gwaslab 3.4.23__tar.gz → 3.4.25__tar.gz

{gwaslab-3.4.23/src/gwaslab.egg-info → gwaslab-3.4.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gwaslab
-Version: 3.4.23
+Version: 3.4.25
 Summary: A collection of handy tools for GWAS SumStats
 Author-email: Yunye <yunye@gwaslab.com>
 Project-URL: Homepage, https://cloufield.github.io/gwaslab/
@@ -8,7 +8,7 @@ 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: >=3.8
+Requires-Python: <=3.9,>=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
@@ -32,7 +32,7 @@ Note: GWASLab is being updated very frequently for now. I will release the first
 ## Install
 
 ```
-pip install gwaslab==3.4.22
+pip install gwaslab==3.4.24
 ```
 
 

{gwaslab-3.4.23 → gwaslab-3.4.25}/README.md

@@ -18,7 +18,7 @@ Note: GWASLab is being updated very frequently for now. I will release the first
 ## Install
 
 ```
-pip install gwaslab==3.4.22
+pip install gwaslab==3.4.24
 ```
 
 

{gwaslab-3.4.23 → gwaslab-3.4.25}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gwaslab"
-version = "3.4.23"
+version = "3.4.25"
 authors = [
   { name="Yunye", email="yunye@gwaslab.com" },
 ]
@@ -18,7 +18,7 @@ readme = "README.md"
 dependencies = [
     "pandas>=1.3,<1.5",
     "numpy>=1.21.2",
-    "matplotlib>=3.5",
+    "matplotlib>=3.5,<=3.7.1",
     "seaborn>=0.11.1",
     "scipy>=1.6.2",
     "pySAM>=0.18.1,<0.20",
@@ -31,7 +31,7 @@ dependencies = [
     "gtfparse==1.3.0"
 ]
 
-requires-python = ">=3.8"
+requires-python = ">=3.8,<=3.9"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/Sumstats.py

@@ -605,6 +605,7 @@ class Sumstats():
               build="19", 
               n=None,
               verbose=True,
+              no_status=False,
               output_log=True,
               to_csvargs=None,
               float_formats=None,
@@ -713,6 +714,7 @@ class Sumstats():
                   suffix=suffix,
                   build=build,
                   verbose=True,
+                  no_status=no_status,
                   log=onetime_log,
                   to_csvargs=to_csvargs,
                   chr_prefix=chr_prefix,

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/compare_effect.py

@@ -728,6 +728,8 @@ def compare_effect(path1,
         if verbose:log.write(" -Beta_se = ", reg[4])
         #if verbose:log.write(" -H0 beta = ", null_beta, ", recalculated p = ", "{:.2e}".format(p))
         if verbose:log.write(" -H0 beta =  0",", default p = ", "{:.2e}".format(reg[3]))
+        if verbose:log.write(" -Peason correlation coefficient =  ", "{:.2f}".format(reg[2]))
+        if verbose:log.write(" -r2 =  ", "{:.2f}".format(reg[2]**2))
         if r_se==True:
             if verbose:log.write(" -R se (jackknife) = {:.2e}".format(r_se_jackknife))
 

