Skip to content

Commit

Permalink
update arguments
Browse files Browse the repository at this point in the history
  • Loading branch information
sainirmayi committed Aug 22, 2024
1 parent 914fdb7 commit e5ed85a
Show file tree
Hide file tree
Showing 17 changed files with 503 additions and 742 deletions.
585 changes: 230 additions & 355 deletions src/datasets/resource_scripts/spatial_10x_visium.sh

Large diffs are not rendered by default.

41 changes: 16 additions & 25 deletions src/datasets/resource_scripts/spatial_10x_visium_zenodo.sh
Original file line number Diff line number Diff line change
Expand Up @@ -7,46 +7,32 @@ param_list:
dataset_name: 10X Visium - Human Heart MI 1
dataset_url: "https://www.nature.com/articles/s41586-022-05060-x"
dataset_summary: Gene expression library of human heart using 10x Visium.
dataset_description: "Frozen heart samples were embedded in OCT (Tissue-Tek) and cryosectioned (Thermo Cryostar). The 10-µm section was placed on the pre-chilled Optimization slides (Visium, 10X Genomics, PN-1000193) and the optimal lysis time was determined. The tissues were treated as recommended by 10X Genomics and the optimization procedure showed an optimal permeabilization time of 12 or 18min of digestion and release of RNA from the tissue slide. Spatial gene expression slides (Visium, 10X Genomics, PN-1000187) were used for spatial transcriptomics following the Visium User Guides"
dataset_description: "Frozen heart samples were embedded in OCT (Tissue-Tek) and cryosectioned (Thermo Cryostar). The 10-µm section was placed on the pre-chilled Optimization slides (Visium, 10X Genomics, PN-1000193) and the optimal lysis time was determined. The tissues were treated as recommended by 10X Genomics and the optimization procedure showed an optimal permeabilization time of 12 or 18 min of digestion and release of RNA from the tissue slide. Spatial gene expression slides (Visium, 10X Genomics, PN-1000187) were used for spatial transcriptomics following the Visium User Guides"
dataset_reference: kuppe2022spatial
dataset_organism: Homo sapiens
spot_filter_min_genes: 200
gene_filter_min_spots: 50
num_reference_genes: 200
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: grid
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
- id: spatial_10x_visium/human_heart_myocardial_infarction_2
input_data: "https://zenodo.org/records/13328275/files/10X009.h5ad?download=1"
dataset_name: 10X Visium - Human Heart MI 2
dataset_url: "https://www.nature.com/articles/s41586-022-05060-x"
dataset_summary: Gene expression library of human heart using 10x Visium.
dataset_description: "Frozen heart samples were embedded in OCT (Tissue-Tek) and cryosectioned (Thermo Cryostar). The 10-µm section was placed on the pre-chilled Optimization slides (Visium, 10X Genomics, PN-1000193) and the optimal lysis time was determined. The tissues were treated as recommended by 10X Genomics and the optimization procedure showed an optimal permeabilization time of 12 or 18min of digestion and release of RNA from the tissue slide. Spatial gene expression slides (Visium, 10X Genomics, PN-1000187) were used for spatial transcriptomics following the Visium User Guides"
dataset_description: "Frozen heart samples were embedded in OCT (Tissue-Tek) and cryosectioned (Thermo Cryostar). The 10-µm section was placed on the pre-chilled Optimization slides (Visium, 10X Genomics, PN-1000193) and the optimal lysis time was determined. The tissues were treated as recommended by 10X Genomics and the optimization procedure showed an optimal permeabilization time of 12 or 18 min of digestion and release of RNA from the tissue slide. Spatial gene expression slides (Visium, 10X Genomics, PN-1000187) were used for spatial transcriptomics following the Visium User Guides"
dataset_reference: kuppe2022spatial
dataset_organism: Homo sapiens
spot_filter_min_genes: 200
gene_filter_min_spots: 50
num_reference_genes: 200
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: grid
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
normalization_methods: [log_cp10k]
output_dataset: '$id/dataset.h5ad'
output_meta: '$id/dataset_metadata.yaml'
output_state: '$id/state.yaml'
output_raw: force_null
output_normalized: force_null
publish_dir: s3://openproblems-data/resources/datasets
publish_dir: resources/datasets
remove_mitochondrial: true
HERE

