Data Science for Life Sciences
Enterprise Training
- Customised Data Science for Life Sciences Enterprise training for companies, institutions and their teams based your organisation’s individual requirements
- Developed and delivered by industry-experienced and research-driven Life Scientists together with Data Science and Machine Learning experts
- Covering the basics of modern Data Science for Life Science use cases
- Including both theory and hands-on labs
- Customisable module selection and content adoption
- Certification at completion

Customised Data Science for Life Sciences Enterprise Training
Customised DSfLS Enterprise training offer for companies, institutions and their teams based your organisation’s individual requirements.
Optional adoption of the modules, labs and applied tools to your environment.
Training modules (1 Module = 1 Day)
Data Science Fundamentals
Topics: Data Science’s role within a business & challenges – Skills to be a successful Data Scientist – Data Visualization tools – Use and Share Jupyter Notebooks and features – Identify a problem, collect and analyze data, build a model and understand feedbacks
Goals:
- Introduction to Data Science
- Methodology to handle Data Science questions
Tools for Data Science
Topics: Sclkit-learn – Apache Spark – TensorFlow, Colab, BigML – Excel – D3.Js for data visualization
Goals:
- Get hands-on experience on Data Science
Building valuable models for Life Science
Topics: Clustering, Classification, regression – Learn/Optimize (experimentation, simple Machine Learning algorithms) – Machine Learning use case in Life Sceince (feature selection, classification, regression, visualization)
Goals:
- Build and Test an end-to-end Machine Learning model.
ML/DL Frameworks
Topics: Methods, models and practices for Healthcare – Reinforcement Learning Paradigm & Markov Decision Processes – Q-Learning, Sequence data analysis, Series data – Reccurent neural networks and representation techniques – FRNN (Fully Reccurent NN) & LSTM (Long Short-Term Memory)
Goals:
- Specify a meaningful pipeline
- Get hands-on experience on Deep Learning
Building a ML Life Science application
Topics: Use case: Breast cancer stage prediction – Use Cloud computing services based on Machine Learning As a Service (MLaaS) – Build and deploy a Flask application using Docker
Goals:
- Implementing AI services for enterprise applications
Data Science Workflow for Life Sciences
Topics: Methods, models and practices for data Science – Data Strategy – Operation on data – Data cleaning – Data analysis and models with Machine Learning – Data Visualization and Operationalization
Goals:
- Specify meaningful pipeline
- Get hands-on experience in Data Science
Data Engineering
Topics: Types of Data (numerical, categorical, ordinal) – High dimensional data VS Low dimensional data – SQL essentials & Labelling (analytics, metrics, segments, aggregates, features, training data) – Map/Reduce on Hadoop – Data modeling with Apache Cassandra & Databricks
Goals:
- Data management for Data Science
ML/DL Fundamentals
Topics: Context and Healthcare applications – Machine Learning/ Convolutional neural network – Image classification : supervised learning/regression – Data-driven approach: Representation – Overfitting and Underfitting, Generalization – Back propagation fundamentals/ Model selection/ Validation/ Parameters
Goals:
- Understand the basics of ML/DL in Healthcare context
Relevant ML/DL Frameworks
Topics: Notebook/ TensorFlow/ Google Cloud ML engine hands-on lab – Learn & Optimize (experimentation, recent architecture: Inception/ Yolo) – Deep Learning use cases in Healthcare (feature selection, classification, regression, visualization)
Goals:
- Get hands-on experience in Machine Learning & Deep Learning (ML/DL)
Evaluation Metrics of ML models
Topics: Collaboration between clinicians and scientists – Training sets, Testing sets, Seens and Unseens – Various types of errors and cross-validation protocols – Parameter tuning and evaluation – Performance management and Observability
Goals:
- Evaluate & Leverage your ML models