From 70c507793d8ae3bbca611c8341a352001b0d55ec Mon Sep 17 00:00:00 2001
From: Daniel Munro <danbmunro@gmail.com>
Date: Thu, 5 Sep 2024 13:55:14 -0700
Subject: [PATCH] Bug fixes

---
 Pheast/environment.yml | 15 ++++++++-------
 Pheast/steps/setup.smk |  2 +-
 README.md              |  2 +-
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/Pheast/environment.yml b/Pheast/environment.yml
index 3898ab8..ca99ecd 100644
--- a/Pheast/environment.yml
+++ b/Pheast/environment.yml
@@ -4,18 +4,19 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconductor-impute
-  - bioconductor-qvalue
-  - bioconductor-variantannotation
-  - dask<2024.2
+  - bioconductor-impute  # for covariates
+  - bioconductor-qvalue  # for tensorqtl
+  - bioconductor-variantannotation  # for covariates
+  - dask<2024.2  # for tensorqtl (pandas-plink)
+  - gcta  # for heritability
   - pandas
-  - pandas-plink
+  - pandas-plink  # for tensorqtl
   - pip
   - plink
   - plink2=2
-  - r-glmnet
+  - r-glmnet  # for FUSION
   - r-optparse
-  - rpy2
+  - rpy2  # for tensorqtl
   - snakemake
   - pip:
     - tensorqtl
diff --git a/Pheast/steps/setup.smk b/Pheast/steps/setup.smk
index 9fa710f..74e3ca0 100644
--- a/Pheast/steps/setup.smk
+++ b/Pheast/steps/setup.smk
@@ -49,7 +49,7 @@ geno_prefix = config['geno_prefix']
 # samples_file = Path(config['samples_file'])
 # samples = pd.read_csv(samples_file, sep='\t', header=None)[0].tolist()
 samples = config['samples']
-geno_samples = pd.read_csv(geno_prefix + '.fam', sep='\t', header=None)[1].tolist()
+geno_samples = pd.read_csv(geno_prefix + '.fam', sep=r'\s+', header=None)[1].tolist()
 missing_samples = [s for s in samples if s not in geno_samples]
 if len(missing_samples) > 0:
     raise Exception(f'Samples missing from genotypes: {missing_samples}')
diff --git a/README.md b/README.md
index 68b99ae..7e2de23 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # Pantry
 
-Pantry (PAN-TRanscriptome phenotYping) is a framework for generating multimodal transcriptomic phenotypes from RNA-Seq and applying them to genetic analyses. The goal is to make genetic analyses as easy to perform with a multitude of transcriptomic phenotype modalities as it is with gene expression alone.
+Pantry (PAN-TRanscriptomic phenotYping) is a framework for generating multimodal transcriptomic phenotypes from RNA-Seq and applying them to genetic analyses. The goal is to make genetic analyses as easy to perform with a multitude of transcriptomic phenotype modalities as it is with gene expression alone.
 
 **Contact us** if you have a method for an additional modality that you would like to add to Pantry. Your collaboration will result in authorship on a subsequent Pantry publication, and Pantry users will be instructed to cite your original study every time they use the results in a publication.