Expand All @@ -63,11 +49,16 @@ process {
}
HERE

tw launch https://github.com/openproblems-bio/openproblems-v2.git \
--revision main_build \
--pull-latest \
--main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
--workspace 53907369739130 \
--compute-env 6TeIFgV5OY4pJCk8I0bfOh \
--params-file "/tmp/params.yaml" \
--config /tmp/nextflow.config
# tw launch https://github.com/openproblems-bio/openproblems-v2.git \
# --revision main_build \
# --pull-latest \
# --main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
# --workspace 53907369739130 \
# --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
# --params-file "/tmp/params.yaml" \
# --config /tmp/nextflow.config
nextflow run . \
-main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
-c src/wf_utils/labels_ci.config \
-profile docker \
-params-file "/tmp/params.yaml"
41 changes: 15 additions & 26 deletions src/datasets/resource_scripts/spatial_10x_xenium.sh
Original file line number Diff line number Diff line change
Expand Up @@ -13,14 +13,7 @@ param_list:
dataset_organism: Homo sapiens
spot_filter_min_genes: 100
gene_filter_min_spots: 50
num_reference_genes: 100
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: grid
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
- id: spatial_10x_xenium/mouse_brain
input_expression: "https://cf.10xgenomics.com/samples/spatial-exp/2.1.0/CytAssist_FreshFrozen_Mouse_Brain_Post_Xenium_Rep1/CytAssist_FreshFrozen_Mouse_Brain_Post_Xenium_Rep1_filtered_feature_bc_matrix.h5"
Expand All @@ -33,25 +26,15 @@ param_list:
dataset_organism: Mus musculus
spot_filter_min_genes: 100
gene_filter_min_spots: 50
num_reference_genes: 100
select_top_variable_genes: 50
remove_mitochondrial: false
coord_type_proc: grid
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
normalization_methods: [log_cp10k]
output_dataset: '$id/dataset.h5ad'
output_meta: '$id/dataset_metadata.yaml'
output_state: '$id/state.yaml'
output_raw: force_null
output_normalized: force_null
publish_dir: s3://openproblems-data/resources/datasets
spot_filter_min_genes: 100
gene_filter_min_spots: 50
remove_mitochondrial: true
publish_dir: resources/datasets
HERE

cat > /tmp/nextflow.config << HERE
Expand All @@ -67,11 +50,17 @@ process {
}
HERE

tw launch https://github.com/openproblems-bio/openproblems-v2.git \
--revision main_build \
--pull-latest \
--main-script target/nextflow/datasets/workflows/process_10x_datasets/main.nf \
--workspace 53907369739130 \
--compute-env 6TeIFgV5OY4pJCk8I0bfOh \
--params-file "/tmp/params.yaml" \
--config /tmp/nextflow.config
# tw launch https://github.com/openproblems-bio/openproblems-v2.git \
# --revision main_build \
# --pull-latest \
# --main-script target/nextflow/datasets/workflows/process_10x_datasets/main.nf \
# --workspace 53907369739130 \
# --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
# --params-file "/tmp/params.yaml" \
# --config /tmp/nextflow.config

nextflow run . \
-main-script target/nextflow/datasets/workflows/process_10x_datasets/main.nf \
-c src/wf_utils/labels_ci.config \
-profile docker \
-params-file "/tmp/params.yaml"
67 changes: 15 additions & 52 deletions src/datasets/resource_scripts/spatial_dbit_seq.sh
Original file line number Diff line number Diff line change
Expand Up @@ -12,14 +12,7 @@ param_list:
dataset_reference: liu2020high
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 200
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 4
n_cp: -1
- id: spatial_dbit_seq/mouse_e10_eye
input_data: "https://zenodo.org/records/12785822/files/DBiT-seq_liu2020high_E10_eye_and_nearby_data.h5ad?download=1"
Expand All @@ -31,14 +24,7 @@ param_list:
dataset_reference: liu2020high
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 200
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 4
n_cp: -1
- id: spatial_dbit_seq/mouse_e10_whole_body
input_data: "https://zenodo.org/records/12785822/files/DBiT-seq_liu2020high_E10_whole_gene_best_data.h5ad?download=1"
Expand All @@ -50,14 +36,7 @@ param_list:
dataset_reference: liu2020high
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 200
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 4
n_cp: -1
- id: spatial_dbit_seq/mouse_e11_lower_body
input_data: "https://zenodo.org/records/12785822/files/DBiT-seq_liu2020high_E11_lower_body_data.h5ad?download=1"
Expand All @@ -69,14 +48,7 @@ param_list:
dataset_reference: liu2020high
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 200
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 4
n_cp: -1
- id: spatial_dbit_seq/mouse_e11_1
input_data: "https://zenodo.org/records/12785822/files/DBiT-seq_liu2020high_GSM4364244_E11-FL-1L_gene_data.h5ad?download=1"
Expand All @@ -88,14 +60,7 @@ param_list:
dataset_reference: liu2020high
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 200
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 4
n_cp: -1
- id: spatial_dbit_seq/mouse_e11_2
input_data: "https://zenodo.org/records/12785822/files/DBiT-seq_liu2020high_GSM4364245_E11-FL-2L_gene_data.h5ad?download=1"
Expand All @@ -107,23 +72,15 @@ param_list:
dataset_reference: liu2020high
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 200
select_top_variable_genes: 50
remove_mitochondrial: true
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 4
n_cp: -1
normalization_methods: [log_cp10k]
output_dataset: '$id/dataset.h5ad'
output_meta: '$id/dataset_metadata.yaml'
output_state: '$id/state.yaml'
output_raw: force_null
output_normalized: force_null
publish_dir: s3://openproblems-data/resources/datasets
remove_mitochondrial: true
publish_dir: resources/datasets
HERE