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/data/reference.json

@@ -10,6 +10,30 @@
     "1kg_eur_hg38":"https://www.dropbox.com/s/z0mkehg17lryapv/EUR.ALL.split_norm_af.1kg_30x.hg38.vcf.gz?dl=1",
     "1kg_eur_hg38_md5":"228d3285fa99132cc6321e2925e0768d",
     "1kg_eur_hg38_tbi":"https://www.dropbox.com/s/ze8g58x75x9qbf0/EUR.ALL.split_norm_af.1kg_30x.hg38.vcf.gz.tbi?dl=1",
+    "1kg_sas_hg19":"https://www.dropbox.com/scl/fi/fubqvuj3p4ii4y35zknv8/SAS.ALL.split_norm_af.1kgp3v5.hg19.vcf.gz?rlkey=5z50f66iltjchcaszznq5bczt&dl=1",
+    "1kg_sas_hg19_md5":"e2d3f9e2e6580d05e877e9effd435c4e",
+    "1kg_sas_hg19_tbi":"https://www.dropbox.com/scl/fi/icnmrnzee7ofdpx5l96tg/SAS.ALL.split_norm_af.1kgp3v5.hg19.vcf.gz.tbi?rlkey=st8t88snby26q37rqi6zh5zck&dl=1",
+    "1kg_amr_hg19":"https://www.dropbox.com/scl/fi/bxa4zfngsxsc38rhtiv8c/AMR.ALL.split_norm_af.1kgp3v5.hg19.vcf.gz?rlkey=ibcn8hb1n8n36j3u0jfzci267&dl=1",
+    "1kg_amr_hg19_md5":"68d3cdf01cbabdae6e74a07795fa881c",
+    "1kg_amr_hg19_tbi":"https://www.dropbox.com/scl/fi/1zk16x7h4r89jurzwu05u/AMR.ALL.split_norm_af.1kgp3v5.hg19.vcf.gz.tbi?rlkey=b4cere4w38zvzyfitfge3r8n0&dl=1",
+    "1kg_sas_hg38":"https://www.dropbox.com/scl/fi/jr3l5zz42py3kny2bccmj/SAS.ALL.split_norm_af.1kg_30x.hg38.vcf.gz?rlkey=x0t6tsy71jxzf021wfqdn8k5q&dl=1",
+    "1kg_sas_hg38_md5":"e5d79bea1958aa50c23f618d342ccc83",
+    "1kg_sas_hg38_tbi":"https://www.dropbox.com/scl/fi/02oia4ur5r7w9qgiuf6i9/SAS.ALL.split_norm_af.1kg_30x.hg38.vcf.gz.tbi?rlkey=00p9rxe0xzfs6hr1rg4d8oadm&dl=1",
+    "1kg_amr_hg38":"https://www.dropbox.com/scl/fi/4t4tyuhzp78uyb6tgkroq/AMR.ALL.split_norm_af.1kg_30x.hg38.vcf.gz?rlkey=p96gbs1tcdia31jnjv1b82kuz&dl=1",
+    "1kg_amr_hg38_md5":"229fbd610001cf6f137b7f738352a44a",
+    "1kg_amr_hg38_tbi":"https://www.dropbox.com/scl/fi/x0dby543tr9xpaqj2i0ba/AMR.ALL.split_norm_af.1kg_30x.hg38.vcf.gz.tbi?rlkey=uj8o7j0cy0spipe174jn54sqs&dl=1",
+    "1kg_afr_hg19":"https://www.dropbox.com/scl/fi/tq4w9lyt5z47ym7grtrxg/AFR.ALL.split_norm_af.1kgp3v5.hg19.vcf.gz?rlkey=k3bimeu3yr5loq8hohba5mr6k&dl=1",
+    "1kg_afr_hg19_md5":"f7b4425f39e8292dce6f13711e7f6c50",
+    "1kg_afr_hg19_tbi":"https://www.dropbox.com/scl/fi/0giiptu0btwj1kfm6jdzr/AFR.ALL.split_norm_af.1kgp3v5.hg19.vcf.gz.tbi?rlkey=ucb5weprsc5prcg8hvtgmruxx&dl=1",
+    "1kg_pan_hg19":"https://www.dropbox.com/scl/fi/6b4j9z9knmllfnbx86aw6/PAN.ALL.split_norm_af.1kgp3v5.hg19.vcf.gz?rlkey=eento8vg06zyrkvooc9wd4cvu&dl=1",
+    "1kg_pan_hg19_md5":"fed846482204487b60d33b21ddb18106",
+    "1kg_pan_hg19_tbi":"https://www.dropbox.com/scl/fi/stco946scio5tvto0ln4j/PAN.ALL.split_norm_af.1kgp3v5.hg19.vcf.gz.tbi?rlkey=hfh53beb627lmqwv3d8mzqy0c&dl=1",
+    "1kg_afr_hg38":"https://www.dropbox.com/scl/fi/239xmm7qijtnsks97chc9/AFR.ALL.split_norm_af.1kg_30x.hg38.vcf.gz?rlkey=47en5fk1icbekpg7we3uot9g8&dl=1",
+    "1kg_afr_hg38_md5":"3bb7923be0809a324d7b7633b8d58a3b",
+    "1kg_afr_hg38_tbi":"https://www.dropbox.com/scl/fi/3y3pg4yqwo2jaaamx1c8f/AFR.ALL.split_norm_af.1kg_30x.hg38.vcf.gz.tbi?rlkey=say0ihfwa51z3otgn4bjtze8p&dl=1",
+    "1kg_pan_hg38":"https://www.dropbox.com/scl/fi/nf01487smtmeq243ihfwm/PAN.ALL.split_norm_af.1kg_30x.hg38.vcf.gz?rlkey=3pefbkzxwcnejx4inynifpft7&dl=1",
+    "1kg_pan_hg38_md5":"23bb86d748c4a66e85e087f647e8b60e",
+    "1kg_pan_hg38_tbi":"https://www.dropbox.com/scl/fi/hu7cttr4cenw5yjsm2775/PAN.ALL.split_norm_af.1kg_30x.hg38.vcf.gz.tbi?rlkey=568u7bkvkybm4wt2q9284o198&dl=1",
     "dbsnp_v151_hg19": "https://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh37p13/VCF/00-All.vcf.gz",
     "dbsnp_v151_hg19_tbi": "https://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh37p13/VCF/00-All.vcf.gz.tbi",
     "dbsnp_v151_hg38": "https://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/VCF/00-All.vcf.gz",
@@ -33,3 +57,5 @@
     "testlink":"https://www.dropbox.com/s/8u7capwge0ihshu/EAS.chr22.split_norm_af.1kgp3v5.vcf.gz?dl=1",
     "testlink_tbi":"https://www.dropbox.com/s/hdneg53t6u1j6ib/EAS.chr22.split_norm_af.1kgp3v5.vcf.gz.tbi?dl=1"
 }
+
+

