gwaslab 3.4.41__tar.gz → 3.4.43__tar.gz

{gwaslab-3.4.41/src/gwaslab.egg-info → gwaslab-3.4.43}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gwaslab
-Version: 3.4.41
+Version: 3.4.43
 Summary: A collection of handy tools for GWAS SumStats
 Author-email: Yunye <yunye@gwaslab.com>
 Project-URL: Homepage, https://cloufield.github.io/gwaslab/
@@ -24,6 +24,7 @@ Requires-Dist: liftover>=1.1.13
 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
 
 # GWASLab
 
@@ -50,7 +51,7 @@ Warning: Known issues of GWASLab are summarized in [https://cloufield.github.io/
 ### install via pip
 
 ```
-pip install gwaslab==3.4.40
+pip install gwaslab==3.4.41
 ```
 
 ```python
@@ -89,7 +90,7 @@ Create a Python 3.9 environment and install gwaslab using pip:
 ```
 conda env create -n gwaslab_test -c conda-forge python=3.9
 conda activate gwaslab
-pip install gwaslab==3.4.40
+pip install gwaslab==3.4.41
 ```
 
 or create a new environment using yml file [environment_3.4.40.yml](https://github.com/Cloufield/gwaslab/blob/main/environment_3.4.40.yml)
@@ -193,6 +194,7 @@ dependencies:
       - adjustText==0.8
       - pysam==0.19
       - pyensembl==2.2.3
+      - h5py==3.10.0
 ```
 
 ## How to cite
@@ -201,6 +203,9 @@ dependencies:
 ## Sample Data
 - Sample GWAS data used in GWASLab is obtained from: http://jenger.riken.jp/ (Suzuki, Ken, et al. "Identification of 28 new susceptibility loci for type 2 diabetes in the Japanese population." Nature genetics 51.3 (2019): 379-386.).
 
+## Acknowledgement
+
+Thanks to @sup3rgiu, @soumickmj and @gmauro for their contributions to the source codes.
 
 ## Contacts
 * Github: [https://github.com/Cloufield/gwaslab](https://github.com/Cloufield/gwaslab)

{gwaslab-3.4.41 → gwaslab-3.4.43}/README.md

@@ -23,7 +23,7 @@ Warning: Known issues of GWASLab are summarized in [https://cloufield.github.io/
 ### install via pip
 
 ```
-pip install gwaslab==3.4.40
+pip install gwaslab==3.4.41
 ```
 
 ```python
@@ -62,7 +62,7 @@ Create a Python 3.9 environment and install gwaslab using pip:
 ```
 conda env create -n gwaslab_test -c conda-forge python=3.9
 conda activate gwaslab
-pip install gwaslab==3.4.40
+pip install gwaslab==3.4.41
 ```
 
 or create a new environment using yml file [environment_3.4.40.yml](https://github.com/Cloufield/gwaslab/blob/main/environment_3.4.40.yml)
@@ -166,6 +166,7 @@ dependencies:
       - adjustText==0.8
       - pysam==0.19
       - pyensembl==2.2.3
+      - h5py==3.10.0
 ```
 
 ## How to cite
@@ -174,6 +175,9 @@ dependencies:
 ## Sample Data
 - Sample GWAS data used in GWASLab is obtained from: http://jenger.riken.jp/ (Suzuki, Ken, et al. "Identification of 28 new susceptibility loci for type 2 diabetes in the Japanese population." Nature genetics 51.3 (2019): 379-386.).
 
+## Acknowledgement
+
+Thanks to @sup3rgiu, @soumickmj and @gmauro for their contributions to the source codes.
 
