"Hybrid Deep Learning Framework for Melanoma Detection Published"

A faculty-research team from Harrisburg University has published groundbreaking research on the use of artificial intelligence in the early detection of Alzheimer’s disease. Dr. Ziyuan Huang, Dr. Roozbeh Sadeghian, and Dr. Maria Vaida published their findings in IEEE Xplore and presented at the 2025 Alzheimer's Association® International Conference in Toronto. Developed in collaboration with UMass Chan Medical School and The Johns Hopkins University, the team's AI framework integrates microbiome science, bioinformatics, machine learning, and large language models to enhance classification, accuracy, and interpretability for Alzheimer’s research. Read more here: https://lnkd.in/eDNDQ4Nw

Meet Dominika Matus, a former Master’s fellow at The University of Freiburg and the Zuse School ELIZA site in Freiburg, where she applied deep learning to understand the structures and interactions of RNA molecules. Her research bridges AI and molecular biology—focusing on how biomolecules like RNA fold, bind, and function. Dominika presented her work “RNA-Protein Interactions via Sequence Embeddings” at the Generative and Experimental Perspectives for Biomolecular Design (GEM) workshop at ICLR 2024 in Vienna. The project explored how AI models can predict RNA-protein binding—an important step in applying machine learning to the life sciences. Her path through ELIZA highlights how the program supports early-career researchers working on cross-disciplinary challenges at the intersection of AI and biology. #ELIZA #MachineLearning #AIResearch #MolecularBiology #RNA #DeepLearning #ICLR2024 #StudentSpotlight #ZuseSchools #ELIZAFellow #ELLIS

🔬 Vladimir Kovacevic, PhD is an algorithm developer and team lead at BGI Research Serbia, with a background that spans Intel and Seven Bridges, and over eight years of teaching Genome Informatics at the School of Electrical Engineering in Belgrade. His research focuses on applying machine learning in life sciences, data science, precision medicine, and bioinformatics. At our session, he will walk you through how AI algorithms in spatial transcriptomics are transforming the analysis of gene expression at spatial resolution, unlocking new frontiers in biomedical research and precision medicine. Don’t miss the chance to hear from one of the leading experts at the intersection of computer science and genomics! #GDGBelgrade #AI #Bioinformatics #MachineLearning #DataScience #SpatialTranscriptomics #PrecisionMedicine

Turning Jupyter into a lab, and code & math into tools—simulating neurons, one at a time. 🧪 I recently extended the classic Hodgkin-Huxley model to simulate the effect of different drugs on neuronal activity. By adjusting ion channel dynamics, I could observe how each drug modulates neuronal firing patterns—all in a virtual, in-silico environment. This project merges: - Computational Neuroscience – modeling neuron behavior - Pharmacology – testing drug effects without a wet lab - Simulation & Data Analysis – turning equations into insights The goal? Understanding how drugs interact with neurons at a mechanistic level—an approach sometimes called pharmaNeuroSimulation. Even if you’re not a neuroscientist, the idea is simple: instead of testing on actual neurons, I let code and math do the experiment. #ComputationalNeuroscience #InSilicoExperiments

X-CRISP introduces a flexible, interpretable neural network for predicting CRISPR repair outcomes. By using a compact set of sequence and outcome features, it outperforms existing models on detailed and aggregate predictions, highlighting the role of microhomology location in deletions. With transfer learning, X-CRISP adapts across human and mouse cell lines, requiring as few as 50 samples for new domains.  Explore the full paper in Bioinformatics Advances: https://lnkd.in/gBgaxwjC

I am pleased to announce that our paper, "Deep Learning Based Colon Cancer Detection Using Ensemble Transfer Learning," has been published in IEEE Xplore following its presentation at the IEEE 2025 33rd Signal Processing and Communications Applications Conference (SIU). Colon cancer remains one of the most prevalent and lethal cancers worldwide. Traditional histopathological diagnosis, while the current standard, can be time-consuming and subject to diagnostic variability. To address this challenge, our research leverages an ensemble deep learning model utilizing pre-trained convolutional neural networks (CNNs) and transfer learning. This approach is designed to facilitate faster and more accurate diagnostic support. Evaluated on the LC25000 and EBHI-Seg datasets, our model demonstrated exceptional performance, achieving 100% accuracy on the LC25000 dataset and 98.63% accuracy on the EBHI-Seg dataset. The reliability of these results was further substantiated through repeated holdout cross-validation. These findings underscore the significant potential of AI-driven methodologies to serve as robust decision-support tools in clinical pathology. I would like to express my profound gratitude to Prof. Dr. Selim Akyokuş , whose vision, deep expertise and continuous mentorship greatly shaped and elevated this study. His insightful guidance, encouragement, and unwavering support were invaluable throughout every stage of this research journey. And to Dr. Busra Sinan for her valuable collaboration and contributions throughout this project. Access the full paper here: https://lnkd.in/d95WQvCr #AI #MachineLearning #DeepLearning #ColonCancer #DigitalPathology #MedicalImaging #CancerDetection #AIinHealthcare #IEEE #Publication #Research #HealthTech

