task_cyto_batch_integration/src/control_methods/perfect_integration/script.py at 62d88631836d0f01b05c3049d5f62eec32d7f2ed · openproblems-bio/task_cyto_batch_integration · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
import anndata as ad

## VIASH START
# The following code has been auto-generated by Viash.
par = {
    "input_unintegrated": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/unintegrated.h5ad",
    "output_integrated_split1": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/perfect_integrated_split1.h5ad",
    "output_integrated_split2": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/perfect_integrated_split2.h5ad",
}
meta = {"name": "perfect_integration"}

## VIASH END

print("Reading input files", flush=True)
adata = ad.read_h5ad(par["input_unintegrated"])

print("Extracting and splitting unintegrated data", flush=True)

# split 1
adata_split1 = adata[(adata.obs.is_control > 0) | (adata.obs.batch == 1)]
integrated_split1 = adata_split1.layers["preprocessed"]

# split 2 == split 1 in this case

print("Write output AnnData to file", flush=True)
# split 1
output_split1 = ad.AnnData(
    obs=adata_split1.obs[[]],
    var=adata_split1.var[[]],
    layers={"integrated": integrated_split1},
    uns={
        "dataset_id": adata.uns["dataset_id"],
        "method_id": meta["name"],
        "parameters": {},
    },
)
# split 2
output_split2 = ad.AnnData(
    obs=adata_split1.obs[[]],
    var=adata_split1.var[[]],
    layers={"integrated": integrated_split1},
    uns={
        "dataset_id": adata.uns["dataset_id"],
        "method_id": meta["name"],
        "parameters": {},
    },
)

output_split1.write_h5ad(par["output_integrated_split1"], compression="gzip")
output_split2.write_h5ad(par["output_integrated_split2"], compression="gzip")