gwaslab 3.5.4__py3-none-any.whl → 3.5.5__py3-none-any.whl

gwaslab/qc_check_datatype.py

@@ -5,7 +5,54 @@ from gwaslab.g_Log import Log
 # pandas.api.types.is_int64_dtype
 # pandas.api.types.is_categorical_dtype
 
+dtype_dict ={
+    "SNPID":["string","object"],
+    "rsID":["string","object"],
+    "CHR":["Int64","int64","int32","Int32","int"],
+    "POS":["int64","Int64"],
+    "EA":["category"],  
+    "NEA":["category"],  
+    "REF":["category"],  
+    "ALT":["category"],  
+    "BETA":["float64"],
+    "BETA_95L":["float64"],
+    "BETA_95U":["float64"],
+    "SE":["float64"],
+    "N":["Int64","int64","int32","Int32","int"],
+    "N_CASE":["Int64","int64","int32","Int32","int"],
+    "N_CONTROL":["Int64","int64","int32","Int32","int"],
+    "OR":["float64"],
+    "OR_95L":["float64"],
+    "OR_95U":["float64"],
+    "HR":["float64"],
+    "HR_95L":["float64"],
+    "HR_95U":["float64"],
+    "P":["float64"],
+    "MLOG10P":["float64"],
+    "Z":["float64"],
+    "F":["float64"],
+    "T":["float64"],
+    "TEST":["string","object","category"],
+    "CHISQ":["float64"],
+    "I2":["float64"],
+    "PHET":["float64"],
+    "SNPR2":["float64"],
+    "EAF":["float64","float","float32"],
+    "NEAF":["float64","float","float32"],
+    "MAF":["float64","float","float32"],
+    "INFO":["float64","float","float32"],
+    "DOF":["Int64","int64","int32","Int32","int"],  
+    "STATUS":["category"],  
+    "DIRECTION":["string","object"],
+    'PIP'               :["float64","float","float32"],
+    'CREDIBLE_SET_INDEX':["Int64","int64","int32","Int32","int"],
+    'N_SNP'             :["Int64","int64","int32","Int32","int"],
+    'LOCUS'             :["string","object","category"],
+    'STUDY'             :["string","object","category"]
+    }
+
 def check_datatype(sumstats, verbose=True, log=Log()):
+    
     try:
         headers = []
         dtypes = []
@@ -39,47 +86,6 @@ def check_datatype(sumstats, verbose=True, log=Log()):
 
 def verify_datatype(header, dtype):
 
-    dtype_dict ={
-    "SNPID":["object","string"],
-    "rsID":["object","string"],
-    "CHR":["int32","Int32","int64","Int64"],
-    "POS":["int64","Int64"],
-    "EA":"category",
-    "NEA":"category",
-    "REF":"category",
-    "ALT":"category",
-    "BETA":"float64",
-    "BETA_95L":"float64",
-    "BETA_95U":"float64",
-    "SE":"float64",
-    "N":["int","Int32","Int64","int32","int64"],
-    "N_CASE":["int","Int32","Int64","int32","int64"],
-    "N_CONTROL":["int","Int32","Int64","int32","int64"],
-    "OR":"float64",
-    "OR_95L":"float64",
-    "OR_95U":"float64",
-    "HR":"float64",
-    "HR_95L":"float64",
-    "HR_95U":"float64",
-    "P":"float64",
-    "MLOG10P":"float64",
-    "Z":"float64",
-    "F":"float64",
-    "T":"float64",
-    "TEST":["object","string","category"],
-    "CHISQ":"float64",
-    "I2":"float64",
-    "PHET":"float64",
-    "SNPR2":"float64",
-    "EAF":["float","float32","float64"],
-    "NEAF":["float","float32","float64"],
-    "MAF":["float","float32","float64"],
-    "INFO":["float32","float64"],  
-    "DOF":["int","Int32","Int64","int32","int64"],   
-    "STATUS":"category",  
-    "DIRECTION":["object","string"], 
-    }
-
     if header in dtype_dict.keys():
         if str(dtype) in dtype_dict[header]:
             return "T"
@@ -88,6 +94,22 @@ def verify_datatype(header, dtype):
     else:
         return "NA"
 
