SFtool/SFtool.py at geneBePharmCAT · babelomics/SFtool · 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
#!/usr/bin/python3
# -*- coding: utf-8 -*-

"""
Herramienta para el manejo automático de hallazgos secundarios.

Esta herramienta permite a los usuarios analizar archivos VCF para el manejo automático de hallazgos secundarios relacionados con riesgo personal, riesgo reproductivo y farmacogenético.

@Dependencies InterVar and AnnoVar
@Usage python3 SFtool.py input_file.vcf --mode <Option: 'basic' or 'advanced'> --evidence <integer> --assembly <Option: '37' or '38'>
@Arguments:
    -vcf (str): Ruta al archivo VCF de entrada.
    -outpath (str): Ruta al directorio donde se guardarán los resultados.
    -mode (str): Modo de análisis (básico o avanzado).
    -evidence (int): Nivel de evidencia de ClinVar para el modo avanzado (1-4).#comprobar que lo he puesto de memoria
    -assembly (str): Ensamblaje genómico a utilizar (GRCh37 o GRCh38).

@Author Javier Perez FLorido, Edurne Urrutia Lafuente
@Date 2023/08/01
@email javier.perez.florido.sspa@juntadeandalucia.es, edurlaf@gmail.com
@github https://github.com/babelomics/secondaryfindings
"""

import os
import sys

from modules.misc.errors import (
    BootstrapError
)

from modules.misc.arguments import parse_arguments
from modules.bootstrap import bootstrap_execution
from modules.FG.run_fg_module import run_pharmacogenomic_risk_module
from modules.misc.report_utils import generate_report
from steps.catalog_generation import run as run_catalog_generation
from steps.clinvar_setup import run as run_clinvar_setup
from steps.sample_preprocessing import run as run_sample_preprocessing
from steps.variant_evidence_preparation import run as run_variant_evidence_preparation
from steps.variant_collection import run as run_variant_collection
from steps.variant_selection import run as run_variant_selection


def main():

    # --------------------------
    # Parse CLI arguments
    # --------------------------
    args = parse_arguments()
    outdir = args.outdir

    # ----------------------------
    # STEP 1: SFtool bootstraping: JSON inputs validation, create execution context object and validate run dependencies
    # ----------------------------

    try:
        ctx = bootstrap_execution(args.samples, args.config, outdir)
    except BootstrapError as e:
        print(f"[ERROR] {e}")
        sys.exit(1)

    # ----------------------------
    # STEP 2: JSON and BED files catalog generation
    # ----------------------------
    run_catalog_generation(ctx)

    # ----------------------------
    # STEP 3: CLINVAR DDBB MANAGEMENT
    #           Only if profile is advanced and for PR and RR categories
    # ----------------------------
    profile = ctx.profile
    # Get unique list of categories for all samples
    categories = sorted({
        c for s in ctx.samples for c in s.categories
    })

    if profile == 'advanced' and ("PR" in categories or "RR" in categories):
        run_clinvar_setup(ctx)


    # ----------------------------
    # STEP 4: SAMPLE PREPROCESSING
    #
    # ----------------------------
    run_sample_preprocessing(ctx)


    # ----------------------------
    # STEP 5: VARIANT EVIDENCE PREPARATION (GENEBE AND/OR CLINVAR)
    #
    # ----------------------------
    run_variant_evidence_preparation(ctx)


    # ----------------------------
    # STEP 6: VARIANT COLLECTION (GENEBE AND/OR CLINVAR, STRs and SMN1-copy, pharmCAT)
    #
    # ----------------------------
    run_variant_collection(ctx)

    # ----------------------------
    # STEP 7: VARIANT SELECTION from the set of VARIANT COLLECTION
    #
    # ----------------------------
    run_variant_selection(ctx)


if __name__ == "__main__":
    main()