diff --git a/_includes/themes/lab/paper.html b/_includes/themes/lab/paper.html index 7acb310ce..fb8f87b36 100755 --- a/_includes/themes/lab/paper.html +++ b/_includes/themes/lab/paper.html @@ -160,7 +160,7 @@
- Open Science Framework + Open Science Framework
{% endif %} diff --git a/assets/images/news/Certificate.jpg b/assets/images/news/Certificate.jpg new file mode 100644 index 000000000..ba87ed47d Binary files /dev/null and b/assets/images/news/Certificate.jpg differ diff --git a/assets/images/news/Certificate.pdf b/assets/images/news/Certificate.pdf new file mode 100644 index 000000000..3990c3b72 Binary files /dev/null and b/assets/images/news/Certificate.pdf differ diff --git a/assets/images/papers/acm.jpg b/assets/images/papers/acm.jpg new file mode 100644 index 000000000..e3c796c00 Binary files /dev/null and b/assets/images/papers/acm.jpg differ diff --git a/assets/images/papers/brain-informatics.png b/assets/images/papers/brain-informatics.png new file mode 100644 index 000000000..7b969bb69 Binary files /dev/null and b/assets/images/papers/brain-informatics.png differ diff --git a/assets/images/papers/methodsx.jpg b/assets/images/papers/methodsx.jpg new file mode 100644 index 000000000..017b68d72 Binary files /dev/null and b/assets/images/papers/methodsx.jpg differ diff --git a/assets/images/papers/neuroinformatics.jpeg b/assets/images/papers/neuroinformatics.jpeg new file mode 100644 index 000000000..fad34b2c9 Binary files /dev/null and b/assets/images/papers/neuroinformatics.jpeg differ diff --git a/assets/images/papers/plos.jpg b/assets/images/papers/plos.jpg new file mode 100644 index 000000000..b6a69c876 Binary files /dev/null and b/assets/images/papers/plos.jpg differ diff --git a/assets/images/projects/2026-02-18-molecules-proteins.png b/assets/images/projects/2026-02-18-molecules-proteins.png new file mode 100644 index 000000000..744e01fb6 Binary files /dev/null and b/assets/images/projects/2026-02-18-molecules-proteins.png differ diff --git a/assets/images/team/Brett_picture.jpg b/assets/images/team/Brett_picture.jpg new file mode 100644 index 000000000..162657e60 Binary files /dev/null and b/assets/images/team/Brett_picture.jpg differ diff --git a/assets/images/team/Group_2019.jpg b/assets/images/team/Group_2019.jpg new file mode 100644 index 000000000..a6a2c437d Binary files /dev/null and b/assets/images/team/Group_2019.jpg differ diff --git a/assets/images/team/Mohammed_Khubaib.png b/assets/images/team/Mohammed_Khubaib.png new file mode 100644 index 000000000..ad467b6a2 Binary files /dev/null and b/assets/images/team/Mohammed_Khubaib.png differ diff --git a/assets/images/team/RobertLoredo_BwHiRes.png b/assets/images/team/RobertLoredo_BwHiRes.png new file mode 100644 index 000000000..f000da512 Binary files /dev/null and b/assets/images/team/RobertLoredo_BwHiRes.png differ diff --git a/assets/images/team/avash_pic.jpg b/assets/images/team/avash_pic.jpg new file mode 100644 index 000000000..7cbfe39bd Binary files /dev/null and b/assets/images/team/avash_pic.jpg differ diff --git a/assets/images/team/gabriel_oliveira.jpg b/assets/images/team/gabriel_oliveira.jpg new file mode 100644 index 000000000..e2d07ee88 Binary files /dev/null and b/assets/images/team/gabriel_oliveira.jpg differ diff --git a/assets/images/team/group_2015.jpg b/assets/images/team/group_2015.jpg new file mode 100644 index 000000000..b92eb1c0b Binary files /dev/null and b/assets/images/team/group_2015.jpg differ diff --git a/assets/images/team/group_2016.jpg b/assets/images/team/group_2016.jpg new file mode 100644 index 000000000..ddda4a38b Binary files /dev/null and b/assets/images/team/group_2016.jpg differ diff --git a/assets/images/team/group_2017.jpg b/assets/images/team/group_2017.jpg new file mode 100644 index 000000000..5b1681bba Binary files /dev/null and b/assets/images/team/group_2017.jpg differ diff --git a/assets/images/team/group_2018.jpg b/assets/images/team/group_2018.jpg new file mode 100644 index 000000000..efc6d34d7 Binary files /dev/null and b/assets/images/team/group_2018.jpg differ diff --git a/assets/pdfs/Avash_Palikhe_CV.pdf b/assets/pdfs/Avash_Palikhe_CV.pdf new file mode 100644 index 000000000..ffe27fe91 Binary files /dev/null and b/assets/pdfs/Avash_Palikhe_CV.pdf differ diff --git a/assets/pdfs/BBrett_CSR.pdf b/assets/pdfs/BBrett_CSR.pdf new file mode 100644 index 000000000..502538a2c Binary files /dev/null and b/assets/pdfs/BBrett_CSR.pdf differ diff --git a/assets/pdfs/CV_Gabriel.pdf b/assets/pdfs/CV_Gabriel.pdf new file mode 100644 index 000000000..4191676fe Binary files /dev/null and b/assets/pdfs/CV_Gabriel.pdf differ diff --git a/assets/pdfs/CV_Robert_Loredo.pdf b/assets/pdfs/CV_Robert_Loredo.pdf new file mode 100644 index 000000000..445d13050 Binary files /dev/null and b/assets/pdfs/CV_Robert_Loredo.pdf differ diff --git a/assets/pdfs/Mohammed_Khubaib_CV.pdf b/assets/pdfs/Mohammed_Khubaib_CV.pdf new file mode 100644 index 000000000..cdd43809b Binary files /dev/null and b/assets/pdfs/Mohammed_Khubaib_CV.pdf differ diff --git a/assets/themes/lab/images/banner/banner-2.png b/assets/themes/lab/images/banner/banner-2.png new file mode 100644 index 000000000..220ad1409 Binary files /dev/null and b/assets/themes/lab/images/banner/banner-2.png differ diff --git a/assets/themes/lab/images/banner/banner-3.png b/assets/themes/lab/images/banner/banner-3.png new file mode 100644 index 000000000..5c546c667 Binary files /dev/null and b/assets/themes/lab/images/banner/banner-3.png differ diff --git a/assets/themes/lab/images/banner/banner-4.png b/assets/themes/lab/images/banner/banner-4.png new file mode 100644 index 000000000..4e7bca1b9 Binary files /dev/null and b/assets/themes/lab/images/banner/banner-4.png differ diff --git a/news/_posts/2026-02-11-Saeed-Seminar.md b/news/_posts/2026-02-11-Saeed-Seminar.md new file mode 100644 index 000000000..3b22efbe4 --- /dev/null +++ b/news/_posts/2026-02-11-Saeed-Seminar.md @@ -0,0 +1,15 @@ +--- +layout: news +title: Invited Distinguished Research Seminar, Ulster University, Ireland UK. +tags: [talks] +image: +excerpt: Prof. Saeed delivers a distinguished invited talk at Ulster University, UK. +--- + +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. + +![Certificate of Distinguished Talk](/assets/images/news/Certificate.jpg) + + diff --git a/papers/_posts/2021-01-01-specollate--deep-cross-modal-similarity-network-for-mass-spectrometry-data-based-peptide-deductions.md b/papers/_posts/2021-01-01-specollate--deep-cross-modal-similarity-network-for-mass-spectrometry-data-based-peptide-deductions.md index 6004ffd6a..179a19bde 100644 --- a/papers/_posts/2021-01-01-specollate--deep-cross-modal-similarity-network-for-mass-spectrometry-data-based-peptide-deductions.md +++ b/papers/_posts/2021-01-01-specollate--deep-cross-modal-similarity-network-for-mass-spectrometry-data-based-peptide-deductions.md @@ -9,7 +9,7 @@ volume: 16 issue: pages: e0259349 is_published: True -image: /assets/images/papers/plos.png +image: /assets/images/papers/plos.jpg projects: [ML-MS] tags: [] diff --git a/papers/_posts/2025-02-02-survey.md b/papers/_posts/2025-02-02-survey.md index 9808c618c..eb5871253 100644 --- a/papers/_posts/2025-02-02-survey.md +++ b/papers/_posts/2025-02-02-survey.md @@ -9,7 +9,7 @@ volume: issue: Vol. 12, article 8 pages: 1-27 is_published: True -image: /assets/images/papers/springer.png +image: /assets/images/papers/brain-informatics.png projects: [ML-ADRD] tags: [journal] diff --git a/papers/_posts/2024-07-22-MLSPred-Bench.md b/papers/_posts/2025-07-22-MLSPred-Bench.md similarity index 77% rename from papers/_posts/2024-07-22-MLSPred-Bench.md rename to papers/_posts/2025-07-22-MLSPred-Bench.md index 2cd4b62ba..b37cece44 100644 --- a/papers/_posts/2024-07-22-MLSPred-Bench.md +++ b/papers/_posts/2025-07-22-MLSPred-Bench.md @@ -1,24 +1,24 @@ --- layout: paper -title: "MLSPred-Bench: ML-Ready Benchmark Leveraging Seizure Detection EEG data for Predictive Models" +title: "MLSPred-Bench: Transforming Electroencephalography (EEG) Datasets into Machine Learning-Ready Seizure Prediction Benchmarks" nickname: MLSPred-Bench-paper authors: "Mohammad, Umair; Saeed, Fahad; " -year: "2024" -journal: "bioRxiv" +year: "2025" +journal: "Elsevier MethodsX" volume: issue: pages: 1-8 -is_published: False -image: /assets/images/papers/biorxiv.png -projects: [ML-seizure] -tags: [preprint] +is_published: True +image: /assets/images/papers/methodsx.jpg +projects: [ML-seizure, MLSPred-Bench] +tags: [ML, EEG, Epilepsy] # Text -fulltext: https://www.biorxiv.org/content/10.1101/2024.07.17.604006v1 +fulltext: https://doi.org/10.1016/j.mex.2025.103574 pdf: -pdflink: https://www.biorxiv.org/content/10.1101/2024.07.17.604006v1.full.pdf +pdflink: pmcid: -preprint: +preprint: https://www.biorxiv.org/content/10.1101/2024.07.17.604006v1.full.pdf supplement: # Links @@ -26,12 +26,12 @@ doi: "10.1101/2024.07.17.604006" pmid: # Data and code -github: [] +github: [https://github.com/pcdslab/MLSPred-Bench] neurovault: openneuro: [] figshare: figshare_names: -osf: +osf: --- {% include JB/setup %} diff --git a/papers/_posts/2025-08-18-Overcoming-Site-Variability.md b/papers/_posts/2025-08-18-Overcoming-Site-Variability.md new file mode 100644 index 000000000..20594dd19 --- /dev/null +++ b/papers/_posts/2025-08-18-Overcoming-Site-Variability.md @@ -0,0 +1,40 @@ +--- +layout: paper +title: "Overcoming Site Variability in Multisite fMRI Studies: An Autoencoder Framework for Enhanced Generalizability of Machine Learning Models" +nickname: AE-Harmonization-paper +authors: "Almuqhim, Fahad; Saeed, Fahad; " +year: "2025" +journal: "Springer Neuroinformatics" +volume: 23 +issue: article 46 +pages: +is_published: True +image: /assets/images/papers/neuroinformatics.jpeg +projects: [ML-brain-imaging] +tags: [ML, AE, ComBat, ASD, Multisite] + +# Text +fulltext: https://link.springer.com/article/10.1007/s12021-025-09746-1 +pdf: +pdflink: https://link.springer.com/content/pdf/10.1007/s12021-025-09746-1.pdf +pmcid: +preprint: +supplement: + +# Links +doi: 10.1007/s12021-025-09746-1 +pmid: + +# Data and code +github: [https://github.com/pcdslab/Autoencoder-fMRI-Harmonization] +neurovault: +openneuro: [] +figshare: +figshare_names: +osf: [d8253] +--- +{% include JB/setup %} + +# Abstract + +Harmonizing multisite functional magnetic resonance imaging (fMRI) data is crucial for eliminating site-specific variability that hinders the generalizability of machine learning models. Traditional harmonization techniques, such as ComBat, depend on additive and multiplicative factors, and may struggle to capture the non-linear interactions between scanner hardware, acquisition protocols, and signal variations between different imaging sites. In addition, these statistical techniques require data from all the sites during their model training which may have the unintended consequence of data leakage for ML models trained using this harmonized data. The ML models trained using this harmonized data may result in low reliability and reproducibility when tested on unseen data sets, limiting their applicability for general clinical usage. In this study, we propose Autoencoders (AEs) as an alternative for harmonizing multisite fMRI data. Our designed and developed framework leverages the non-linear representation learning capabilities of AEs to reduce site-specific effects while preserving biologically meaningful features. Our evaluation using Autism Brain Imaging Data Exchange I (ABIDE-I) dataset, containing 1,035 subjects collected from 17 centers demonstrates statistically significant improvements in leave-one-site-out (LOSO) cross-validation evaluations. All AE variants (AE, SAE, TAE, and DAE) significantly outperformed the baseline mode (p<0.01), with mean accuracy improvements ranging from 3.41% to 5.04%. Our findings demonstrate the potential of AEs to harmonize multisite neuroimaging data effectively enabling robust downstream analyses across various neuroscience applications while reducing data-leakage, and preservation of neurobiological features. Our open-source code is made available at https://github.com/pcdslab/Autoencoder-fMRI-Harmonization \ No newline at end of file diff --git a/papers/_posts/2025-12-1-Raptor.md b/papers/_posts/2025-12-1-Raptor.md new file mode 100644 index 000000000..0e843a268 --- /dev/null +++ b/papers/_posts/2025-12-1-Raptor.md @@ -0,0 +1,40 @@ +--- +layout: paper +title: "RAPTOR: Reconfigurable Advanced Platform for Trans- disciplinary Open Research" +nickname: Raptor-colab-paper +authors: "Hamed Najafi; Pratik Poudel; Kiavash Bahreini; Julio Ibarra; Fahad Saeed; Yuepeng Li; Jayantha Obeysekera; Jason Liu;" +year: "2025" +journal: "Proceedings of 15th Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures (FlexScience)" +volume: +issue: Article 50 +pages: 1 - 5 +is_published: True +image: /assets/images/papers/acm.jpg +projects: [HPC-MS] +tags: [ML, AE, ComBat, ASD, Multisite] + +# Text +fulltext: https://dl.acm.org/doi/pdf/10.1145/3731545.3744665 +pdf: +pdflink: +pmcid: +preprint: +supplement: + +# Links +doi: 10.1145/3731545.3744665 +pmid: + +# Data and code +github: [] +neurovault: +openneuro: [] +figshare: +figshare_names: +osf: [] +--- +{% include JB/setup %} + +# Abstract + +Scientific research is increasingly relying on complex workflows that span multiple computing paradigms, including high-performance computing (HPC), high-throughput computing (HTC), and machine learning/artificial intelligence (ML/AI). Traditional monolithic computing infrastructures often struggle to accommodate these diverse and evolving demands. The Reconfigurable Advanced Platform for Transdisciplinary Open Research (RAPTOR) addresses this challenge by providing a dynamically reconfigurable computing environment that integrates with federated resources. RAPTOR's architecture enables dynamic provisioning between an HPC cluster and the Chameleon Cloud platform based on workload requirements, supporting bare-metal customization for specialized applications. This paper focuses on RAPTOR's reconfigurability features and demonstrates their effectiveness through quantitative performance evaluations across four scientific domains: computational proteomics, climate modeling, weather research, and hurricane risk assessment. Our results demonstrate that RAPTOR's reconfigurable design significantly enhances research productivity by providing an appropriate computing environment for diverse computational needs. diff --git a/papers/_posts/2025-12-1-fairGNN-WOD.md b/papers/_posts/2025-12-1-fairGNN-WOD.md new file mode 100644 index 000000000..b2ec52b64 --- /dev/null +++ b/papers/_posts/2025-12-1-fairGNN-WOD.md @@ -0,0 +1,40 @@ +--- +layout: paper +title: "fairGNN-WOD: fair graph learning without demographics" +nickname: fairGNN-colab-paper +authors: "Zichong Wang; Fang Liu; Shimei Pan; Jun Liu; Fahad Saeed; Meikang Qiu; Wenbin Zhang;" +year: "2025" +journal: "IJCAI '25: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence" +volume: +issue: Article 63 +pages: 556 - 564 +is_published: True +image: /assets/images/papers/acm.jpg +projects: [ML-brain-imaging] +tags: [ML, ASD, ADRD, Multisite] + +# Text +fulltext: +pdf: +pdflink: https://www.ijcai.org/proceedings/2025/0063.pdf +pmcid: +preprint: +supplement: + +# Links +doi: 10.24963/ijcai.2025/63 +pmid: + +# Data and code +github: [] +neurovault: +openneuro: [] +figshare: +figshare_names: +osf: [] +--- +{% include JB/setup %} + +# Abstract + +Graph Neural Networks (GNNs) have excelled in diverse applications due to their outstanding predictive performance, yet they often overlook fairness considerations, prompting numerous recent efforts to address this societal concern. However, most fair GNNs assume complete demographics by design, which is impractical in most real-world socially sensitive applications due to privacy, legal, or regulatory restrictions. For example, the Consumer Financial Protection Bureau (CFPB) mandates that creditors ensure fairness without requesting or collecting information about an applicant's race, religion, nationality, sex, or other demographics. To this end, this paper proposes fairGNN-WOD, a first-of-its-kind framework that considers mitigating unfairness in graph learning without using demographic information. In addition, this paper provides a theoretical perspective on analyzing bias in node representations and establishes the relationship between utility and fairness objectives. Experiments on three real-world graph datasets illustrate that fairGNN-WOD outperforms state-of-the-art baselines in achieving fairness but also maintains comparable prediction performance. \ No newline at end of file diff --git a/papers/_posts/2026-01-01-systems-and-methods-for-pred-seizures.md b/papers/_posts/2026-01-01-systems-and-methods-for-pred-seizures.md new file mode 100644 index 000000000..7dd2a72b3 --- /dev/null +++ b/papers/_posts/2026-01-01-systems-and-methods-for-pred-seizures.md @@ -0,0 +1,40 @@ +--- +layout: paper +title: "Systems and methods for patient-specific epileptic seizure prediction" +nickname: seizure-patent +authors: "Mohammad, Umair; Saeed, Fahad;" +year: "2026" +journal: "US Patent