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

gwaslab/viz_plot_mqqplot.py

@@ -174,6 +174,8 @@ def mqqplot(insumstats,
           include_chrXYMT = True,
           ylim=None,
           xpad=None,
+          xpadl=None,
+          xpadr=None,
           chrpad=0.03, 
           drop_chr_start=False,
           title =None,
@@ -213,7 +215,6 @@ def mqqplot(insumstats,
         chr_dict = get_chr_to_number()
     if xtick_chr_dict is None:         
         xtick_chr_dict = get_number_to_chr()
-
     if gtf_chr_dict is None:   
         gtf_chr_dict = get_number_to_chr()
     if rr_chr_dict is None:   
@@ -304,40 +305,42 @@ def mqqplot(insumstats,
                     scatter_args["rasterized"]=True
                     qq_scatter_args["rasterized"]=True
 
-    if verbose: log.write("Start to create MQQ plot with the following basic settings {}:".format(_get_version()))
-    if verbose: log.write(" -Genomic coordinates version: {}...".format(build))
+    log.write("Start to create MQQ plot...{}:".format(_get_version()),verbose=verbose)
+    log.write(" -Genomic coordinates version: {}...".format(build),verbose=verbose)
     if build is None or build=="99":
-        if verbose: log.write("   -WARNING: Genomic coordinates version is unknown...")
-    if verbose: log.write(" -Genome-wide significance level to plot is set to "+str(sig_level_plot)+" ...")
-    if verbose: log.write(" -Raw input contains "+str(len(insumstats))+" variants...")
-    if verbose: log.write(" -MQQ plot layout mode is : "+mode)
+        log.warning("Genomic coordinates version is unknown.")
+    log.write(" -Genome-wide significance level to plot is set to "+str(sig_level_plot)+" ...",verbose=verbose)
+    log.write(" -Raw input contains "+str(len(insumstats))+" variants...",verbose=verbose)
+    log.write(" -MQQ plot layout mode is : "+mode,verbose=verbose)
+    
     if len(anno_set)>0 and ("m" in mode):
-        if verbose: log.write(" -Variants to annotate : "+",".join(anno_set))    
+        log.write(" -Variants to annotate : "+",".join(anno_set),verbose=verbose)    
+    
     if len(highlight)>0 and ("m" in mode):
         if pd.api.types.is_list_like(highlight[0]):
             if highlight_chrpos==False:
-                if len(highlight[0]) == len(highlight_color):
-                    log.write(" -WARNING: number of locus list does not match number of colors !!!")
+                if len(highlight) != len(highlight_color):
+                    log.warning("Number of locus groups in the list does not match number of provided 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))
+                    log.write(" -Set {} loci to highlight ({}) : ".format(i+1, highlight_color[i%len(highlight_color)])+",".join(highlight_set),verbose=verbose)
             else:
-                if verbose: log.write(" -Loci to highlight ({}): {}".format(highlight_color,highlight))
-            if verbose: log.write("  -Highlight_window is set to: ", highlight_windowkb, " kb") 
+                log.write(" -Loci to highlight ({}): {}".format(highlight_color,highlight),verbose=verbose)
+            log.write("  -highlight_windowkb is set to: ", highlight_windowkb, " kb",verbose=verbose) 
         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") 
+            log.write(" -Loci to highlight ({}): ".format(highlight_color)+",".join(highlight),verbose=verbose)    
+            log.write("  -highlight_windowkb is set to: ", highlight_windowkb, " kb",verbose=verbose) 
     
     if len(pinpoint)>0 :
         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 !!!")
+            if len(pinpoint) != len(pinpoint_color):
+                log.warning("Number of variant groups in the list does not match number of provided 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))      
+                  log.write(" -Set {} variants to pinpoint ({}) : ".format(i+1,pinpoint_color[i%len(pinpoint_color)])+",".join(pinpoint_set),verbose=verbose)      
         else:
-            if verbose: log.write(" -Variants to pinpoint ({}) : ".format(pinpoint_color)+",".join(pinpoint))   
+            log.write(" -Variants to pinpoint ({}) : ".format(pinpoint_color)+",".join(pinpoint),verbose=verbose)   
     
     if region is not None:
-        if verbose: log.write(" -Region to plot : chr"+str(region[0])+":"+str(region[1])+"-"+str(region[2])+".")  
+        log.write(" -Region to plot : chr"+str(region[0])+":"+str(region[1])+"-"+str(region[2])+".",verbose=verbose)  
     