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/download.py

@@ -7,6 +7,7 @@ import shutil
 import hashlib
 from gwaslab.Log import Log
 from gwaslab.config import options
+import re
 
 #### config ##############################################################################################
 # config.json
@@ -184,6 +185,7 @@ def get_path(name,log=Log(),verbose=True):
 def download_ref(name,
                 directory=None,
                 local_filename=None,
+                overwrite=False,
                 log=Log()):
     '''
     Download the reference file for a given keyword. Url are retrieved from the reference.json file.
@@ -213,6 +215,9 @@ def download_ref(name,
         # if existing in default path
         if search_local(local_path) == True:
             log.write(" -File {} exists.".format(local_path))
+            if overwrite == True:
+                log.write(" -Overwriting the existing file.")
+                download_file(url,local_path)
         else:
             download_file(url,local_path)
 
@@ -233,6 +238,9 @@ def download_ref(name,
                 try:
                     if search_local(local_path+".tbi") == True:
                         log.write(" -File {} exists.".format(local_path+".tbi"))
+                        if overwrite == True:
+                            log.write(" -Overwriting the existing file.")
+                            download_file(tbi_url,local_path+".tbi")
                     else:
                         download_file(tbi_url,local_path+".tbi")
                     #download_file(tbi_url, local_path+".tbi")
@@ -327,12 +335,14 @@ def url_to_local_file_name(local_filename, url, from_dropbox):
         # if local name not provided, grab it from url
         local_filename = url.split('/')[-1]
         
-    if local_filename.endswith("?dl=1"):
+    if local_filename.endswith("dl=1"):
         # if file are downloaded form dropbox
         # set from_dropbox indicator to 1
         from_dropbox=1
         # remove "?dl=1" suffix
-        local_filename = local_filename[:-5]
+        #local_filename = local_filename[:-5]
+        local_filename = re.match(r'([^\?]+)(\?rlkey=[\w]+)?[&\?]dl=1$', local_filename)
+        local_filename = local_filename.group(1)
     return local_filename, from_dropbox
 
 ##########################################################################################################

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/fixdata.py

@@ -722,7 +722,7 @@ def sanitycheckstats(sumstats,
                      z=(-37.5,37.5),
                      f=(0,float("Inf")),
                      p=(5e-300,1.000001),
-                     mlog10p=(0,float("Inf")),
+                     mlog10p=(0,9999),
                      beta=(-10,10),
                      se=(0,float("Inf")),
                      OR=(0,10),