US-12544002-B2" +volume: +issue: +pages: +is_published: True +image: /assets/images/papers/uspto.png +projects: [ML-seizure] +tags: [patent] + +# Text +fulltext: https://ppubs.uspto.gov/api/patents/html/12544002?source=USPAT&requestToken=eyJzdWIiOiI1ODY2Y2I2YS02ZDc5LTRmMTAtOWI2Ni05YTk3ZjgzNjA5MGEiLCJ2ZXIiOiI0ODcwYTRlMi00YThhLTQ4NzQtOTIyOC01NTE0NjRmNGY0ZmYiLCJleHAiOjB9 +pdf: https://ppubs.uspto.gov/api/pdf/downloadPdf/12544002?requestToken=eyJzdWIiOiI1ODY2Y2I2YS02ZDc5LTRmMTAtOWI2Ni05YTk3ZjgzNjA5MGEiLCJ2ZXIiOiI0ODcwYTRlMi00YThhLTQ4NzQtOTIyOC01NTE0NjRmNGY0ZmYiLCJleHAiOjB9 +pdflink: +pmcid: +preprint: +supplement: + +# Links +doi: "" +pmid: + +# Data and code +github: [] +neurovault: +openneuro: [] +figshare: +figshare_names: +osf: +--- +{% include JB/setup %} + +# Abstract + +A patient specific epileptic seizure(ES) prediction model using only electroencephalography (EEG) data with residual neural networks (ResNets) and transfer learning (TL) techniques (i.e., SPERTL) is provided. One exemplary provided model was trained on EEG data from 23 patients with a seizure prediction horizon (SPH) of 5 minutes and used the validation data to plot precision-recall curves to aid in selecting preferred thresholds. Testing on unseen data shows the provided model outperforms related art methods by achieving the highest average sensitivity of 88.1%, specificity of 92.3%, and accuracy of 92.3%. Results also demonstrate the proposed model is less susceptible to false positives while maintaining a high positive prediction rate. diff --git a/papers/_posts/2026-02-18-FiCOPS.md b/papers/_posts/2026-02-18-FiCOPS.md new file mode 100644 index 000000000..d5791642d --- /dev/null +++ b/papers/_posts/2026-02-18-FiCOPS.md @@ -0,0 +1,40 @@ +--- +layout: paper +title: "FiCOPS: Hardware and Software Co-Design of FPGA Computational Framework for Mass Spectrometry-Based Peptide Database Search" +nickname: FiCOPS-paper +authors: "Kumar, Sumesh; Zambreno, Joseph; Khokhar, Ashfaq; Akram, Shoaib; Saeed, Fahad;" +year: "2026" +journal: +volume: +issue: +pages: +is_published: False +image: /assets/images/papers/biorxiv.png +projects: [HPC-MS] +tags: [preprint] + +# Text +fulltext: https://www.biorxiv.org/content/10.64898/2026.02.15.706012v1 +pdf: +pdflink: https://www.biorxiv.org/content/10.64898/2026.02.15.706012v1.full.pdf +pmcid: +preprint: +supplement: + +# Links +doi: https://doi.org/10.64898/2026.02.15.706012 +pmid: + +# Data and code +github: [] +neurovault: +openneuro: [] +figshare: +figshare_names: +osf: [] +--- +{% include JB/setup %} + +# Abstract + +Improving the speed and efficiency of database search algorithms that deduce peptides from mass spectrometry (MS) data has been an active area of research for more than three decades. The significance of the need for faster database search methods has rapidly increased due to the growing interest in studying non-model organisms, meta-proteomics, and proteogenomic data, which are notorious for their enormous search space. Poor scalability of serial algorithms with the growing size of the database and increasing parameters of post-translational modifications is a widely recognized problem. While high-performance computing techniques can be used on supercomputing machines, the need for real-time, on-the-instrument solutions necessitates the development of an efficient system-on-chip that optimizes design constraints such as cost, performance, and power of the system. To show case that such a system can work, we present an FPGA-based computational framework called FiCOPS to accelerate database search using a hardware/software co-design methodology. First, we theoretically analyze the database-search algorithm (closed-search) to reveal opportunities for parallelism and uncover computational bottlenecks. We then design an FPGA-based architectural template to exploit parallelism inherent in the search workload. We also formulate an analytical performance model for the architecture template to perform rapid design space exploration and find a near-optimal accelerator configuration. Finally, we implement our design on the Intel Stratix 10 FPGA platform and evaluate it using real-world datasets. Our experiments demonstrate that FiCOPS achieves 3.5 times speed-up over existing CPU solutions and 3 times and 5 times reduction in power consumption compared to existing CPU and GPU solutions. diff --git a/papers/_posts/2026-02-18-MolDeBERTa.md b/papers/_posts/2026-02-18-MolDeBERTa.md new file mode 100644 index 000000000..0afef53cd --- /dev/null +++ b/papers/_posts/2026-02-18-MolDeBERTa.md @@ -0,0 +1,40 @@ +--- +layout: paper +title: "MolDeBERTa: Foundational Model for Physicochemical and Structural-Informed Molecular Representation Learning" +nickname: MolDeBERTa-paper +authors: "Oliveira, Gabriel Bianchin; Saeed, Fahad;" +year: "2026" +journal: +volume: +issue: +pages: +is_published: False +image: /assets/images/papers/biorxiv.png +projects: [ML-molecular-protein-representation] +tags: [preprint] + +# Text +fulltext: https://www.biorxiv.org/content/10.64898/2026.02.15.706011v1 +pdf: +pdflink: https://www.biorxiv.org/content/10.64898/2026.02.15.706011v1.full.pdf +pmcid: +preprint: +supplement: + +# Links +doi: https://doi.org/10.64898/2026.02.15.706011 +pmid: + +# Data and code +github: [https://github.com/pcdslab/MolDeBERTa] +neurovault: +openneuro: [] +figshare: +figshare_names: +osf: [] +--- +{% include JB/setup %} + +# Abstract + +Foundational models that learn the language of molecules are essential for accelerating the material and drug discovery. These self-learning models can be trained on a large number of unlabelled molecules, enabling applications like property prediction, molecule de-sign (de novo generation, optimization), and screening for specific functions. However, existing molecular language models are built upon first-generation transformer architectures and are pretrained using masked language modeling, a generic token-level objective that is agnostic to physicochemical and structural molecular properties. Here we introduce MolDe-BERTa, a structure-informed self-supervised molecular encoder that leverages a byte-level Byte-Pair Encoding (BPE) tokenization strategy. MolDeBERTa is pretrained on up to 123 million SMILES molecules from PubChem, representing one of the largest publicly available SMILES-based corpora. To achieve this, we introduce three novel pretraining objectives designed to inject strong inductive biases for molecular properties and structural similarity directly into the latent space, resulting in reduced gap between linguistic chemical representations and physical molecular properties. The model was then systematically investigated across three architectural scales, two dataset sizes, and five distinct pretraining objectives. MolDeBERTa when evaluated on 9 downstream MoleculeNet benchmarks outperformed existing masked language models, achieving up to a 16% reduction in regression error and improvements of up to 3.0 ROC-AUC points on classification benchmarks. MolDeBERTa advances unsupervised encoder-based foundational models at scale both for pretraining data and downstream evaluation, enabling data-efficient chemistry-informed representation learning. The source code is publicly available at https://github.com/pcdslab/MolDeBERTa, and Hugging Face at https://huggingface.co/collections/SaeedLab/moldeberta. All the pretraining datasets are available at https://huggingface.co/datasets/SaeedLab/MolDeBERTa. \ No newline at end of file diff --git a/papers/_posts/2026-02-18-TITAN-BBB.md b/papers/_posts/2026-02-18-TITAN-BBB.md new file mode 100644 index 000000000..6b132b3ee --- /dev/null +++ b/papers/_posts/2026-02-18-TITAN-BBB.md @@ -0,0 +1,40 @@ +--- +layout: paper +title: "TITAN-BBB: Predicting BBB Permeability using Multi-Modal Deep-Learning Models" +nickname: TITAN-BBB-paper +authors: "Oliveira, Gabriel Bianchin; Saeed, Fahad;" +year: "2026" +journal: +volume: +issue: +pages: +is_published: False +image: /assets/images/papers/biorxiv.png +projects: [ML-molecular-protein-representation] +tags: [preprint] + +# Text +fulltext: https://www.biorxiv.org/content/10.64898/2026.02.15.706007v1 +pdf: +pdflink: https://www.biorxiv.org/content/10.64898/2026.02.15.706007v1.full.pdf +pmcid: +preprint: +supplement: + +# Links +doi: https://doi.org/10.64898/2026.02.15.706007 +pmid: + +# Data and code +github: [https://github.com/pcdslab/TITAN-BBB] +neurovault: +openneuro: [] +figshare: +figshare_names: +osf: [] +--- +{% include JB/setup %} + +# Abstract + +Computational prediction of blood-brain barrier (BBB) permeability