','glb_naf_wild','glb_naf_wild_c','glb_naf_ncl','glb_naf_ncl_c','glb_naf_vrt','glb_naf_vrt_c', 'glb_naf_homv', 'glb_naf_homv_c','glb_naf_altaf',udf_i('glb_naf_wild_c').alias('glb_naf_wild_c2'),udf_i('glb_naf_ncl_c').alias('glb_naf_ncl_c2'),udf_i('glb_naf_vrt_c').alias('glb_naf_vrt_c2'),udf_i('glb_naf_homv_c').alias('glb_naf_homv_c2'))
-    del df3
-    # udf_2b = udf(lambda x,ref: [x[i] for i in ref])
-    df5=df4.select('glb_naf_wild',udf_2b('glb_naf_r', 'glb_naf_wild_c2').alias('glb_naf_wild_s'),'glb_naf_ncl',udf_2b('glb_naf_r', 'glb_naf_ncl_c2').alias('glb_naf_ncl_s'),'glb_naf_vrt', udf_2b('glb_naf_r', 'glb_naf_vrt_c2').alias('glb_naf_vrt_s'),'glb_naf_homv', udf_2b('glb_naf_r', 'glb_naf_homv_c2').alias('glb_naf_homv_s'),'glb_naf_altaf')
-    # str_udf = F.udf(str_list, T.StringType())
-    df6=df5.select('glb_naf_wild',str_udf('glb_naf_wild_s').alias('glb_naf_wild_samp'),'glb_naf_ncl',str_udf('glb_naf_ncl_s').alias('glb_naf_ncl_samp'),'glb_naf_vrt', str_udf('glb_naf_vrt_s').alias('glb_naf_vrt_samp'),'glb_naf_homv',str_udf('glb_naf_homv_s').alias('glb_naf_homv_samp'),'glb_naf_altaf')
-    del df5
-    name_glb_csv=f'{outfolder}/samp/glb_nafcsv'
-    df6.repartition(1).write.format("csv").mode('overwrite').option("sep","\t").option("header", "true").save(name_glb_csv)
-    del df6
-    cmd_glb_aff0=f'cd {outfolder}/samp/glb_nafcsv ; find . -type f -name \""*.csv"\" -exec mv {{}} ../glb_naf_out \; ; rm -r  ../glb_nafcsv'
-    os.system(cmd_glb_aff0)  
-    cmd_prune_glb=f'cd {outfolder}/samp;' + ' sed -i glb_naf_out -e \"s/\[\]/\[\\"\\"\]/g ; s/\[\'/\[\\"/g ;  s/\'\]/\\"\]/g ;  s/\'/\\"/g ; s/\[\]/\[\"\"\]/g \" '
-    os.system(cmd_prune_glb)
-    cmd_prune_glb_mv=f'mv {outfolder}/samp/glb_naf_out {outfolder}/glb_naf_out'
-    os.system(cmd_prune_glb_mv)
+    if len(glb_naf) > 0:
+        glb_naf_sam = hl.literal(hl.set(glb_naf))
+        glb_naf_sam_mt=mt.filter_cols(glb_naf_sam.contains(mt.s))
+        # glb_naf_sam_mt.count()
+        ## wildtype 
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_r= glb_naf)
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_wild = hl.agg.sum(glb_naf_sam_mt.wild))
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_wild_c = hl.agg.collect(glb_naf_sam_mt.wild))
+        # no call
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_ncl = hl.agg.sum(glb_naf_sam_mt.ncl))
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_ncl_c = hl.agg.collect(glb_naf_sam_mt.ncl))
+        # variant 
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_vrt = hl.agg.sum(glb_naf_sam_mt.vrt))
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_vrt_c = hl.agg.collect(glb_naf_sam_mt.vrt))
+        # hom_var: contains identical alternate alleles
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_homv = hl.agg.sum(glb_naf_sam_mt.homv))
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_homv_c = hl.agg.collect(glb_naf_sam_mt.homv))
+        # altaf: contains  ALT allele frequency   
+        glb_naf_sam_mt = glb_naf_sam_mt.annotate_rows(glb_naf_altaf = (hl.agg.call_stats(glb_naf_sam_mt.GT, glb_naf_sam_mt.alleles).AF[1]))
+        # listt2=[]
+        # name2=f'{outfolder}/samp/glb_naf.csv'
+        listt2=['glb_naf_r','glb_naf_wild','glb_naf_wild_c','glb_naf_ncl','glb_naf_ncl_c','glb_naf_vrt','glb_naf_vrt_c', 'glb_naf_homv', 'glb_naf_homv_c','glb_naf_altaf']
+        # spark = SparkSession.builder.appName("myApp").getOrCreate()
+        df3=glb_naf_sam_mt.rows().select(*listt2).to_spark()
+        # udf_i = udf(lambda x: np.where(x)[0].tolist(), ArrayType(IntegerType()))
