set up repo for better management of OSF downloads

.gitignore

@@ -1,3 +1,15 @@
+# downloaded data
+data/dataset_2_submissions
+data/dataset_1_submissions
+data/dataset_2_ground_truth
+
+# data for testing and resulting outputs
+tests/data/Ground_truth
+tests/data/dataset_2_submissions/
+tests/data/unprocessed_dataset_2_submissions/submission_x/
+tests/results/
+
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

README.md

@@ -1,7 +1,7 @@
 <h1 align='center'>Cryo-EM Heterogeneity Challenge</h1>
 
 <p align="center">
-        
+
 <img alt="Supported Python versions" src="https://img.shields.io/badge/Supported_Python_Versions-3.8_%7C_3.9_%7C_3.10_%7C_3.11-blue">
 <img alt="GitHub Downloads (all assets, all releases)" src="https://img.shields.io/github/downloads/flatironinstitute/Cryo-EM-Heterogeneity-Challenge-1/total">
 <img alt="GitHub branch check runs" src="https://img.shields.io/github/check-runs/flatironinstitute/Cryo-EM-Heterogeneity-Challenge-1/main">
@@ -10,13 +10,13 @@
 </p>
 
 <p align="center">
-        
+
 <img alt="Cryo-EM Heterogeneity Challenge" src="https://simonsfoundation.imgix.net/wp-content/uploads/2023/05/15134456/Screenshot-2023-05-15-at-1.39.07-PM.png?auto=format&q=90">
 
 </p>
 
 
-        
+
 This repository contains the code used to analyse the submissions for the [Inaugural Flatiron Cryo-EM Heterogeneity Challenge](https://www.simonsfoundation.org/flatiron/center-for-computational-biology/structural-and-molecular-biophysics-collaboration/heterogeneity-in-cryo-electron-microscopy/).
 
 # Scope
@@ -26,13 +26,13 @@ This repository explains how to preprocess a submission (80 maps and correspondi
 This is a work in progress, while the code will probably not change, we are still writting better tutorials, documentation, and other ideas for analyzing the data. We are also in the process of making it easier for other people to contribute with their own metrics and methods. We are also in the process of distributing the code to PyPi.
 
 # Accesing the data
-The data is available via the Open Science Foundation project [The Inaugural Flatiron Institute Cryo-EM Heterogeneity Community Challenge](https://osf.io/8h6fz/). You can download via a web browser, or programatically with wget as per [this script](https://github.com/flatironinstitute/Cryo-EM-Heterogeneity-Challenge-1/blob/main/tests/scripts/fetch_test_data.sh).
+The data is available via the Open Science Foundation project [The Inaugural Flatiron Institute Cryo-EM Heterogeneity Community Challenge](https://osf.io/8h6fz/). You can download via a web browser, or programatically with wget as per [this script](https://github.com/flatironinstitute/Cryo-EM-Heterogeneity-Challenge-1/blob/main/data/fetch_data.sh).
 
 **_NOTE_**: We recommend downloadaing the data with the script and wget as the downloads from the web browser might be unstable.
 