has emerged as a vital alternative to traditional experimental assays, which are often resource-intensive and low-throughput to meet the demands of early-stage drug discovery. While early machine learn-ing approaches have shown promise, integration of traditional chemical descriptors with deep learning embeddings remains an underexplored frontier. In this paper, we introduce TITAN-BBB, a multi-modal deep-learning architecture that utilizes tabular, image, and text-based features and combines them using attention mechanisms. To evaluate, we aggregated multiple literature sources to create the largest BBB permeability dataset to date, enabling robust training for both classification and regression tasks. Our results demonstrate that TITAN-BBB achieves 86.5% of balanced accuracy on classification tasks and 0.436 of mean absolute error for regression, outperforming the state-of-the-art by 3.1 percentage points in balanced accuracy and reducing the regression error by 20%. Our approach also outperforms state-of-the-art models in both classification and regression performance, demonstrating the benefits of combining deep and domain-specific representations. The source code is publicly available at https://github.com/pcdslab/TITAN-BBB. The inference-ready model is hosted on Hugging Face at https://huggingface.co/SaeedLab/TITAN-BBB, and the aggregated BBB permeability datasets are available at https://huggingface.co/datasets/SaeedLab/BBBP. \ No newline at end of file diff --git a/papers/_posts/2026-02-23-dom-formula-assignment.md b/papers/_posts/2026-02-23-dom-formula-assignment.md new file mode 100644 index 000000000..54d48fe22 --- /dev/null +++ b/papers/_posts/2026-02-23-dom-formula-assignment.md @@ -0,0 +1,40 @@ +--- +layout: paper +title: "A Machine Learning and Benchmarking Approach for Molecular Formula Assignment of Ultra High-Resolution Mass Spectrometry Data from Complex Mixtures" +nickname: dom-formula-assignment-paper +authors: "Shabbir, Bilal; Oliveira, Pablo R B; Fernandez-Lima, Francisco; Saeed, Fahad;" +year: "2026" +journal: +volume: +issue: +pages: +is_published: False +image: /assets/images/papers/biorxiv.png +projects: [ML-MS] +tags: [preprint] + +# Text +fulltext: https://www.biorxiv.org/content/10.64898/2026.02.17.706479v1 +pdf: +pdflink: https://www.biorxiv.org/content/10.64898/2026.02.17.706479v1.full.pdf +pmcid: +preprint: +supplement: + +# Links +doi: https://doi.org/10.64898/2026.02.17.706479 +pmid: + +# Data and code +github: [https://github.com/pcdslab/dom-formula-assignment-using-ml] +neurovault: +openneuro: [] +figshare: +figshare_names: +osf: [] +--- +{% include JB/setup %} + +# Abstract + +A machine learning approach to molecular formula assignment is crucial for unlocking the full potential of ultra-high resolution mass spectrometry (UHRMS) when analyzing complex mixtures. By combining data-driven models with rigorous benchmarking, the accuracy, consistency, and speed in identifying plausible molecular formulas from vast spectral datasets can be improved. Compared with traditional de novo methods that rely heavily on rule-based heuristics, and manual parameter tuning, machine learning approaches can capture complex patterns in data and adapt more readily to diverse sample types. In this paper, we describe the application of a machine learning methods using the k-nearest neighbors (KNN) algorithm trained on curated chemical formula datasets of UHRMS analysis of dissolved organic matter (DOM) covering the saline river continuum and tropical wet/dry season variability. The influence of the mass accuracy (training set with 0.15-1ppm) was evaluated on a blind test set of DOMs of different geographical origins. A Decision Tree Regressor (DTR) and Random Forest Regressor (RFR) based on mass accuracy (<1ppm) was used. Results from our ML models exhibit 43% more formulas annotated than traditional methods (5796 vs 4047), Model-Synthetic achieved 99.9% assignment rate and annotated/assigned 2x more formulas (8,268 vs 4047). DTR and RFR achieved formula-level accuracies (FA) of 86.5% and 60.4%, respectively. Overall, results show an increase in formula assignment when compared with traditional methods. This ultimately enables more reliable characterization of complex natural and engineered systems, supporting advances in fields such as environmental science, metabolomics, and petroleomics. Furthermore, the novel data set produced for this study is made publicly available, establishing an initial benchmark for molecular formula assignment in UHRMS using machine learning. The dataset and code are publicly available at: https://github.com/pcdslab/dom-formula-assignment-using-ml. \ No newline at end of file diff --git a/projects/_posts/2024-06-22-MLSPred-Bench.md b/projects/_posts/2024-06-22-MLSPred-Bench.md index d79173084..a6177443f 100644 --- a/projects/_posts/2024-06-22-MLSPred-Bench.md +++ b/projects/_posts/2024-06-22-MLSPred-Bench.md @@ -28,6 +28,19 @@ MLSPred-Bench will create 12 different benchmarks based on different values of t For each benchmark, MLSPred-Bench draws preictal segments of length from the SPH duration. We assume there is a gap equal to the SOP in minutes before the start of a seizure where the SPH ends. The datasets are class-balanced where an equal amount of interictal samples are drawn from sessions of the same subject where there were no seizures. +We designed and developed a method called MLSPred-Bench that can be used for converting any EEG big data annotated for detection into ML-ready data suitable for prediction. We apply our methods to the existing EEG data corpus to generate 12 ML-ready benchmarks comprising data for training, validating, and testing seizure prediction models. Our strategy uses different variations of seizure prediction horizon (SPH) and the seizure occurrence period (SOP) to produce more than 150GB of ML-ready data. We hope that the generated benchmarking data will be utilized by various computational groups for their seizure prediction model development. + +Send an email at fsaeed@fiu.edu if you want to get pre-processed MLSPred-Bench data. + +The work can be summarized as follows: +1. Extract short preictal and interictal segments from long-duration annotated EEG montages. +2. Generate a comprehensive list of ML-ready benchmarks with varying SPH and SOP. +3. Technically validate the generated data with multiple ML and DL models with up-to 88.73% validation accuracy +4. Opensource code and related materials are available at https://github.com/pcdslab/MLSPred-Bench. + + + + ## Participate Data collection and curation for this study is complete. diff --git a/projects/_posts/2026-02-18-ML-molecules-proteins.md b/projects/_posts/2026-02-18-ML-molecules-proteins.md new file mode 100644 index 000000000..51291e55c --- /dev/null +++ b/projects/_posts/2026-02-18-ML-molecules-proteins.md @@ -0,0 +1,31 @@ +--- +layout: project +title: "Molecular and Protein Representation Learning" +contributors: [Prof-S,gabrielbianchin] +handle: ML-molecular-protein-representation +status: analysis +type: Method Development + +# Optional +website: +grant: [{id: NIH}] +image: /assets/images/projects/2026-02-18-molecules-proteins.png +tagline: 'Machine learning and foundation models for molecular and protein representation learning and biomedical applications' +tags: [molecules,proteins] + +# Data and code +github: [] +neurovault: +openneuro: +figshare: +figshare_names: +osf: +--- +{% include JB/setup %} + +This project focuses on developing advanced machine learning and foundational models for molecular and protein representation learning. The research aims to integrate physicochemical properties, structural information, and dynamic biological signals into scalable deep learning architectures. By leveraging large-scale pretraining, self-supervised learning, and multimodal modeling, the project seeks to bridge the gap between data-driven representations and real-world biological functionality. The resulting models enable a wide range of applications, including molecular property prediction, drug discovery, protein function annotation, and biomedical data analysis. Ultimately, this research aims to advance AI-driven approaches that can improve our understanding of biological systems and accelerate translational applications in precision medicine and therapeutics. + + +## Methods + +Method development for this work is ongoing. diff --git a/projects/index.html b/projects/index.html index 09fc0c6a1..8877ed819 100644 --- a/projects/index.html +++ b/projects/index.html @@ -51,6 +51,12 @@

