Update Batch Integration results

CHANGELOG.md

@@ -2,6 +2,8 @@
 
 ## MAJOR CHANGES
 
+* Update Batch Integration task to OpenProblems v2 results (PR #324).
+
 * Migrated the result scaling from R to JavaScript to allow dynamically updating the results (PR #332).
 
 ## MINOR CHANGES

results/batch_integration/data/dataset_info.json

@@ -0,0 +1,82 @@
+[
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "openproblems_v1/immune_cells",
+    "dataset_name": "Human immune",
+    "dataset_summary": "Human immune cells dataset from the scIB benchmarks",
+    "data_reference": "luecken2022benchmarking",
+    "data_url": "https://theislab.github.io/scib-reproducibility/dataset_immune_cell_hum.html"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "openproblems_v1/pancreas",
+    "dataset_name": "Human pancreas",
+    "dataset_summary": "Human pancreas cells dataset from the scIB benchmarks",
+    "data_reference": "luecken2022benchmarking",
+    "data_url": "https://theislab.github.io/scib-reproducibility/dataset_pancreas.html"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "openproblems_v1/cengen",
+    "dataset_name": "CeNGEN",
+    "dataset_summary": "Complete Gene Expression Map of an Entire Nervous System",
+    "data_reference": "hammarlund2018cengen",
+    "data_url": "https://www.cengen.org"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "cellxgene_census/gtex_v9",
+    "dataset_name": "GTEX v9",
+    "dataset_summary": "Single-nucleus cross-tissue molecular reference maps to decipher disease gene function",
+    "data_reference": "eraslan2022singlenucleus",
+    "data_url": "https://cellxgene.cziscience.com/collections/a3ffde6c-7ad2-498a-903c-d58e732f7470"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "cellxgene_census/mouse_pancreas_atlas",
+    "dataset_name": "Mouse Pancreatic Islet Atlas",
+    "dataset_summary": "Mouse pancreatic islet scRNA-seq atlas across sexes, ages, and stress conditions including diabetes",
+    "data_reference": "hrovatin2023delineating",
+    "data_url": "https://cellxgene.cziscience.com/collections/296237e2-393d-4e31-b590-b03f74ac5070"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "cellxgene_census/hypomap",
+    "dataset_name": "HypoMap",
+    "dataset_summary": "A unified single cell gene expression atlas of the murine hypothalamus",
+    "data_reference": "steuernagel2022hypomap",
+    "data_url": "https://cellxgene.cziscience.com/collections/d86517f0-fa7e-4266-b82e-a521350d6d36"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "cellxgene_census/immune_cell_atlas",
+    "dataset_name": "Immune Cell Atlas",
+    "dataset_summary": "Cross-tissue immune cell analysis reveals tissue-specific features in humans",
+    "data_reference": "dominguez2022crosstissue",
+    "data_url": "https://cellxgene.cziscience.com/collections/62ef75e4-cbea-454e-a0ce-998ec40223d3"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "cellxgene_census/tabula_sapiens",
+    "dataset_name": "Tabula Sapiens",
+    "dataset_summary": "A multiple-organ, single-cell transcriptomic atlas of humans",
+    "data_reference": "consortium2022tabula",
+    "data_url": "https://cellxgene.cziscience.com/collections/e5f58829-1a66-40b5-a624-9046778e74f5"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "openproblems_v1/zebrafish",
+    "dataset_name": "Zebrafish embryonic cells",
+    "dataset_summary": "Single-cell mRNA sequencing of zebrafish embryonic cells.",
+    "data_reference": "wagner2018single",
+    "data_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112294"
+  },
+  {
+    "task_id": "batch_integration",
+    "dataset_id": "cellxgene_census/dkd",
+    "dataset_name": "Diabetic Kidney Disease",
+    "dataset_summary": "Multimodal single cell sequencing implicates chromatin accessibility and genetic background in diabetic kidney disease progression",
+    "data_reference": "wilson2022multimodal",
+    "data_url": "https://cellxgene.cziscience.com/collections/b3e2c6e3-9b05-4da9-8f42-da38a664b45b"
+  }
+]

