GenomePlatform/docker-compose.yml at main · cinnetcrash/GenomePlatform · 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
# ─────────────────────────────────────────────────────────────────────────────
# LycianWay — Docker Compose
#
# Quick start:
#   1. cp .env.example .env        # fill in ANTHROPIC_API_KEY + DATABASES_DIR
#   2. docker compose build        # ~30-60 min first time (conda envs)
#   3. docker compose up -d        # start in background
#   4. docker compose logs -f      # stream logs
#   5. docker compose down         # stop
#
# Database volumes:
#   Set DATABASES_DIR in .env to the directory containing your databases.
#   Expected subdirectory layout:
#     $DATABASES_DIR/
#       kraken2_db/           → hash.k2d (Kraken2)
#       bact_databases_ALL/checkm2_v2_20210323/uniref100.KO.1.dmnd  (CheckM2)
#       checkv_db/            → genome_db.faa.dmnd (CheckV, optional)
#       database_pharokka/    → PHROG_phrogs_profile_db (optional)
# ─────────────────────────────────────────────────────────────────────────────

services:
  genome-platform:
    build:
      context: .
      dockerfile: docker/Dockerfile
    image: lycianway:latest
    container_name: genome-platform
    restart: unless-stopped

    ports:
      - "${PORT:-8000}:8000"

    environment:
      # ── Required ───────────────────────────────────────────────────────────
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}

      # ── Container-internal tool paths (do not change) ──────────────────────
      - CONDA_BASE=/opt/conda
      - BANDAGE_BIN=/opt/conda/envs/analiz/bin/Bandage
      - AUTOCYCLER_BIN=/usr/local/bin/autocycler

      # ── Database paths inside the container (relative to /databases mount) ─
      - KRAKEN2_DEFAULT_DB=/databases/kraken2_db
      - CHECKM2_DB=/databases/bact_databases_ALL/checkm2_v2_20210323/uniref100.KO.1.dmnd
      - CHECKV_DB=/databases/checkv_db

      # ── Python / app ───────────────────────────────────────────────────────
      - PYTHONUNBUFFERED=1

    volumes:
      # ── Databases (host → container, read-only) ────────────────────────────
      # Point DATABASES_DIR in .env to your databases root directory.
      - ${DATABASES_DIR:-/home/analysis/databases_all}:/databases:ro

      # ── Persistent job data (Docker-managed named volumes) ─────────────────
      - genome_uploads:/app/data/uploads
      - genome_results:/app/data/results
      - genome_logs:/app/data/logs

      # ── Development: hot-reload source code (comment out for production) ───
      # - ./backend:/app/backend:ro
      # - ./frontend:/app/frontend:ro

    # ── Resource limits (adjust to your server) ────────────────────────────────
    deploy:
      resources:
        limits:
          cpus: "${CPU_LIMIT:-16}"
          memory: "${MEM_LIMIT:-32G}"
        reservations:
          cpus: "2"
          memory: 4G

    # ── Security hardening ─────────────────────────────────────────────────────
    security_opt:
      - no-new-privileges:true
    cap_drop:
      - ALL
    cap_add:
      - SETUID   # required for subprocess execution
      - SETGID

    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s

    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"


# ── Named volumes ──────────────────────────────────────────────────────────────
volumes:
  genome_uploads:
    driver: local
  genome_results:
    driver: local
  genome_logs:
    driver: local