     # construct line series for coversion
     if additional_line is None:
@@ -399,7 +402,7 @@ def mqqplot(insumstats,
                                      pinpoint=pinpoint,
                                      density_color=density_color)
     
-    sumstats = insumstats.loc[:,usecols].copy()
+    sumstats = insumstats[usecols].copy()
     
     #################################################################################################
     
@@ -408,7 +411,7 @@ def mqqplot(insumstats,
     if (anno == "GENENAME"):
         anno_sig=True
     elif (anno is not None) and (anno is not True):
-        sumstats["Annotation"]=sumstats.loc[:,anno].astype("string")   
+        sumstats["Annotation"]=sumstats[anno].astype("string")   
       
     ## P value
     ## m, qq, r
@@ -432,15 +435,15 @@ def mqqplot(insumstats,
         region_start = region[1]
         region_end = region[2]
         marker_size=(25,45)
-        if verbose:log.write(" -Extract SNPs in region : chr{}:{}-{}...".format(region_chr, region[1], region[2]))
+        log.write(" -Extract SNPs in region : chr{}:{}-{}...".format(region_chr, region[1], region[2]),verbose=verbose)
         
-        in_region_snp = (sumstats[chrom]==region_chr) &(sumstats[pos]<region_end) &(sumstats[pos]>region_start)
+        in_region_snp = (sumstats[chrom]==region_chr) & (sumstats[pos]<region_end) & (sumstats[pos]>region_start)
         
-        if verbose:log.write(" -Extract SNPs in specified regions: "+str(sum(in_region_snp)))
+        log.write(" -Extract SNPs in specified regions: "+str(sum(in_region_snp)),verbose=verbose)
         sumstats = sumstats.loc[in_region_snp,:]
         
         if len(sumstats)==0:
-            log.write(" -Warning : No valid data! Please check the input.")
+            log.warning("No valid data! Please check the input.")
             return None
     
     ## EAF
@@ -454,11 +457,11 @@ def mqqplot(insumstats,
         sumstats["HUE"] = pd.NA
         sumstats["HUE"] = sumstats["HUE"].astype("Int64")
 
-    if verbose: log.write("Finished loading specified columns from the sumstats.")
+    log.write("Finished loading specified columns from the sumstats.",verbose=verbose)
 
 
 #sanity check############################################################################################################
-    log.write("Start conversion and sanity check:",verbose=verbose)
+    log.write("Start data conversion and sanity check:",verbose=verbose)
     
     if _if_quick_qc == False:
         log.write(" -Sanity check will be skipped.", verbose=verbose)
@@ -527,15 +530,19 @@ def mqqplot(insumstats,
                                                                         lines_to_plot=lines_to_plot,
                                                                         log = log)
     except:
-        log.write(" -Warning : No valid data! Please check the input.")
+        log.warning("No valid data! Please check the input.")
         return None
     
+    log.write("Finished data conversion and sanity check.",verbose=verbose)
+    
     # Manhattan plot ##########################################################################################################
+    log.write("Start to create MQQ plot with "+str(len(sumstats))+" variants...",verbose=verbose)
     ## regional plot ->rsq
         #calculate rsq]
     if vcf_path is not None:
         if tabix is None:
             tabix = which("tabix")
+            log.write(" -tabix will be used: {}".format(tabix),verbose=verbose)
         sumstats = process_vcf(sumstats=sumstats, 
                                vcf_path=vcf_path,
                                region=region, 
@@ -568,8 +575,6 @@ def mqqplot(insumstats,
 
         if vcf_path is not None:
             sumstats["chr_hue"]=sumstats["LD"]
-
-        if verbose:log.write("Start to create MQQ plot with "+str(len(sumstats))+" variants:")
         ## default seetings
         