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/mqqplot.py

@@ -229,7 +229,7 @@ def mqqplot(insumstats,
     if highlight_anno_args is None:
         highlight_anno_args = {}
     if pinpoint is None:
-        pinpoint = list()
+        pinpoint = list()  
     if build is None:
         build = "19"
     if scatter_kwargs is None:
@@ -255,10 +255,25 @@ def mqqplot(insumstats,
     if len(anno_set)>0 and ("m" in mode):
         if verbose: log.write(" -Variants to annotate : "+",".join(anno_set))    
     if len(highlight)>0 and ("m" in mode):
-        if verbose: log.write(" -Loci to highlight : "+",".join(highlight))    
-        if verbose: log.write("  -Highlight_window is set to: ", highlight_windowkb, " kb")  
+        if pd.api.types.is_list_like(highlight[0]):
+            if len(highlight[0]) == len(highlight_color):
+                log.write(" -WARNING: number of locus list does not match number of colors !!!")
+            for i, highlight_set in enumerate(highlight):
+                  if verbose: log.write(" -Set {} loci to highlight ({}) : ".format(i+1, highlight_color[i%len(highlight_color)])+",".join(highlight_set))   
+            if verbose: log.write("  -Highlight_window is set to: ", highlight_windowkb, " kb") 
+        else:
+            if verbose: log.write(" -Loci to highlight ({}): ".format(highlight_color)+",".join(highlight))    
+            if verbose: log.write("  -Highlight_window is set to: ", highlight_windowkb, " kb") 
+    
     if len(pinpoint)>0 :
-        if verbose: log.write(" -Variants to pinpoint : "+",".join(pinpoint))  
+        if pd.api.types.is_list_like(pinpoint[0]):
+            if len(pinpoint[0]) == len(pinpoint_color):
+                log.write(" -WARNING: number of variant list does not match number of colors !!!")
+            for i, pinpoint_set in enumerate(pinpoint):
+                  if verbose: log.write(" -Set {} variants to pinpoint ({}) : ".format(i+1,pinpoint_color[i%len(pinpoint_color)])+",".join(pinpoint_set))      
+        else:
+            if verbose: log.write(" -Variants to pinpoint ({}) : ".format(pinpoint_color)+",".join(pinpoint))   
+    
     if region is not None:
         if verbose: log.write(" -Region to plot : chr"+str(region[0])+":"+str(region[1])+"-"+str(region[2])+".")  
     
@@ -425,8 +440,9 @@ def mqqplot(insumstats,
         eaf_raw = sumstats["MAF"].copy()
         
     if len(highlight)>0 and ("m" in mode):
-        sumstats["HUE"] = sumstats[chrom].astype("string")
-    
+        sumstats["HUE"] = pd.NA
+        sumstats["HUE"] = sumstats["HUE"].astype("Int64")
+
     if verbose: log.write("Finished loading specified columns from the sumstats.")
 
 
@@ -451,15 +467,27 @@ def mqqplot(insumstats,
             
         ## Highlight
     if len(highlight)>0 and ("m" in mode or "r" in mode):
-        to_highlight = sumstats.loc[sumstats[snpid].isin(highlight),:]
-        #assign colors: 0 is hightlight color
-        for i,row in to_highlight.iterrows():
-            target_chr = int(row[chrom])
-            target_pos = int(row[pos])
-            right_chr=sumstats[chrom]==target_chr
-            up_pos=sumstats[pos]>target_pos-highlight_windowkb*1000
-            low_pos=sumstats[pos]<target_pos+highlight_windowkb*1000
-            sumstats.loc[right_chr&up_pos&low_pos,"HUE"]="0"
+        if pd.api.types.is_list_like(highlight[0]):
+            for i, highlight_set in enumerate(highlight):
+                to_highlight = sumstats.loc[sumstats[snpid].isin(highlight_set),:]
+                #assign colors: 0 is hightlight color
+                for index,row in to_highlight.iterrows():
+                    target_chr = int(row[chrom])
+                    target_pos = int(row[pos])
+                    right_chr=sumstats[chrom]==target_chr
+                    up_pos=sumstats[pos]>target_pos-highlight_windowkb*1000
+                    low_pos=sumstats[pos]<target_pos+highlight_windowkb*1000
+                    sumstats.loc[right_chr&up_pos&low_pos,"HUE"]=i
+        else:
+            to_highlight = sumstats.loc[sumstats[snpid].isin(highlight),:]
+            #assign colors: 0 is hightlight color
+            for index,row in to_highlight.iterrows():
+                target_chr = int(row[chrom])
+                target_pos = int(row[pos])
+                right_chr=sumstats[chrom]==target_chr
+                up_pos=sumstats[pos]>target_pos-highlight_windowkb*1000
+                low_pos=sumstats[pos]<target_pos+highlight_windowkb*1000
+                sumstats.loc[right_chr&up_pos&low_pos,"HUE"]=0
 
