Merge pull request #190 from zhx828/skip-token-validation

Support python 3.11

.github/workflows/pytest.yml

@@ -31,8 +31,8 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest]
-        python-version: [2.7, 3.7, 3.8]
+        os: [ ubuntu-latest, macos-latest ]
+        python-version: [ '2.7','3.7','3.8','3.9','3.10','3.11' ]
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}
@@ -45,19 +45,20 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install pytest
-        if [[ $PYTHON_VERSION =~ ^2\.[0-9]$ ]]; then pip install -r requirements/common.txt -r requirements/pip2.7.txt; fi
-        if [[ $PYTHON_VERSION =~ ^3\.[0-9]$ ]]; then pip install -r requirements/common.txt -r requirements/pip3.txt; fi
+        if [[ $PYTHON_VERSION =~ ^2\.[0-9]+$ ]]; then pip install -r requirements/common.txt -r requirements/pip2.7.txt; fi
+        if [[ $PYTHON_VERSION =~ ^3\.[0-9]+$ ]]; then pip install -r requirements/common.txt -r requirements/pip3.txt; fi
     - name: Test with pytest
       env:
         ONCOKB_API_TOKEN: ${{ secrets.ONCOKB_BOT_API_TOKEN }}
       run: |
         pytest
 
   build-in-windows:
+    needs: lint
     runs-on: windows-latest
     strategy:
       matrix:
-        python-version: [2.7, 3.7, 3.8]
+        python-version: [ '2.7','3.7','3.8','3.9','3.10','3.11' ]
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}
@@ -70,11 +71,11 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install pytest
-        if ( $env:PYTHON_VERSION -match '^2\.[0-9]$' )
+        if ( $env:PYTHON_VERSION -match '^2\.[0-9]+$' )
         {
           pip install -r requirements/common.txt -r requirements/pip2.7.txt
         }
-        if ( $env:PYTHON_VERSION -match '^3\.[0-9]$' )
+        if ( $env:PYTHON_VERSION -match '^3\.[0-9]+$' )
         {
           pip install -r requirements/common.txt -r requirements/pip3.txt
         }

AnnotatorCore.py

@@ -2,6 +2,8 @@
 import datetime
 import json
 import csv
+import sys
+
 import requests
 import os.path
 import logging
@@ -35,6 +37,11 @@
 
 oncokb_api_bearer_token = ""
 
+# 'U', which no longer has any effect in python 3. 3.11 completely removed the option.
+# It will throw error if we don't do condition check.
+# https://stackoverflow.com/questions/56791545/what-is-the-non-deprecated-version-of-open-u-mode
+DEFAULT_READ_FILE_MODE = 'r' if sys.version_info.major > 2 else 'rU'
+
 
 def setoncokbbaseurl(u):
     if u and u is not None:
@@ -416,7 +423,7 @@ def get_tumor_type_from_row(row, row_index, defaultCancerType, icancertype, canc
         cancertype = cancerTypeMap[sample]
     if cancertype == "":
         log.info(
-            "Cancer type for the sample should be defined for a more accurate result\nline %s: %s\n" % (row_index, row))
+            "Cancer type for the sample should be defined for a more accurate result. \tLine %s" % (row_index))
         # continue
     return cancertype
 
@@ -483,7 +490,7 @@ def processalterationevents(eventfile, outfile, previousoutfile, defaultCancerTy
     if os.path.isfile(previousoutfile):
         cacheannotated(previousoutfile, defaultCancerType, cancerTypeMap)
     outf = open(outfile, 'w+', 1000)
-    with open(eventfile, 'rU') as infile:
+    with open(eventfile, DEFAULT_READ_FILE_MODE) as infile:
         reader = csv.reader(infile, delimiter='\t')
 
         headers = readheaders(reader)
@@ -791,7 +798,7 @@ def process_fusion(svdata, outfile, previousoutfile, defaultCancerType, cancerTy
     if os.path.isfile(previousoutfile):
         cacheannotated(previousoutfile, defaultCancerType, cancerTypeMap)
     outf = open(outfile, 'w+')
-    with open(svdata, 'rU') as infile:
+    with open(svdata, DEFAULT_READ_FILE_MODE) as infile:
         reader = csv.reader(infile, delimiter='\t')
 
         headers = readheaders(reader)
@@ -861,7 +868,7 @@ def process_sv(svdata, outfile, previousoutfile, defaultCancerType, cancerTypeMa
     if os.path.isfile(previousoutfile):
         cacheannotated(previousoutfile, defaultCancerType, cancerTypeMap)
     outf = open(outfile, 'w+')
-    with open(svdata, 'rU') as infile:
+    with open(svdata, DEFAULT_READ_FILE_MODE) as infile:
         reader = csv.reader(infile, delimiter='\t')
 
         headers = readheaders(reader)
@@ -945,7 +952,7 @@ def get_cna(cell_value, annotate_gain_loss=False):
 
 
 def process_gistic_data(outf, gistic_data_file, defaultCancerType, cancerTypeMap, annotate_gain_loss):
-    with open(gistic_data_file, 'rU') as infile:
+    with open(gistic_data_file, DEFAULT_READ_FILE_MODE) as infile:
         reader = csv.reader(infile, delimiter='\t')
         headers = readheaders(reader)
         samples = []
@@ -1000,7 +1007,7 @@ def process_gistic_data(outf, gistic_data_file, defaultCancerType, cancerTypeMap
 