         palette = sns.color_palette(colors,n_colors=sumstats[chrom].nunique())  
@@ -601,6 +606,7 @@ def mqqplot(insumstats,
         ## if highlight 
         highlight_i = pd.DataFrame()
         if len(highlight) >0:
+            log.write(" -Creating background plot...",verbose=verbose)
             plot = sns.scatterplot(data=sumstats, x='i', y='scaled_P',
                                hue='chr_hue',
                                palette=palette,
@@ -612,8 +618,7 @@ def mqqplot(insumstats,
                                zorder=2,ax=ax1,edgecolor=edgecolor, **scatter_args)   
             if pd.api.types.is_list_like(highlight[0]) and highlight_chrpos==False:
                 for i, highlight_set in enumerate(highlight):
-                    if verbose: log.write(" -Highlighting set {} target loci...".format(i+1))
-                    print(sumstats["HUE"].dtype)
+                    log.write(" -Highlighting set {} target loci...".format(i+1),verbose=verbose)
                     sns.scatterplot(data=sumstats.loc[sumstats["HUE"]==i], x='i', y='scaled_P',
                         hue="HUE",
                         palette={i:highlight_color[i%len(highlight_color)]},
@@ -625,7 +630,7 @@ def mqqplot(insumstats,
                         zorder=3+i,ax=ax1,edgecolor=edgecolor,**scatter_args)  
                 highlight_i = sumstats.loc[~sumstats["HUE"].isna(),"i"].values
             else:
-                if verbose: log.write(" -Highlighting target loci...")
+                log.write(" -Highlighting target loci...",verbose=verbose)
                 sns.scatterplot(data=sumstats.loc[sumstats["HUE"]==0], x='i', y='scaled_P',
                     hue="HUE",
                     palette={0:highlight_color},
@@ -674,6 +679,7 @@ def mqqplot(insumstats,
                 hue = 'chr_hue'
                 hue_norm=None
                 to_plot = sumstats
+                log.write(" -Creating background plot...",verbose=verbose)
                 plot = sns.scatterplot(data=to_plot, x='i', y='scaled_P',
                        hue=hue,
                        palette= palette,
@@ -693,17 +699,17 @@ def mqqplot(insumstats,
                 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))
+                        log.write(" -Pinpointing set {} target vairants...".format(i+1),verbose=verbose)
                         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...")
+                        log.write(" -Target vairants to pinpoint were not found. Skip pinpointing process...",verbose=verbose)
             else:
                 if sum(sumstats[snpid].isin(pinpoint))>0:
                     to_pinpoint = sumstats.loc[sumstats[snpid].isin(pinpoint),:]
-                    if verbose: log.write(" -Pinpointing target vairants...")
+                    log.write(" -Pinpointing target vairants...",verbose=verbose)
                     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...")
+                    log.write(" -Target vairants to pinpoint were not found. Skip pinpointing process...",verbose=verbose)
             
 
         
@@ -767,12 +773,15 @@ def mqqplot(insumstats,
             lead_snp_i= None
             lead_snp_i2=None
         
