Module 1

Conventional Machine Learning

Week 1: Getting Started with Python & Google Colab

Python basics: variables, lists, loops and functions, Introduction to Python for life-science researchers, Using Google Colab: running cells, uploading files, saving notebooks, Introduction to data tables using pandas, Basic plots with matplotlib

Week 2: Data Cleaning & Exploratory Data Analysis (EDA)

Lists, dictionaries and pandas indexing, Identifying data quality issues in biological datasets, Handling missing values, Scaling and normalization, Basic statistics, EDA workflow, Introduction to train/test split

Week 3: Introduction to Machine Learning

ML vs classical statistical approaches, Supervised vs unsupervised learning, Classification and regression, Model training, validation and testing, Key metrics: accuracy, AUROC, RMSE

Week 4: Feature Engineering & Model Selection

Feature scaling: StandardScaler, MinMax, Feature selection: variance filtering, ANOVA, L1/Lasso, Overfitting and underfitting, Model complexity and regularisation, Hyperparameter tuning with GridSearchCV, Building ML pipelines

Week 5: Imbalanced Data & Biomedical Evaluation Metrics

Why biomedical datasets are often imbalanced, Precision, recall, F1 score, Precision–recall curves, Oversampling (SMOTE) and class weighting, Calibration curves and reliability plots

Week 6: Unsupervised Learning & Dimensionality Reduction

Clustering: k-means and hierarchical clustering, PCA: variance, components and projection, t-SNE and UMAP for biological data, Visualising biological structure (for example, cell populations)

Module 2

Deep Learning

Week 7: Neural Networks & Deep Learning Fundamentals

What deep learning offers for biological research, Structure of neural networks, Activations, losses and optimisers, Training loops and overfitting, Introduction to PyTorch or TensorFlow

Week 8: Convolutional Neural Networks (CNNs) & Transfer Learning

Understanding convolutions, kernels and feature maps, CNN architectures, Transfer learning for biological images, Data augmentation, Evaluation and visualisation of predictions

Week 9: Deep Learning for Genomics & Sequence Data

String manipulation for biological sequences, Encoding DNA and protein sequences, 1D CNNs for motif detection, RNNs/LSTMs (conceptual overview), Sequence classification tasks, Basic sequence-model interpretation

Week 10: Single-Cell RNAseq + Machine Learning Integration

Introduction to single-cell datasets, Scanpy workflow: normalisation, HVG selection, neighbours, UMAP, Clustering and marker gene identification, Integrating ML for cell-type prediction, Using ML for automated annotation

Week 11: Transformers & Attention in Biology

Introduction to Transformer architecture, Self-attention and attention heads, Sequence modelling using Transformers, Applications in genomics, proteomics and biomedical NLP, Fine-tuning pretrained models, Visualising attention maps

Week 12: Final Project Presentations & Reproducibility Practices

Student project presentations, Writing reproducible ML workflows, Version control (GitHub basics), Managing randomness and seeds, Documentation and workflow organisation, Suggested pathways for advanced learning in ML for life sciences