galaxytools/tools/aoptk/aoptk_finalize_output.xml at 192da7c426609ca5863469da10b0c97bb1804b9d · rdurnik/galaxytools · 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
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
<tool id="aoptk_final_modification" name="aoptk final modification" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="25.1" license="MIT">
    <description>Finalize the output of relationship identification.</description>
    <macros>
        <import>macros.xml</import>
    </macros>

    <requirements>
        <expand macro="requirements"/>
        <requirement type="package" version="3.1.5">openpyxl</requirement>
    </requirements>

    <command detect_errors="exit_code"><![CDATA[
        python3 '${final_modification}'
    ]]></command>

<configfiles>
    <configfile name="final_modification"><![CDATA[
import pandas as pd

def join_unique(series):
    values = series.dropna().astype(str).str.strip()
    return ";".join(pd.unique(values))

output = pd.read_csv("$input_file", sep="\t")

for effect in output["effect"].unique():
    file_name = effect.strip().lower().replace(" ", "_")

    output_filtered = output[output["effect"] == effect].copy()

    group_column = "heading" if "heading" in output_filtered.columns else "chemical"
    if group_column not in output_filtered.columns:
        raise ValueError("Input must contain either a heading or chemical column.")

    output_filtered["relationship"] = output_filtered["relationship"].astype(str).str.strip().str.lower()
    relationships = sorted(output_filtered["relationship"].unique())
    final_output = output_filtered[[group_column]].drop_duplicates()

    for relationship in relationships:
        subset = output_filtered[output_filtered["relationship"] == relationship]
        result = subset.groupby(group_column, as_index=False, dropna=False).agg(
            hits=("id", "size"),
            ids=("id", join_unique),
        )
        result.rename(columns={"hits": f"{relationship}", "ids": f"{relationship} IDs"}, inplace=True)
        final_output = final_output.merge(result, on=group_column, how="left")

    final_output.to_excel(f"./{file_name}.xlsx", index=False)
]]></configfile>
</configfiles>

    <inputs>
        <param name="input_file" type="data" format="tabular" label="TSV with heading or chemical column." help="Input tsv file with heading column when available, otherwise chemical column." />
    </inputs>

    <outputs>
        <collection name="final_outputs" type="list" label="Final outputs" format="xlsx">
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\.xlsx$" ext="xlsx" directory="." />
        </collection>
    </outputs>

    <tests>
        <test>
           <param name="input_file" value="output.tsv"/>
           <output_collection name="final_outputs" type="list" count="2"/>
        </test>
        <test>
           <param name="input_file" value="output_no_heading.tsv"/>
           <output_collection name="final_outputs" type="list" count="1"/>
        </test>
    </tests>

    <help><![CDATA[
Final Modification
===================

Tool to remove duplicates and finalize the output of relationship identification.

    ]]></help>

    <citations>
        <citation type="doi">10.5281/zenodo.20036704</citation>
    </citations>

</tool>