Core Research Areas

Bioinformatics & Genomics

Developing advanced methods for modern challenges in the field of bioinformatics and genomics, such as Antimicrobial Resistance (AMR) prediction or Spatial Transcriptomics research.

Biomedical Imaging & Signals

Designing novel deep learning frameworks for medical image analysis and physiological signal-based diagnostics.

Explainable AI for Healthcare

Building interpretable models whose decisions can be understood and trusted by clinicians/biologists. We aim to validate our models using XAI techniques and uncover underlying biological signals.

Ongoing Projects

AudioFuse Project Image

Multi-Modal Fusion of Different Representations of the Signal for Biomedical Audio Analysis

Audio Processing Deep Learning Multi-Modal Learning

This project explores fusion of features learned from different representations of biomedical audio signals, to exploit the complementary strengths of each representation. We explored different representations including waveforms, spectrograms, and scalograms for robust diagnostic models, and one paper from this research is currently under review.

BIOML Investigators: Md. Saiful Bari Siddiqui, Utsab Saha

AMR Project Image

Antimicrobial Resistance (AMR) Prediction from Genomic Data (SNPs) Leveraging Deep Learning & Explainable AI

Bioinformatics Explainable AI Genomics Ensemble Learning

This research exploits different perspectives provided by different types of models. We explored the utility of the sequential information available in SNPs through sequence-aware models and currently investigating fusion mechanisms to combine them with "bag-of-features" models. We also incorporate Explainable-AI methods to biologically validate our models. One paper from this research has been accepted at SCA/HPCAsia 2026.

BIOML Investigators: Md. Saiful Bari Siddiqui, Nowshin Tarannum

S3F-Net Project Image

Medical Image Segmentation & Classification based on a Dual-Domain Approach of Spatial and Spectral Feature Fusion

Computer Vision Biomedical Imaging Multi-Modal Fusion

Proposed S³F-Net, a dual-branch framework that learns from both spatial (CNN) and spectral (SpectraNet) domains simultaneously, achieving performance improvements over unimodal baselines & state-of-the-art competitive accuracy on multiple medical imaging datasets.

We are currently working on the extension of S³F-Net, where we intend to apply the concept of multi-domain learning for medical image segmentation. The original S³F-Net paper is currently under review.

BIOML Investigators: Md. Saiful Bari Siddiqui

Collaborate With Us

We are always looking for passionate students, researchers, and collaborators. If our work interests you, please get in touch. You can find us on GitHub or send a direct email.