I develop AI systems for molecular discovery,
multi-omics analysis, and precision medicine.

I'm an AI ML scientist working at the intersection of machine learning and computational biology, designing generative models for proteins and RNAs, predicting protein behavior with language models, and building diagnostic AI for cardiac health. My goal is to make drug discovery faster, cheaper, and more accessible.

📍 Lawrence, Kansas 🏛 University of Kansas · EECS 📬 shishir@ku.edu
Fairuz Shadmani Shishir

University of Kansas.

Latest

News & Achievements

News
June 2026
Appointed in Program Committee

Selected to serve on the Program Committee for leading AI and Computational Biology conferences, contributing to the peer-review process of cutting-edge research. IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

May 2026
Media Coverage

KU graduate research assistant publishes breakthrough studies across AI, healthcare, and sustainability University of Kansas.

April 2026
Paper

Our paper on privacy-preserving ECG diagnostics is published in Springer Nature Scientific Reports.

Mar 2026
Paper

NbBayesLM paper accepted at Frontiers in Bioinformatics — Bayesian uncertainty quantification for nanobody thermostability.

Jan 2026
Preprint

CIgFlow preprint posted — antigen-conditioned antibody generation via conditional flow matching.

GitHub ↗

Sep 2025
Paper

Protein-to-metal binding prediction paper accepted in IEEE Transactions on Computational Biology and Bioinformatics.

Aug 2024
Preprint

Bloom Filter IC authentication framework posted on arXiv.

Jun 2023
Talk

Presented MetaLLM at IWBBIO 2023 in Granada, Spain.

Achievements
2026
Publication

Two journal papers in 2026 — Scientific Reports and Frontiers in Bioinformatics.

2023–present
Grant

Research supported by the American Heart Association (AHA) — collaborative work on cardiac AI and antibody design.

2023–present
Position

Appointed Visiting Researcher at KU Medical Center, School of Medicine for ECG AI collaboration with cardiologists.

2020
Award

Best Paper Award — IEEE IEMCON 2020 for "Graph Theory for Dimensionality Reduction: Prognosticating Parkinson's."

2022
Position

Joined the University of Kansas as a Graduate Research Assistant in the EECS department.

2019–2021
Industry

Shipped production ML systems at BJIT Group and Inside Maps — face recognition, real-time detection, and forecasting at scale.

Background
Degree
PhD, EECS
Institution
Univ. of Kansas
Since
2022
Publications
15+
Citations
500+
Funding
AHA-supported
Open to
Collaborations

I'm a machine learning researcher with a focus on protein design, drug discovery, and computational biology. My day-to-day involves training and fine-tuning large protein language models, building generative frameworks for antibody engineering, and developing clinical AI tools for cardiac diagnostics — all in close collaboration with biologists and physicians.

Before starting my PhD, I spent two years as an AI ML software engineer building production ML systems — face recognition, real-time object detection, and forecasting pipelines deployed on AWS at scale.

I'm part of an AHA-funded project and hold a visiting researcher position at the KU Medical Center, where I work on privacy-preserving ECG analysis with the School of Medicine.

"I believe the next breakthrough therapies will emerge where artificial intelligence meets biology—turning complex molecular data into actionable insights for human health."
Presenting research at a conference

