gwaslab 3.6.0__tar.gz → 3.6.2__tar.gz

{gwaslab-3.6.0/src/gwaslab.egg-info → gwaslab-3.6.2}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: gwaslab
-Version: 3.6.0
+Version: 3.6.2
 Summary: A collection of handy tools for GWAS SumStats
-Author-email: Yunye <yunye@gwaslab.com>
+Author-email: Yunye <gwaslab@gmail.com>
 Project-URL: Homepage, https://cloufield.github.io/gwaslab/
 Project-URL: Github, https://github.com/Cloufield/gwaslab
 Classifier: Programming Language :: Python :: 3
@@ -25,6 +25,7 @@ Requires-Dist: scikit-allel>=1.3.5
 Requires-Dist: pyensembl==2.2.3
 Requires-Dist: gtfparse==1.3.0
 Requires-Dist: h5py>=3.10.0
+Requires-Dist: pyarrow
 Dynamic: license-file
 
 # GWASLab

{gwaslab-3.6.0 → gwaslab-3.6.2}/pyproject.toml

@@ -7,9 +7,9 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gwaslab"
-version = "3.6.0"
+version = "3.6.2"
 authors = [
-  { name="Yunye", email="yunye@gwaslab.com" },
+  { name="Yunye", email="gwaslab@gmail.com" },
 ]
 description = "A collection of handy tools for GWAS SumStats"
 
@@ -28,7 +28,8 @@ dependencies = [
     "scikit-allel>=1.3.5",
     "pyensembl==2.2.3",
     "gtfparse==1.3.0",
-    "h5py>=3.10.0"
+    "h5py>=3.10.0",
+    "pyarrow"
 ]
 
 requires-python = ">=3.9,<3.13"

{gwaslab-3.6.0 → gwaslab-3.6.2}/src/gwaslab/g_Sumstats.py

@@ -2,6 +2,7 @@ import pandas as pd
 import numpy as np
 import time
 import copy
+import gc
 from gwaslab.g_Sumstats_summary import summarize
 from gwaslab.g_Sumstats_summary import lookupstatus
 from gwaslab.io_preformat_input import preformat
@@ -69,16 +70,24 @@ from gwaslab.g_version import gwaslab_info
 from gwaslab.g_meta import _init_meta
 from gwaslab.g_meta import _append_meta_record
 from gwaslab.g_meta_update import _update_meta
-from gwaslab.util_ex_run_clumping import _clump
-from gwaslab.util_ex_calculate_ldmatrix import tofinemapping
 from gwaslab.io_load_ld import tofinemapping_using_ld
-from gwaslab.util_ex_calculate_prs import _calculate_prs
+from gwaslab.qc_fix_sumstats import _check_data_consistency
+from gwaslab.bd_get_hapmap3 import gethapmap3
+from gwaslab.util_abf_finemapping import abf_finemapping
+from gwaslab.util_abf_finemapping import make_cs
+from gwaslab.io_read_pipcs import _read_pipcs
+from gwaslab.util_in_estimate_ess import _get_ess
+from gwaslab.hm_casting import _align_with_mold
+from gwaslab.hm_casting  import _merge_mold_with_sumstats_by_chrpos
+from gwaslab.viz_plot_phe_heatmap import _gwheatmap
 from gwaslab.viz_plot_mqqplot import mqqplot
 from gwaslab.viz_plot_trumpetplot import plottrumpet
 from gwaslab.viz_plot_compare_af import plotdaf
+from gwaslab.viz_plot_credible_sets import _plot_cs
+from gwaslab.util_ex_run_clumping import _clump
+from gwaslab.util_ex_calculate_ldmatrix import tofinemapping
 from gwaslab.util_ex_run_susie import _run_susie_rss
 from gwaslab.util_ex_run_susie import _get_cs_lead
-from gwaslab.qc_fix_sumstats import _check_data_consistency
 from gwaslab.util_ex_ldsc import _estimate_h2_by_ldsc
 from gwaslab.util_ex_ldsc import _estimate_rg_by_ldsc
 from gwaslab.util_ex_ldsc import _estimate_h2_cts_by_ldsc
@@ -86,17 +95,9 @@ from gwaslab.util_ex_ldsc import _estimate_partitioned_h2_by_ldsc
 from gwaslab.util_ex_ldproxyfinder import _extract_ld_proxy
 from gwaslab.util_ex_run_magma import _run_magma
 from gwaslab.util_ex_infer_ancestry import _infer_ancestry
-from gwaslab.bd_get_hapmap3 import gethapmap3
-from gwaslab.util_abf_finemapping import abf_finemapping
-from gwaslab.util_abf_finemapping import make_cs
-from gwaslab.io_read_pipcs import _read_pipcs
-from gwaslab.util_in_estimate_ess import _get_ess
-from gwaslab.viz_plot_credible_sets import _plot_cs
-from gwaslab.hm_casting import _align_with_mold
-from gwaslab.hm_casting  import _merge_mold_with_sumstats_by_chrpos
-import gc
-from gwaslab.viz_plot_phe_heatmap import _gwheatmap
 from gwaslab.util_ex_run_prscs import _run_prscs
+from gwaslab.util_ex_calculate_prs import _calculate_prs
+from gwaslab.util_ex_run_scdrs import _run_scdrs
 