cat > /tmp/nextflow.config << HERE
Expand All @@ -139,11 +96,17 @@ process {
}
HERE

tw launch https://github.com/openproblems-bio/openproblems-v2.git \
--revision main_build \
--pull-latest \
--main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
--workspace 53907369739130 \
--compute-env 6TeIFgV5OY4pJCk8I0bfOh \
--params-file "/tmp/params.yaml" \
--config /tmp/nextflow.config
# tw launch https://github.com/openproblems-bio/openproblems-v2.git \
# --revision main_build \
# --pull-latest \
# --main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
# --workspace 53907369739130 \
# --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
# --params-file "/tmp/params.yaml" \
# --config /tmp/nextflow.config

nextflow run . \
-main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
-c src/wf_utils/labels_ci.config \
-profile docker \
-params-file "/tmp/params.yaml"
60 changes: 15 additions & 45 deletions src/datasets/resource_scripts/spatial_merfish.sh
Original file line number Diff line number Diff line change
Expand Up @@ -12,14 +12,7 @@ param_list:
dataset_reference: fang2022conservation
spot_filter_min_genes: 10
gene_filter_min_spots: 100
num_reference_genes: 25
select_top_variable_genes: 25
remove_mitochondrial: false
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
- id: spatial_merfish/human_cortex_2
input_data: "https://zenodo.org/records/12785822/files/MERFISH_Fang2022Conservation_H18.06.006.MTG.4000.expand.rep1_data.h5ad?download=1"
Expand All @@ -31,14 +24,7 @@ param_list:
dataset_reference: fang2022conservation
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 50
select_top_variable_genes: 50
remove_mitochondrial: false
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
- id: spatial_merfish/human_cortex_3
input_data: "https://zenodo.org/records/12785822/files/MERFISH_Fang2022Conservation_H18.06.006.MTG.4000.expand.rep2_data.h5ad?download=1"
Expand All @@ -50,14 +36,7 @@ param_list:
dataset_reference: fang2022conservation
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 50
select_top_variable_genes: 50
remove_mitochondrial: false
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
- id: spatial_merfish/human_cortex_4
input_data: "https://zenodo.org/records/12785822/files/MERFISH_Fang2022Conservation_H18.06.006.MTG.4000.expand.rep3_data.h5ad?download=1"
Expand All @@ -69,14 +48,7 @@ param_list:
dataset_reference: fang2022conservation
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 50
select_top_variable_genes: 50
remove_mitochondrial: false
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
- id: spatial_merfish/mouse_cortex
input_data: "https://zenodo.org/records/12785822/files/MERFISH_Fang2022Conservation_mouse1.AUD_TEA_VIS.242.unexpand_data.h5ad?download=1"
Expand All @@ -88,23 +60,15 @@ param_list:
dataset_reference: fang2022conservation
spot_filter_min_genes: 10
gene_filter_min_spots: 50
num_reference_genes: 25
select_top_variable_genes: 25
remove_mitochondrial: true
coord_type_proc: generic
coord_type_moran_i: generic
coord_type_sepal: grid
max_neighs_speal: 6
n_cp: -1
normalization_methods: [log_cp10k]
output_dataset: '$id/dataset.h5ad'
output_meta: '$id/dataset_metadata.yaml'
output_state: '$id/state.yaml'
output_raw: force_null
output_normalized: force_null
publish_dir: s3://openproblems-data/resources/datasets
remove_mitochondrial: true
publish_dir: resources/datasets
HERE

cat > /tmp/nextflow.config << HERE
Expand All @@ -120,11 +84,17 @@ process {
}
HERE

tw launch https://github.com/openproblems-bio/openproblems-v2.git \
--revision main_build \
--pull-latest \
--main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
--workspace 53907369739130 \
--compute-env 6TeIFgV5OY4pJCk8I0bfOh \
--params-file "/tmp/params.yaml" \
--config /tmp/nextflow.config
# tw launch https://github.com/openproblems-bio/openproblems-v2.git \
# --revision main_build \
# --pull-latest \
# --main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
# --workspace 53907369739130 \
# --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
# --params-file "/tmp/params.yaml" \
# --config /tmp/nextflow.config

nextflow run . \
-main-script target/nextflow/datasets/workflows/process_spatial_from_zenodo/main.nf \
-c src/wf_utils/labels_ci.config \
-profile docker \
-params-file "/tmp/params.yaml"
Loading

0 comments on commit e5ed85a

Please sign in to comment.