+        log.write("Finished creating MQQ plot successfully!",verbose=verbose)
+
         # Get top variants for annotation #######################################################
+        log.write("Start to extract variants for annotation...",verbose=verbose)
         if (anno and anno!=True) or (len(anno_set)>0):
             if len(anno_set)>0:
                 to_annotate=sumstats.loc[sumstats[snpid].isin(anno_set),:]
                 if to_annotate.empty is not True:
-                    if verbose: log.write(" -Found "+str(len(to_annotate))+" specified variants to annotate...")
+                    log.write(" -Found "+str(len(to_annotate))+" specified variants to annotate...",verbose=verbose)
             else:
                 to_annotate=getsig(sumstats.loc[sumstats["scaled_P"]> float(-np.log10(sig_level_lead)),:],
                                snpid,
@@ -785,7 +794,7 @@ def mqqplot(insumstats,
                                mlog10p="scaled_P",
                                verbose=False)
                 if (to_annotate.empty is not True) and ("b" not in mode):
-                    if verbose: log.write(" -Found "+str(len(to_annotate))+" significant variants with a sliding window size of "+str(windowsizekb)+" kb...")
+                    log.write(" -Found "+str(len(to_annotate))+" significant variants with a sliding window size of "+str(windowsizekb)+" kb...",verbose=verbose)
         else:
             to_annotate=getsig(sumstats.loc[sumstats["scaled_P"]> float(-np.log10(sig_level_lead)),:],
                                "i",
@@ -798,7 +807,7 @@ def mqqplot(insumstats,
                                mlog10p="scaled_P",
                                sig_level=sig_level_lead)
             if (to_annotate.empty is not True) and ("b" not in mode):
-                if verbose: log.write(" -Found "+str(len(to_annotate))+" significant variants with a sliding window size of "+str(windowsizekb)+" kb...")
+                log.write(" -Found "+str(len(to_annotate))+" significant variants with a sliding window size of "+str(windowsizekb)+" kb...",verbose=verbose)
         if (to_annotate.empty is not True) and anno=="GENENAME":
             to_annotate = annogene(to_annotate,
                                    id=snpid,
@@ -808,16 +817,21 @@ def mqqplot(insumstats,
                                    build=build,
                                    source=anno_source,
                                    verbose=verbose).rename(columns={"GENE":"Annotation"})
+        log.write("Finished extracting variants for annotation...",verbose=verbose)
 
         # Configure X, Y axes #######################################################
+        log.write("Start to process figure arts.",verbose=verbose)
         if region is None:
             # if Manhattan plot 
+ 
             ax1 = _process_xtick(ax1=ax1, 
                                  chrom_df=chrom_df, 
                                  xtick_chr_dict=xtick_chr_dict, 
                                  fontsize = fontsize, 
-                                 font_family=font_family)
-        
+                                 font_family=font_family,
+                                 log=log, 
+                                 verbose=verbose)   
+
         ax1, ax3 = _process_xlabel(region=region, 
                                    xlabel=xlabel, 
                                    ax1=ax1, 
@@ -825,7 +839,9 @@ def mqqplot(insumstats,
                                    mode=mode, 
                                    fontsize=fontsize, 
                                    font_family=font_family,  
-                                   ax3=ax3 )
+                                   ax3=ax3,
+                                   log=log, 
+                                   verbose=verbose)      
         
         ax1, ax4 = _process_ylabel(ylabel=ylabel, 
                                    ax1=ax1,  
@@ -833,8 +849,11 @@ def mqqplot(insumstats,
                                    bwindowsizekb=bwindowsizekb, 
                                    fontsize=fontsize, 
                                    font_family=font_family, 
-                                   ax4=ax4)     
+                                   ax4=ax4,
+                                   log=log, 
+                                   verbose=verbose)      
         
+
         ax1 = _set_yticklabels(cut=cut,
                      cutfactor=cutfactor,
                      cut_log=cut_log,
@@ -849,19 +868,28 @@ def mqqplot(insumstats,
                      font_family=font_family,
                      ytick3=ytick3,
                      ylabels=ylabels,
-                     ylabels_converted=ylabels_converted
-                     )
+                     ylabels_converted=ylabels_converted,
+                     log=log, 
+                     verbose=verbose)  
         
         ax1, ax4 = _process_ytick(ax1=ax1,  
                                    fontsize=fontsize, 
                                    font_family=font_family, 
-                                   ax4=ax4)  
+                                   ax4=ax4, 
+                                   log=log, 
+                                   verbose=verbose)  
         