+ ![Saeed Lab Research Overview](/assets/themes/lab/images/banner/banner-2.png) + + + + +
diff --git a/software/_posts/2026-01-09-ASD-AE-Harmonization.md b/software/_posts/2026-01-09-ASD-AE-Harmonization.md new file mode 100644 index 000000000..0b36dc16f --- /dev/null +++ b/software/_posts/2026-01-09-ASD-AE-Harmonization.md @@ -0,0 +1,30 @@ +--- +layout: project +title: ASD-AE-Harmonization +contributors: [Prof-S, falmuqhim] +handle: AE-fMRI-Harmonization +status: complete + + +# Optional +website: +grant: +grant_url: +image: /assets/images/software/open-source.png +tagline: Autoencoder-based harmonization of multisite fMRI for robust autism classification +tags: [software] + +# Data and code +github: https://github.com/pcdslab/Autoencoder-fMRI-Harmonization +neurovault: +openneuro: +figshare: +figshare_names: +osf: https://osf.io/d8253 +--- +{% include JB/setup %} + +We propose an autoencoder-based framework for harmonizing multisite functional magnetic resonance imaging (fMRI) data to improve the generalizability of machine learning models across imaging centers. Our approach leverages the non-linear representation learning capability of autoencoders to reduce site-specific variability while preserving biologically meaningful signal, without relying on additive or multiplicative statistical assumptions. Unlike traditional harmonization methods, our framework avoids data leakage by eliminating the need for access to data from all sites during model training. We design and evaluate multiple autoencoder variants, including AE, SAE, TAE, and DAE, and assess their effectiveness using the Autism Brain Imaging Data Exchange I (ABIDE-I) dataset comprising 1,035 subjects from 17 imaging centers. Experimental results using leave-one-site-out cross-validation demonstrate statistically significant improvements over baseline models (p < 0.01), with mean classification accuracy gains ranging from 3.41% to 5.04%. These findings highlight the effectiveness of autoencoder-based harmonization for reducing site effects, improving robustness on unseen sites, and enabling reliable downstream neuroimaging analyses. + +## Status +The method development for this work is complete \ No newline at end of file diff --git a/software/_posts/2026-01-09-NeuroCLR.md b/software/_posts/2026-01-09-NeuroCLR.md new file mode 100644 index 000000000..31ccc581c --- /dev/null +++ b/software/_posts/2026-01-09-NeuroCLR.md @@ -0,0 +1,30 @@ +--- +layout: project +title: NeuroCLR +contributors: [Prof-S, falmuqhim] +handle: NeuroCLR +status: complete + + +# Optional +website: +grant: +grant_url: +image: /assets/images/software/open-source.png +tagline: Self-supervised learning framework for disorder classification from fMRI data +tags: [software] + +# Data and code +github: https://github.com/pcdslab/NeuroCLR +neurovault: +openneuro: +figshare: +figshare_names: +osf: https://osf.io/mf5xk +--- +{% include JB/setup %} + +We propose NeuroCLR, a self-supervised contrastive learning framework for learning robust and generalizable neural representations directly from raw resting-state functional magnetic resonance imaging (rs-fMRI) data. Our approach leverages contrastive objectives, anatomically consistent sampling, and augmented views of unlabeled fMRI time series to extract invariant representations that are consistent across subjects, imaging sites, and diagnostic categories. Unlike supervised and disorder-specific SSL approaches, NeuroCLR is pre-trained in a disorder-agnostic manner, enabling effective transfer to downstream classification tasks with limited labeled data. We pre-train NeuroCLR on large-scale multisite neuroimaging data comprising more than 3,600 participants from 44 imaging centers and over 720,000 region-specific fMRI time series. The resulting pre-trained model is fine-tuned for multiple disorder-specific classification tasks and consistently outperforms both supervised deep learning models and SSL methods trained on single disorders. Extensive experiments demonstrate robust generalizability across sites, highlighting NeuroCLR’s ability to learn biologically meaningful and transferable representations from unlabeled fMRI data. These findings establish NeuroCLR as a scalable and reproducible self-supervised framework for multisite neuroimaging analysis and cross-disorder clinical modeling. + +## Status +The method development for this work is complete \ No newline at end of file diff --git a/team/_posts/1000-01-01-Fahad-Saeed.md b/team/_posts/1000-01-01-Fahad-Saeed.md index 38422fb63..883c55b3d 100644 --- a/team/_posts/1000-01-01-Fahad-Saeed.md +++ b/team/_posts/1000-01-01-Fahad-Saeed.md @@ -1,7 +1,7 @@ --- layout: member title: "Fahad Saeed" -position: Associate Professor and Lab Director +position: Full Professor of Computing and Lab Director nickname: Fahad handle: Prof-S email: fsaeed@fiu.edu @@ -16,10 +16,42 @@ image: /assets/images/team/Saeed_pic_resized.jpg cv: /assets/pdfs/CV_Saeed.pdf alum: false --- -Fahad Saeed is an Award-winning Scientist, Entrepreneur, and Tenured Associate Professor in the School of Computing and Information Sciences at Florida International University (FIU), Miami FL and is the director of Saeed Lab at FIU. Dr. Saeed's research interests are at the intersection of machine-learning, high performance computing and real-world applications, especially in computational biology. His research is supported by highly competitive grants mainly from National Science Foundation (NSF) and National Institutes of Health (NIH). +**Short Bio** -Dr. Saeed has published 90+ peer-reviewed research papers in leading proceedings, and journals, and 3 Book Chapter, edited 4 Conference Proceedings, 3 special issue journals, and 1 Book. He has been awarded over US$ 6.85 million in external research funds - with more than US$ 5.45 million as a PI. +Dr. Fahad Saeed is [Full Professor and Director of Graduate Studies](https://www.cis.fiu.edu/faculty-staff/fahad-saeed/) in the Knight Foundation [School of Computing and Information Sciences](https://www.cis.fiu.edu/) at [Florida International University (FIU)](https://www.fiu.edu/), Miami FL. He received his PhD in the [Department of Electrical and Computer Engineering](https://www.ece.uic.edu/), [University of Illinois at Chicago (UIC)](http://www.uic.edu/uic/) in 2010. He was trained as a Post-Doctoral Fellow and Research Fellow in the [Systems Biology Center](https://esbl.nhlbi.nih.gov/) at [National Institutes of Health (NIH)](https://www.nih.gov/), Bethesda MD from Aug 2010 to January 2014 respectively, under the supervision of Mark Knepper. Prior to joining FIU, Prof. Saeed was a tenure-track Assistant Professor in the [Department of Electrical & Computer Engineering](https://wmich.edu/ece/) and [Department of Computer Science](http://wmich.edu/cs/) at [Western Michigan University (WMU)](http://wmich.edu/), Kalamazoo Michigan since Jan 2014. He was tenured and promoted to the rank of Associate Professor at WMU in August 2018. He has served as a visiting scientist in world-renowned prestigious institutions such as [Department of Bio-Systems Science and Engineering (D-BSSE)](http://www.bsse.ethz.ch/), [ETH Zurich](http://www.ethz.ch/index_EN), [Swiss Institute of Bioinformatics (SIB)](http://www.isb-sib.ch/) and [Epithelial Systems Biology Laboratory (ESBL)](https://esbl.nhlbi.nih.gov/) at [National Institutes of Health (NIH)](http://www.nih.gov/) Bethesda, Maryland. -Prior to joining FIU, Prof. Saeed was a tenure-track Assistant Professor in the Department of Electrical & Computer Engineering and Department of Computer Science at Western Michigan University (WMU), Kalamazoo Michigan since Jan 2014. He was tenured and promoted to the rank of Associate Professor at WMU in August 2018. Dr. Saeed was a Post-Doctoral Fellow and then a Research Fellow in the Systems Biology Center at National Institutes of Health (NIH), Bethesda MD from Aug 2010 to June 2011 and from June 2011 to January 2014 respectively. He received his PhD in the Department of Electrical and Computer Engineering, University of Illinois at Chicago (UIC) in 2010. He has served as a visiting scientist in world-renowned prestigious institutions such as Department of Bio-Systems Science and Engineering (D-BSSE), ETH Zurich, Swiss Institute of Bioinformatics (SIB) and Epithelial Systems Biology Laboratory (ESBL) at National Institutes of Health (NIH) Bethesda, Maryland. +Dr. Saeed's research interests are at the intersection of machine-learning, high performance computing and real-world applications, especially in computational biology. He is the director of [Precision Computational Health and Biomedical Data Science Lab (Saeed Lab)](https://pcdslab.github.io/) at FIU. His lab develops machine-learning models, combined with high-performance computing, and