 # Density #####################################################################################################              
     if "b" in mode and "DENSITY" not in sumstats.columns:
@@ -612,18 +640,33 @@ def mqqplot(insumstats,
                                sizes=marker_size,
                                linewidth=linewidth,
                                zorder=2,ax=ax1,edgecolor=edgecolor, **scatter_kwargs)   
-            
-            if verbose: log.write(" -Highlighting target loci...")
-            sns.scatterplot(data=sumstats.loc[sumstats["HUE"]=="0"], x='i', y='scaled_P',
-                   hue="HUE",
-                   palette={"0":highlight_color},
-                   legend=legend,
-                   style=style,
-                   size="s",
-                   sizes=(marker_size[0]+1,marker_size[1]+1),
-                   linewidth=linewidth,
-                   zorder=3,ax=ax1,edgecolor=edgecolor,**scatter_kwargs)  
-            highlight_i = sumstats.loc[sumstats[snpid].isin(highlight),"i"].values
+            if pd.api.types.is_list_like(highlight[0]):
+                for i, highlight_set in enumerate(highlight):
+                    if verbose: log.write(" -Highlighting set {} target loci...".format(i+1))
+                    print(sumstats["HUE"].dtype)
+                    sns.scatterplot(data=sumstats.loc[sumstats["HUE"]==i], x='i', y='scaled_P',
+                        hue="HUE",
+                        palette={i:highlight_color[i%len(highlight_color)]},
+                        legend=legend,
+                        style=style,
+                        size="s",
+                        sizes=(marker_size[0]+1,marker_size[1]+1),
+                        linewidth=linewidth,
+                        zorder=3+i,ax=ax1,edgecolor=edgecolor,**scatter_kwargs)  
+                highlight_i = sumstats.loc[~sumstats["HUE"].isna(),"i"].values
+            else:
+                if verbose: log.write(" -Highlighting target loci...")
+                sns.scatterplot(data=sumstats.loc[sumstats["HUE"]==0], x='i', y='scaled_P',
+                    hue="HUE",
+                    palette={0:highlight_color},
+                    legend=legend,
+                    style=style,
+                    size="s",
+                    sizes=(marker_size[0]+1,marker_size[1]+1),
+                    linewidth=linewidth,
+                    zorder=3,ax=ax1,edgecolor=edgecolor,**scatter_kwargs)  
+                # for annotate
+                highlight_i = sumstats.loc[sumstats[snpid].isin(highlight),"i"].values
         
         ## if not highlight    
         else:
@@ -673,12 +716,23 @@ def mqqplot(insumstats,
         
         ## if pinpoint variants
         if (len(pinpoint)>0):
-            if sum(sumstats[snpid].isin(pinpoint))>0:
-                to_pinpoint = sumstats.loc[sumstats[snpid].isin(pinpoint),:]
-                if verbose: log.write(" -Pinpointing target vairants...")
-                ax1.scatter(to_pinpoint["i"],to_pinpoint["scaled_P"],color=pinpoint_color,zorder=3,s=marker_size[1]+1)
+            if pd.api.types.is_list_like(pinpoint[0]):
+                for i, pinpoint_set in enumerate(pinpoint):
+                    if sum(sumstats[snpid].isin(pinpoint_set))>0:
+                        to_pinpoint = sumstats.loc[sumstats[snpid].isin(pinpoint_set),:]
+                        if verbose: log.write(" -Pinpointing set {} target vairants...".format(i+1))
+                        ax1.scatter(to_pinpoint["i"],to_pinpoint["scaled_P"],color=pinpoint_color[i%len(pinpoint_color)],zorder=100,s=marker_size[1]+1)
+                    else:
+                        if verbose: log.write(" -Target vairants to pinpoint were not found. Skip pinpointing process...")
             else:
-                if verbose: log.write(" -Target vairants to pinpoint were not found. Skip pinpointing process...")
+                if sum(sumstats[snpid].isin(pinpoint))>0:
+                    to_pinpoint = sumstats.loc[sumstats[snpid].isin(pinpoint),:]
+                    if verbose: log.write(" -Pinpointing target vairants...")
+                    ax1.scatter(to_pinpoint["i"],to_pinpoint["scaled_P"],color=pinpoint_color,zorder=100,s=marker_size[1]+1)
+                else:
+                    if verbose: log.write(" -Target vairants to pinpoint were not found. Skip pinpointing process...")
+            
+
         