-        if cbar is not None:
-            # regional plot cbar
-            cbar = _process_cbar(cbar, cbar_fontsize=fontsize, cbar_font_family=font_family, cbar_title=cbar_title)        
+        # regional plot cbar
+        if cbar is not None:    
+            cbar = _process_cbar(cbar, 
+                                 cbar_fontsize=fontsize, 
+                                 cbar_font_family=font_family, 
+                                 cbar_title=cbar_title, 
+                                 log=log, 
+                                 verbose=verbose)         
         
         ax1 = _process_spine(ax1, mode)
+        
         # genomewide significant line
         ax1 = _process_line(ax1, 
                             sig_line, 
@@ -874,7 +902,9 @@ def mqqplot(insumstats,
                             additional_line_color,
                             mode, 
                             bmean, 
-                            bmedian )  
+                            bmedian,
+                            log=log,
+                            verbose=verbose )  
 
         
         if mtitle and anno and len(to_annotate)>0: 
@@ -882,8 +912,10 @@ def mqqplot(insumstats,
             ax1.set_title(mtitle,pad=pad,fontsize=title_fontsize,family=font_family)
         elif mtitle:
             ax1.set_title(mtitle,fontsize=title_fontsize,family=font_family)
-            
+        log.write("Finished processing figure arts.",verbose=verbose)
+
         # Add annotation arrows and texts
+        log.write("Start to annotate variants...",verbose=verbose)
         ax1 = annotate_single(
                                 sumstats=sumstats,
                                 anno=anno,
@@ -917,6 +949,7 @@ def mqqplot(insumstats,
                                 log=log,
                                _invert=_invert
                             )  
+        log.write("Finished annotating variants.",verbose=verbose)
     # Manhatann-like plot Finished #####################################################################
 
     # QQ plot #########################################################################################################
@@ -961,9 +994,9 @@ def mqqplot(insumstats,
 
     # Y axis jagged
     if jagged==True:
-        ax1 = _jagged_y(cut=cut,skip=skip,ax1=ax1,mode=1,mqqratio=mqqratio,jagged_len=jagged_len,jagged_wid=jagged_wid)
+        ax1 = _jagged_y(cut=cut,skip=skip,ax1=ax1,mode=1,mqqratio=mqqratio,jagged_len=jagged_len,jagged_wid=jagged_wid,log=log, verbose=verbose)
         if "qq" in mode:
-            ax2 = _jagged_y(cut=cut,skip=skip,ax1=ax2,mode=2,mqqratio=mqqratio,jagged_len=jagged_len,jagged_wid=jagged_wid)
+            ax2 = _jagged_y(cut=cut,skip=skip,ax1=ax2,mode=2,mqqratio=mqqratio,jagged_len=jagged_len,jagged_wid=jagged_wid,log=log, verbose=verbose)
     
     # XY lim
     if ylim is not None:
@@ -971,8 +1004,7 @@ def mqqplot(insumstats,
         if "qq" in mode:
             ax2.set_ylim(ylim)
     
-    if xpad!=None:
-        ax1.set_xlim([0 - xpad* sumstats["i"].max(),(1+xpad)*sumstats["i"].max()])
+    ax1 = _add_pad_to_x_axis(ax1, xpad, xpadl, xpadr, sumstats)
 
     # Titles 
     if title and anno and len(to_annotate)>0:
@@ -989,7 +1021,7 @@ def mqqplot(insumstats,
     if _get_region_lead==True:
         return fig, log, lead_snp_i, lead_snp_i2
     
-    if verbose: log.write("Finished creating MQQ plot successfully!")
+    log.write("Finished creating plot successfully!",verbose=verbose)
     return fig, log
 
 ##############################################################################################################################################################################
@@ -997,8 +1029,21 @@ def mqqplot(insumstats,
 
 
 
+def _add_pad_to_x_axis(ax1, xpad, xpadl, xpadr, sumstats):
+    
+    xmin, xmax = ax1.get_xlim() 
+    
+    if xpad is not None:
+        pad = xpad* sumstats["i"].max()
+        ax1.set_xlim([xmin - pad, xmin + pad])
+    if xpadl is not None:
+        pad = xpadl* sumstats["i"].max()
+        ax1.set_xlim([xmin - pad,xmax])
+    if xpadr is not None:
+        pad = xpadr* sumstats["i"].max()
+        ax1.set_xlim([xmin, xmax + pad])
 
-
+    return ax1
 
 
 