+def quick_convert_datatype(sumstats, log, verbose):
+    for col in sumstats.columns:
+        if col in dtype_dict.keys():
+            if str(sumstats[col].dtypes) not in dtype_dict[col]:
+                datatype=dtype_dict[col][0]
+                log.write(" -Trying to convert datatype for {}: {} -> {}...".format(col, str(sumstats[col].dtypes), datatype), end="" ,verbose=verbose)
+                try:
+                    sumstats[col] = sumstats[col].astype(datatype)
+                    log.write("{}".format(datatype),show_time=False, verbose=verbose)
+                except:
+                    log.write("Failed...",show_time=False,verbose=verbose)
+                    pass
+    return sumstats
+
+
+
 def check_dataframe_shape(sumstats, log, verbose):
     memory_in_mb = sumstats.memory_usage().sum()/1024/1024
     try:
@@ -100,4 +122,5 @@ def check_dataframe_memory_usage(sumstats, log, verbose):
     try:
         log.write(" -Current Dataframe memory usage: {:.2f} MB".format(memory_in_mb), verbose=verbose)
     except:
-        log.warning("Error: cannot get Memory usage...")
+        log.warning("Error: cannot get Memory usage...")
+

gwaslab/util_ex_ldsc.py

@@ -260,6 +260,9 @@ class ARGS():
 def _estimate_h2_by_ldsc(insumstats, log, verbose=True, munge=False, munge_args=None, **kwargs):
     sumstats = insumstats.copy()
     
+    if "N" in sumstats.columns:
+        sumstats["N"] = sumstats["N"].astype("int64")
+
     if munge:
         if munge_args is None:
             munge_args={}
@@ -320,6 +323,8 @@ def _estimate_h2_by_ldsc(insumstats, log, verbose=True, munge=False, munge_args=
 
 def _estimate_partitioned_h2_by_ldsc(insumstats, log, verbose=True, **kwargs):
     sumstats = insumstats.copy()
+    if "N" in sumstats.columns:
+        sumstats["N"] = sumstats["N"].astype("int64")
     ##start function with col checking##########################################################
     _start_line = "run LD score regression"
     _end_line = "running LD score regression"
@@ -366,6 +371,8 @@ def _estimate_partitioned_h2_by_ldsc(insumstats, log, verbose=True, **kwargs):
 
 def _estimate_rg_by_ldsc(insumstats, other_traits ,log, verbose=True, **kwargs):
     sumstats = insumstats.copy()
+    if "N" in sumstats.columns:
+        sumstats["N"] = sumstats["N"].astype("int64")
     ##start function with col checking##########################################################
     _start_line = "run LD score regression for genetic correlation"
     _end_line = "running LD score regression for genetic correlation"
@@ -426,6 +433,8 @@ def _estimate_rg_by_ldsc(insumstats, other_traits ,log, verbose=True, **kwargs):
 
 def _estimate_h2_cts_by_ldsc(insumstats, log, verbose=True, **kwargs):
     sumstats = insumstats.copy()
+    if "N" in sumstats.columns:
+        sumstats["N"] = sumstats["N"].astype("int64")
     ##start function with col checking##########################################################
     _start_line = "run LD score regression"
     _end_line = "running LD score regression"

gwaslab/util_ex_run_2samplemr.py

@@ -21,6 +21,8 @@ def _run_two_sample_mr(sumstatspair_object,
                        n1=None,
                        n2=None,
                        binary1=False,
+                       cck1=None,
+                       cck2=None,
                        ncase1=None,
                        ncontrol1=None,
                        prevalence1=None,
@@ -35,6 +37,22 @@ def _run_two_sample_mr(sumstatspair_object,
     if methods is None:
         methods = ["mr_ivw","mr_simple_mode","mr_weighted_median","mr_egger_regression","mr_ivw_mre", "mr_weighted_mode"]
         methods_string = '"{}"'.format('","'.join(methods))
+    
+    if cck1 is not None:
+        log.write(" - ncase1, ncontrol1, prevalence1:{}".format(cck1))
+        binary1 = True
+        ncase1 = cck1[0]
+        ncontrol1 = cck1[1]
+        prevalence1 =  cck1[2]
+        n1 = ncase1 + ncontrol1
+    if cck2 is not None:
+        log.write(" - ncase2, ncontrol2, prevalence2:{}".format(cck2))
+        binary2 = True
+        ncase2 = cck2[0]
+        ncontrol2 = cck2[1]
+        prevalence2 =  cck2[2]
+        n2 = ncase2 + ncontrol2
+
     if clump==True:
         sumstatspair = sumstatspair_object.clumps["clumps"]
     else: 
@@ -64,10 +82,16 @@ def _run_two_sample_mr(sumstatspair_object,
     
