Prof. Saeed delivered a distinguished invited talk entitled “Capturing Proteomic and Neuro Architecture Complexity using Advance Machine Learning Modelling” at the School of Computing, Faculty of Computing, Engineering and the Built Environment, Ulster University at Belfast Campus, Northern Ireland, UK.

In this talk, Dr. Saeed discussed different challenges and opportunities specific to AI models for biomedical and health data.

The lab proudly congratulates Dr. Fahad Almuqhim on the successful defense of his PhD dissertation titled:“Self-Supervised Representation Learning from Multi-Cohort Neuroimaging for Neurodevelopmental and Neurodegenerative Disorders.”.

Dr. Almuqhim’s research addresses a critical “identity crisis” in neuroimaging AI: Are our models actually identifying disease, or are they simply picking up on the technical quirks of a specific MRI scanner?

Under the guidance of Prof. Fahad Saeed at Florida International University, Almuqhim developed NeuroCLR. This novel, region-wise self-supervised contrastive learning framework is designed to filter out “site noise” and focus on what matters most: authentic neural signatures.

Key Breakthroughs in this dissertation:

• True Generalization: By training on massive multisite datasets like ABIDE and ADNI, NeuroCLR creates representations that remain accurate across different hospitals and cohorts.

• Neural Invariants: The research proves that self-learning models can identify universal brain patterns shared across different neurological disorders.

• Robust Biomarkers: These site-invariant models significantly improve the performance of downstream tasks, such as clinical diagnosis and classification.

His Dissertation Committee consisted of Dr. Angela Laird, Dr. Leonardo Bobadilla, Dr. Ananda Mondal, and Dr. Kaoutar Ben Ahmed.

Dr. Almuqhim also wanted to recognize the support and collaboration of his fellow lab members, whose contributions and discussions played an important role throughout this work.

We congratulate Dr. Almuqhim on this major milestone and look forward to his continued impact in AI-driven neuro-imaging research. He joined Imam Mohammad Ibn Saud Islamic University in Saudi Arabia, as Assistant Professor. Congratulations again!

We are proud to announce that Anju Singh has been selected for two prestigious undergraduate research programs:

• OURS FIU (Opportunities for Undergraduate Research at FIU) – providing funding and mentorship to support undergraduate research.
• UR2PhD (Undergraduate Research to PhD) – a national program designed to prepare undergraduates for advanced study and careers in research.

Both awards come with funding support, empowering Anju to continue impactful research at the intersection of computer science, biology, and bioinformatics.

Congratulations to Anju for this well-deserved recognition!

Bilal Shabbir presented latest research at the 73rd ASMS Conference on Mass Spectrometry and Allied Topics (ASMS 2025), held in Baltimore, Maryland. The poster, titled “Beyond Mass-Only Filtering: A Multitask Deep Learning Framework for Predicting Peptide Properties from Mass Spectrometry Data,” introduced a novel approach that leverages multitask deep learning to extract richer biological insights from MS data. This work moves beyond traditional mass-based peptide filtering by jointly learning multiple peptide properties, potentially transforming workflows in proteomics and accelerating peptide identification. The presentation drew significant interest from both computational and experimental researchers for its innovation and broad applicability in mass spectrometry-based proteomics.

The College of Engineering and Computing (CEC) 3-Minute Thesis (3MT) competition challenges graduate students to present their research concisely and compellingly to a non-specialist audience within three minutes. Paras Parani participated in this prestigious competition, showcasing his innovative research on utilizing Large Language Models (LLMs) and Vision Transformers (ViTs) for epileptic seizure prediction. His latest findings demonstrate the potential of transformer-based architectures to achieve significant accuracy while maintaining computational efficiency for real-time applications. Out of 13 participants, Paras was selected among the top two and has been nominated by the college to represent CEC at the university-wide competition in January.

The American Epilepsy Society (AES) Fellowship is a reward for early career medical professionals and researchers in the area of epilepsy. Approximately 105 fellows are selected for this prestigious award each year out of thousands of applicants. The award comes with a 1-year complimentary membership to the AES, registration fee waiver, and a $575 USD award to travel to 2024 AES Annual meeting (in Los Angeles, CA this year). Attending this event and a 1-year membership will provide Dr. Umair with further resources and networking opportunities to take the early lab’s early seizure prediction research forward.

Preliminary results from the work of Paras Parani, Dr. Umair Mohammad, and Dr. Fahad Saeed on lightweight seizure prediction models were accepted at the 2024 IEEE International Conference on Big Data workshop HPC-BOD. This research introduces ESPFormer, a lightweight transformer-based model, designed to predict epileptic seizures using patient-independent EEG data. By tokenizing and adapting multi-channel EEG time-series data, the model achieves a balance between accuracy and computational efficiency, enabling near real-time prediction capabilities. The proposed architecture outperforms resource-intensive models like Vision Transformers (ViTs) and Large Language Models (LLMs) on several benchmarks. Successful implementation of ESPFormer marks a significant step forward in developing scalable and effective seizure prediction technologies.

Preliminary results from the work of Paras Parani, Dr. Umair Mohammad and Dr. Fahad Saeed on early seizure prediction using pre-trained large language models (LLMs) and vision transformers (ViTs) were accepted at the 8th International Conference on Data Science and Machine Learning (CDMA 2024). The work proposes techniques to modify multi-channel time-series electroencephalography (EEG) data and pre-trained ViTs and LLMs to predict seizures with the partial re-design and re-training of only the first and last layers. Successful execution of this strategy will be a game-changer for seizure prediction technologies. It will allow for the accurate and precise prediction of seizures using models with billions of parameters that have been trained on huge volumes of data by applying it to retroactive EEG datasets that are comparable much smaller in size.

Saeed Lab webpage (https://pcdslab.github.io/) is now up and running. This will ensure that all members of the team can contribute to the webpage for better science communication to the scientific community as well as general audience. We are very excited to be here!