 
 def process_individual_cna_file(outf, cna_data_file, defaultCancerType, cancerTypeMap, annotate_gain_loss):
-    with open(cna_data_file, 'rU') as infile:
+    with open(cna_data_file, DEFAULT_READ_FILE_MODE) as infile:
         reader = csv.reader(infile, delimiter='\t')
         headers = readheaders(reader)
         row_headers = headers['^-$'].split('\t') + get_oncokb_annotation_column_headers()
@@ -1112,7 +1119,7 @@ def process_clinical_data(annotatedmutfiles, clinicalfile, outfile):
     sample_tx_resistance_count = {}
     samplealterationcount = {}
     for annotatedmutfile in annotatedmutfiles:
-        with open(annotatedmutfile, 'rU') as mutfile:
+        with open(annotatedmutfile, DEFAULT_READ_FILE_MODE) as mutfile:
             reader = csv.reader(mutfile, delimiter='\t')
             headers = readheaders(reader)
 
@@ -1232,7 +1239,7 @@ def process_clinical_data(annotatedmutfiles, clinicalfile, outfile):
     outf = open(outfile, 'w+')
 
     # export to anntoated file
-    with open(clinicalfile, 'rU') as clinfile:
+    with open(clinicalfile, DEFAULT_READ_FILE_MODE) as clinfile:
         reader = csv.reader(clinfile, delimiter='\t')
         headers = readheaders(reader)
         outf.write(headers['^-$'])
@@ -1346,7 +1353,7 @@ def process_clinical_data(annotatedmutfiles, clinicalfile, outfile):
 
 
 def cacheannotated(annotatedfile, defaultCancerType, cancerTypeMap):
-    with open(annotatedfile, 'rU') as infile:
+    with open(annotatedfile, DEFAULT_READ_FILE_MODE) as infile:
         try:
             reader = csv.reader(infile, delimiter='\t')
             headers = readheaders(reader)
@@ -1454,6 +1461,9 @@ def __init__(self, hugo, hgvs, cancertype, reference_genome=None, consequence=No
         if reference_genome is not None:
             self.referenceGenome = reference_genome.value
 
+    def __repr__(self):
+        return ",".join([self.gene.hugoSymbol, self.alteration, self.tumorType, self.consequence, self.proteinStart, self.proteinEnd, self.referenceGenome])
+
 
 class HGVSgQuery:
     def __init__(self, hgvsg, cancertype, reference_genome=None):
@@ -1462,6 +1472,9 @@ def __init__(self, hgvsg, cancertype, reference_genome=None):
         if reference_genome is not None:
             self.referenceGenome = reference_genome.value
 
+    def __repr__(self):
+        return ",".join([self.hgvsg, self.tumorType, self.referenceGenome])
+
 
 def gettumortypename(tumortype):
     if 'code' in tumortype and tumortype['code'] is not None and tumortype['code'] != '':
@@ -1496,15 +1509,18 @@ def __init__(self, chromosome, start, end, ref_allele, var_allele, cancertype, r
         if reference_genome is not None:
             self.referenceGenome = reference_genome.value
 
+    def __repr__(self):
+        return " ".join([self.genomicLocation, self.tumorType, self.referenceGenome])
+
 
 class CNAQuery:
     def __init__(self, hugo, cnatype, cancertype):
         self.gene = Gene(hugo)
         self.copyNameAlterationType = cnatype.upper()
         self.tumorType = cancertype
 
-    def __str__(self):
-        return "\t".join([self.gene.hugoSymbol, self.copyNameAlterationType, self.tumorType])
+    def __repr__(self):
+        return ",".join([self.gene.hugoSymbol, self.copyNameAlterationType, self.tumorType])
 
 
 class StructuralVariantQuery:
@@ -1521,8 +1537,8 @@ def __init__(self, hugoA, hugoB, structural_variant_type, cancertype):
         self.structuralVariantType = structural_variant_type.upper()
         self.tumorType = cancertype
 
-    def __str__(self):
-        return "\t".join(
+    def __repr__(self):
+        return ",".join(
             [self.geneA.hugoSymbol, self.geneB.hugoSymbol, str(self.functionalFusion), self.structuralVariantType,
              self.tumorType])
 
@@ -1831,7 +1847,7 @@ def gettreatments(evidence):
 
 
 def readCancerTypes(clinicalFile, data):
-    with open(clinicalFile, 'rU') as infile:
+    with open(clinicalFile, DEFAULT_READ_FILE_MODE) as infile:
         reader = csv.reader(infile, delimiter='\t')
         headers = readheaders(reader)
 

example.sh

@@ -28,8 +28,6 @@ OICNA="data/example_individual_cna.oncokb.txt"
 IC="data/example_clinical.txt"
 OC="data/example_clinical.oncokb.txt"
 
-OCPDF="data/example_clinical.oncokb.pdf"
-
 TOKEN="" #OncoKB API Token
 README="data/example_README.txt"
 

requirements/pip2.7.txt

@@ -1,3 +1,2 @@
-matplotlib==2.2.4
 enum34==1.1.10
 kiwisolver==1.1.0

requirements/pip3.txt

@@ -1,2 +1 @@
-matplotlib==3.1.2
 kiwisolver==1.2.0