Presenting research in conference

Career

Experience

2022 – present
Graduate Research Assistant
University of Kansas · EECS
My main research home. I developed MetaLLM for protein-metal binding prediction (5% SOTA improvement), built parameter-efficient fine-tuning pipelines using LoRA and adapters for protein LMs, and am leading the CIgFlow and NbBayesLM projects on antibody and nanobody design. Funded in part by the American Heart Association.
ESM-2LoRAFlow MatchingPyTorchAlphaFold
2023 – present
Visiting Researcher
KU Medical Center · School of Medicine
Working with cardiologists to build privacy-preserving ECG analysis models using a CNN-VAE architecture. The system corrects for demographic and acquisition bias across diverse patient populations — now published in Scientific Reports.
CNN-VAEECGClinical AIFederated Learning
Fall 2024
Graduate Teaching Assistant
University of Kansas
Led weekly Python programming labs for undergraduate CS students. Focused on making programming approachable — covering data structures, algorithms, and introductory ML.
2020 – 2021
Machine Learning Engineer
BJIT Group · Dhaka
Built and shipped a production FaceAI engine with anti-spoofing using ResNet/EfficientNet ensembles. Cut inference latency 20% through quantization and TensorRT optimization.
TensorRTResNetAnti-spoofing
2020 – 2021
Machine Learning Engineer
Inside Maps · Dhaka
YOLOv3 asset detection pipeline at 95% accuracy; LSTM/Transformer forecasting for BI; AWS SageMaker deployment serving 10K+ concurrent users.
YOLOv3LSTMAWS SageMaker
2019 – 2020
Software Engineer
ACI Limited · Dhaka
Designed data-centric business policies and integrated recommendation systems, increasing the company's digital presence by 25%.
Toolkit

Technical Skills

Generative AI & Deep Learning
PyTorch / TensorFlowExpert
ESM-2, ProtGPT2, AbLangExpert
Diffusion & Flow MatchingExpert
Graph Neural NetworksAdvanced
Bayesian Deep LearningAdvanced
Knowledge DistillationAdvanced
VAE / CVAEAdvanced
MLOps & DeploymentAdvanced
Computational Biology
Protein Structure AnalysisExpert
ChEMBL / UniProtExpert
SMILES & Mol. FingerprintsExpert
Antibody / Nanobody DesignExpert
Sequence AlignmentAdvanced
MetagenomicsAdvanced
Drug Discovery
RDKit & CheminformaticsExpert
Lead OptimizationExpert
ADMET PredictionAdvanced
Molecular DockingAdvanced
Virtual ScreeningAdvanced
PK ModelingAdvanced
Selected Work

Projects

🧬
CIgFlow
PyTorch ESM-2 Flow Matching ProtGPT2 AlphaFold
Antigen-Conditioned Antibody Design via Conditional Flow Matching

CIgFlow is a generative framework that learns a continuous mapping from joint antibody-antigen embeddings to novel antibody sequences. It combines Conditional Flow Matching with a GPT-2-style autoregressive decoder, protein language model embeddings, and classifier-free guidance — generating antigen-specific antibodies while maintaining humanness and developability. The ODE-based latent sampler allows diverse exploration of sequence space without sacrificing quality.

🔬
NbBayesLM
PyTorch ESM-2 AbLang Bayesian NN
Bayesian Nanobody Thermostability Prediction with Calibrated Uncertainty

Predicts nanobody melting temperature (Tm) using ESM-2 and AbLang embeddings as input to a Bayesian deep learning framework that also encodes physicochemical features as priors. Evaluated on 10,000+ nanobody sequences: MAE of 1.89°C and R² of 0.67. The model decomposes epistemic and aleatoric uncertainty, letting researchers prioritize which candidates are actually worth synthesizing.

⚗️
GPCR-SLM
PyTorch Transformers Knowledge Distillation
Small Language Model for GPCR Classification (86 Families, 33.5× Speedup)

GPCRs are the target of ~35% of all approved drugs, but classifying them at scale is computationally expensive. GPCR-SLM uses knowledge distillation to compress large protein LM knowledge into a lightweight transformer that classifies 86 GPCR families at 99% accuracy while being 33.5× faster. Validated on clinical variants, metagenomic sequences, and tumor-derived data. Also supports open-set recognition for novel families.

💊
Drug Toxicity
RDKit ChemBERT XGBoost SMILES
Multimodal Drug Toxicity Prediction Pipeline

A machine learning pipeline that combines SMILES representations, molecular fingerprints, and physicochemical descriptors with ChemBERT to predict drug-induced toxicity. Achieves 92% accuracy on cardiotoxicity prediction, significantly outperforming traditional QSAR baselines. Built as part of parameter-efficient deep learning work for computational drug discovery.

