BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260808T230102Z UID:d3334568-9960-4297-8a17-c647cf871f50 DTSTART:20250527T070000Z DTEND:20250606T150000Z DESCRIPTION:Organizer &\; Educators:\nSilvia Di Giorgio (ZB MED – Info rmation Centre for Life Sciences - Associated Partner)\, Sabry Razick & \; Pubudu Samarakoon (University of Oslo)\n\nDate: \nModule 1: 27-28.05.20 25\nModule 2: 02-06.06.2025 \n\nLocation: \nOnline\n\nContents:\nThis inte nsive workshop focuses on applying machine learning techniques to biologic al and genomic data\, combining theoretical foundations with hands-on codi ng experience. Participants will work through real-world scenarios using P ython-based tools and frameworks that are critical for modern bioinformati cs.\n\nModule 1 (optional) provides a solid foundation in scientific compu ting with Python. Across two half-day sessions\, participants will explore essential data handling techniques using NumPy and Pandas—tools widely adopted for manipulating and analyzing biological data. \n\nModule 2 (mand atory) spans five full days and begins by introducing core concepts in mac hine learning. On the first day\, the participants will be introduced to u nsupervised learning\, and they will implement clustering algorithms and d imensionality reduction techniques using real-world genomics data. The wor kshop then dives into supervised learning with a focus on classification a nd regression\, including logistic regression and tree-based methods. Part icipants will construct and evaluate ML models\, perform cross-validation\ , and tune hyperparameters in hands-on sessions tailored to cancer genomic s datasets. Later sessions introduce deep learning concepts and the PyTorc h framework. Participants will learn to build and train simple neural netw orks and explore a deep learning-based bioinformatics tool used in genomic variant calling. The final day introduces accelerated genomics through GP U-powered workflows. Participants will learn about GPU technology and how to use containerized bioinformatics tools. They will also implement high-p erformance\, GPU-accelerated pipelines using Parabricks.\n\nPlease note: R egistration is only required for participation in Module 2. Module 1 is o ptional and does not require registration.\n\nThis workshop offers a compr ehensive\, practical journey through the machine learning landscape in bio informatics\, from data wrangling to deep learning and scalable genomic wo rkflows.\n\nLearning goals:\nBy the end of this workshop\, you will be abl e to:\n\nApply data manipulation techniques using NumPy and Pandas.\nDefin e essential machine learning terminology and differentiate between supervi sed and unsupervised learning approaches.\nImplement and evaluate regressi on and classification models on biological datasets through hands-on codin g exercises.\nApply regularization techniques and hyperparameter tuning to optimize model performance while preventing overfitting.\nAnalyze biologi cal questions to determine the most appropriate machine learning approach (regression\, classification\, clustering).\nInterpret and evaluate machin e learning models using appropriate metrics and cross-validation technique s to ensure reliability.\nDevelop scripts using PyTorch to build and train simple neural networks and implement deep learning based bioinformatics t ools using genomics datasets. \nDesign end-to-end machine learning workflo ws for biological applications\, from data preprocessing to model deployme nt.\nImplement containerization using Docker to enhance reproducibility an d scalability in bioinformatics workflows.\nCompare CPU-native versus GPU- accelerated approaches for genomic data processing and identify computatio nal bottlenecks.\nPrerequisites:\n\nA life scientist\, bioinformatician\, or data analyst working with biological or genomic data\nCurious about how machine learning can be applied to biological research questions\nLooking to strengthen your Python skills for data handling and analysis\nInterest ed in implementing classification\, regression\, or clustering models on r eal-world datasets\nExploring the use of deep learning techniques\, in bio informatics\nInvolved in next-generation sequencing (NGS) workflows and wa nt to optimize them with GPU acceleration\nCommitted to building reproduci ble and scalable analysis pipelines using container technology\nEager to u nderstand and apply best practices in model evaluation\, tuning\, and vali dation\nNew to machine learning and seeking a hands-on\, structured introd uction\nKeywords:\nMachine Learning \n\nTools:\nPython SUMMARY:Applied Machine Learning for Biological Data URL;VALUE=URI:https://www.denbi.de/training-courses-2025/1881-applied-machi ne-learning-for-biological-data END:VEVENT END:VCALENDAR