data science approaches, to study the functional genomics (proteomics), and organization of the human brain and its function in the context of prediction, diagnosis and characterization of biomarkers specific to disorders such as epilepsy, ADHD, Autism, and Alzheimer’s. His research has been funded by NVIDIA, Intel/Altera, Xilinx, National Science Foundation (NSF) and National Institutes of Health (NIH) including the highly prestigious NSF CAREER, and NIH R01 (and R01-equivalent R35 MIRA) grants. More information about his lab research activities can be found at . +He also maintains a webpage at -Dr. Saeed is a Senior Member of ACM and also a Senior Member of IEEE. His honors include ThinkSwiss Fellowship (2007,2008), NIH Postdoctoral Fellowship Award (2010), Fellows Award for Research Excellence (FARE) at NIH (2012), NSF CRII Award (2015), WMU Outstanding New Researcher Award (2016), WMU Distinguished Research and Creative Scholarship Award (2018), , NSF CAREER Award (2017), FIU KFSCIS Excellence in Applied Research Award (2020). More recently he was recognized as "Top Scholar” in "Research and Creative Activities" by FIU in 2022. More info about Dr. Saeed can be read [here](https://prof-s.github.io). +Complete list of publications is available at: + +**Honors and Awards** + +1. Excellence in Research and Creative Activities Award, Knight Foundation School of Computing and Information Science (KFSCIS), FIU, Dec 2024 +3. **FIU Top Scholar**, _Research and Creative Activities_ , Florida International University, Sept 2022 [CEC News Page](https://cec.fiu.edu/2022/09/congratulations-to-the-college-of-engineering-computing-cec-faculty-named-fiu-top-scholars) +5. **Keynote Speaker** at the 14th International Conference on Bioinformatics and Computational Biology (BICOB). More info here: [BiCOB-2022](https://sce.uhcl.edu/bicob22/) [KeyNote Certificate](about:blank) +6. Excellence in Applied Research Award, School of Computing and Information Science (SCIS), Florida International University (FIU), Dec 2020 +7. Distinguished Research and Creative Scholarship Award, Office of Vice President of Research WMU, Feb 2018 +8. **NSF CAREER Award**, 2017-2022 +9. **ACM Senior Member**, May 2017 +10. Outstanding New Researcher Award, College of Engineering and Applied Science (CEAS), Western Michigan University, Jan 2016 (1 faculty member gets the award in a single year for the entire college consisting of 7 academic departments) +11. **IEEE Senior Member**, March 2015 +12. NSF CISE Research Initiation Initiative (CRII) Award, Feb 2015 - Feb 2018 +13. Fellows Award for Research Excellence (FARE), National Institutes of Health (NIH), June 2012 (Official award ceremony and US\\$1000 travel grant) +14. Travel award from Swiss Institute of Bioinformatics (SIB), Summers 2009. +15. Recipient of Think Swiss Scholarship, by the Government of Switzerland for two years (2007 and 2008). +16. Travel award from D-BSSE ETH Zurich, Summers 2008. + +**RESEARCH AND EDUCATIONAL INTERESTS** + +Machine-Learning for health and biomedical data, proteomics, neuroinformatics, computational systems biology, high-performance computing + +**EDUCATION AND PROFESSIONAL PREPARATION** + +Research Fellowship, Computational Systems Biology, National Institutes of Health, Bethesda MD. (2011-2014) + +Postdoctoral Training, Computational Proteomics, National Institutes of Health, Bethesda MD. (2010-2011) + +PhD, Electrical and Computer Engineering, University of Illinois at Chicago, Chicago IL USA. (2006-2010) + +BSc Engg, Electrical Engineering, University of Engineering and Technology, Lahore. (2002-2006) diff --git a/team/_posts/2020-05-24-Sumesh-Kumar copy.md b/team/_posts/2020-05-24-Sumesh-Kumar.md similarity index 97% rename from team/_posts/2020-05-24-Sumesh-Kumar copy.md rename to team/_posts/2020-05-24-Sumesh-Kumar.md index 28f2c610c..75294a820 100644 --- a/team/_posts/2020-05-24-Sumesh-Kumar copy.md +++ b/team/_posts/2020-05-24-Sumesh-Kumar.md @@ -12,7 +12,7 @@ orcid: osf: image: /assets/images/team/Sumesh_Kumar.jpg cv: -alum: true +alum: false --- ### B.Sc. - National University of Sciences and Technology (NUST), Islamabad; MSc. diff --git a/team/_posts/2020-11-04-Samuel-Ebert.md b/team/_posts/2020-11-04-Samuel-Ebert.md index 7c8fd653a..6b23f0293 100644 --- a/team/_posts/2020-11-04-Samuel-Ebert.md +++ b/team/_posts/2020-11-04-Samuel-Ebert.md @@ -12,7 +12,7 @@ orcid: osf: image: /assets/images/team/headshot_sam-e1691088484270.jpg cv: -alum: false +alum: True --- ### BSc - CS - North Carolina State University Raleigh, NC USA diff --git a/team/_posts/2024-02-18-Atwell-Jalen.md b/team/_posts/2024-02-18-Atwell-Jalen.md index aa137912d..b80677b6b 100644 --- a/team/_posts/2024-02-18-Atwell-Jalen.md +++ b/team/_posts/2024-02-18-Atwell-Jalen.md @@ -12,7 +12,7 @@ orcid: osf: image: /assets/images/team/Atwell-Jalen-2024_cropped.jpg cv: /assets/pdfs/CV_Atwell.pdf -alum: false +alum: True --- Jalen Atwell bio diff --git a/team/_posts/2024-05-20-Robert-Loredo.md b/team/_posts/2024-05-20-Robert-Loredo.md deleted file mode 100644 index ea1509a7d..000000000 --- a/team/_posts/2024-05-20-Robert-Loredo.md +++ /dev/null @@ -1,21 +0,0 @@ ---- -layout: member -title: "Robert Loredo" -position: PhD Student -nickname: robert -handle: robert -email: -twitter: -github: -scholar: jyceGwoAAAAJ -orcid: -osf: -image: /assets/images/team/RobertLoredo_BwHiResCopy.png -cv: -alum: false ---- - -### BSc. University of Miami, Coral Gables, FL USA -### MSc. University of Miami, Coral Gables, FL USA - -__Research Focus:__ Quantum Neuroinformatics \ No newline at end of file diff --git a/team/_posts/2024-05-20-Syed-Talha-Khalid.md b/team/_posts/2024-05-20-Syed-Talha-Khalid.md index 7c0458093..b972095f7 100644 --- a/team/_posts/2024-05-20-Syed-Talha-Khalid.md +++ b/team/_posts/2024-05-20-Syed-Talha-Khalid.md @@ -12,7 +12,7 @@ orcid: osf: image: /assets/images/team/talha.jpg cv: /assets/pdfs/talha-khalid-resume.pdf -alum: false +alum: True --- Syed Talha Khalid is currently a Master’s student at the Knight Foundation School of Computing & Information Sciences (KFSCIS) at Florida International University. He is also working as a Backend Engineer with Professor Fahad Saeed [@Prof-S](https://github.com/Prof-S), to develop backend for transformer and Large Language Models (LLMs) for biomedical data. diff --git a/team/_posts/2024-05-27-Parani-Paras.md b/team/_posts/2024-05-27-Parani-Paras.md index 7b5b66aea..f38daddd7 100644 --- a/team/_posts/2024-05-27-Parani-Paras.md +++ b/team/_posts/2024-05-27-Parani-Paras.md @@ -12,7 +12,7 @@ orcid: 0009-0004-4688-5059 osf: ukgp4 image: /assets/images/team/parani.jpg cv: /assets/pdfs/CV_Paras.pdf -alum: false +alum: True --- Paras Parani is currently a Master’s student at the Knight Foundation School of Computing & Information Sciences (KFSCIS) at Florida International University. He is also working as a Student Research Assistant with Professor Fahad Saeed [@Prof-S](https://github.com/Prof-S), to develop transformer and Large Language Models (LLMs) for biomedical data. diff --git a/team/_posts/2024-10-28-Bisht-Myrah.md b/team/_posts/2024-10-28-Bisht-Myrah.md index f9abc6ca6..838b11836 100644 --- a/team/_posts/2024-10-28-Bisht-Myrah.md +++ b/team/_posts/2024-10-28-Bisht-Myrah.md @@ -12,7 +12,7 @@ orcid: osf: image: /assets/images/team/bisht.jpeg cv: -alum: false +alum: True --- Myrah Bisht is currently a Master’s student at the Knight Foundation School of Computing & Information Sciences (KFSCIS) at Florida International University. She is doing independent study under Professor Fahad Saeed [@Prof-S](https://github.com/Prof-S) to develop models for protein identification. \ No newline at end of file diff --git a/team/_posts/2024-12-04-Jesus-Casasanta.md b/team/_posts/2024-12-04-Jesus-Casasanta.md index 8f3b608e4..363a16ef3 100644 --- a/team/_posts/2024-12-04-Jesus-Casasanta.md +++ b/team/_posts/2024-12-04-Jesus-Casasanta.md @@ -12,6 +12,6 @@ orcid: osf: image: /assets/images/team/Jesus-Casasanta.jpg cv: -alum: false +alum: True --- diff --git a/team/_posts/2025-07-09-Anju-SIngh.md b/team/_posts/2025-07-09-Anju-SIngh.md deleted file mode 100644 index 4d6f0f3ca..000000000 --- a/team/_posts/2025-07-09-Anju-SIngh.md +++ /dev/null @@ -1,26 +0,0 @@ ---- -layout: member -title: "Fahad Saeed" -position: Associate Professor and Lab Director -nickname: Fahad -handle: Prof-S -email: fsaeed@fiu.edu -twitter: Prof_FahadSaeed -github: Prof-S -scholar: IPXv-GQAAAAJ&hl=en -orcid: 0000-0002-3410-9552 -osf: 3k6mj -figshare: Saeed_Lab/19508632 -dataverse: Saeed-Lab -image: /assets/images/team/Saeed_pic_resized.jpg -cv: /assets/pdfs/CV_Saeed.pdf -title: "Anju Singh" -position: Undergraduate Research Assistant -nickname: Anju -email: asing184@fiu.edu -github: anjusings -orcid: 0009-0001-9019-6830 -image:/assets/images/team/Singh-Anju-picture.jpg -alum: false ---- -Anju Singh is an undergraduate researcher at FIU with a strong interest in computational biology and protein science. Her work focuses on using data-driven methods to better understand how protein behavior influences human health, particularly in underserved communities. She is passionate about applying machine learning to solve real-world biomedical challenges. \ No newline at end of file diff --git a/team/_posts/2025-07-23-Brett-Bronwyn.md b/team/_posts/2025-07-23-Brett-Bronwyn.md new file mode 100644 index 000000000..6d01abe31 --- /dev/null +++ b/team/_posts/2025-07-23-Brett-Bronwyn.md @@ -0,0 +1,17 @@ +--- +layout: member +title: "Bronwyn Brett" +position: MS Student +nickname: Bronwyn +email: jbret009@fiu.edu +github: BronwynB19 +scholar: schhp?hl=en +orcid: 0009-0000-6198-171X +osf: 3wje5 +image: /assets/images/team/Brett_picture.jpg +cv: /assets/pdfs/BBrett_CSR.pdf +alum: false +--- +**Short Bio** + +Bronwyn Brett is an MS student pursuing a degree in Computer Science at Florida International University. She's currently working as a research assistant at Saeed Lab where she is learning how to process health/biomedical data for machine-learning models to predict Alzheimer's disease. Her research and educational interests include machine-learning and high-performance computing with a focus on computational biology and biomedical data science and is interested in learning more about their applications in neurodevelopmental disorders such as ADHD. diff --git a/team/_posts/2025-08-15-Oliveira-Gabriel.md b/team/_posts/2025-08-15-Oliveira-Gabriel.md new file mode 100644 index 000000000..ba1f7538e --- /dev/null +++ b/team/_posts/2025-08-15-Oliveira-Gabriel.md @@ -0,0 +1,18 @@ +--- +layout: member +title: "Gabriel Bianchin de Oliveira" +position: Postdoctoral Fellow +nickname: GabrielBianchin +handle: gabrielbianchin +email: gabbianc@fiu.edu +twitter: Ga_Bianchin +github: gabrielbianchin +scholar: hSQGmeYAAAAJ&hl=en +orcid: 0000-0002-1238-4860 +osf: 7f9me +image: /assets/images/team/gabriel_oliveira.jpg +cv: /assets/pdfs/CV_Gabriel.pdf +alum: false +--- + +Gabriel Bianchin de Oliveira is a Postdoctoral Fellow at Florida International University (FIU) in the Knight Foundation School of Computing and Information Sciences (KFSCIS). Gabriel earned his PhD in Computer Science from the University of Campinas, Brazil, in 2025. His research interests include machine learning, natural language processing, and bioinformatics. \ No newline at end of file diff --git a/team/_posts/2025-08-28-Loredo-Robert.md b/team/_posts/2025-08-28-Loredo-Robert.md new file mode 100644 index 000000000..a9f725723 --- /dev/null +++ b/team/_posts/2025-08-28-Loredo-Robert.md @@ -0,0 +1,40 @@ +--- +layout: member +title: "Robert Loredo" +position: PhD student +nickname: Robert +handle: +email: +twitter: +github: RobertLoredo +scholar: jyceGwoAAAAJ&hl=en +orcid: 0000-0001-7231-1068 +osf: wu5ys +figshare: +dataverse: +image: /assets/images/team/RobertLoredo_BwHiRes.png +cv: /assets/pdfs/CV_Robert_Loredo.pdf +alum: false +--- +**Short Bio** + +Accomplished educational leader and thought leader with 20+ years of experience transforming complex technical concepts into accessible learning experiences for global audiences. Proven track record of building and mentoring large-scale educational networks, having led 300+ quantum computing ambassadors worldwide while developing comprehensive curricula and training programs across diverse industries. Distinguished [author of two best-selling quantum computing books](https://www.amazon.com/stores/Robert-Loredo/author/B08HXMCZ8Z?ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true&ccs_id=805da7a8-828d-4e99-b7b7-e55bcd5757d7) and holder of 270+ patents, demonstrating exceptional research capabilities and innovative thinking essential for modern STEM education. Expertise spans curriculum development, instructional design, educational technology integration, and strategic program development, with a demonstrated ability to translate cutting-edge research into practical learning applications. Successfully designed and delivered customized educational experiences that have driven multimillion-dollar business outcomes, showcasing the ability to align educational initiatives with real-world impact and stakeholder needs. + +Research interests are at the intersection of machine-learning, quantum computing, high performance computing and real-world applications, especially in computational neuroscience. He has his masters and bachelors from the University of Miami in Computer and Electrical Engineering and is currently pursuing his PhD in computational neuroscience at FIU. He has developed many applications during his 21 years at IBM which include machine-learning models, quantum computing combined with high-performance computing, and data science approaches for various industry leaders in finance, healthcare and life sciences, automotive, and energy. His focus of study in computational neuroscience will include analysis of the human brain and its function in the context of prediction, diagnosis and characterization of biomarkers specific to neurodegenerative disorders such as Autism, and Alzheimer’s disease. + +A list of publications is available at: +A list of certifications and badges is available here: + + + +**RESEARCH AND EDUCATIONAL INTERESTS** + +Machine-Learning for health and biomedical data, neuroinformatics, neurodegenerative diseases, high-performance computing and quantum computational science + +**EDUCATION AND PROFESSIONAL PREPARATION** + +PhD, Computer Science, Florida International University, Miami, FL, USA. (Expected 2026) + +MSc Eng, Computer and Electrical Engineering, University of Miami, Miami, FL, USA. (2002-2004) + +BSc Eng, Computer and Electrical Engineering, University of Miami, Miami, FL, USA. (1998-2002) diff --git a/team/_posts/2025-11-03-Mohammed-Khubaib.md b/team/_posts/2025-11-03-Mohammed-Khubaib.md new file mode 100644 index 000000000..8b69664c1 --- /dev/null +++ b/team/_posts/2025-11-03-Mohammed-Khubaib.md @@ -0,0 +1,22 @@ +--- +layout: member +title: "Mohammed Khubaib" +position: Graduate Research Assistant +nickname: Khubaib +handle: Mohammed-Khubaib +email: fmoha039@fiu.edu +twitter: Khubaib_21 +github: Mohammed-Khubaib +scholar: ZMZx42gAAAAJ +orcid: 0009-0000-7936-2642 +researchgate: Mohammed-Khubaib-2 +dataverse: mohammedkhubaib +osf: 5x8ht +cv: /assets/pdfs/Mohammed_Khubaib_CV.pdf +image: /assets/images/team/Mohammed_Khubaib.png +alum: false +--- + +[**Mohammed Khubaib**](https://md-khubaib.vercel.app/) is a graduate student at **Florida International University (FIU)**, majoring in **Computer Science**. He is a Graduate Research Assistant in the **Precision Computational Health and Biomedical Data Science Lab (Saeed Lab)** under the supervision of [**Dr. Fahad Saeed**](./1000-01-01-Fahad-Saeed) and [**Dr. Kaoutar Ben Ahmed**](https://www.cis.fiu.edu/faculty-staff/kaoutar-ben-ahmed/). + +His research involves developing and fine-tuning deep learning models for **medical imaging analysis**, with a focus on processing **volumetric medical imaging** data to support computational health applications. diff --git a/team/_posts/2026-03-05-Palikhe-Avash.md b/team/_posts/2026-03-05-Palikhe-Avash.md new file mode 100644 index 000000000..b819ced0d --- /dev/null +++ b/team/_posts/2026-03-05-Palikhe-Avash.md @@ -0,0 +1,17 @@ +--- +layout: member +title: "Avash Palikhe" +position: PhD Student +nickname: Avash +handle: apali007 +email: apali007@fiu.edu +github: apali007 +scholar: ax8-_XwAAAAJ +orcid: 0009-0008-2676-3731 +osf: abx45 +cv: /assets/pdfs/Avash_Palikhe_CV.pdf +image: /assets/images/team/avash_pic.jpg +alum: false +--- + +[**Avash Palikhe**](https://avashpalikhe.github.io/) is currently a Ph.D. student at the Knight Foundation School of Computing & Information Sciences (KFSCIS) at Florida International University, where he conducts research under the supervision of Dr. Fahad Saeed. He is a Graduate Research Assistant at the Precision Computational Health and Biomedical Data Science Lab (PCDS Lab), also known as the Saeed Lab. His research focuses on Algorithmic Fairness, Health AI, and Trustworthy AI. He has also delivered tutorials at IJCAI’25, CIKM’25, and ICDM’25. \ No newline at end of file diff --git a/team/index.html b/team/index.html index 77399a08f..4cbdb25a2 100644 --- a/team/index.html +++ b/team/index.html @@ -7,6 +7,7 @@ --- {% include JB/setup %} +
{% assign current_team = site.categories.team | where: "alum","false"%} {% assign memberindex = 0 %} @@ -45,11 +46,207 @@ +Lab 2015 | +Lab 2016 | +Lab 2017 | +Lab 2018 | +Lab 2019 | +Lab 2024 + + +
+
+
Research Trainee Alumni Placement
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+