🫀
Cardiac ECG AI
TensorFlow CNN-VAE WFDB Federated
Privacy-Preserving 12-Lead ECG Analysis for Cardiac Risk Prediction

A CNN-VAE architecture for analyzing 12-lead ECG signals that directly addresses demographic and acquisition bias — a known problem in cardiac AI that causes models to perform worse on underrepresented populations. Achieves 88% sensitivity and 94% specificity. Privacy-preserving by design. Published in Springer Nature Scientific Reports, 2026.

Publications

Research Papers

AI-Enabled Privacy-Preserving Cardiac Diagnostics via Electrocardiograms
F. S. Shishir, C. J. Harvey, A. Gupta, A. Noheria, S. Shomaji
Springer Nature Scientific Reports, 2026
NbBayesLM: Bayesian Prediction of Nanobody Thermostability with Uncertainty Quantification
F. S. Shishir et al.
Frontiers in Bioinformatics, 2026
A Deep Learning Framework for Protein-to-Metal Binding Prediction Using Protein Language Models
F. S. Shishir, B. Sarker, F. Rahman, S. Shomaji
IEEE Trans. Computational Biology and Bioinformatics, 2025
Digital Twins in Healthcare IoT: A Systematic Review
M. R. Kabir, F. S. Shishir, S. Shomaji, S. Ray
High-Confidence Computing, 2025
Data-Driven Insights into Sustainability: AI-Powered Analysis of ESG Practices in Textile & Apparel
A. Magotra, M. R. I. Rana, F. S. Shishir, S. Shomaji
ITAA Annual Conference Proceedings, 2025
A Persistent Hierarchical Bloom Filter-based Framework for Authentication and Tracking of ICs
F. S. Shishir, M. M. Rizvee, T. Hossain, T. Hoque, D. Forte, S. Shomaji
arXiv:2408.16950, 2024
MetaLLM: Residue-wise Metal Ion Prediction Using Deep Transformer Model
F. S. Shishir, B. Sarker, F. Rahman, S. Shomaji
IWBBIO 2023, Granada, Spain
De Novo Drug Property Prediction using Graph Convolutional Neural Network
F. S. Shishir, K. Md. Hasib, S. Sakib, S. Maitra, F. M. Shah
IEEE R10-HTC, 2021
Artistic Natural Images Generation Using Neural Style Transfer
A. I. Chowdhury, F. S. Shishir, A. Islam, E. Ahmed, M. M. Rahman
Emerging Technologies in Data Mining and Information Security, Springer, 2021
Graph Theory for Dimensionality Reduction: A Case Study to Prognosticate Parkinson's
S. Maitra, T. Hossain, K. Md. Hasib, F. S. Shishir
IEEE IEMCON 2020
EsharaGAN: Disentangled Sign Language Representation Using InfoGAN
F. M. Shah, F. S. Shishir, T. Hossain
IEEE TENSYMP 2020
Brain Tumor Segmentation Techniques on Medical Images — A Review
F. M. Shah, F. S. Shishir, T. Hossain, et al.
International Journal of Scientific and Engineering Research, vol. 10, no. 2, 2020
Brain Tumor Detection using Convolutional Neural Network
T. Hossain, F. S. Shishir, M. Ashraf, M. D. A. Al Nasim, F. M. Shah
ICASERT 2019
A Novel Approach to Classify Bangla Sign Digits using Capsule Network
T. Hossain, F. S. Shishir, F. M. Shah
ICCIT 2019
Get in Touch

Let's Collaborate

I'm always interested in research collaborations, visiting opportunities, and conversations about computational biology, drug discovery, or biomedical AI. If you're working on something interesting — even tangentially related — feel free to reach out.

I typically reply within 24–48 hours.

📧
Email
shishir@ku.edu
🏛
Location
University of Kansas · Lawrence, KS
🐦
Twitter / X