     ###
     calculate_r_script = ""
+    
     if binary1==True:
         calculate_r_script+= _make_script_for_calculating_r("exposure", ncase1, ncontrol1, prevalence1)
+    else:
+        calculate_r_script+= _make_script_for_calculating_r_quant("exposure")
+    
     if binary2==True:
         calculate_r_script+= _make_script_for_calculating_r("outcome", ncase2, ncontrol2, prevalence2)
+    else:
+        calculate_r_script+= _make_script_for_calculating_r_quant("outcome")
     
     # create scripts
     directionality_test_script='''
@@ -218,6 +242,16 @@ def _make_script_for_calculating_r(exposure_or_outcome, ncase, ncontrol, prevale
         return script
 
 
+def _make_script_for_calculating_r_quant(exposure_or_outcome):
+        script = """
+        harmonized_data$"r.{exposure_or_outcome}" <- get_r_from_bsen(  harmonized_data$"beta.{exposure_or_outcome}",
+                                                        harmonized_data$"se.{exposure_or_outcome}",
+                                                        harmonized_data$"samplesize.{exposure_or_outcome}"
+                                                        )
+        """.format(
+             exposure_or_outcome = exposure_or_outcome
+        )
+        return script
 
 
 def _filter_by_f(sumstatspair, f_check, n1, binary1=None, ncase1=None, ncontrol1=None, prevalence1=None, log=Log() ):

gwaslab/util_ex_run_clumping.py

@@ -162,7 +162,7 @@ def _clump(insumstats, vcf=None, scaled=False, out="clumping_plink2",
             log.write(e.output)
         #os.system(script)
         
-        clumped = pd.read_csv("{}.clumps".format(out_single_chr),usecols=[2,0,1,3],sep="\s+")
+        clumped = pd.read_csv("{}.clumps".format(out_single_chr),sep="\s+")
         results = pd.concat([results,clumped],ignore_index=True)
         
         # remove temp SNPIDP file 
@@ -172,7 +172,9 @@ def _clump(insumstats, vcf=None, scaled=False, out="clumping_plink2",
     log.write("Finished clumping.",verbose=verbose)
     results_sumstats = insumstats.loc[insumstats["SNPID"].isin(results["SNPID"]),:].copy()
     finished(log=log, verbose=verbose, end_line=_end_line)
-    return results_sumstats, plink_log
+
+    return results_sumstats, results, plink_log
+
 
 
        

gwaslab/util_in_fill_data.py

@@ -1,6 +1,7 @@
 import pandas as pd
 import numpy as np
 import scipy.stats as ss
+from scipy.stats import norm
 from scipy import stats
 from gwaslab.g_Log import Log
 import gc
@@ -8,6 +9,7 @@ import gc
 from gwaslab.g_version import _get_version
 from gwaslab.qc_check_datatype import check_datatype
 
+
 def filldata( 
     insumstats,
     to_fill=None,
@@ -330,4 +332,10 @@ def _convert_or_to_beta(OR):
     return np.log(OR)  
 
 def _convert_beta_to_or(beta):
-    return np.exp(beta)   
+    return np.exp(beta)   
+
+def rank_based_int(series, c=3/8):
+    #https://onlinelibrary.wiley.com/doi/10.1111/biom.13214
+    n=sum(~series.isna())
+    normalized_value = norm.ppf((series.rank()-c)/(n+1-2*c))
+    return normalized_value