 # Installation
 
-## Stable installation 
+## Stable installation
 Installing this repository is simply. We recommend creating a virtual environment (using conda or pyenv), since we have dependencies such as PyTorch or Aspire, which are better dealt with in an isolated environment. After creating your environment, make sure to activate it and run
 
 ```bash
@@ -63,7 +63,7 @@ pytest tests/test_distribution_to_distribution.py
 If you want to run our code on the full challenge data, or you own local data, please complete the following steps
 
 ### 1. Download the full challenge data from [The Inaugural Flatiron Institute Cryo-EM Heterogeneity Community Challenge](https://osf.io/8h6fz/)
-You can do this through the web browser, or programatically with wget (you can get inspiration from [this script](https://github.com/flatironinstitute/Cryo-EM-Heterogeneity-Challenge-1/blob/main/tests/scripts/fetch_test_data.sh), which is just for the test data, not the full datasets)
+You can do this through the web browser, or programatically with wget (you can use [this script](https://github.com/flatironinstitute/Cryo-EM-Heterogeneity-Challenge-1/blob/main/data/fetch_data.sh, this will download around 220 GB of data)
 
 ### 2. Modify the config files and run the commands on the full challenge data
 Point to the path where the data is locally

data/fetch_data.sh

@@ -0,0 +1,21 @@
+mkdir -p data/dataset_2_submissions data/dataset_1_submissions data/dataset_2_ground_truth
+
+# dataset 1 submissions
+for i in {0..10}
+do
+    wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/dataset_1_submissions/submission_${i}.pt?download=true -O data/dataset_1_submissions/submission_${i}.pt
+done
+
+# dataset 2 submissions
+for i in {0..11}
+do
+    wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/dataset_2_submissions/submission_${i}.pt?download=true -O data/dataset_2_submissions/submission_${i}.pt
+done
+
+# ground truth
+
+wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/Ground_truth/maps_gt_flat.pt?download=true -O data/dataset_2_ground_truth/maps_gt_flat.pt
+
+wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/Ground_truth/metadata.csv?download=true -O data/dataset_2_ground_truth/metadata.csv
+
+wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/Ground_truth/mask_dilated_wide_224x224.mrc?download=true -O data/dataset_2_ground_truth/mask_dilated_wide_224x224.mrc

src/cryo_challenge/_preprocessing/preprocessing_pipeline.py

@@ -124,7 +124,10 @@ def preprocess_submissions(submission_dataset, config):
         print(f"   submission saved as submission_{idx}.pt")
         print(f"Preprocessing submission {idx} complete")
 
-    with open("hash_table.json", "w") as f:
+    hash_table_path = os.path.join(
+        config["output_path"], "submission_to_icecream_table.json"
+    )
+    with open(hash_table_path, "w") as f:
         json.dump(hash_table, f, indent=4)
 
     return

tests/config_files/test_config_distribution_to_distribution.yaml

@@ -9,4 +9,4 @@ cvxpy_solver: ECOS
 optimal_q_kl:
   n_iter: 100000
   break_atol: 0.0001
-output_fname: results/test_distribution_to_distribution_submission_0.pkl
+output_fname: tests/results/test_distribution_to_distribution_submission_0.pkl

tests/config_files/test_config_map_to_map.yaml

@@ -1,17 +1,17 @@
 data:
   n_pix: 224
-  psize: 2.146 
+  psize: 2.146
   submission:
     fname: tests/data/dataset_2_submissions/test_submission_0_n8.pt
     volume_key: volumes
     metadata_key: populations
     label_key: id
   ground_truth:
-    volumes: tests/data/Ground_truth/test_maps_gt_flat_10.pt 
-    metadata: tests/data/Ground_truth/test_metadata_10.csv 
-  mask: 
+    volumes: tests/data/Ground_truth/test_maps_gt_flat_10.pt
+    metadata: tests/data/Ground_truth/test_metadata_10.csv
+  mask:
     do: true
-    volume: data/Ground_truth/mask_dilated_wide_224x224.mrc
+    volume: tests/data/Ground_truth/mask_dilated_wide_224x224.mrc
 analysis:
   metrics:
     - l2
@@ -20,4 +20,4 @@ analysis:
   normalize:
     do: true
     method: median_zscore
-output: tests/results/test_map_to_map_distance_matrix_submission_0.pkl
+output: tests/results/test_map_to_map_distance_matrix_submission_0.pkl

tests/scripts/fetch_test_data.sh

@@ -1,11 +1,11 @@
-mkdir -p tests/data/dataset_2_submissions data/dataset_2_submissions tests/results tests/data/unprocessed_dataset_2_submissions/submission_x tests/data/Ground_truth/ data/Ground_truth
+mkdir -p tests/data/dataset_2_submissions tests/data/dataset_2_submissions tests/results tests/data/unprocessed_dataset_2_submissions/submission_x tests/data/Ground_truth/ tests/data/Ground_truth
 wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/tests/dataset_2_submissions/test_submission_0_n8.pt?download=true -O tests/data/dataset_2_submissions/test_submission_0_n8.pt
 ADIR=$(pwd)
 ln -s $ADIR/tests/data/dataset_2_submissions/test_submission_0_n8.pt $ADIR/tests/data/dataset_2_submissions/submission_0.pt # symlink for svd which needs submission_0.pt for filename
 wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/tests/Ground_truth/test_maps_gt_flat_10.pt?download=true -O tests/data/Ground_truth/test_maps_gt_flat_10.pt
-wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/tests/Ground_truth/test_metadata_10.csv?download=true -O tests/data/Ground_truth/test_metadata_10.csv 
-wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/tests/Ground_truth/1.mrc?download=true -O tests/data/Ground_truth/1.mrc 
-wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/Ground_truth/mask_dilated_wide_224x224.mrc?download=true -O data/Ground_truth/mask_dilated_wide_224x224.mrc 
+wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/tests/Ground_truth/test_metadata_10.csv?download=true -O tests/data/Ground_truth/test_metadata_10.csv
+wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/tests/Ground_truth/1.mrc?download=true -O tests/data/Ground_truth/1.mrc
+wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/Ground_truth/mask_dilated_wide_224x224.mrc?download=true -O tests/data/Ground_truth/mask_dilated_wide_224x224.mrc
 for FILE in 1.mrc 2.mrc 3.mrc 4.mrc populations.txt
 do
     wget https://files.osf.io/v1/resources/8h6fz/providers/dropbox/tests/unprocessed_dataset_2_submissions/submission_x/${FILE}?download=true -O tests/data/unprocessed_dataset_2_submissions/submission_x/${FILE}