 #20220309
 class Sumstats():
@@ -895,6 +896,11 @@ class Sumstats():
         _run_magma(self.data, 
                    study=self.meta["gwaslab"]["study_name"], 
                    build=build, verbose=verbose, log=self.log, **kwargs)
+        
+    def run_scdrs(self, build=None, verbose=True, **kwargs):
+        _run_scdrs(
+                   study=self.meta["gwaslab"]["study_name"], 
+                   build=build, verbose=verbose, log=self.log, **kwargs)
 ## LDSC ##############################################################################################
     def estimate_h2_by_ldsc(self, build=None, verbose=True, match_allele=True, how="right", **kwargs):
         if build is None:

{gwaslab-3.6.0 → gwaslab-3.6.2}/src/gwaslab/g_version.py

@@ -15,8 +15,8 @@ def _get_version():
 def gwaslab_info():
     # version meta information
     dic={
-   "version":"3.6.0",
-   "release_date":"20250504"
+   "version":"3.6.2",
+   "release_date":"20250509"
     }
     return dic   
 

{gwaslab-3.6.0 → gwaslab-3.6.2}/src/gwaslab/qc_fix_sumstats.py

@@ -1107,11 +1107,11 @@ def normalizevariant(pos,a,b,status):
 
 ###############################################################################################################
 # 20220426
-def add_tolerence(stats, float_tolerence, mode):
+def add_tolerence(stats, float_tolerance, mode):
     if "l" in mode:
-        stats = (stats[0] - float_tolerence if stats[0]!=float("Inf") else float("Inf"), stats[1])
+        stats = (stats[0] - float_tolerance if stats[0]!=float("Inf") else float("Inf"), stats[1])
     if "r" in mode:
-        stats = (stats[0] , stats[1] + float_tolerence if stats[0]!=float("Inf") else float("Inf"))
+        stats = (stats[0] , stats[1] + float_tolerance if stats[0]!=float("Inf") else float("Inf"))
     return stats
 
 
@@ -1183,27 +1183,27 @@ def sanitycheckstats(sumstats,
                      mlog10p=(0,99999),
                      beta=(-100,100),
                      se=(0,float("Inf")),
-                     OR=(-100,100),
+                     OR=(np.exp(-100),np.exp(100)),
                      OR_95L=(0,float("Inf")),
                      OR_95U=(0,float("Inf")),
-                     HR=(-100,100),
+                     HR=(np.exp(-100),np.exp(100)),
                      HR_95L=(0,float("Inf")),
                      HR_95U=(0,float("Inf")),
                      info=(0,2),
-                     float_tolerence = 1e-7,
+                     float_tolerance = 1e-7,
                      verbose=True,
                      log=Log()):
     '''
     Sanity check (default; v3.4.33):
         N:      Int32    , N>0 , 
-        EAF:    float32  , 0<= EAF <=1, 
-        P:      float64  , 0< P < 1, 
-        BETA:   float64  , abs(BETA) <10
+        EAF:    float32  , 0 <= EAF <=1, 
+        P:      float64  , 0 <= P <= 1, 
+        BETA:   float64  , abs(BETA) <100
         SE:     float64  , SE > 0
-        OR:     float64  , -10 <log(OR) <10
+        OR:     float64  , np.exp(-100) <OR < np.exp(100)
         OR_95L: float64  , OR_95L >0
         OR_95U: float64  , OR_95L >0
-        HR:     float64  , -10 <log(HR) <10
+        HR:     float64  , np.exp(-100) <log(HR) <np.exp(100)
         HR_95L: float64  , HR_95L >0
         HR_95U: float64  , HR_95L >0
         INFO:   float32  , 1>=INFO>0
@@ -1229,23 +1229,23 @@ def sanitycheckstats(sumstats,
     if is_enough_info == False: return sumstats
     ############################################################################################
 
