Merge pull request #28 from openproblems-bio/feature/add_migration

Feature/add migration
openproblems-bio · Dec 19, 2022 · d2ae01a · d2ae01a
2 parents cec4711 + 3f9d837
commit d2ae01a
Show file tree

Hide file tree

Showing 8 changed files with 160 additions and 45 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -0,0 +1,26 @@
+
+## website-experimental 0.1.0
+
+Initial release
+
+* Main page (hero + text)
+
+* v1 results:
+  - Per-task summary funky heatmap
+  - Per-task QC report
+  - Overall QC report
+  - Render of NBT manuscript
+
+* v2 results:
+  - Per-task metadata viewer
+  - Per-task summary funky heatmap
+  - Overall QC report (To do)
+  - Overall migration status report
+  - Ported tasks:
+    * Denoising
+    * Dimensionality reduction (some metadata missing so results are not rendered)
+    * Label projection
+
+* Team view (cards)
+
+* Documentation (proposed structure, no content yet)
diff --git a/results_v2/denoising/data/method_info.json b/results_v2/denoising/data/method_info.json
@@ -3,7 +3,7 @@
     "id": "no_denoising",
     "type": "negative_control",
     "label": "no denoising",
-    "v1_url": "/openproblems/tasks/denoising/methods/baseline.py",
+    "v1_url": "openproblems/tasks/denoising/methods/baseline.py",
     "v1_commit": "b460ecb183328c857cbbf653488f522a4034a61c",
     "v1_comp_id": "no_denoising",
     "preferred_normalization": "counts",
@@ -12,13 +12,14 @@
     "description": "negative control by copying train counts",
     "paper_doi": null,
     "code_url": null,
-    "doc_url": null
+    "doc_url": null,
+    "status": "up to date"
   },
   {
     "id": "perfect_denoising",
     "type": "positive_control",
     "label": "perfect denoising",
-    "v1_url": "/openproblems/tasks/denoising/methods/baseline.py",
+    "v1_url": "openproblems/tasks/denoising/methods/baseline.py",
     "v1_commit": "b460ecb183328c857cbbf653488f522a4034a61c",
     "v1_comp_id": "perfect_denoising",
     "preferred_normalization": "counts",
@@ -27,13 +28,14 @@
     "description": "Negative control by copying the train counts",
     "paper_doi": null,
     "code_url": null,
-    "doc_url": null
+    "doc_url": null,
+    "status": "up to date"
   },
   {
     "id": "alra",
     "type": "method",
     "label": "ALRA",
-    "v1_url": "/openproblems/tasks/denoising/methods/alra.py",
+    "v1_url": "openproblems/tasks/denoising/methods/alra.py",
     "v1_commit": "411a416150ecabce25e1f59bde422a029d0a8baa",
     "v1_comp_id": "alra",
     "preferred_normalization": "counts",
@@ -42,13 +44,14 @@
     "description": "Adaptively-thresholded Low Rank Approximation (ALRA). \n\nALRA is a method for imputation of missing values in single cell RNA-sequencing data, \ndescribed in the preprint, \"Zero-preserving imputation of scRNA-seq data using low-rank approximation\" \navailable [here](https://www.biorxiv.org/content/early/2018/08/22/397588). Given a \nscRNA-seq expression matrix, ALRA first computes its rank-k approximation using randomized SVD. \nNext, each row (gene) is thresholded by the magnitude of the most negative value of that gene. \nFinally, the matrix is rescaled.\n",
     "paper_doi": "10.1101/397588",
     "code_url": "https://github.com/KlugerLab/ALRA",
-    "doc_url": "https://github.com/KlugerLab/ALRA/blob/master/README.md"
+    "doc_url": "https://github.com/KlugerLab/ALRA/blob/master/README.md",
+    "status": "up to date"
   },
   {
     "id": "dca",
     "type": "method",
     "label": "DCA",
-    "v1_url": "/openproblems/tasks/denoising/methods/dca.py",
+    "v1_url": "openproblems/tasks/denoising/methods/dca.py",
     "v1_commit": "c2470ce02e6f196267cec1c554ba7ae389c0956a",
     "v1_comp_id": "dca",
     "preferred_normalization": "counts",
@@ -57,13 +60,14 @@
     "description": "Deep Count Autoencoder",
     "paper_doi": "10.1038/s41467-018-07931-2",
     "code_url": "https://github.com/theislab/dca",
-    "doc_url": null
+    "doc_url": null,
+    "status": "out of date (sha: aa2253779e9aa9cd178f54ac0f3b6ba521ecd59f)"