 ## Contacts
 * Github: [https://github.com/Cloufield/gwaslab](https://github.com/Cloufield/gwaslab)

{gwaslab-3.4.41 → gwaslab-3.4.43}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gwaslab"
-version = "3.4.41"
+version = "3.4.43"
 authors = [
   { name="Yunye", email="yunye@gwaslab.com" },
 ]
@@ -27,7 +27,8 @@ dependencies = [
     "liftover>=1.1.13",
     "scikit-allel>=1.3.5",
     "pyensembl==2.2.3",
-    "gtfparse==1.3.0"
+    "gtfparse==1.3.0",
+    "h5py>=3.10.0"
 ]
 
 requires-python = ">=3.9,<=3.10"

{gwaslab-3.4.41 → gwaslab-3.4.43}/src/gwaslab/bd_common_data.py

@@ -298,9 +298,22 @@ def gtf_to_protein_coding(gtfpath,log=Log(),verbose=True):
 
     return protein_coding_path
 
+####################################################################################################################   
+# From BioPython: https://github.com/biopython/biopython/blob/c5a6b1374267d769b19c1022b4b45472316e78b4/Bio/Seq.py#L36
+def _maketrans(complement_mapping):
+    """Make a python string translation table.
+
+    Arguments:
+     - complement_mapping - a dictionary.
 
-      
+    Returns a translation table (a bytes object of length 256) for use with
+    the python string's translate method.
 
+    Compatible with lower case and upper case sequences.
+    """
+    keys = "".join(complement_mapping.keys()).encode("ASCII")
+    values = "".join(complement_mapping.values()).encode("ASCII")
+    return bytes.maketrans(keys + keys.lower(), values + values.lower())
         
 ####################################################################################################################   
         

{gwaslab-3.4.41 → gwaslab-3.4.43}/src/gwaslab/bd_get_hapmap3.py

@@ -12,7 +12,7 @@ from gwaslab.qc_fix_sumstats import finished
 #A P-value
 #A signed summary statistic (beta, OR, log odds, Z-score, etc)
 
-def gethapmap3(sumstats,rsid="rsID",chrom="CHR", pos="POS", ea="EA", nea="NEA",build="19", verbose=True, match_allele= True, log=Log()):
+def gethapmap3(sumstats,rsid="rsID",chrom="CHR", pos="POS", ea="EA", nea="NEA",build="19", verbose=True, match_allele= True, how="inner", log=Log()):
     ##start function with col checking##########################################################
     _start_line = "extract HapMap3 SNPs"
     _end_line = "extracting HapMap3 SNPs"
@@ -47,7 +47,7 @@ def gethapmap3(sumstats,rsid="rsID",chrom="CHR", pos="POS", ea="EA", nea="NEA",b
     #rsid    A1      A2      #CHROM  POS
     #rs3094315       G       A       1       752566
     
-    if rsid in sumstats.columns:
+    if rsid in sumstats.columns and how=="inner":
         output = sumstats.loc[sumstats[rsid].isin(hapmap3_ref["rsid"].values),:].copy()
         return output
     
@@ -56,11 +56,15 @@ def gethapmap3(sumstats,rsid="rsID",chrom="CHR", pos="POS", ea="EA", nea="NEA",b
         sumstats   ["chr:pos"] = sumstats[chrom].astype("string")+":"+sumstats[pos].astype("string")
         hapmap3_ref["chr:pos"] = hapmap3_ref["#CHROM"]+":"+hapmap3_ref["POS"]
         hapmap3_ref = hapmap3_ref.rename(columns={"rsid":"rsID"})
-        output = pd.merge(sumstats,hapmap3_ref.loc[:,["chr:pos","rsID"]+additional_cols],left_on="chr:pos",right_on="chr:pos",how="inner",suffixes=('', '_hapmap3')).copy()
+        output = pd.merge(sumstats,hapmap3_ref.loc[:,["chr:pos","rsID"]+additional_cols],left_on="chr:pos",right_on="chr:pos",how=how,suffixes=('', '_hapmap3')).copy()
         if match_allele:
             log.write(" -Checking if alleles are same...")
             is_matched = ((output[ea].astype("string") == output["A1"]) & (output[nea].astype("string") == output["A2"])) \
                             | ((output[ea].astype("string") == output["A2"]) & (output[nea].astype("string") == output["A1"]))
+            if how=="right":
+                is_matched = ((output[ea].astype("string") == output["A1"]) & (output[nea].astype("string") == output["A2"])) \
+                            | ((output[ea].astype("string") == output["A2"]) & (output[nea].astype("string") == output["A1"])) | output[ea].isna()
+
             log.write(" -Variants with macthed alleles: {}".format(sum(is_matched)))
             output = output.loc[is_matched,:]
         output = output.drop(columns=["chr:pos"]+additional_cols)