         #ax1.set_xticks(chrom_df.astype("float64"))
         #ax1.set_xticklabels(chrom_df.index.astype("Int64").map(xtick_chr_dict),fontsize=fontsize,family=font_family)

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/read_ldsc.py

@@ -105,52 +105,56 @@ def read_popcorn(filelist=[]):
 #h2 mode
 #####################################################################    
     summary = pd.DataFrame(columns = ["Filename", 'sfile1', 'sfile2', 'mode', 'pg', 'pg_se','pg_z','pg_p', 'h1^2', 'h1^2_se','h1^2_z','h1^2_p', 'h2^2', 'h2^2_se','h2^2_z','h2^2_p'])
-    
+
     for index, ldscfile in enumerate(filelist):
         print("Loading file "+str(index+1)+" :" + ldscfile +" ...")
-        
+
         row={}
-        
-        with open(ldscfile,"r") as file:
-            row["Filename"]=ldscfile.split("/")[-1]
-            line=""
-            while not re.compile('^Invoking command').match(line):
-                line = file.readline()
-                if not line: break
-                    
-            
-                    ## first line h2 se
-            objects = re.compile('--sfile1 ([^\s]+) --sfile2 ([^\s]+)[ /n]').findall(line)
-            row["sfile1"]=objects[0][0]
-            row["sfile2"]=objects[0][1]
-            
-            while not re.compile('^Jackknife iter:').match(line):
-                line = file.readline()
-                if not line: break
-            ##next line lambda gc
-            line = file.readline()
-            
-            #objects = re.compile('[a-zA-Z\s\d]+:|[-0-9.]+[e]?[-0-9.]+|NA').findall(file.readline())
-            objects = file.readline().split()
-            row["h1^2"] = objects[1]
-            row["h1^2_se"] = objects[2]
-            row["h1^2_z"] = objects[3]
-            row["h1^2_p"] = objects[4]
-
-            objects = file.readline().split()
-            row["h2^2"] = objects[1]
-            row["h2^2_se"] = objects[2]
-            row["h2^2_z"] = objects[3]
-            row["h2^2_p"] = objects[4]
-
-            objects = file.readline().split()
-            row["mode"] = objects[0]
-            row["pg"] = objects[1]
-            row["pg_se"] = objects[2]
-            row["pg_z"] = objects[3]
-            row["pg_p"] = objects[4]
+        try:
+            with open(ldscfile,"r") as file:
+                row["Filename"]=ldscfile.split("/")[-1]
+                line=""
+                while not re.compile('^Invoking command').match(line):
+                    line = file.readline()
+                    if not line: break
+
+
+                        ## first line h2 se
+                objects = re.compile('--sfile1 ([^\s]+) --sfile2 ([^\s]+)[ /n]').findall(line)
+                row["sfile1"]=objects[0][0]
+                row["sfile2"]=objects[0][1]
+
+                #while not re.compile(r'^Jackknife iter:').match(line):
+                #    line = file.readline()
+                #    print(line)
+                #    if not line: break
+                while not re.compile(r'P \(Z\)').findall(line.strip()):
+                    line = file.readline()
+                    if not line: break
+
+                #objects = re.compile('[a-zA-Z\s\d]+:|[-0-9.]+[e]?[-0-9.]+|NA').findall(file.readline())
+                objects = file.readline().split()
+                row["h1^2"] = objects[1]
+                row["h1^2_se"] = objects[2]
+                row["h1^2_z"] = objects[3]
+                row["h1^2_p"] = objects[4]
+
+                objects = file.readline().split()
+                row["h2^2"] = objects[1]
+                row["h2^2_se"] = objects[2]
+                row["h2^2_z"] = objects[3]
+                row["h2^2_p"] = objects[4]
+
+                objects = file.readline().split()
+                row["mode"] = objects[0]
+                row["pg"] = objects[1]
+                row["pg_se"] = objects[2]
+                row["pg_z"] = objects[3]
+                row["pg_p"] = objects[4]
+        except:
+            continue
 
         #summary = summary.append(row,ignore_index=True)
         row = pd.DataFrame([row], columns = summary.columns)
         summary = pd.concat([summary, row], ignore_index=True)
-    return summary   
+    return summary

