projectglow · karenfeng · Jun 23, 2020 · May 15, 2020 · May 19, 2020 · May 19, 2020
diff --git a/docs/source/_static/images/wgr_runtime.png b/docs/source/_static/images/wgr_runtime.png
diff --git a/docs/source/_static/notebooks/tertiary/glowgr.html b/docs/source/_static/notebooks/tertiary/glowgr.html
diff --git a/docs/source/etl/vcf2delta.rst b/docs/source/etl/vcf2delta.rst
@@ -1,3 +1,5 @@
+.. _vcf2delta:
+
 ============================
 Create a Genomics Delta Lake
 ============================

diff --git a/docs/source/tertiary/index.rst b/docs/source/tertiary/index.rst
@@ -13,3 +13,4 @@ Perform population-scale statistical analyses of genetic variants.
    pipe-transformer
    pandas-udf
    regression-tests
+   whole-genome-regression
diff --git a/docs/source/tertiary/regression-tests.rst b/docs/source/tertiary/regression-tests.rst
@@ -81,7 +81,7 @@ Example
      standardError=0.1783963733160434,
      pValue=0.44349953631952943
    )
-   assert_rows_equal(lin_reg_df.head(), expected_lin_reg_row)
+   assert_rows_equal(lin_reg_df.filter('contigName = 22 and start = 16050114').head(), expected_lin_reg_row)
 
 Parameters
 ----------
@@ -191,7 +191,7 @@ Example
      waldConfidenceInterval=[0.7813704896767115, 3.247273366082802],
      pValue=0.19572327843236637
    )
-   assert_rows_equal(lrt_log_reg_df.head(), expected_lrt_log_reg_row)
+   assert_rows_equal(lrt_log_reg_df.filter('contigName = 22 and start = 16050114').head(), expected_lrt_log_reg_row)
 
    expected_firth_log_reg_row = Row(
      contigName='22',
@@ -202,7 +202,7 @@ Example
      waldConfidenceInterval=[0.7719062301156017, 3.2026291934794795],
      pValue=0.20086839802280376
    )
-   assert_rows_equal(firth_log_reg_df.head(), expected_firth_log_reg_row)
+   assert_rows_equal(firth_log_reg_df.filter('contigName = 22 and start = 16050114').head(), expected_firth_log_reg_row)
 
 Parameters
 ----------

diff --git a/docs/source/tertiary/whole-genome-regression.rst b/docs/source/tertiary/whole-genome-regression.rst
diff --git a/test-data/gwas/README b/test-data/gwas/README
@@ -1,4 +1,4 @@
-The genotypes are sampled from the Thousand Genomes Project Phase 3 release chr22 VCF
+The genotypes are sampled from the Thousand Genomes Project Phase 3 release chr21 and chr22 VCFs
 (ALL.chr22.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf).
 
 The covariates and continuous phenotypes are simulated with PhenotypeSimulator

diff --git a/test-data/gwas/binary-phenotypes.csv.gz b/test-data/gwas/binary-phenotypes.csv.gz
diff --git a/test-data/gwas/continuous-phenotypes.csv.gz b/test-data/gwas/continuous-phenotypes.csv.gz
diff --git a/test-data/gwas/covariates.csv.gz b/test-data/gwas/covariates.csv.gz
diff --git a/test-data/gwas/genotypes.vcf.gz b/test-data/gwas/genotypes.vcf.gz