+        df4=df3.select('glb_naf_r','glb_naf_wild','glb_naf_wild_c','glb_naf_ncl','glb_naf_ncl_c','glb_naf_vrt','glb_naf_vrt_c', 'glb_naf_homv', 'glb_naf_homv_c','glb_naf_altaf',udf_i('glb_naf_wild_c').alias('glb_naf_wild_c2'),udf_i('glb_naf_ncl_c').alias('glb_naf_ncl_c2'),udf_i('glb_naf_vrt_c').alias('glb_naf_vrt_c2'),udf_i('glb_naf_homv_c').alias('glb_naf_homv_c2'))
+        del df3
+        # udf_2b = udf(lambda x,ref: [x[i] for i in ref])
+        df5=df4.select('glb_naf_wild',udf_2b('glb_naf_r', 'glb_naf_wild_c2').alias('glb_naf_wild_s'),'glb_naf_ncl',udf_2b('glb_naf_r', 'glb_naf_ncl_c2').alias('glb_naf_ncl_s'),'glb_naf_vrt', udf_2b('glb_naf_r', 'glb_naf_vrt_c2').alias('glb_naf_vrt_s'),'glb_naf_homv', udf_2b('glb_naf_r', 'glb_naf_homv_c2').alias('glb_naf_homv_s'),'glb_naf_altaf')
+        # str_udf = F.udf(str_list, T.StringType())
+        df6=df5.select('glb_naf_wild',str_udf('glb_naf_wild_s').alias('glb_naf_wild_samp'),'glb_naf_ncl',str_udf('glb_naf_ncl_s').alias('glb_naf_ncl_samp'),'glb_naf_vrt', str_udf('glb_naf_vrt_s').alias('glb_naf_vrt_samp'),'glb_naf_homv',str_udf('glb_naf_homv_s').alias('glb_naf_homv_samp'),'glb_naf_altaf')
+        del df5
+        name_glb_csv=f'{outfolder}/samp/glb_nafcsv'
+        df6.repartition(1).write.format("csv").mode('overwrite').option("sep","\t").option("header", "true").save(name_glb_csv)
+        del df6
+        cmd_glb_aff0=f'cd {outfolder}/samp/glb_nafcsv ; find . -type f -name \""*.csv"\" -exec mv {{}} ../glb_naf_out \; ; rm -r  ../glb_nafcsv'
+        os.system(cmd_glb_aff0)  
+        cmd_prune_glb=f'cd {outfolder}/samp;' + ' sed -i glb_naf_out -e \"s/\[\]/\[\\"\\"\]/g ; s/\[\'/\[\\"/g ;  s/\'\]/\\"\]/g ;  s/\'/\\"/g ; s/\[\]/\[\"\"\]/g \" '
+        os.system(cmd_prune_glb)
+        cmd_prune_glb_mv=f'mv {outfolder}/samp/glb_naf_out {outfolder}/glb_naf_out'
+        os.system(cmd_prune_glb_mv)
     # mt.rows().export(f'{outfolder}/out_locus0',delimiter='\t')
     # cmd_glb_csq=f'cut -f 1-2 {outfolder}/out_locus0 > {outfolder}/out_locus; rm {outfolder}/out_locus0'
     # os.system(cmd_glb_csq)
@@ -304,7 +309,6 @@ def segrun_family_wise_whole(mt, ped, outfolder, hl, csqlabel, affecteds_only, f
         cmd_paste = 'paste $(ls -rt ' +  f'{outfolder}/out_csq_*) > {outfolder}/out_csq; rm {outfolder}/out_csq_*'
         os.system(cmd_paste)
         timekeeping(step, start_time)
-    
     # processing the rest of the INFO field data
     # pseudo:   vcf INFO fields are not natively exportable as separate columns to tsv;
     #           therefore the process to do so is:
diff --git a/segpy/segpy/segrun/segrun_family_wise_whole_multiple.py b/segpy/segpy/segrun/segrun_family_wise_whole_multiple.py
@@ -63,7 +63,10 @@ def export_counts(mt, prefix, outfile):
 
 # generate wild/ncl/vrt/homv counts for one matrixTable for multiple family
 def generate_counts_m(mt, fam, sample_list,ped):
-    fam_aff=[ x for x in ped.loc[ped.loc[:,'familyid']==fam,'individualid']]
+    # fam_aff=[ x for x in ped.loc[ped.loc[:,'familyid']==fam,'individualid']]
+    fam_aff=sample_list
+    if not sample_list:
+        fam_aff=[ x for x in ped.loc[ped.loc[:,'familyid']==fam,'individualid']]
     aff_sam = hl.literal(hl.set(fam_aff))
     aff_sam2=mt.filter_cols(aff_sam.contains(mt.s))
     if len(sample_list) > 0:
diff --git a/segpy/setup.py b/segpy/setup.py
@@ -12,7 +12,7 @@
     # Needed for dependencies
     install_requires=['numpy', 'pandas', 'hail'],
     # *strongly* suggested for sharing
-    version='0.0.7',
+    version='0.0.8',
     license='MIT',
     description='Segpy: A pipeline for segregation analysis',
     # We will also need a readme eventually (there will be a warning)
diff --git a/test/.DS_Store b/test/.DS_Store
diff --git a/test/module_python.txt b/test/module_python.txt
@@ -0,0 +1,111 @@
+Package                  Version
+------------------------ ----------------
