JiecongLin/EPInformer-pipeline

EPInformer — pipeline (pretrained checkpoints)

Pretrained checkpoints for the EPInformer pipeline — a from-raw-ENCODE pipeline for EPInformer across 6 cell lines (K562, GM12878, H1, HepG2, HUVEC, NHEK).

Two models (defined in EPInformer/models.py on the pipeline branch):

• enhancer_predictor_256bp — 256 bp enhancer-activity encoder; predicts log2(0.1 + sqrt(H3K27ac·DNase)) activity from sequence.
• EPInformer_v2 — gene-expression model (RNA / CAGE) that reuses the frozen encoder as its sequence backbone.

Results (12-fold leave-chromosome-out, pooled Pearson R)

Enhancer encoder (log2 activity):

	H1	HepG2	K562	HUVEC	NHEK	GM12878
R	0.820	0.743	0.740	0.742	0.677	0.617

Gene expression (shipped f3 = frozen encoder + 3 enhancer features + promoter signal):

	K562	GM12878	HepG2	HUVEC	NHEK	H1
RNA	0.856	0.860	0.845	0.839	0.828	0.781
CAGE	0.867	0.890	—	—	—	—

CAGE labels exist only for K562/GM12878 (the other four are RNA-only).

Files

enhancer_encoders/{CELL}/fold_{i}.pt   # CELL ∈ {K562, GM12878, H1, HepG2, HUVEC, NHEK}, i ∈ 1..12
expression_models/{CELL}/{ASSAY}/{FEATURE}/fold_*.pt
# ASSAY ∈ {RNA, CAGE}; FEATURE ∈ {f1, f2, f3}

These are the pipeline's 256 bp enhancer-activity encoders — the best checkpoint for each of the 12 leave-chromosome-out folds, for all 6 cell lines (72 checkpoints). Any fold works for inference; the R values in the table above are pooled across all 12 held-out folds.

The gene-expression checkpoint directories contain 12 folds for each supported cell/assay/feature configuration. Use the matching HDF5 input, expression labels, fold split, and pretrained enhancer encoder described in the pipeline README.

The KLF1 demo in the notebooks uses the original published EPInformer encoder shipped in the repo's trained_models/pretrained_enhancer_encoder/ — a separate checkpoint from these folds.

Usage

import torch
from huggingface_hub import hf_hub_download
# the model class lives on the pipeline branch:
#   git clone -b pipeline https://github.com/pinellolab/EPInformer
from EPInformer.models import enhancer_predictor_256bp

ckpt = hf_hub_download("JiecongLin/EPInformer-pipeline", "enhancer_encoders/K562/fold_8.pt")
net = enhancer_predictor_256bp()
net.load_state_dict(torch.load(ckpt, map_location="cpu", weights_only=False)["model_state_dict"])
net.eval()

See the project wiki for the full training and evaluation guide, and the pipeline branch for code.