gwaslab/util_in_filter_value.py

@@ -513,4 +513,18 @@ def _exclude(sumstats, exclude=None, id_use="SNPID", log=Log(), verbose=True ):
         log.write(" -Excluding {} variants from sumstats...".format(len(exclude)),verbose=verbose)
         sumstats = sumstats.loc[~sumstats[id_use].isin(exclude),:]
         log.write(" -Excluded {} variants from sumstats...".format(len(sumstats)),verbose=verbose)
-    return sumstats
+    return sumstats
+
+def _filter_region(sumstats, region, chrom="CHR",pos="POS",log=Log(),verbose=True):
+    if region is not None:
+        region_chr = region[0]
+        region_start = region[1]
+        region_end = 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)
+        
+        log.write(" -Extract SNPs in specified regions: "+str(sum(in_region_snp)),verbose=verbose)
+        sumstats = sumstats.loc[in_region_snp,:]
+        return sumstats.copy()

gwaslab/viz_plot_credible_sets.py

@@ -0,0 +1,99 @@
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+import seaborn as sns
+from gwaslab.g_Log import Log
+from gwaslab.viz_aux_quickfix import _quick_assign_i_with_rank
+from gwaslab.viz_plot_mqqplot import _process_xtick
+from gwaslab.viz_plot_mqqplot import _process_xlabel
+from gwaslab.bd_common_data import get_number_to_chr
+from gwaslab.util_in_filter_value import _filter_region
+from gwaslab.io_process_args import _extract_kwargs
+
+def _plot_cs(pipcs,
+            region, 
+            figax=None, 
+            _posdiccul=None,
+            xtick_chr_dict=None,
+            pip="PIP",
+            onlycs=False,
+            cs="CREDIBLE_SET_INDEX",
+            marker_size=(45,85),
+            fontsize = 12,
+            font_family = "Arial",
+            legend_title="Credible sets",
+            log=Log(),
+            verbose=True,
+            **kwargs):
+        '''
+        pipcs : a DataFrame of finemapping results
+        '''   
+        ## parameters ############################# 
+        if xtick_chr_dict is None:         
+                xtick_chr_dict = get_number_to_chr()
+
+        scatter_kwargs =   _extract_kwargs("scatter", dict(), locals())
+
+        region_marker_shapes = ['o', '^','s','D','*','P','X','h','8']
+        region_ld_colors_m = ["grey","#E51819","green","#F07818","#AD5691","yellow","purple"]
+        
+
+        ## filter data #############################
+        pipcs = _filter_region(pipcs, region)
+        if onlycs ==True:
+                pipcs = pipcs.loc[pipcs[cs]>0,:]
+
+        pipcs[cs] = pipcs[cs].astype("string")
+
+        ## figure and ax ############################# 
+        if figax is not None:
+                ax=figax[1]
+                fig=figax[0]
+        else:
+                fig, ax = plt.subplots()
+
+        # assign i
+        pipcs,chrom_df=_quick_assign_i_with_rank(pipcs,  chrpad=0.00, 
+                                                use_rank=False, 
+                                                chrom="CHR",pos="POS",
+                                                drop_chr_start=False,
+                                                _posdiccul=_posdiccul)
+        pipcs = pipcs.sort_values(by=cs,ascending=True)
+
+        ## plot ##########################################
+        scatter_kwargs["markers"]= {m:region_marker_shapes[i] for i,m in enumerate(pipcs[cs].unique())}
+        palette = sns.color_palette(region_ld_colors_m,n_colors=pipcs[cs].nunique()) 
+        edgecolor="none"
+
+        plot = sns.scatterplot(data=pipcs,
+                        x="i",
+                        y=pip,
+                        hue=cs,
+                        edgecolor=edgecolor,
+                        palette=palette, 
+                        style=cs,
+                        s=marker_size[1],
+                        ax=ax,
+                        **scatter_kwargs)
+
+        # process legend
+        handles, labels = ax.get_legend_handles_labels()
+        new_labels = []
+        new_handles = []
+        ncol = len(labels)
+
+        for i,label in enumerate(labels):
+                if label in [str(j) for j in range(1,10)]:
+                        new_labels.append(labels[i])
+                        new_handles.append(handles[i])
+        
+        ax.legend(labels =new_labels,  
+                  handles=new_handles, 
+                  loc="upper right", 
+                  bbox_to_anchor=(0.995, 0.995), 
+                  ncol=1, 
+                  scatterpoints=2, 
+                  title=legend_title, 
+                  frameon=True)
+
+        return fig, log

