deploy: 33a2752

Author: rcannood

.gitignore

@@ -0,0 +1,9 @@
+resources
+work
+.nextflow*
+.idea
+.vscode
+.DS_Store
+output
+trace-*
+.ipynb_checkpoints

.nojekyll

@@ -0,0 +1,10 @@
+# task_perturbation_prediction 1.0.0
+
+Initial release of the Perturbation Prediction task. Initial components:
+
+* `src/process_dataset`: Compute the DGE data from the raw single-cell counts using Limma.
+* `src/control_methods`: Baseline control methods: sample, ground_truth, zeros, mean_across_celltypes, mean_across_compounds, mean_outcome.
+* `src/methods`: Perturbation prediction methods: jn_ap_op2, lgc_ensemble, nn_retraining_with_pseudolabels, pyboost, scape, transformer_ensemble.
+* `src/metrics`: Evaluation metrics: mean_rowwise_error, mean_rowwise_correlation.
+
+

CHANGELOG.md

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Open Problems in Single-Cell Analysis
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

LICENSE

@@ -0,0 +1,15 @@
+viash_version: 0.8.6
+
+source: src
+target: target
+
+config_mods: |
+  .functionality.version := 'dev'
+  .functionality.arguments[.multiple == true].multiple_sep := ';'
+  .platforms[.type == 'docker'].target_registry := 'ghcr.io'
+  .platforms[.type == 'docker'].target_organization := 'openproblems-bio/task_perturbation_prediction'
+  .platforms[.type == 'docker'].target_image_source := 'https://github.com/openproblems-bio/task_perturbation_prediction'
+  .platforms[.type == "nextflow"].directives.tag := "$id"
+  .platforms[.type == "nextflow"].auto.simplifyOutput := false
+  .platforms[.type == "nextflow"].config.labels := { lowmem : "memory = 20.Gb", midmem : "memory = 50.Gb", highmem : "memory = 100.Gb", lowcpu : "cpus = 5", midcpu : "cpus = 15", highcpu : "cpus = 30", lowtime : "time = 1.h", midtime : "time = 4.h", hightime : "time = 8.h", veryhightime : "time = 24.h" }
+  .platforms[.type == "nextflow"].config.script := "process.errorStrategy = 'ignore'"

README.md

@@ -0,0 +1,3 @@
+workflow {
+    print("This is a dummy placeholder for pipeline execution. Please use the corresponding nf files for running pipelines.")
+}

_viash.yaml

@@ -0,0 +1 @@
+process.container = 'nextflow/bash:latest'

main.nf

@@ -0,0 +1,42 @@
+#!/bin/bash
+
+echo "This script is not supposed to be run directly."
+echo "Please run the script step-by-step."
+exit 1
+
+# sync resources
+scripts/download_resources.sh
+
+# create a new component
+method_id="my_method"
+method_lang="python" # change this to "r" if need be
+
+viash run src/common/create_component/config.vsh.yaml -- \
+  --language "$method_lang" \
+  --name "$method_id"
+
+# TODO: fill in required fields in src/methods/foo/config.vsh.yaml
+# TODO: edit src/methods/foo/script.py/R
+
+# test the component
+viash test src/methods/$method_id/config.vsh.yaml
+
+# rebuild the container (only if you change something to the docker platform)
+# You can reduce the memory and cpu allotted to jobs in _viash.yaml by modifying .platforms[.type == "nextflow"].config.labels
+viash run src/methods/$method_id/config.vsh.yaml -- \
+  ---setup cachedbuild ---verbose
+
+# run the method (using h5ad as input)
+viash run src/methods/$method_id/config.vsh.yaml -- \
+  --de_train_h5ad "resources/neurips-2023-kaggle/2023-09-12_de_by_cell_type_train.h5ad" \
+  --id_map "resources/neurips-2023-kaggle/id_map.csv" \
+  --output "output/prediction.h5ad"
+
+# run evaluation metric
+viash run src/metrics/mean_rowwise_error/config.vsh.yaml -- \
+  --de_test_h5ad "resources/neurips-2023-kaggle/de_test.h5ad" \
+  --prediction "output/prediction.h5ad" \
+  --output "output/score.h5ad"
+
+# print score on kaggle test dataset
+python -c 'import anndata; print(anndata.read_h5ad("output/score.h5ad").uns)'

nextflow.config

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+viash ns build --parallel --setup cachedbuild