@@ -1084,22 +1129,22 @@ def _sanity_check(sumstats, mode, chrom, pos, stratified, _if_quick_qc, log, ver
         #sanity check : drop variants with na values in chr and pos df
         sumstats = sumstats.dropna(subset=[chrom,pos])
         after_number=len(sumstats)
-        if verbose:log.write(" -Removed "+ str(pre_number-after_number) +" variants with nan in CHR or POS column ...")
+        log.write(" -Removed "+ str(pre_number-after_number) +" variants with nan in CHR or POS column ...",verbose=verbose)
         out_of_range_chr = sumstats[chrom]<=0
-        if verbose:log.write(" -Removed {} variants with CHR <=0...".format(sum(out_of_range_chr)))
+        log.write(" -Removed {} variants with CHR <=0...".format(sum(out_of_range_chr)),verbose=verbose)
         sumstats = sumstats.loc[~out_of_range_chr,:]
     
     if stratified is True and _if_quick_qc: 
         pre_number=len(sumstats)
         sumstats = sumstats.dropna(subset=["MAF"])
         after_number=len(sumstats)
-        if verbose:log.write(" -Removed "+ str(pre_number-after_number) +" variants with nan in EAF column ...")
+        log.write(" -Removed "+ str(pre_number-after_number) +" variants with nan in EAF column ...",verbose=verbose)
     
     if "b" not in mode and _if_quick_qc:
         pre_number=len(sumstats)
         sumstats = sumstats.dropna(subset=["raw_P"])
         after_number=len(sumstats)
-        if verbose:log.write(" -Removed "+ str(pre_number-after_number) +" variants with nan in P column ...")
+        log.write(" -Removed "+ str(pre_number-after_number) +" variants with nan in P column ...",verbose=verbose)
     return sumstats
 
 def _process_p_value(sumstats, mode,p, mlog10p, scaled, log, verbose ):
@@ -1108,7 +1153,7 @@ def _process_p_value(sumstats, mode,p, mlog10p, scaled, log, verbose ):
         sumstats["scaled_P"] = sumstats["DENSITY"].copy()
         sumstats["raw_P"] = -np.log10(sumstats["DENSITY"].copy()+2)
     elif scaled is True:
-        if verbose:log.write(" -P values are already converted to -log10(P)!")
+        log.write(" -P values are already converted to -log10(P)!",verbose=verbose)
         sumstats["scaled_P"] = sumstats["raw_P"].copy()
         sumstats["raw_P"] = np.power(10,-sumstats["scaled_P"].astype("float64"))
     else:
@@ -1156,7 +1201,7 @@ def _process_highlight(sumstats, highlight, highlight_chrpos, highlight_windowkb
                         sumstats.loc[right_chr&up_pos&low_pos,"HUE"]=0                        
         else:
             # highlight for one set
-            # to_highlight = sumstats.loc[sumstats[snpid].isin(highlight),:]
+            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])
@@ -1169,7 +1214,7 @@ def _process_highlight(sumstats, highlight, highlight_chrpos, highlight_windowkb
 
 def _process_density(sumstats, mode, bwindowsizekb, chrom, pos, verbose, log):
     if "b" in mode and "DENSITY" not in sumstats.columns:
-        if verbose:log.write(" -Calculating DENSITY with windowsize of ",bwindowsizekb ," kb")
+        log.write(" -Calculating DENSITY with windowsize of ",bwindowsizekb ," kb",verbose=verbose)
         large_number = _get_largenumber(sumstats[pos].max(),log=log)
 
         stack=[]
@@ -1190,11 +1235,12 @@ def _process_density(sumstats, mode, bwindowsizekb, chrom, pos, verbose, log):
     elif "b" in mode and "DENSITY" in sumstats.columns:
         bmean=sumstats["DENSITY"].mean()
         bmedian=sumstats["DENSITY"].median()
-        if verbose:log.write(" -DENSITY column exists. Skipping calculation...") 
+        log.write(" -DENSITY column exists. Skipping calculation...",verbose=verbose) 
     return   sumstats, bmean, bmedian
 