gwaslab/viz_plot_mqqplot.py

@@ -51,6 +51,7 @@ from gwaslab.bd_common_data import get_chr_to_number
 from gwaslab.bd_common_data import get_number_to_chr
 from gwaslab.bd_common_data import get_recombination_rate
 from gwaslab.bd_common_data import get_gtf
+from gwaslab.util_in_filter_value import _filter_region
 from gwaslab.g_version import _get_version
 from matplotlib.colors import ListedColormap
 from matplotlib.colors import LinearSegmentedColormap
@@ -475,18 +476,20 @@ def mqqplot(insumstats,
         sumstats[chrom] = _quick_fix_chr(sumstats[chrom], chr_dict=chr_dict)
 
     ## r
+    
     if region is not None:
-        region_chr = region[0]
-        region_start = region[1]
-        region_end = 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)
-        
-        log.write(" -Extract SNPs in specified regions: "+str(sum(in_region_snp)),verbose=verbose)
-        sumstats = sumstats.loc[in_region_snp,:]
-        
+        sumstats = _filter_region(sumstats, region, log=log, verbose=verbose)
+    #    region_chr = region[0]
+    #    region_start = region[1]
+    #    region_end = 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)
+    #    
+    #    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.warning("No valid data! Please check the input.")
             return None

gwaslab/viz_plot_stackedregional.py

@@ -38,9 +38,10 @@ from gwaslab.io_to_pickle import load_data_from_pickle
 from gwaslab.g_Sumstats import Sumstats
 from gwaslab.viz_aux_save_figure import save_figure
 from gwaslab.viz_plot_mqqplot import mqqplot
+from gwaslab.viz_plot_credible_sets import _plot_cs
 import matplotlib.patches as patches
 
-def plot_stacked_mqq(objects,
+def plot_stacked_mqq(   objects,
                         vcfs=None,
                         mode="r",
                         mqqratio=3,
@@ -62,10 +63,12 @@ def plot_stacked_mqq(objects,
                         region_ld_legends = None,
                         fontsize=9,
                         font_family="Arial",
+                        common_ylabel=True,
                         build="99", 
                         save=None,
                         save_args=None,
                         verbose=True,
+                        pm=None,
                         log=Log(),
                         **mqq_args
                         ):
@@ -74,10 +77,28 @@ def plot_stacked_mqq(objects,
     # load sumstats
     
     ##########################################################################################################################################
+    if pm is None:
+        pm=[]
+
     sumstats_list = [] 
     for each_object in objects:
-        sumstats_list.append(each_object.data)
+        if type(each_object) is Sumstats:
+            if "P" in each_object.data.columns or "MLOG10P" in each_object.data.columns:
+                sumstats_list.append(each_object.data)
+                pm.append("m")
+        else:
+            if "PIP" in each_object.columns:
+                sumstats_list.append(each_object)
+                pm.append("pip")
+                common_ylabel=False
+    
+    if common_ylabel==True:
+        rr_ylabel=False
+    else:
+        rr_ylabel=True
 
