greenelab · ajlee21 · Jul 9, 2020 · Jun 30, 2020 · Jun 30, 2020 · Jul 1, 2020
diff --git a/.github/workflows/tests.yaml b/.github/workflows/tests.yaml
@@ -1,10 +1,10 @@
-name: Test analysis notebooks
+name: Test simulations
 
 on: [push, pull_request]
 
 jobs:
   run-analysis:
-    name: Test analysis notebooks
+    name: Test simulation notebooks
     runs-on: ubuntu-latest
 
     steps:
@@ -20,16 +20,13 @@ jobs:
         run: |
           # $CONDA is an environment variable pointing to the root of the miniconda directory
           $CONDA/bin/conda env update --file environment.yml --name base
-          $CONDA/bin/pip install .
+          $CONDA/bin/pip install -e .
           $CONDA/bin/pip install pytest
           $CONDA/bin/pip install nbval
 
-      - name: Run analysis notebooks
+      - name: Run simulation notebooks
         run: |
-          export R_HOME=`$CONDA/bin/R RHOME`
-          $CONDA/bin/pytest -v --nbval-lax --current-env Pseudomonas_tests/Pseudomonas_sample_limma.ipynb
-          $CONDA/bin/pytest -v --nbval-lax --current-env Pseudomonas_tests/Pseudomonas_sample_combat.ipynb
-          $CONDA/bin/pytest -v --nbval-lax --current-env Pseudomonas_tests/Pseudomonas_experiment_limma.ipynb
-          $CONDA/bin/pytest -v --nbval-lax --current-env Human_tests/Human_sample_limma.ipynb
-          $CONDA/bin/pytest -v --nbval-lax --current-env Human_tests/Human_experiment_limma.ipynb
-
+          $CONDA/bin/pytest -v --nbval-lax --current-env human_tests/Human_random_sampling_simulation.ipynb
+          $CONDA/bin/pytest -v --nbval-lax --current-env human_tests/Human_latent_transform_simulation.ipynb
+          $CONDA/bin/pytest -v --nbval-lax --current-env human_tests/Human_template_simulation.ipynb
+
diff --git a/Human_tests/Human_experiment_limma.ipynb b/Human_tests/Human_experiment_limma.ipynb
diff --git a/Human_tests/Human_sample_limma.ipynb b/Human_tests/Human_sample_limma.ipynb
diff --git a/Pseudomonas_tests/Pseudomonas_experiment_limma.ipynb b/Pseudomonas_tests/Pseudomonas_experiment_limma.ipynb
diff --git a/Pseudomonas_tests/Pseudomonas_sample_combat.ipynb b/Pseudomonas_tests/Pseudomonas_sample_combat.ipynb
diff --git a/Pseudomonas_tests/Pseudomonas_sample_limma.ipynb b/Pseudomonas_tests/Pseudomonas_sample_limma.ipynb
diff --git a/Pseudomonas_tests/data/input/train_set_normalized_test.tsv b/Pseudomonas_tests/data/input/train_set_normalized_test.tsv
diff --git a/Pseudomonas_tests/data/metadata/experiment_ids.txt b/Pseudomonas_tests/data/metadata/experiment_ids.txt
diff --git a/Pseudomonas_tests/data/metadata/sample_annotations.tsv b/Pseudomonas_tests/data/metadata/sample_annotations.tsv
diff --git a/README.md b/README.md
@@ -16,6 +16,31 @@ pip install ponyo
 ```
 
 ## How to use
-This method has been used in [simulate-expression-compendia repo](https://github.com/greenelab/simulate-expression-compendia)
-
-Example analysis notebooks using ponyo can be found in [Human_tests](Human_tests/) and [Pseudomonas_tests](Pseudomonas_tests/). 
+Example notebooks using ponyo on test data can be found in [human_tests](https://github.com/greenelab/ponyo/tree/master/human_tests)
+
+Additionally, this method has been used in [simulate-expression-compendia](https://github.com/greenelab/simulate-expression-compendia) repository.
+
+## Configuration file
+
+The tables lists the core parameters required to generate simulated data using modules from [ponyo](https://github.com/greenelab/ponyo). Those marked with * indicate those parameters that will vary depending on the type of approach .
+
+| Name | Description |
+| :--- | :---------- |
+| local_dir| str: Parent directory on local machine to store intermediate results|
+| scaler_transform_file| str: File to store mapping from normalized to raw gene expression range|
+| dataset_name| str: Name for analysis directory containing notebooks using ponyo|
+| simulation_type | str: Name of simulation approach directory to store results locally|
+| NN_architecture | str: Name of neural network architecture to use. Format 'NN_<intermediate layer>_<latent layer>'|
+| learning_rate| float: Step size used for gradient descent. In other words, it's how quickly the  methods is learning|
+| batch_size | str: Training is performed in batches. So this determines the number of samples to consider at a given time|
+| epochs | int: Number of times to train over the entire input dataset|
+| kappa | float: How fast to linearly ramp up KL loss|
+| intermediate_dim| int: Size of the hidden layer|
+| latent_dim | int: Size of the bottleneck layer|
+| epsilon_std | float: Standard deviation of Normal distribution to sample latent space|
+| validation_frac | float: Fraction of input samples to use to validate for VAE training|
+| num_simulated_samples* | int: If using random sampling approach, simulate a compendia with these many samples|
+| num_simulated_experiments*| int: If using latent-transformation approach, simulate a compendia with these many experiments|
+| num_simulated*| int: If using template-based approach, simulate these many experiments|
+| project_id*| int: If using template-based approach, experiment id to use as template experiment|
+| metadata_colname | str: Column header that contains sample id that maps expression data and metadata|
diff --git a/configs/config_test_Pa_experiment_limma.tsv b/configs/config_test_Pa_experiment_limma.tsv
diff --git a/configs/config_test_Pa_sample_combat.tsv b/configs/config_test_Pa_sample_combat.tsv
diff --git a/configs/config_test_Pa_sample_limma.tsv b/configs/config_test_Pa_sample_limma.tsv
diff --git a/configs/config_test_human_experiment_limma.tsv b/configs/config_test_human_experiment_limma.tsv
diff --git a/configs/config_test_human_sample_limma.tsv b/configs/config_test_human_sample_limma.tsv
diff --git a/environment.yml b/environment.yml
@@ -1,12 +1,7 @@
-name: simulate_expression_compendia
+name: test_ponyo
 channels:
 - conda-forge
-- r
-- bioconda
 dependencies:
-- r::r-base=3.6.0
-- bioconda::bioconductor-limma
-- bioconda::bioconductor-sva
 - conda-forge::python=3.7
 - conda-forge::keras
 - conda-forge::tensorflow=1
@@ -21,6 +16,7 @@ dependencies:
 - conda-forge::ipykernel=5.1.1
 - conda-forge::nb_conda_kernels
 - conda-forge::gxx_linux-64
+- conda-forge::rpy2
 - conda-forge::libiconv=1.15
 - conda-forge::joblib=0.13.2
 - anaconda::protobuf
@@ -29,5 +25,4 @@ dependencies:
   - torch>=0.4.0
   - matplotlib==3.0.0
   - pillow
-  - requests
-  - rpy2
+  - requests