-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy path.env.example
More file actions
72 lines (55 loc) · 2.23 KB
/
Copy path.env.example
File metadata and controls
72 lines (55 loc) · 2.23 KB
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
# Autism Pathway Framework - Environment Configuration
# Copy this file to .env and fill in your values
# DO NOT commit .env to version control
# =============================================================================
# Google Cloud Configuration
# =============================================================================
GCP_PROJECT_ID=your-project-id
GCP_REGION=us-central1
GCP_ZONE=us-central1-a
# Cloud Storage bucket for data
GCS_BUCKET=your-bucket-name
GCS_DATA_PREFIX=data/
# =============================================================================
# Local Development Paths
# =============================================================================
# Base directory for local data (gitignored)
DATA_DIR=./data
# Raw data downloads
RAW_DATA_DIR=${DATA_DIR}/raw
# Processed data
PROCESSED_DATA_DIR=${DATA_DIR}/processed
# Model checkpoints and embeddings
MODELS_DIR=${DATA_DIR}/models
EMBEDDINGS_DIR=${DATA_DIR}/embeddings
# =============================================================================
# External Database Paths (download these)
# =============================================================================
# Gene Ontology
GO_OBO_PATH=${RAW_DATA_DIR}/go-basic.obo
# Reactome pathways
REACTOME_GMT_PATH=${RAW_DATA_DIR}/ReactomePathways.gmt
# STRING PPI network
STRING_PPI_PATH=${RAW_DATA_DIR}/9606.protein.links.v12.0.txt
# gnomAD constraints
GNOMAD_CONSTRAINTS_PATH=${RAW_DATA_DIR}/gnomad.v2.1.1.lof_metrics.by_gene.txt
# SFARI genes
SFARI_GENES_PATH=${RAW_DATA_DIR}/SFARI-Gene_genes.csv
# BrainSpan expression
BRAINSPAN_DIR=${RAW_DATA_DIR}/brainspan
# =============================================================================
# Pipeline Configuration
# =============================================================================
# Logging level: DEBUG, INFO, WARNING, ERROR
LOG_LEVEL=INFO
# Number of parallel workers
NUM_WORKERS=4
# Random seed for reproducibility
RANDOM_SEED=42
# =============================================================================
# Development Settings
# =============================================================================
# Set to 'true' for development mode (uses smaller test datasets)
DEV_MODE=true
# Test data size (number of samples for dev mode)
DEV_SAMPLE_SIZE=100