reformat_repurposing_data.conseq

rule reformat_dose_level_repurposing_secondary:
    inputs: script=fileref("scripts/compounds/repurposing/reformat_dose_level_repurposing_secondary.py"),
        filter_script=fileref("scripts/compounds/repurposing/filter_repurposing_data.py"),
        hdf5_utils=fileref('scripts/hdf5_utils.py', copy_to='hdf5_utils.py'),
        data={'type': 'repurposing-dose'},
        taiga_token={"type": "config-file", "name": "taiga-token"}
    outputs: {
            'type': 'dep-matrix', 
            "label": "Repurposing_secondary_dose", # matches with the enum
            "orig_dataset_id": "{{inputs.data.dataset_id}}",
            'filename': {'$filename': 'out.hdf5'}
          }, {
            'type': "dropped-repurposing-secondary-doses",
            'filename': {'$filename': 'dropped.json'}
          }
    run "cp {{ inputs.taiga_token.filename }} ./.taiga-token"
    run "python3 {{ inputs.filter_script.filename }} {{ inputs.data.dataset_id }} {{ inputs.data.treatment_info_dataset_id }} {{ inputs.data.cell_line_info_dataset_id }} --screens HTS002"
    run "python3 {{inputs.script.filename}} filtered_data.csv filtered_treatment_info.csv"


rule reformat_dose_replicate_level_repurposing_secondary:
    executor: dsub {"min_ram": "10"}
    inputs: script=fileref("scripts/compounds/repurposing/reformat_dose_replicate_level_repurposing_secondary.py"),
        filter_script=fileref("scripts/compounds/repurposing/filter_repurposing_data.py"),
        data={'type': 'repurposing-dose-replicate'},
        taiga_token={"type": "config-file", "name": "taiga-token"}
    outputs: {
        "type": 'dose-replicate-level',
        "label": "{{ inputs.data.label }}",
        "orig_dataset_id": "{{ inputs.data.dataset_id }}",
        "filename": {"$filename": "reformatted_dose_replicate_level_secondary_screen_repurposing_data.csv"} }

    run "cp {{ inputs.taiga_token.filename }} ./.taiga-token"
    run "python3 {{ inputs.filter_script.filename }} {{ inputs.data.dataset_id }} {{ inputs.data.treatment_info_dataset_id }} {{ inputs.data.cell_line_info_dataset_id }} --screens HTS002"
    run "python3 {{inputs.script.filename}} filtered_data.csv filtered_treatment_info.csv"

rule reformat_curve_params_secondary_repurposing_data:
    executor: dsub {"min_ram": "20"}
    inputs: script=filename("scripts/compounds/repurposing/reformat_dose_response_curve_params_repurposing_secondary.py"),
        hdf5_utils=fileref('scripts/hdf5_utils.py', copy_to='hdf5_utils.py'),
        data={'type': 'repurposing-curves'},
        taiga_token={"type": "config-file", "name": "taiga-token"}
    outputs: {
        "type": 'dose-response-curve-params',
        "orig_dataset_id": "{{ inputs.data.dataset_id }}",
        "filename": {"$filename": "curves.csv"} },
        {"type": 'dep-matrix',
        "label": "{{ inputs.data.label }}",
        "orig_dataset_id": "{{ inputs.data.dataset_id }}",
        "filename": {"$filename": "auc.hdf5" } }
    run "cp {{ inputs.taiga_token.filename }} ./.taiga-token"
    run "python3 {{inputs.script.filename}} {{ inputs.data.dataset_id }}"

rule reformat_repurposing_single_pt_data:
    inputs: script=fileref("scripts/compounds/repurposing/reformat_repurposing_single_pt.py"),
        data={'type': 'repallsinglept-taiga-id'},
        hdf5_utils=fileref('scripts/hdf5_utils.py', copy_to='hdf5_utils.py')
    outputs: {
        "type": 'dep-matrix',
        "label": "{{ inputs.data.label }}",
        "confounders_label": "repallsinglept-confounders",
        "filename": {"$filename": "{{inputs.data.label}}.hdf5" },
        "orig_dataset_id": "{{inputs.data.dataset_id}}"
    }
    run "python3 {{ inputs.script.filename }} {{ inputs.data.dataset_id }} {{inputs.data.label}}.hdf5"