-    log.write(" -Comparison tolerance for floats: {}".format(float_tolerence), verbose=verbose) 
-    eaf = add_tolerence(eaf, float_tolerence, "lr")
-    maf = add_tolerence(maf, float_tolerence, "lr")
-    beta = add_tolerence(beta, float_tolerence, "lr")
-    se = add_tolerence(se, float_tolerence, "lr")
-    mlog10p = add_tolerence(mlog10p, float_tolerence, "lr")
-    OR = add_tolerence(OR, float_tolerence, "lr")
-    OR_95L = add_tolerence(OR_95L, float_tolerence, "lr")
-    OR_95U = add_tolerence(OR_95U, float_tolerence, "lr")
-    HR = add_tolerence(HR, float_tolerence, "lr")
-    HR_95L = add_tolerence(HR_95L, float_tolerence, "lr")
-    HR_95U = add_tolerence(HR_95U, float_tolerence, "lr")
-    info = add_tolerence(info, float_tolerence, "lr")
-    z = add_tolerence(z, float_tolerence, "lr")
-    p = add_tolerence(p, float_tolerence, "lr")
-    f = add_tolerence(f, float_tolerence, "lr")
-    chisq = add_tolerence(chisq, float_tolerence, "lr")
+    log.write(" -Comparison tolerance for floats: {}".format(float_tolerance), verbose=verbose) 
+    eaf = add_tolerence(eaf, float_tolerance, "lr")
+    maf = add_tolerence(maf, float_tolerance, "lr")
+    beta = add_tolerence(beta, float_tolerance, "lr")
+    se = add_tolerence(se, float_tolerance, "lr")
+    mlog10p = add_tolerence(mlog10p, float_tolerance, "lr")
+    OR = add_tolerence(OR, float_tolerance, "lr")
+    OR_95L = add_tolerence(OR_95L, float_tolerance, "lr")
+    OR_95U = add_tolerence(OR_95U, float_tolerance, "lr")
+    HR = add_tolerence(HR, float_tolerance, "lr")
+    HR_95L = add_tolerence(HR_95L, float_tolerance, "lr")
+    HR_95U = add_tolerence(HR_95U, float_tolerance, "lr")
+    info = add_tolerence(info, float_tolerance, "lr")
+    z = add_tolerence(z, float_tolerance, "lr")
+    p = add_tolerence(p, float_tolerance, "lr")
+    f = add_tolerence(f, float_tolerance, "lr")
+    chisq = add_tolerence(chisq, float_tolerance, "lr")
     ############################################################################################
     ## add direction
     if coltocheck is None:

{gwaslab-3.6.0 → gwaslab-3.6.2}/src/gwaslab/util_ex_run_magma.py

@@ -41,14 +41,11 @@ def _run_magma(sumstats,
     log.write(f" --bfile: {ref}", verbose=verbose)
     log.write(f" Output prefix: {out}", verbose=verbose)
 
-    bash_script=f'''
-
-#!/bin/bash
+    bash_script=f'''#!/bin/bash
 
 {magma} --annotate window={window}  --snp-loc {snploc} --gene-loc {ncbi} --out {study}
 
 {magma} --bfile {ref} --pval {pval} ncol={ncol} --gene-annot {study}.genes.annot --out {study}
-
 '''
     
     if set_annot is not None:

gwaslab-3.6.2/src/gwaslab/util_ex_run_scdrs.py

@@ -0,0 +1,108 @@
+import subprocess
+import os
+import gc
+import pandas as pd
+import numpy as np
+from gwaslab.g_Log import Log
+
+def _run_scdrs( scdrs="scdrs",
+                python="python",
+                study="Study1",
+                conda_env=None,
+                zscore_file=None,
+                out_file=None,
+                h5ad_file=None,
+                out_folder=None,
+                exclude_hla=True,
+                group_analysis = None,
+                gene_analysis = False,
+                gs_species="human",
+                h5ad_species="human",
+                flag_filter_data=True,
+                flag_raw_count=True,
+                munge_gs=True,
+                compute_score=True,
+                perform_downstream=True,
+                out="./",
+                delete=True, 
+                ncol="N",
+                build="19",
+                log=Log(), 
+                verbose=True):
+    
+    log.write(" Start to run scDRS from command line:", verbose=verbose)
+    
+    trait = study
+    if out_file is None:
+        out_file = f"./{trait}.gs"
+    if out_folder is None:
+        out_folder = f"./"
+    if conda_env is not None:
+        conda_env_string = f"conda init bash\n conda activate {conda_env}\n"
+    else:
+        conda_env_string=""
+    log.write(f" Output prefix: {out}", verbose=verbose)
+
+    if group_analysis is not None:
+        analysis_string = f"--group-analysis {group_analysis} "
+    if gene_analysis == True:
+        analysis_string += "--gene-analysis"
+    
+    bash_script=f'''#!/bin/bash
+{conda_env_string} 
+'''
+
+    if munge_gs==True:
+    
+        bash_script+=f'''
+{python} {scdrs} munge-gs \
+    --out-file {out_file} \
+    --zscore-file {zscore_file} \
+    --weight zscore \
+    --n-max 1000
+
+'''
+    
+    if compute_score==True:
+    
+        bash_script+=f'''
+{python} {scdrs} compute-score \
+    --h5ad-file {h5ad_file} \
+    --h5ad-species {h5ad_species} \
+    --gs-file {out_file} \
+    --gs-species {gs_species} \
+    --out-folder {out_folder} \
+    --flag-filter-data {flag_filter_data} \
+    --flag-raw-count {flag_raw_count} \
+    --n-ctrl 1000 \
+    --flag-return-ctrl-raw-score False \
+    --flag-return-ctrl-norm-score True
+
+'''
+    
+    if perform_downstream==True:
+        bash_script+=f'''
+{python} {scdrs} perform-downstream {analysis_string} \
+    --h5ad-file {h5ad_file} \
+    --score-file {trait}.full_score.gz \
+    --out-folder {out_folder} \
+    --min_genes 250 \
+    --min_cells 50 \
+    --knn_n_neighbors 15 \
+    --knn_n_pcs 20 \
+    --flag-filter-data {flag_filter_data} \
+    --flag-raw-count {flag_raw_count} 
+
+'''
+    log.write(f"Script: {bash_script}")
+
+    try:
+        log.write(" Running scDRS from command line...", verbose=verbose)
+        output = subprocess.check_output(bash_script, stderr=subprocess.STDOUT, shell=True,text=True)
+        output =  output + "\n"
+        
+    except subprocess.CalledProcessError as e:
+        log.warning("ERROR!")
+        log.write(e.output)
+
+    log.write("Finished running scDRS.", verbose=verbose)

{gwaslab-3.6.0 → gwaslab-3.6.2}/src/gwaslab/util_in_meta.py

@@ -7,7 +7,6 @@ from gwaslab.g_Log import Log
 from gwaslab.io_to_pickle import load_data_from_pickle
 from gwaslab.g_Sumstats import Sumstats
 import gc
-import statsmodels.api as sm
 
 def meta_analyze(sumstats_list,
                  random_effects=False, 

{gwaslab-3.6.0 → gwaslab-3.6.2}/src/gwaslab/util_in_meta_polars.py

@@ -6,9 +6,7 @@ from scipy.stats import norm
 from gwaslab.g_Log import Log
 from gwaslab.io_to_pickle import load_data_from_pickle
 from gwaslab.g_Sumstats import Sumstats
-import gc
 import polars as pl
-import statsmodels.api as sm
 ########################################################################################################################################################################################################################################################################################################################################################
 ########################################################################################################################################################################################################################################################################################################################################################
 ########################################################################################################################################################################################################################################################################################################################################################

{gwaslab-3.6.0 → gwaslab-3.6.2/src/gwaslab.egg-info}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: gwaslab
-Version: 3.6.0
+Version: 3.6.2
 Summary: A collection of handy tools for GWAS SumStats
-Author-email: Yunye <yunye@gwaslab.com>
+Author-email: Yunye <gwaslab@gmail.com>
 Project-URL: Homepage, https://cloufield.github.io/gwaslab/
 Project-URL: Github, https://github.com/Cloufield/gwaslab
 Classifier: Programming Language :: Python :: 3
@@ -25,6 +25,7 @@ Requires-Dist: scikit-allel>=1.3.5
 Requires-Dist: pyensembl==2.2.3
 Requires-Dist: gtfparse==1.3.0
 Requires-Dist: h5py>=3.10.0
+Requires-Dist: pyarrow
 Dynamic: license-file
 
 # GWASLab

{gwaslab-3.6.0 → gwaslab-3.6.2}/src/gwaslab.egg-info/SOURCES.txt

@@ -71,6 +71,7 @@ src/gwaslab/util_ex_run_magma.py
 src/gwaslab/util_ex_run_mesusie.py
 src/gwaslab/util_ex_run_mtag.py
 src/gwaslab/util_ex_run_prscs.py
+src/gwaslab/util_ex_run_scdrs.py
 src/gwaslab/util_ex_run_susie.py
 src/gwaslab/util_in_calculate_gc.py
 src/gwaslab/util_in_calculate_power.py

{gwaslab-3.6.0 → gwaslab-3.6.2}/src/gwaslab.egg-info/requires.txt

@@ -11,3 +11,4 @@ scikit-allel>=1.3.5
 pyensembl==2.2.3
 gtfparse==1.3.0
 h5py>=3.10.0
+pyarrow