add script to export environments

.github/workflows/export_envs.py

@@ -0,0 +1,51 @@
+import os
+import re
+from pathlib import Path
+from functools import reduce
+from operator import concat
+import yaml
+import pandas as pd
+import numpy as np
+
+class IndentDumper(yaml.Dumper):
+    def increase_indent(self, flow=False, indentless=False):
+        return super(IndentDumper, self).increase_indent(flow, False)
+
+container_table = pd.read_csv("../../container/containers.csv")
+container_table_universal = container_table[(container_table.Environment == "universal")]
+container_table_envs = container_table[(container_table.Environment != "universal")]
+
+# Hard code channels in the correct order
+channels = ["dnachun", "conda-forge", "bioconda", "nodefaults"]
+
+environment_list = [re.sub(r'\s+', "", env).split(",") for env in container_table_envs.Environment]
+environments = list(np.unique(reduce(concat, environment_list, [])))
+
+package_dict = {package: version for package, version in zip(container_table_envs.Package, container_table_envs.Version)}
+environment_dict = {package: environment for package, environment in zip(container_table_envs.Package, container_table_envs.Environment)}
+environment_package_dict = {environment: {} for environment in environments}
+for environment in environments:
+    for package in sorted(environment_dict.keys()):
+        if environment in environment_dict[package]:
+            environment_package_dict[environment][package] = package_dict[package]
+for environment in environment_package_dict.keys():
+    if environment != "dapars2":
+        universal_packages = sorted(set(container_table_universal.Package) - set(environment_package_dict[environment].keys()))
+        for package in universal_packages:
+            environment_package_dict[environment][package] = np.nan
+
+yaml_dict = {environment: {"name": str(environment), "channels": channels, "dependencies": []} for environment in environment_package_dict.keys()}
+for environment in yaml_dict.keys():
+    for package in environment_package_dict[environment].keys():
+        version = environment_package_dict[environment][package]
+        if pd.notna(version):
+            yaml_dict[environment]["dependencies"].append(f"{package}={version}")
+        else:
+            yaml_dict[environment]["dependencies"].append(package)
+
+for environment in yaml_dict.keys():
+    yml_file = f"../../container/{environment}/{environment}.yml"
+    yml_path = Path(yml_file)
+    yml_path.parent.mkdir(parents=True, exist_ok=True)
+    with open(yml_file, 'w') as file_handle:
+        yaml.dump(yaml_dict[environment], file_handle, sort_keys = False, Dumper=IndentDumper)

container/apex/apex.yml

@@ -6,24 +6,24 @@ channels:
   - nodefaults
 dependencies:
   - apex=0.2-alpha
-  - htslib
   - bcftools=1.17
-  - seaborn
-  - bash_kernel
-  - r-tidyverse
-  - ptpython
+  - htslib
   - altair
-  - matplotlib
-  - rpy2
+  - bash_kernel
   - formulaic
-  - scipy
+  - ipykernel
+  - jupyterlab
+  - matplotlib
   - numpy
+  - openpyxl
+  - pandas
+  - plotnine
+  - ptpython
   - pytables
   - r-irkernel
-  - statsmodels
-  - plotnine
-  - jupyterlab
-  - ipykernel
+  - r-tidyverse
+  - rpy2
   - scikit-learn
-  - openpyxl
-  - pandas
+  - scipy
+  - seaborn
+  - statsmodels

container/bioinfo/bioinfo.yml

@@ -5,31 +5,31 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - htslib
+  - bcftools=1.17
   - gcta=1.94.1
+  - htslib
+  - plink=1.90b6.21
   - plink2=2.00a3.7
   - qtl=0.1.8
+  - r-igraph=1.5.1
   - snpeff=5.1
   - snpsift=5.1
-  - bcftools=1.17
-  - r-igraph=1.5.1
-  - plink=1.90b6.21
-  - seaborn
-  - bash_kernel
-  - r-tidyverse
-  - ptpython
   - altair
-  - matplotlib
-  - rpy2
+  - bash_kernel
   - formulaic
-  - scipy
+  - ipykernel
+  - jupyterlab
+  - matplotlib
   - numpy
+  - openpyxl
+  - pandas
+  - plotnine
+  - ptpython
   - pytables
   - r-irkernel
-  - statsmodels
-  - plotnine
-  - jupyterlab
-  - ipykernel
+  - r-tidyverse
+  - rpy2
   - scikit-learn
-  - openpyxl
-  - pandas
+  - scipy
+  - seaborn
+  - statsmodels

container/fastenloc/fastenloc.yml

@@ -8,24 +8,24 @@ dependencies:
   - bcftools=1.17
   - dap-g=1.0.0
   - fastenloc=2
-  - torus=1
   - r-susier=0.12.35
-  - seaborn
-  - bash_kernel
-  - r-tidyverse
-  - ptpython
+  - torus=1
   - altair
-  - matplotlib
-  - rpy2
+  - bash_kernel
   - formulaic
-  - scipy
+  - ipykernel
+  - jupyterlab
+  - matplotlib
   - numpy
+  - openpyxl
+  - pandas
+  - plotnine
+  - ptpython
   - pytables
   - r-irkernel
-  - statsmodels
-  - plotnine
-  - jupyterlab
-  - ipykernel
+  - r-tidyverse
+  - rpy2
   - scikit-learn
-  - openpyxl
-  - pandas
+  - scipy
+  - seaborn
+  - statsmodels

