# Jonas Ferrao | Intelligence Engineer

> Portfolio of Jonas Chris Ferrao, an AI ML Engineer specializing in machine learning, data science, and software engineering. Explore innovative projects in neural networks, computer vision, and production-grade ML systems.

Return to GridBioinformaticsGraph Neural NetworksAttentionTensorFlow

# GCBLANE

Graph-enhanced Convolutional BiLSTM Attention Network

Project Dossier

A research project developing a novel deep learning model for Transcription Factor Binding Site (TFBS) prediction. Existing methods struggle with the complexity of DNA sequences; GCBLANE leverages Graph Neural Networks and Attention mechanisms to capture both local and global dependencies.

####  Technical Architecture

We developed **GCBLANE (Graph-enhanced Convolutional BiLSTM Attention Network)**, a hybrid deep learning architecture that processes DNA sequences using one-hot encoding and de Bruijn graphs to capture sequential and structural dependencies. The architecture consists of:

- **GNN Module:** Graph Neural Network on de Bruijn graph representations of k-mers to model multi-hop structural relationships.
- **CNN Module:** Convolutional layers to extract local motifs from encoded sequences.
- **Multi-Head Attention Module:** Self-Attention applied to focus on important TF binding motifs.
- **BiLSTM Module:** Bidirectional LSTM layers to capture forward and backward contextual dependencies in sequences.

[REF_IMG]: GCBLANE Architecture

####  Results

The below tables demonstrate GCBLANE's superior performance compared to various other state-of-the-art methods across different dataset sizes and feature types.

Performance on 690 DatasetsModelAllSmallMediumLargeGCBLANE0.9430.9040.9300.973MSDenseNet0.9330.8970.9210.973MAResNet0.9270.8830.9140.972SAResNet0.9200.8760.9070.966Comparison on 165 DatasetsModelAccuracyROC AUCPR AUCInput TypeGCBLANE0.8870.94950.949Sequence OnlyBERT-TFBS0.8510.9190.920Sequence OnlyTBCA0.8230.8940.899Sequence & ShapeDSAC0.8160.8870.883Sequence & ShapeDeepSTF0.8140.8830.890Sequence & ShapeKey Stats>25MSequences0.887Accuracy0.943AUC-ROCActions[Live System](https://projectultra.github.io/GCBLANE/)[Source Code](https://github.com/projectultra/GCBLANE)[Preprint](https://arxiv.org/abs/2503.12377)

## Reach out to me

[EMAIL](mailto:jonasferrao21@gmail.com)[PHONE](tel:+918805513038)[LINKEDIN](https://www.linkedin.com/in/jonas-ferrao/)

© 2026 JONAS FERRAO

@PROJECTULTRA