results/batch_integration/data/method_info.json

@@ -0,0 +1,218 @@
+[
+  {
+    "task_id": "batch_integration",
+    "method_id": "bbknn",
+    "method_name": "BBKNN",
+    "method_summary": "BBKNN creates k nearest neighbours graph by identifying neighbours within batches, then combining and processing them with UMAP for visualization.",
+    "is_baseline": false,
+    "paper_reference": "polanski2020bbknn",
+    "code_url": "https://github.com/Teichlab/bbknn",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/bbknn/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "combat",
+    "method_name": "Combat",
+    "method_summary": "Adjusting batch effects in microarray expression data using empirical Bayes methods",
+    "is_baseline": false,
+    "paper_reference": "hansen2012removing",
+    "code_url": "https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.combat.html",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/combat/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "fastmnn_embedding",
+    "method_name": "fastMnn (embedding)",
+    "method_summary": "A simpler version of the original mnnCorrect algorithm.",
+    "is_baseline": false,
+    "paper_reference": "haghverdi2018batch",
+    "code_url": "https://code.bioconductor.org/browse/batchelor/",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/fastmnn_embedding/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "fastmnn_feature",
+    "method_name": "fastMnn (feature)",
+    "method_summary": "A simpler version of the original mnnCorrect algorithm.",
+    "is_baseline": false,
+    "paper_reference": "haghverdi2018batch",
+    "code_url": "https://code.bioconductor.org/browse/batchelor/",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/fastmnn_feature/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "liger",
+    "method_name": "LIGER",
+    "method_summary": "Linked Inference of Genomic Experimental Relationships",
+    "is_baseline": false,
+    "paper_reference": "welch2019single",
+    "code_url": "https://github.com/welch-lab/liger",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/liger/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "mnn_correct",
+    "method_name": "mnnCorrect",
+    "method_summary": "Correct for batch effects in single-cell expression data using the mutual nearest neighbors method.",
+    "is_baseline": false,
+    "paper_reference": "haghverdi2018batch",
+    "code_url": "https://code.bioconductor.org/browse/batchelor/",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/mnn_correct/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "mnnpy",
+    "method_name": "mnnpy",
+    "method_summary": "Batch effect correction by matching mutual nearest neighbors, Python implementation.",
+    "is_baseline": false,
+    "paper_reference": "hie2019efficient",
+    "code_url": "https://github.com/chriscainx/mnnpy",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/mnnpy/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "pyliger",
+    "method_name": "pyliger",
+    "method_summary": "Python implementation of LIGER (Linked Inference of Genomic Experimental Relationships",
+    "is_baseline": false,
+    "paper_reference": "welch2019single",
+    "code_url": "https://github.com/welch-lab/pyliger",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/pyliger/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "scalex_embed",
+    "method_name": "SCALEX (embedding)",
+    "method_summary": "Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space",
+    "is_baseline": false,
+    "paper_reference": "xiong2021online",
+    "code_url": "https://github.com/jsxlei/SCALEX",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/scalex_embed/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "scalex_feature",
+    "method_name": "SCALEX (feature)",
+    "method_summary": "Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space",
+    "is_baseline": false,
+    "paper_reference": "xiong2021online",
+    "code_url": "https://github.com/jsxlei/SCALEX",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/scalex_feature/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "scanorama_embed",
+    "method_name": "Scanorama (embedding)",
+    "method_summary": "Efficient integration of heterogeneous single-cell transcriptomes using Scanorama",
+    "is_baseline": false,
+    "paper_reference": "hie2019efficient",
+    "code_url": "https://github.com/brianhie/scanorama",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/scanorama_embed/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "scanorama_feature",
+    "method_name": "Scanorama (feature)",
+    "method_summary": "Efficient integration of heterogeneous single-cell transcriptomes using Scanorama",
+    "is_baseline": false,
+    "paper_reference": "hie2019efficient",
+    "code_url": "https://github.com/brianhie/scanorama",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/scanorama_feature/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "scanvi",
+    "method_name": "ScanVI",
+    "method_summary": "ScanVI is a deep learning method that considers cell type labels.",
+    "is_baseline": false,
+    "paper_reference": "lopez2018deep",
+    "code_url": "https://github.com/YosefLab/scvi-tools",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/scanvi/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "scvi",
+    "method_name": "scVI",
+    "method_summary": "scVI combines a variational autoencoder with a hierarchical Bayesian model.",
+    "is_baseline": false,
+    "paper_reference": "lopez2018deep",
+    "code_url": "https://github.com/YosefLab/scvi-tools",
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/methods/scvi/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "no_integration_batch",
+    "method_name": "No integration by Batch",
+    "method_summary": "Cells are embedded by computing PCA independently on each batch",
+    "is_baseline": true,
+    "paper_reference": null,
+    "code_url": null,
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/control_methods/no_integration_batch/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "random_embed_cell",
+    "method_name": "Random Embedding by Celltype",
+    "method_summary": "Cells are embedded as a one-hot encoding of celltype labels",
+    "is_baseline": true,
+    "paper_reference": null,
+    "code_url": null,
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/control_methods/random_embed_cell/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "random_embed_cell_jitter",
+    "method_name": "Random Embedding by Celltype with jitter",
+    "method_summary": "Cells are embedded as a one-hot encoding of celltype labels, with a small amount of random noise added to the embedding",
+    "is_baseline": true,
+    "paper_reference": null,
+    "code_url": null,
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/control_methods/random_embed_cell_jitter/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  },
+  {
+    "task_id": "batch_integration",
+    "method_id": "random_integration",
+    "method_name": "Random integration",
+    "method_summary": "Feature values, embedding coordinates, and graph connectivity are all randomly permuted.",
+    "is_baseline": true,
+    "paper_reference": null,
+    "code_url": null,
+    "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/tree/2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a/src/tasks/batch_integration/control_methods/random_integration/config.vsh.yaml",
+    "code_version": null,
+    "commit_sha": "2ebb7c01db18f3e3498c4d144020a7e6f4ce0f1a"
+  }
+]