container/flashpcar/flashpcar.yml

@@ -5,26 +5,26 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
+  - r-flashpcar=2.1
   - r-gridextra=2.3
   - r-matrixstats=1.0.0
-  - r-flashpcar=2.1
   - r-rlang=1.1.1
-  - seaborn
-  - bash_kernel
-  - r-tidyverse
-  - ptpython
   - altair
-  - matplotlib
-  - rpy2
+  - bash_kernel
   - formulaic
-  - scipy
+  - ipykernel
+  - jupyterlab
+  - matplotlib
   - numpy
+  - openpyxl
+  - pandas
+  - plotnine
+  - ptpython
   - pytables
   - r-irkernel
-  - statsmodels
-  - plotnine
-  - jupyterlab
-  - ipykernel
+  - r-tidyverse
+  - rpy2
   - scikit-learn
-  - openpyxl
-  - pandas
+  - scipy
+  - seaborn
+  - statsmodels

container/leafcutter/leafcutter.yml

@@ -5,25 +5,25 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - samtools=1.17
   - r-leafcutter=0.2.9
   - regtools=1.0.0
-  - seaborn
-  - bash_kernel
-  - r-tidyverse
-  - ptpython
+  - samtools=1.17
   - altair
-  - matplotlib
-  - rpy2
+  - bash_kernel
   - formulaic
-  - scipy
+  - ipykernel
+  - jupyterlab
+  - matplotlib
   - numpy
+  - openpyxl
+  - pandas
+  - plotnine
+  - ptpython
   - pytables
   - r-irkernel
-  - statsmodels
-  - plotnine
-  - jupyterlab
-  - ipykernel
+  - r-tidyverse
+  - rpy2
   - scikit-learn
-  - openpyxl
-  - pandas
+  - scipy
+  - seaborn
+  - statsmodels

container/metal/metal.yml

@@ -6,22 +6,22 @@ channels:
   - nodefaults
 dependencies:
   - metal=2020_05_05
-  - seaborn
-  - bash_kernel
-  - r-tidyverse
-  - ptpython
   - altair
-  - matplotlib
-  - rpy2
+  - bash_kernel
   - formulaic
-  - scipy
+  - ipykernel
+  - jupyterlab
+  - matplotlib
   - numpy
+  - openpyxl
+  - pandas
+  - plotnine
+  - ptpython
   - pytables
   - r-irkernel
-  - statsmodels
-  - plotnine
-  - jupyterlab
-  - ipykernel
+  - r-tidyverse
+  - rpy2
   - scikit-learn
-  - openpyxl
-  - pandas
+  - scipy
+  - seaborn
+  - statsmodels

container/methylation/methylation.yml

@@ -5,32 +5,32 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - htslib
-  - r-data.table=1.14.8
-  - r-glmnet=4.1
   - bioconductor-illuminahumanmethylation450kmanifest=0.4.0
   - bioconductor-illuminahumanmethylationepicmanifest=0.3.0
   - bioconductor-limma=3.56.2
   - bioconductor-minfi=1.46.0
   - bioconductor-preprocesscore=1.62.1
   - bioconductor-sesame=1.18.4
   - bioconductor-sesamedata=1.18.0
-  - seaborn
-  - bash_kernel
-  - r-tidyverse
-  - ptpython
+  - htslib
+  - r-data.table=1.14.8
+  - r-glmnet=4.1
   - altair
-  - matplotlib
-  - rpy2
+  - bash_kernel
   - formulaic
-  - scipy
+  - ipykernel
+  - jupyterlab
+  - matplotlib
   - numpy
+  - openpyxl
+  - pandas
+  - plotnine
+  - ptpython
   - pytables
   - r-irkernel
-  - statsmodels
-  - plotnine
-  - jupyterlab
-  - ipykernel
+  - r-tidyverse
+  - rpy2
   - scikit-learn
-  - openpyxl
-  - pandas
+  - scipy
+  - seaborn
+  - statsmodels

container/pcatools/pcatools.yml

@@ -5,27 +5,27 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - htslib
   - bcftools=1.17
   - bioconductor-biocsingular=1.16.0
   - bioconductor-pcatools=2.12.0
+  - htslib
   - r-rmtstat=0.3.1
-  - seaborn
-  - bash_kernel
-  - r-tidyverse
-  - ptpython
   - altair
-  - matplotlib
-  - rpy2
+  - bash_kernel
   - formulaic
-  - scipy
+  - ipykernel
+  - jupyterlab
+  - matplotlib
   - numpy
+  - openpyxl
+  - pandas
+  - plotnine
+  - ptpython
   - pytables
   - r-irkernel
-  - statsmodels
-  - plotnine
-  - jupyterlab
-  - ipykernel
+  - r-tidyverse
+  - rpy2
   - scikit-learn
-  - openpyxl
-  - pandas
+  - scipy
+  - seaborn
+  - statsmodels