   },
   {
     "id": "knn_smoothing",
     "type": "method",
     "label": "knn_smooth",
-    "v1_url": "/openproblems/tasks/denoising/methods/knn_smoothing.py",
+    "v1_url": "openproblems/tasks/denoising/methods/knn_smoothing.py",
     "v1_commit": "bbecf4e9ad90007c2711394e7fbd8e49cbd3e4a1",
     "v1_comp_id": "knn_smoothing",
     "preferred_normalization": "counts",
@@ -72,13 +76,14 @@
     "description": "iterative K-nearest neighbor smoothing",
     "paper_doi": "10.1101/217737",
     "code_url": "https://github.com/yanailab/knn-smoothing",
-    "doc_url": null
+    "doc_url": null,
+    "status": "up to date"
   },
   {
     "id": "magic",
     "type": "method",
     "label": "magic",
-    "v1_url": "/openproblems/tasks/denoising/methods/magic.py",
+    "v1_url": "openproblems/tasks/denoising/methods/magic.py",
     "v1_commit": "2fbc2d4c8d3ff955ea948fc082635cf779b1927e",
     "v1_comp_id": "magic",
     "preferred_normalization": "counts",
@@ -87,6 +92,7 @@
     "description": "MAGIC: Markov affinity-based graph imputation of cells",
     "paper_doi": "10.1016/j.cell.2018.05.061",
     "code_url": "https://github.com/KrishnaswamyLab/MAGIC",
-    "doc_url": null
+    "doc_url": null,
+    "status": "out of date (sha: 2af9a4918ed3370859f71774558068961f6d22c6)"
   }
-]
+]
diff --git a/results_v2/denoising/data/metric_info.json b/results_v2/denoising/data/metric_info.json
@@ -11,7 +11,8 @@
     "namespace": "denoising/metrics",
     "component_description": "Mean Squared Error.",
     "v1_url": "openproblems/tasks/denoising/metrics/mse.py",
-    "v1_commit": "f24fb718b1115ca85130a45f2e56fddb00075d22"
+    "v1_commit": "f24fb718b1115ca85130a45f2e56fddb00075d22",
+    "status": "out of date (sha: c2470ce02e6f196267cec1c554ba7ae389c0956a)"
   },
   {
     "id": "poisson",
@@ -25,6 +26,7 @@
     "namespace": "denoising/metrics",
     "component_description": "Poisson loss",
     "v1_url": "openproblems/tasks/denoising/metrics/poisson.py",
-    "v1_commit": "4524f7bbcc4ea94cfb4acf1bd7f7c93c1ba7d0c9"
+    "v1_commit": "4524f7bbcc4ea94cfb4acf1bd7f7c93c1ba7d0c9",
+    "status": "out of date (sha: 4bb8a7e04545a06c336d3d9364a1dd84fa2af1a4)"
   }
-]
+]
diff --git a/results_v2/dimensionality_reduction/data/method_info.json b/results_v2/dimensionality_reduction/data/method_info.json
@@ -8,7 +8,8 @@
     "preferred_normalization": "counts",
     "config_path": "control_methods/random_features/config.vsh.yaml",
     "namespace": "dimensionality_reduction/control_methods",
-    "description": "Negative control method which generates a random embedding "
+    "description": "Negative control method which generates a random embedding ",
+    "status": "out of date (sha: 4a0ee9b3731ff10d8cd2e584726a61b502aef613)"
   },
   {
     "id": "true_features",
@@ -19,7 +20,8 @@
     "preferred_normalization": "counts",
     "config_path": "control_methods/true_features/config.vsh.yaml",
     "namespace": "dimensionality_reduction/control_methods",
-    "description": "Positive control method which generates high-dimensional (full data) embedding"
+    "description": "Positive control method which generates high-dimensional (full data) embedding",
+    "status": "up to date"
   },
   {
     "id": "densmap",
@@ -30,7 +32,8 @@
     "preferred_normalization": "log_cpm",
     "config_path": "methods/densmap/config.vsh.yaml",
     "namespace": "dimensionality_reduction/methods",
-    "description": "density-preserving based on UMAP"
+    "description": "density-preserving based on UMAP",
+    "status": "out of date (sha: a796e02e13a43e8861b124edbb9d287f162d4a14)"
   },
   {
     "id": "neuralee",
@@ -41,7 +44,8 @@
     "preferred_normalization": "counts",
     "config_path": "methods/neuralee/config.vsh.yaml",
     "namespace": "dimensionality_reduction/methods",
-    "description": "A neural network implementation of elastic embedding implemented in the [NeuralEE package](https://neuralee.readthedocs.io/en/latest/)."