+aiodns                   2.0.0
+aiohttp                  3.9.1
+aiohttp-session          2.12.0
+aiosignal                1.3.1
+anyio                    4.2.0
+async-timeout            4.0.3
+asyncinit                0.2.4
+attrs                    23.2.0
+avro                     1.11.3
+azure-common             1.1.28
+azure-core               1.29.6
+azure-identity           1.15.0
+azure-mgmt-core          1.4.0
+azure-mgmt-storage       20.1.0
+azure-storage-blob       12.19.0
+bokeh                    1.4.0
+boto3                    1.34.11
+botocore                 1.34.11
+cachetools               5.3.2
+certifi                  2023.11.17
+cffi                     1.16.0
+chardet                  4.0.0
+charset-normalizer       3.3.2
+click                    8.1.7
+commonmark               0.9.1
+contourpy                1.2.0
+cryptography             41.0.7
+dbus-python              1.2.18
+decorator                4.4.2
+Deprecated               1.2.14
+dill                     0.3.7
+exceptiongroup           1.2.0
+frozenlist               1.4.1
+google-api-core          2.15.0
+google-auth              2.14.1
+google-auth-oauthlib     0.8.0
+google-cloud-core        2.4.1
+google-cloud-storage     2.11.0
+google-crc32c            1.5.0
+google-resumable-media   2.7.0
+googleapis-common-protos 1.62.0
+hail                     0.2.109
+humanize                 1.1.0
+hurry.filesize           0.9
+idna                     3.6
+isodate                  0.6.1
+janus                    1.0.0
+Jinja2                   3.0.3
+jmespath                 1.0.1
+jproperties              2.1.1
+MarkupSafe               2.1.3
+msal                     1.26.0
+msal-extensions          1.1.0
+msrest                   0.7.1
+multidict                6.0.4
+nest-asyncio             1.5.8
+numpy                    1.25.2
+oauthlib                 3.2.2
+orjson                   3.9.10
+packaging                23.2
+pandas                   1.5.3
+parsimonious             0.8.1
+Pillow                   10.1.0
+pip                      22.0.2
+plotly                   5.10.0
+portalocker              2.8.2
+protobuf                 3.20.2
+py4j                     0.10.9
+pyasn1                   0.5.1
+pyasn1-modules           0.3.0
+pycares                  4.4.0
+pycparser                2.21
+Pygments                 2.17.2
+PyGObject                3.42.1
+PyJWT                    2.8.0
+pyspark                  3.1.3
+python-apt               2.4.0+ubuntu2
+python-dateutil          2.8.2
+python-debian            0.1.43+ubuntu1.1
+python-json-logger       2.0.7
+pytz                     2023.3.post1
+PyYAML                   6.0.1
+regex                    2023.12.25
+requests                 2.31.0
+requests-oauthlib        1.3.1
+rich                     12.6.0
+rsa                      4.9
+s3transfer               0.10.0
+scipy                    1.9.3
+segpy                    0.0.8
+session-info             1.0.0
+setuptools               59.6.0
+six                      1.16.0
+sniffio                  1.3.0
+sortedcontainers         2.4.0
+stdlib-list              0.10.0
+tabulate                 0.9.0
+tenacity                 8.2.3
+tornado                  6.4
+typer                    0.9.0
+typing_extensions        4.9.0
+tzdata                   2023.4
+urllib3                  2.0.7
+uvloop                   0.19.0
+wheel                    0.37.1
+wrapt                    1.16.0
+xyzservices              2023.10.1
+yarl                     1.9.4
+

Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+v0.0.8, 2026-02-22`
	`2`	`+ * Correct issue in sample id.`
`1`	`3`	`v0.0.5, 2025-09-12`
`2`	`4`	`* Correct issue in case-control.`
`3`	`5`	`v0.0.6, 2024-12-12`