-def _process_line(ax1, sig_line, suggestive_sig_line, additional_line, lines_to_plot , sc_linewidth, sig_line_color, suggestive_sig_line_color, additional_line_color, mode, bmean, bmedian ):
+def _process_line(ax1, sig_line, suggestive_sig_line, additional_line, lines_to_plot , sc_linewidth, sig_line_color, suggestive_sig_line_color, additional_line_color, mode, bmean, bmedian , log=Log(),verbose=True):
     # genomewide significant line
+    log.write(" -Processing lines...",verbose=verbose)
     if sig_line is True:
         sigline = ax1.axhline(y=lines_to_plot[0], 
                                 linewidth = sc_linewidth,
@@ -1220,8 +1266,9 @@ def _process_line(ax1, sig_line, suggestive_sig_line, additional_line, lines_to_
         medianline = ax1.axhline(y=bmedian, linewidth = sc_linewidth,linestyle="--",color=sig_line_color,zorder=1000)
     return ax1
 
-def _process_cbar(cbar, cbar_fontsize, cbar_font_family, cbar_title):
-    if str(type(cbar))=="list":
+def _process_cbar(cbar, cbar_fontsize, cbar_font_family, cbar_title, log=Log(),verbose=True):
+    log.write(" -Processing color bar...",verbose=verbose)
+    if type(cbar) == list:
         for cbar_single in cbar:
             cbar_yticklabels = cbar_single.ax.get_yticklabels()
             cbar_single.ax.set_yticklabels(cbar_yticklabels, fontsize=cbar_fontsize, family=cbar_font_family )
@@ -1232,12 +1279,14 @@ def _process_cbar(cbar, cbar_fontsize, cbar_font_family, cbar_title):
         cbar.ax.set_title(cbar_title, fontsize=cbar_fontsize, family=cbar_font_family, loc="center",y=-0.2 )
     return cbar
 
-def _process_xtick(ax1, chrom_df, xtick_chr_dict, fontsize, font_family):
+def _process_xtick(ax1, chrom_df, xtick_chr_dict, fontsize, font_family, log=Log(),verbose=True):
+    log.write(" -Processing X ticks...",verbose=verbose)
     ax1.set_xticks(chrom_df.astype("float64"))
     ax1.set_xticklabels(chrom_df.index.astype("Int64").map(xtick_chr_dict),fontsize=fontsize,family=font_family)    
     return ax1
 
-def _process_ytick(ax1, fontsize, font_family, ax4):
+def _process_ytick(ax1, fontsize, font_family, ax4, log=Log(),verbose=True):
+    log.write(" -Processing Y labels...",verbose=verbose)
     ax1_yticklabels = ax1.get_yticklabels()
     #ax1.set_yticklabels(ax1_yticklabels,fontsize=fontsize,family=font_family) 
     ax1_yticks = ax1.get_yticks()
@@ -1248,7 +1297,8 @@ def _process_ytick(ax1, fontsize, font_family, ax4):
         ax4.set_yticks(ax4_yticks,ax4_yticklabels, fontsize=fontsize,family=font_family) 
     return ax1, ax4
 
-def _process_xlabel(region, xlabel, ax1, gtf_path, mode, fontsize, font_family,  ax3=None ):
+def _process_xlabel(region, xlabel, ax1, gtf_path, mode, fontsize, font_family,  ax3=None , log=Log(),verbose=True):
+    log.write(" -Processing X labels...",verbose=verbose)
     if region is not None:
         if xlabel is None:
             xlabel = "Chromosome "+str(region[0])+" (MB)"
@@ -1262,7 +1312,8 @@ def _process_xlabel(region, xlabel, ax1, gtf_path, mode, fontsize, font_family,
         ax1.set_xlabel(xlabel,fontsize=fontsize,family=font_family)
     return ax1, ax3
 
