alzheimers-ensemble-94pct

🧬 BioDockify: Multi-Target Alzheimer's Deep Learning Stacked Ensemble (94.20% Accuracy)

Principal Investigator: Tajuddin Shaik ([email protected])
Affiliation: Doctoral Research Program | BioDockify Platform (www.biodockify.com)
Live Research Portal: https://ai.biodockify.com

---

📌 Model Overview

This repository hosts the official 94.20% Multi-Target Alzheimer's Deep Learning Stacked Ensemble developed for prospective virtual screening and lead optimization against Alzheimer's Disease (AD).

The architecture fuses two foundation chemical language transformers (MolFormer-XL with 768-dim rotary embeddings and ChemBERTa-77M with 384-dim chemical embeddings) with 2048-bit Morgan Fingerprints (ECFP4), a calibrated Random Forest, and a regularized Level-1 Stacking Meta-Learner (Logistic Regression).

🎯 Primary Biological Targets

1. Human Acetylcholinesterase (AChE) — PDB ID: 4EY7 (1.90 Å, Catalytic Triad: Ser203, Trp86, Tyr337)
2. Human Beta-Secretase 1 (BACE1) — PDB ID: 1FKN (1.90 Å, Catalytic Dyad: Asp32, Asp228)
3. Human Glycogen Synthase Kinase-3β (GSK-3β) — PDB ID: 1Q41 (2.10 Å, ATP Hinge: Val135, Lys85)

---

📊 5-Fold Stratified Cross-Validation Benchmarks ($N = 10,134$)

---

📐 Mathematical Formulation

The Stacked Meta-Learner computes calibrated multi-target probabilities via:

$$\text{Logit}\big(P(\text{Active})\big) = \beta_0 + \beta_1 \cdot \hat{y}{\text{MolFormer}} + \beta_2 \cdot \hat{y}{\text{ChemBERTa}} + \beta_3 \cdot \hat{y}_{\text{RF}}$$

$$\beta_0 = -3.28631565, \quad \vec{\beta} = [2.48950582, ; 1.79471169, ; 1.82323685]$$

$$P(\text{Active} \mid \vec{\hat{y}}) = \frac{1}{1 + \exp\Big(-\big(-3.2863 + 2.4895 \hat{y}_1 + 1.7947 \hat{y}_2 + 1.8232 \hat{y}_3\big)\Big)}$$

---

💻 Quick-Start Python Inference

import os
import pickle
import numpy as np

# Load Meta-Learner Stacking Head
with open("models/trained_stacked_meta_learner.pkl", "rb") as f:
    meta_learner = pickle.load(f)

# Input Sub-Model Predictions [MolFormer, ChemBERTa, Random Forest]
# Example: Luteolin from Evolvulus alsinoides
z_input = np.array([[0.945, 0.910, 0.895]])
p_active = meta_learner.predict_proba(z_input)[0, 1]

print(f"Predicted Multi-Target Bioactivity Probability: {p_active:.4f} ({(p_active*100):.2f}%)")

---

📜 Citation

@article{Shaik2026BioDockifyEnsemble,
  title={Receptor-Directed Deep Learning Ensemble with Interpretable Mechanisms for Multi-Target Alzheimer's Drug Discovery: Targeting AChE, BACE1, and GSK-3β Inhibitors},
  author={Shaik, Tajuddin and Ravindiran, Saravanan and S., Anbuselvi and Sudhakar, M.},
  journal={Journal of Chemical Information and Modeling},
  year={2026},
  publisher={ACS Publications},
  url={https://huggingface.co/tajo9128/alzheimers-ensemble-94pct}
}