+    "description": "A neural network implementation of elastic embedding implemented in the [NeuralEE package](https://neuralee.readthedocs.io/en/latest/).",
+    "status": "up to date"
   },
   {
     "id": "pca",
@@ -52,7 +56,8 @@
     "preferred_normalization": "log_cpm",
     "config_path": "methods/pca/config.vsh.yaml",
     "namespace": "dimensionality_reduction/methods",
-    "description": "Principal component analysis"
+    "description": "Principal component analysis",
+    "status": "up to date"
   },
   {
     "id": "phate",
@@ -63,7 +68,8 @@
     "preferred_normalization": "sqrt_cpm",
     "config_path": "methods/phate/config.vsh.yaml",
     "namespace": "dimensionality_reduction/methods",
-    "description": "Potential of heat-diffusion for affinity-based transition embedding"
+    "description": "Potential of heat-diffusion for affinity-based transition embedding",
+    "status": "out of date (sha: a796e02e13a43e8861b124edbb9d287f162d4a14)"
   },
   {
     "id": "tsne",
@@ -74,7 +80,8 @@
     "preferred_normalization": "log_cpm",
     "config_path": "methods/tsne/config.vsh.yaml",
     "namespace": "dimensionality_reduction/methods",
-    "description": "t-distributed stochastic neighbor embedding"
+    "description": "t-distributed stochastic neighbor embedding",
+    "status": "out of date (sha: a796e02e13a43e8861b124edbb9d287f162d4a14)"
   },
   {
     "id": "umap",
@@ -85,6 +92,7 @@
     "preferred_normalization": "log_cpm",
     "config_path": "methods/umap/config.vsh.yaml",
     "namespace": "dimensionality_reduction/methods",
-    "description": "Uniform manifold approximation and projection"
+    "description": "Uniform manifold approximation and projection",
+    "status": "out of date (sha: a796e02e13a43e8861b124edbb9d287f162d4a14)"
   }
-]
+]
diff --git a/results_v2/dimensionality_reduction/data/metric_info.json b/results_v2/dimensionality_reduction/data/metric_info.json
@@ -11,7 +11,8 @@
     "namespace": "dimensionality_reduction/metrics",
     "component_description": "density preservation: correlation of local radius with the local radii in the original data space",
     "v1_url": "openproblems/tasks/dimensionality_reduction/metrics/density.py",
-    "v1_commit": "c2470ce02e6f196267cec1c554ba7ae389c0956a"
+    "v1_commit": "c2470ce02e6f196267cec1c554ba7ae389c0956a",
+    "status": "up to date"
   },
   {
     "id": "nn_ranking",
@@ -25,7 +26,8 @@
     "namespace": "dimensionality_reduction/metrics",
     "component_description": "A set of metrics from the pyDRMetrics package.",
     "v1_url": "openproblems/tasks/dimensionality_reduction/metrics/nn_ranking.py",
-    "v1_commit": "a796e02e13a43e8861b124edbb9d287f162d4a14"
+    "v1_commit": "a796e02e13a43e8861b124edbb9d287f162d4a14",
+    "status": "up to date"
   },
   {
     "id": "rmse",
@@ -39,7 +41,8 @@
     "namespace": "dimensionality_reduction/metrics",
     "component_description": "The root mean squared error between the full (or processed) data matrix and a list of dimensionally-reduced matrices",
     "v1_url": "openproblems/tasks/dimensionality_reduction/metrics/root_mean_square_error.py",
-    "v1_commit": "b353a462f6ea353e0fc43d0f9fcbbe621edc3a0b"
+    "v1_commit": "b353a462f6ea353e0fc43d0f9fcbbe621edc3a0b",
+    "status": "up to date"
   },
   {
     "id": "trustworthiness",
@@ -53,6 +56,7 @@
     "namespace": "dimensionality_reduction/metrics",
     "component_description": "To what extent the local structure is retained in a low-dimensional embedding in a value between 0 and 1.",
