Python Fundamentals:
The Python Fundamentals component of the scryptIQ course offers learners a comprehensive introduction to programming in Python. Some of the key study areas covered in this module are:- Algorithmic thinking
- Variables, types and operations
- Conditional statements
- Arrays, tuples, lists and indexing
- Iterations: for and while loops
- Dictionaries: associative arrays
- Functions: defining functions, uses and applications
Data Processing:
-
Import, structuring and manipulation of data using NumPy arrays and Pandas DataFrames
-
Data characterisation, cleaning and transformation for analysis and machine learning
-
Summary statistics and exploratory data analysis
-
Univariate and multivariate analyses of complex datasets
-
Visualisation of data using Matplotlib, Seaborn and Plotly
-
Preparation and pre-processing of data for machine learning workflows
-
Image handling and processing, including greyscale and colour images
-
Image masking, segmentation and augmentation techniques
-
Time series data handling, visualisation and analysis
-
Relationships and patterns in time series data
-
Creation of publication-ready figures with precise control
-
Advanced 3-dimensional and interactive visualisation of data
Networks:
- A comprehensive introduction to Network graph theory, and the NetworkX packages in Python
- Directed, undirected and bipartite network graphs
- Personalised PageRank
- Degree and closeness centrality
- Using biological datasets: protein-protein interactions in the Breast Cancer Network (BCN) and neural signal propagation in the C. elegans connectome
Classical Machine Learning:
Key areas taught in scryptIQ's exploration of Supervised Machine Learning include:-
Preparation and optimisation of data for classical machine learning workflows
-
Introduction to supervised learning and classification using scikit-learn
-
Training, refinement and evaluation of classifier models
-
Interpretation of model outputs and predictive performance
-
Model evaluation using appropriate metrics and validation strategies
-
Comparison and selection of different classifier approaches
-
Introduction to unsupervised learning for unlabelled data
-
Dimensionality reduction as a preliminary step for exploring high-dimensional datasets
-
Clustering techniques for exploratory data analysis
-
K-means clustering for pattern discovery in biological and health data
-
Gaussian Mixture Models (GMMs) for probabilistic clustering
-
Application of clustering techniques to biological and medical image segmentation
Artificial Intelligence:
The Artificial Intelligence module builds upon the concepts and techniques taught in the machine learning module. This broad topic covers three primary AI approaches:
- Multi-Layer Perceptrons (MLPs)
- Convolutional Neural Networks (CNNs)
- Generative AI (Large Language Models).
The course examines the concepts underpinning these tools, teaching students how to implement them using PyTorch – an industry-standard Python framework for building deep learning models. Additionally, we explore how to better interpret the output of deep learning models, despite their “black box” nature, with the goal of gaining insight into the patterns these models identify in data.