Postdoc and MS/PhD Students

+		 +

Year of graduation

+		 +

Focus area

+		 +

First Position

+		 +

Last known Position

+
+

Muhammad Umair

+		 +

2025

+		 +

ML for Neuroscience

+		 +

Union College, Schenectady, N.Y. (TT Faculty)

+		 +

Union College, Schenectady, N.Y. (TT Faculty)

+
+

Usman Tariq

+		 +

2023

+		 +

ML for Proteomics

+		 +

Facebook

+		 +

Facebook (ML scientist)

+
+

Oswaldo Artiles

+		 +

2023

+		 +

ML for Neuroscience

+		 +

Postdoc FIU

+		 +

Postdoc FIU

+
+

Muhammad Haseeb

+		 +

2023

+		 +

HPC for Proteomics

+		 +

UC Berkeley

+		 +

NVIDIA (HPC Software Engineer)

+
+

Taban Eslami

+		 +

2020

+		 +

ML for Neuroscience

+		 +

Zeiss

+		 +

Apple Inc (ML Engineer)

+
+

Muaaz Gul Awan

+		 +

2019

+		 +

HPC for proteomics

+		 +

UC Berkeley

+		 +

Berkeley Labs (staff scientist)

+
+

Sandino Vargas-Perez

+		 +

2017

+		 +

High performance Computing

+		 +

Kalamazoo College

+		 +

Kalamazoo College (TT Faculty)

+
+

Mohammed Aledhari

+		 +

2017

+		 +

Machine-learning for biology

+		 +

Kennesaw state university (TT faculty)

+		 +

University of North Texas (TT Faculty)

+
+

Mohammad Abu Shattal

+		 +

2017

+		 +

Complex Networks

+		 +

Ohio State University (Postdoc)

+		 +

Franklin University, Ohio (TT Faculty)

+
+ + + +
Alumni
+ +
+ {% assign alumni = site.categories.team | where: "alum","true"%} {% assign memberindex = 0 %} {% for member in alumni %}