+    log.write(" -Panel mode:{}...".format(pm),verbose=verbose)
+    
     if fig_args is None:
         fig_args = {"dpi":200}
     if save_args is None:
@@ -200,7 +221,7 @@ def plot_stacked_mqq(objects,
                             region_lead_grid=False,
                             region_ld_legend=region_ld_legend,
                             gtf_path="default",
-                            rr_ylabel=False,
+                            rr_ylabel=rr_ylabel,
                             figax=figax,
                             _get_region_lead=True,
                             _if_quick_qc=False,
@@ -213,33 +234,42 @@ def plot_stacked_mqq(objects,
             lead_variants_is[index] = lead_snp_is
             lead_variants_is_color[index] = lead_snp_is_color
         else:
-            # plot only the scatter plot
-            fig,log,lead_snp_is,lead_snp_is_color = mqqplot(sumstats,
-                            chrom="CHR",
-                            pos="POS",
-                            p="P",
-                            region=region,
-                            mlog10p="MLOG10P",
-                            snpid="SNPID",
-                            vcf_path=vcfs[index],
-                            region_lead_grid=False,
-                            fontsize=fontsize,
-                            font_family=font_family,
-                            mode=mode,
-                            rr_ylabel=False,
-                            region_ld_legend=region_ld_legend,
-                            gtf_path=None,
-                            figax=figax,
-                            _get_region_lead=True,
-                            _if_quick_qc=False,
-                            _posdiccul=_posdiccul,
-                            build=build,
-                            verbose=verbose,
-                            log=log,
-                            **mqq_args_for_each_plot[index]
-                            )
-            lead_variants_is[index] = lead_snp_is
-            lead_variants_is_color[index] = lead_snp_is_color
+            if pm[index]=="m":
+                # plot only the scatter plot
+                fig,log,lead_snp_is,lead_snp_is_color = mqqplot(sumstats,
+                                chrom="CHR",
+                                pos="POS",
+                                p="P",
+                                region=region,
+                                mlog10p="MLOG10P",
+                                snpid="SNPID",
+                                vcf_path=vcfs[index],
+                                region_lead_grid=False,
+                                fontsize=fontsize,
+                                font_family=font_family,
+                                mode=mode,
+                                rr_ylabel=rr_ylabel,
+                                region_ld_legend=region_ld_legend,
+                                gtf_path=None,
+                                figax=figax,
+                                _get_region_lead=True,
+                                _if_quick_qc=False,
+                                _posdiccul=_posdiccul,
+                                build=build,
+                                verbose=verbose,
+                                log=log,
+                                **mqq_args_for_each_plot[index]
+                                )
+                lead_variants_is[index] = lead_snp_is
+                lead_variants_is_color[index] = lead_snp_is_color
+            elif pm[index]=="pip":
+                fig,log =_plot_cs(sumstats,
+                                  region=region,
+                                  _posdiccul=_posdiccul,
+                                  figax=figax,
+                                  log=log,
+                                  verbose=verbose,
+                                  **mqq_args_for_each_plot[index])
     if len(region_chromatin_files)>0 and mode=="r":
         xlim_i = axes[-1].get_xlim()
         fig = _plot_chromatin_state(     region_chromatin_files = region_chromatin_files, 
@@ -295,9 +325,10 @@ def plot_stacked_mqq(objects,
     _draw_grid_line_for_lead_variants(mode, lead_variants_is,lead_variants_is_color, n_plot, axes, region_lead_grid_line,region_chromatin_files,region_lead_grids)
     
     ##########################################################################################################################################  
-    _drop_old_y_labels(axes, n_plot)
-    
-    _add_new_y_label(mode, fig, gene_track_height,n_plot,subplot_height ,fontsize,font_family)
+    if common_ylabel==True:
+        _drop_old_y_labels(axes, n_plot)
+        
+        _add_new_y_label(mode, fig, gene_track_height,n_plot,subplot_height ,fontsize,font_family)
     
     ##########################################################################################################################################
     save_figure(fig = fig, save = save, keyword= "stacked_" + mode, save_args=save_args, log = log, verbose=verbose)

{gwaslab-3.5.4.dist-info → gwaslab-3.5.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gwaslab
-Version: 3.5.4
+Version: 3.5.5
 Summary: A collection of handy tools for GWAS SumStats
 Author-email: Yunye <yunye@gwaslab.com>
 Project-URL: Homepage, https://cloufield.github.io/gwaslab/
@@ -14,7 +14,7 @@ License-File: LICENSE
 License-File: LICENSE_before_v3.4.39
 Requires-Dist: pandas!=1.5,>=1.3
 Requires-Dist: numpy<2,>=1.21.2
-Requires-Dist: matplotlib!=3.7.2,<3.9,>=3.5
+Requires-Dist: matplotlib<3.9,>=3.8
 Requires-Dist: seaborn>=0.12
 Requires-Dist: scipy>=1.12
 Requires-Dist: pySAM==0.22.1
@@ -51,7 +51,7 @@ Warning: Known issues of GWASLab are summarized in [https://cloufield.github.io/
 ### install via pip
 
 ```
-pip install gwaslab==3.5.0
+pip install gwaslab==3.5.4
 ```
 
 ```python