app/config.py

from pathlib import Path

# ── Paths ────────────────────────────────────────────────────────────────────
BASE_DIR      = Path(__file__).resolve().parent.parent
MODEL_PATH    = BASE_DIR / "models" / "best_model.pt"
GO_TERMS_PATH = BASE_DIR / "models" / "go_terms_list.txt"

# ── Model Architecture (must match training exactly) ──────────────────────────
ESM2_MODEL_NAME = "facebook/esm2_t33_650M_UR50D"
ESM2_DIM        = 1280
HIDDEN_DIM      = 512
NUM_LABELS      = 4201

# ── Inference ─────────────────────────────────────────────────────────────────
THRESHOLD       = 0.5        # sigmoid threshold for positive prediction
MAX_SEQ_LEN     = 1022       # ESM2 max tokens (excluding special tokens)
WINDOW_SIZE     = 1022
WINDOW_STRIDE   = 1022 - 256  # = 766  (same overlap used in training)