     "v1_url": "openproblems/tasks/dimensionality_reduction/metrics/trustworthiness.py",
-    "v1_commit": "c2470ce02e6f196267cec1c554ba7ae389c0956a"
+    "v1_commit": "c2470ce02e6f196267cec1c554ba7ae389c0956a",
+    "status": "up to date"
   }
-]
+]
diff --git a/results_v2/label_projection/data/method_info.json b/results_v2/label_projection/data/method_info.json
@@ -15,7 +15,8 @@
     "config_path": "methods/logistic_regression/config.vsh.yaml",
     "namespace": "label_projection/methods",
     "description": "Logistic regression method",
-    "paper_doi": null
+    "paper_doi": null,
+    "status": "out of date (sha: c2470ce02e6f196267cec1c554ba7ae389c0956a)"
   },
   {
     "id": "mlp",
@@ -33,7 +34,8 @@
     "config_path": "methods/mlp/config.vsh.yaml",
     "namespace": "label_projection/methods",
     "description": "Multilayer perceptron",
-    "paper_doi": "10.1016/0004-3702(89)90049-0"
+    "paper_doi": "10.1016/0004-3702(89)90049-0",
+    "status": "up to date"
   },
   {
     "id": "knn",
@@ -51,7 +53,8 @@
     "config_path": "methods/knn/config.vsh.yaml",
     "namespace": "label_projection/methods",
     "description": "K-Nearest Neighbors classifier",
-    "paper_doi": "10.1109/TIT.1967.1053964"
+    "paper_doi": "10.1109/TIT.1967.1053964",
+    "status": "out of date (sha: c2470ce02e6f196267cec1c554ba7ae389c0956a)"
   },
   {
     "id": "scanvi",
@@ -69,7 +72,8 @@
     "config_path": "methods/scanvi/config.vsh.yaml",
     "namespace": "label_projection/methods",
     "description": "Probabilistic harmonization and annotation of single-cell \ntranscriptomics data with deep generative models.\n",
-    "paper_doi": "10.1101/2020.07.16.205997"
+    "paper_doi": "10.1101/2020.07.16.205997",
+    "status": "out of date (sha: 4bb8a7e04545a06c336d3d9364a1dd84fa2af1a4)"
   },
   {
     "id": "seurat_transferdata",
@@ -87,7 +91,8 @@
     "config_path": "methods/seurat_transferdata/config.vsh.yaml",
     "namespace": "label_projection/methods",
     "description": "The Seurat v3 anchoring procedure is designed to integrate\ndiverse single-cell datasets across technologies and modalities. \n",
-    "paper_doi": "10.1101/460147"
+    "paper_doi": "10.1101/460147",
+    "status": "up to date"
   },
   {
     "id": "xgboost",
@@ -105,7 +110,8 @@
     "config_path": "methods/xgboost/config.vsh.yaml",
     "namespace": "label_projection/methods",
     "description": "XGBoost: A Scalable Tree Boosting System",
-    "paper_doi": "10.1145/2939672.2939785"
+    "paper_doi": "10.1145/2939672.2939785",
+    "status": "up to date"
   },
   {
     "id": "majority_vote",
@@ -123,7 +129,8 @@
     "config_path": "control_methods/majority_vote/config.vsh.yaml",
     "namespace": "label_projection/control_methods",
     "description": "Baseline method using majority voting",
-    "paper_doi": null
+    "paper_doi": null,
+    "status": "up to date"
   },
   {
     "id": "random_labels",
@@ -141,7 +148,8 @@
     "config_path": "control_methods/random_labels/config.vsh.yaml",
     "namespace": "label_projection/control_methods",
     "description": "Negative control method which generates random labels",
-    "paper_doi": null
+    "paper_doi": null,
+    "status": "up to date"
   },
   {
     "id": "true_labels",
@@ -159,6 +167,7 @@
     "config_path": "control_methods/true_labels/config.vsh.yaml",
     "namespace": "label_projection/control_methods",
     "description": "Positive control method by returning the true labels",
-    "paper_doi": null
+    "paper_doi": null,
+    "status": "up to date"
   }
-]
+]