Babel/Snakefile at master · NCATSTranslator/Babel · 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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
configfile: "config.yaml"


include: "src/snakefiles/datacollect.snakefile"
include: "src/snakefiles/anatomy.snakefile"
include: "src/snakefiles/cell_line.snakefile"
include: "src/snakefiles/gene.snakefile"
include: "src/snakefiles/protein.snakefile"
include: "src/snakefiles/geneprotein.snakefile"
include: "src/snakefiles/diseasephenotype.snakefile"
include: "src/snakefiles/process.snakefile"
include: "src/snakefiles/chemical.snakefile"
include: "src/snakefiles/drugchemical.snakefile"
include: "src/snakefiles/taxon.snakefile"
include: "src/snakefiles/genefamily.snakefile"
include: "src/snakefiles/leftover_umls.snakefile"
include: "src/snakefiles/macromolecular_complex.snakefile"
include: "src/snakefiles/publications.snakefile"
include: "src/snakefiles/duckdb.snakefile"
include: "src/snakefiles/reports.snakefile"
include: "src/snakefiles/exports.snakefile"


# Some general imports.
import shutil
from src.snakefiles.util import write_done

# Some global settings.
import os

os.environ["TMPDIR"] = config["tmp_directory"]


# Trivial done-marker rules and destructive cleanup rules run locally so they don't consume a SLURM slot.
localrules:
    all,
    all_outputs,
    clean_compendia,
    clean_downloads,


# Top-level rules.
rule all:
    input:
        # See rule all_outputs later in this file for how we generate all the outputs.
        config["output_directory"] + "/reports/outputs_done",
        # reports_done are generated by the rules in src/snakefiles/
        config["output_directory"] + "/reports/reports_done",
        # Build all the Parquet files.
        config["output_directory"] + "/duckdb/done",
        # Build all the DuckDB (index-wide) reports.
        config["output_directory"] + "/reports/duckdb/done",
        # Build all the exports.
        config["output_directory"] + "/kgx/done",
        config["output_directory"] + "/sapbert-training-data/done",
        # Store the config.yaml file used to produce the output.
        config_file="config.yaml",
    output:
        x=config["output_directory"] + "/reports/all_done",
        output_config_file=config["output_directory"] + "/config.yaml",
    run:
        shutil.copyfile(input.config_file, output.output_config_file)
        write_done(output.x)


rule all_outputs:
    input:
        config["output_directory"] + "/reports/anatomy_done",
        config["output_directory"] + "/reports/chemicals_done",
        config["output_directory"] + "/reports/disease_done",
        config["output_directory"] + "/reports/gene_done",
        config["output_directory"] + "/reports/genefamily_done",
        config["output_directory"] + "/reports/geneprotein_done",
        config["output_directory"] + "/reports/process_done",
        config["output_directory"] + "/reports/protein_done",
        config["output_directory"] + "/reports/taxon_done",
        config["output_directory"] + "/reports/cell_line_done",
        config["output_directory"] + "/reports/umls_done",
        config["output_directory"] + "/reports/macromolecular_complex_done",
        config["output_directory"] + "/reports/drugchemical_done",
        config["output_directory"] + "/reports/publications_done",
    output:
        x=config["output_directory"] + "/reports/outputs_done",
    run:
        write_done(output.x)


rule clean_compendia:
    params:
        dir=config["output_directory"],
    shell:
        "rm {params.dir}/compendia/*; rm {params.dir}/synonyms/*"


rule clean_downloads:
    params:
        dir=config["download_directory"],
    shell:
        "rm -rf {params.dir}/*"


# Sometimes a synonyms file is available as a .gz file, but not as the .txt file itself.
# This rule is here so that Snakemake knows how to uncompress it if needed.
rule uncompress_synonym_file:
    input:
        config["output_directory"] + "/synonyms/{synonym_file}.txt.gz",
    output:
        config["output_directory"] + "/synonyms/{synonym_file}.txt",
    benchmark:
        config["output_directory"] + "/benchmarks/uncompress_synonym_file_{synonym_file}.tsv"
    shell:
        "gunzip {input} -c > {output}"