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/to_formats.py

@@ -36,6 +36,7 @@ def tofmt(sumstats,
           bgzip=False,
           tabix=False,
           verbose=True,
+          no_status=False,
           log=Log(),
           to_csvargs=None):
     
@@ -50,7 +51,7 @@ def tofmt(sumstats,
     if verbose: log.write(" - Start outputting sumstats in "+fmt+" format...")
     
     if "CHR" in sumstats.columns:
-        if xymt_number is False and sumstats["CHR"].dtype in ["Int64","int"]:
+        if xymt_number is False and pd.api.types.is_integer_dtype(sumstats["CHR"]):
             sumstats["CHR"]= sumstats["CHR"].map(get_number_to_chr(xymt=xymt,prefix=chr_prefix))
         elif chr_prefix is not None:
             sumstats["CHR"]= chr_prefix + sumstats["CHR"].astype("string")
@@ -364,7 +365,11 @@ def tofmt(sumstats,
                 ouput_cols.append(i)  
         # + additional cols
         ouput_cols = ouput_cols + cols
-        
+        try:
+            if no_status == True:
+                ouput_cols.remove("STATUS")
+        except:
+            pass
         sumstats = sumstats.loc[:,ouput_cols]
         sumstats = sumstats.rename(columns=rename_dictionary) 
         

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/trumpetplot.py

@@ -46,13 +46,15 @@ def plottrumpet(mysumstats,
                 yscale_factor=1,
                 cmap="cool",
                 ylim=None,
+                xlim=None,
                 markercolor="#597FBD",
                 fontsize=15,
                 font_family="Arial",
-                size= "BETA",
+                size= "ABS_BETA",
                 sizes=None,
                 save=False,
                 saveargs=None,
+                figargs=None,
                 build="99",
                 anno_set=None,
                 anno_alias=None,
@@ -94,7 +96,8 @@ def plottrumpet(mysumstats,
         else:
             xticks = [0,0.01,0.05,0.1,0.2,0.5]
             xticklabels = xticks            
-
+    if figargs is None:
+        figargs={"figsize":(10,15)}
     #Checking columns#################################################################################################################
     if verbose: log.write("Start to create trumpet plot...")
     
@@ -201,7 +204,7 @@ def plottrumpet(mysumstats,
     output_hex_colors
 
     ##################################################################################################
-    fig, ax = plt.subplots(figsize=(10,10))
+    fig, ax = plt.subplots(**figargs)
     
     ##creating power line############################################################################################
     if mode=="q":
@@ -284,6 +287,9 @@ def plottrumpet(mysumstats,
         rotation=90    
         ax.set_xticks(xticks,xticklabels,fontsize=fontsize,rotation=rotation)
         ax.set_xlim(-0.02,0.52)
+        
+    if xlim is not None:
+        ax.set_xlim(xlim)
     
     if ylim is not None:
         ax.set_ylim(ylim)

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab/version.py

@@ -8,7 +8,7 @@ def _show_version(log=Log()):
 def gwaslab_info():
     # for output header
     dic={
-   "version":"3.4.23",
-   "release_date":"20230817"
+   "version":"3.4.25",
+   "release_date":"20230905"
     }
     return dic   

{gwaslab-3.4.23 → gwaslab-3.4.25/src/gwaslab.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gwaslab
-Version: 3.4.23
+Version: 3.4.25
 Summary: A collection of handy tools for GWAS SumStats
 Author-email: Yunye <yunye@gwaslab.com>
 Project-URL: Homepage, https://cloufield.github.io/gwaslab/
@@ -8,7 +8,7 @@ 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: >=3.8
+Requires-Python: <=3.9,>=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
@@ -32,7 +32,7 @@ Note: GWASLab is being updated very frequently for now. I will release the first
 ## Install
 
 ```
-pip install gwaslab==3.4.22
+pip install gwaslab==3.4.24
 ```
 
 

{gwaslab-3.4.23 → gwaslab-3.4.25}/src/gwaslab.egg-info/requires.txt

@@ -1,6 +1,6 @@
 pandas<1.5,>=1.3
 numpy>=1.21.2
-matplotlib>=3.5
+matplotlib<=3.7.1,>=3.5
 seaborn>=0.11.1
 scipy>=1.6.2
 pySAM<0.20,>=0.18.1