-def _process_ylabel(ylabel, ax1,  mode, bwindowsizekb, fontsize, font_family, ax4=None):
+def _process_ylabel(ylabel, ax1,  mode, bwindowsizekb, fontsize, font_family, ax4=None, log=Log(),verbose=True):
+    log.write(" -Processing Y labels...",verbose=verbose)
     if "b" in mode:
         if ylabel is None:
             ylabel ="Density of GWAS \n SNPs within "+str(bwindowsizekb)+" kb"
@@ -1336,4 +1387,4 @@ def _process_layout(mode, figax, fig_args, mqqratio, region_hspace):
         raise ValueError("Please select one from the 5 modes: mqq/qqm/m/qq/r/b")
     ax4=None
     cbar=None
-    return fig, ax1, ax2, ax3, ax4, cbar
+    return fig, ax1, ax2, ax3, ax4, cbar

gwaslab/viz_plot_qqplot.py

@@ -45,7 +45,7 @@ def _plot_qq(
 
     # QQ plot #########################################################################################################
     # ax2 qqplot
-    if verbose:log.write("Start to create QQ plot with "+str(len(sumstats))+" variants:")
+    log.write("Start to create QQ plot with "+str(len(sumstats))+" variants:",verbose=verbose )
     
     # plotting qq plots using processed data after cut and skip
     
@@ -59,6 +59,7 @@ def _plot_qq(
     upper_bound_p = np.power(10.0, -expected_min_mlog10p)
 
     if stratified is False:
+        log.write(" -Plotting all variants...",verbose=verbose)
         # sort x,y for qq plot
         # high to low
         observed = p_toplot.sort_values(ascending=False)
@@ -68,13 +69,13 @@ def _plot_qq(
     
         expected_all = -np.log10(np.linspace(minit,upper_bound_p,len(p_toplot_raw)))[:len(observed)]
 
-        if verbose:log.write("Expected range of P: (0,{})".format(upper_bound_p))
+        log.write(" -Expected range of P: (0,{})".format(upper_bound_p),verbose=verbose)
         #p_toplot = sumstats["scaled_P"]
         ax2.scatter(expected_all,observed,s=marker_size[1],color=colors[0],**qq_scatter_args)
 
     else:
         # stratified qq plot
-        
+        log.write(" -Plotting variants stratified by MAF...",verbose=verbose)
         observed = p_toplot.sort_values(ascending=False)
         expected_all = -np.log10(np.linspace(minit,upper_bound_p,len(p_toplot_raw)))[:len(observed)]
 
@@ -115,15 +116,15 @@ def _plot_qq(
 
         if expected_min_mlog10p!=0:
             level = 1 -  np.power(10.0,-np.nanmedian(expected_all))
-            if verbose: log.write(" -Level for calculating lambda GC : {}".format(1 - level))
+            log.write(" -Level for calculating lambda GC : {}".format(1 - level),verbose=verbose)
 
-        if verbose and not include_chrXYMT : log.write(" -Excluding chrX,Y, MT from calculation of lambda GC.")
+        if not include_chrXYMT : log.write(" -Excluding chrX,Y, MT from calculation of lambda GC.",verbose=verbose)
         lambdagc = lambdaGC(p_toplot_raw, 
                             mode="MLOG10P", 
                             level=level, 
                             include_chrXYMT=include_chrXYMT,
                             log=log,
-                            verbose=True)
+                            verbose=verbose)
         
         # annotate lambda gc to qq plot
         ax2.text(0.10, 1.03,"$\\lambda_{GC}$ = "+"{:.4f}".format(lambdagc),
@@ -147,7 +148,9 @@ def _plot_qq(
                         font_family=font_family,
                         ylabels=ylabels,
                         ytick3=ytick3,
-                        ylabels_converted=ylabels_converted
+                        ylabels_converted=ylabels_converted,
+                        log=log,
+                        verbose=verbose
                         )
 
     #if cut == 0: 
@@ -181,7 +184,7 @@ def _plot_qq(
     if qtitle:
         ax2.set_title(qtitle,fontsize=title_fontsize,pad=10,family=font_family)
 
-    if verbose: log.write("Finished creating QQ plot successfully!")
+    log.write("Finished creating QQ plot successfully!",verbose=verbose)
     
     # Creating QQ plot Finished #############################################################################################
     return ax2