Excited to showcase my latest work: a hybrid computational neuropharmacology prototype! In this demo, you can see how we can combine the best of classical and quantum computing to accelerate drug discovery. The process works in two key phases: Classical Analysis: The program uses methods like molecular docking and network analysis to identify potential drug candidates from a vast database of protein targets like the Dopamine D2 and Serotonin 5-HT2A receptors. Quantum Refinement: The top-scoring molecules are then passed to a quantum-inspired model, such as a Quantum Convolutional Neural Network (QCNN) or a Variational Quantum Autoencoder (QVAE), to precisely optimize their structure for maximum efficacy and minimal side effects. This prototype isn't about immediate drug discovery, but rather about exploring the powerful synergy between current computational techniques and future quantum technology. It's a glimpse into how we might one day design more targeted and effective treatments for neurological disorders. What are your thoughts on this fusion of classical and quantum methods in drug research? #Neuropharmacology #QuantumComputing #DrugDiscovery #ComputationalChemistry #HybridComputing #AIinMedicine #Biotechnology #FutureOfScience

MIT Course announcement: Machine Learning for Computational Biology #MLCB25 Fall'24 Lecture Videos: https://lnkd.in/efSvp7hY Fall'24 Lecture Notes: https://lnkd.in/eWBAxQHk (a) Genomes: Statistical genomics, gene regulation, genome language models, chromatin structure, 3D genome topology, epigenomics, regulatory networks. (b) Proteins: Protein language models, structure and folding, protein design, cryo-EM, AlphaFold2, transformers, multimodal joint representation learning. (c) Therapeutics: Chemical landscapes, small-molecule representation, docking, structure-function embeddings, agentic drug discovery, disease circuitry, and target identification. (d) Patients: Electronic health records, medical genomics, genetic variation, comparative genomics, evolutionary evidence, patient latent representation, AI-driven systems biology. Foundations and frontiers of computational biology, combining theory with practice. Generative AI, foundation models, machine learning, algorithm design, influential problems and techniques, analysis of large-scale biological datasets, applications to human disease and drug discovery. First Lecture: Thu Sept 4 at 1pm in 32-144 With: Prof. Manolis Kellis, Prof. Eric Alm, TAs: Ananth Shyamal, Shitong Luo Course website: https://lnkd.in/eemavz6J #MLCB25 #MIT #MITBiology #MITCSAIL #MachineLearning #DeepLearning #ArtificialIntelligence #GenerativeAI #FoundationModels #Transformers #ComputationalBiology #Genomics #Proteomics #Epigenomics #SystemsBiology #GenomeEngineering #PrecisionMedicine #PersonalizedMedicine #MedicalGenomics #GeneticVariation #EvolutionaryBiology #Bioinformatics #MedicalAI #AIinHealthcare #BiomedicalAI #HealthTech #DrugDiscovery #Therapeutics #Biotech #PharmaTech #Cheminformatics #ProteinDesign #ProteinFolding #AlphaFold2 #CryoEM #StructuralBiology #MolecularBiology #SyntheticBiology #NeuroscienceAI #ClinicalAI #BigDataBiology #DataScience #AlgorithmDesign #FoundationAI #Omics #Transcriptomics #Epigenetics #EHR #DiseaseModeling #TargetIdentification #ComputationalGenomics #BiomedicalResearch #HealthcareInnovation

This is a recent paper from our ongoing collaboration between the Radiology Department at UNMC and Electrical & Computer Engineering at UNL! In this project, we apply AI and deep learning tools to advance in vivo molecular imaging, aiming for greater robustness and efficiency. Our first study demonstrates that CEST MRI can be accelerated by up to 10× while maintaining high-quality data in a normal mouse model. Next, we are evaluating the robustness of the method to handle disease mouse models. This is a nice project. Grateful to be part of this team! https://lnkd.in/dmD-CQNb https://lnkd.in/d7D4qNpR

We are pleased to share that our latest article has been published in CAUCHY: Journal of Pure and Applied Mathematics, titled An Explainable Deep Learning Approach for Brain Tumor Detection Using MobileNet and Grad-CAM Visualization. This study explores deep learning approaches for brain tumor detection using MRI images, addressing one of the key challenges in medical AI: the lack of interpretability. By combining MobileNet with Grad-CAM visualization, the proposed framework not only ensures efficiency and speed but also provides clinical transparency through visual explanations of the model’s predictions. When compared to other architectures, MobileNet demonstrated superior performance, offering a better balance of computational efficiency and interpretability. This research highlights the potential of lightweight models in supporting real-world clinical applications where accuracy, speed, and trust are equally important. This work is a collaboration with Amalan Fadil Gaib, Safrizal Ardana Ardiyansa, Eric Julianto, Ngurah Bagus, and Ando Zamhariro Royan. We are grateful for the contributions of everyone involved in making this publication possible. 📖 Read the full article here: https://lnkd.in/gcy5psPq