MTHM015 | 2023%252525252F4 | University of Exeter

MODULE TITLE	AI and Data Science Methods for Life and Health Sciences	CREDIT VALUE	15
MODULE CODE	MTHM015	MODULE CONVENER	Prof Kirsty Wan (Coordinator)

DURATION: TERM	1	2	3
DURATION: WEEKS		11

Number of Students Taking Module (anticipated)	20

DESCRIPTION - summary of the module content

Analysing data and quantitatively comparing mathematical models to data are crucial when using mathematics to improve our understanding of complex biological systems. Data from biology experiments and clinical recordings are diverse and often present challenges for analysis and modelling, such as high dimensionality and non-stationarity. This module will introduce you to some common kinds of data observed in biological and clinical applications such as images, time series and high dimensional sequencing data. You will be introduced to advanced methods that deal with these data, but can also be applicable in other fields, for example in climate systems and finance.

AIMS - intentions of the module

We will introduce data and methods that arise in the above application areas but are also applicable in other fields. The content will be centred on real-world applications: for example, the analysis of motility in single cell organisms, analysis of clinical time series in neurology and neuroendocrinology as well as analysis of next generation sequencing (NGS) data. The study of these examples will require theory in:

image analysis: feature extraction/identification, object tracking, deep learning; time series analysis: clustering, linear and nonlinear time series analysis methods, calibration of models from dynamic data; NGS data: enrichment analysis and dimension reduction (e.g. PCA, UMAP, t-SNE). The presentation of theory will be given in the context of practical, hands-on analysis of real-world data.

INTENDED LEARNING OUTCOMES (ILOs) (see assessment section below for how ILOs will be assessed)

On successful completion of this module you should be able to:

Module Specific Skills and Knowledge

1. Apply common tools for image and time series analysis
2. Apply common algorithms for object detection

3. Develop a working knowledge of supervised and unsupervised learning

4. Study common tools for dimension reduction

5. Learn how to link mechanistic models and data.

Discipline Specific Skills and Knowledge

6. Develop practical skills in handling different kinds of data
7. Develop practical skills to link models and data

Personal and Key Transferable / Employment Skills and Knowledge

9. Develop practical skills in handling diverse data
10. Build the ability to identify which techniques are suitable for which problems

11. Communicate ideas effectively by interpreting real data

SYLLABUS PLAN - summary of the structure and academic content of the module

(i) Image analysis

Introduction to the problem of detecting and tracking objects in images (application to microswimmers and medical MRI)
Deep learning for object detection

(ii) Time series analysis

Spectral decomposition using Fourier transform and wavelets
Deep autoencoders for time series clustering
Linear and nonlinear models for complex physiological systems’ dynamics

(iii) RNA-seq data analysis

Enrichment analysis
Dimension reduction (UMAP, PCA, t-SNE)

(iv) Model calibration

Global optimisation heuristics (particle swarm, genetic algorithms)
Probabilistic and Bayesian methods.

LEARNING AND TEACHING

LEARNING ACTIVITIES AND TEACHING METHODS (given in hours of study time)

Scheduled Learning & Teaching Activities	50	Guided Independent Study	100	Placement / Study Abroad	0

DETAILS OF LEARNING ACTIVITIES AND TEACHING METHODS

Category	Hours of study time	Description
Scheduled learning and teaching activities	20	In lectures, problems and data are introduced; background theory is described
Scheduled learning and teaching activities	30	Students use the knowledge from the lecture to perform a hands-on data analysis task with real data
Guided Independent Study	100	Independent reading and problem solving

ASSESSMENT

FORMATIVE ASSESSMENT - for feedback and development purposes; does not count towards module grade

Form of Assessment	Size of Assessment (e.g. duration/length)	ILOs Assessed	Feedback Method
Questions in practical sessions	10 x 3 hours	All	The lecturer will provide feedback on solutions.

SUMMATIVE ASSESSMENT (% of credit)

Coursework	100	Written Exams	0	Practical Exams	0

DETAILS OF SUMMATIVE ASSESSMENT

Form of Assessment	% of Credit	Size of Assessment (e.g. duration/length)	ILOs Assessed	Feedback Method
Coursework 1	50	4 weeks to complete	All	Marked script
Coursework 2	50	4 weeks to complete	All	Marked script

DETAILS OF RE-ASSESSMENT (where required by referral or deferral)

Original Form of Assessment	Form of Re-assessment	ILOs Re-assessed	Time Scale for Re-assessment
Coursework 1	Coursework piece (50%)	All	During the August Ref/Def period
Coursework 2	Coursework piece (50%)	All	During the August Ref/Def period

RE-ASSESSMENT NOTES

Reassessment will be by coursework in the failed or deferred element only. For deferred candidates, the module mark will be uncapped. For referred candidates, the module mark will be capped at 40%.

RESOURCES

INDICATIVE LEARNING RESOURCES - The following list is offered as an indication of the type & level of
information that you are expected to consult. Further guidance will be provided by the Module Convener

Reading list for this module:

Type	Author	Title
Reference	Cohen, M.X.	Analyzing Neural Time Series Data: Theory and Practice
Reference	Eberhart, R. Shui, Y. and Kennedy, J.	Swarm Intelligence
Reference	Lee, J.A. , Verleysen, M. and Schölkopf, B.	Nonlinear Dimensionality Reduction

CREDIT VALUE	15	ECTS VALUE	7.5

PRE-REQUISITE MODULES	None
CO-REQUISITE MODULES	None

NQF LEVEL (FHEQ)	7	AVAILABLE AS DISTANCE LEARNING	No
ORIGIN DATE	Tuesday 17th January 2023	LAST REVISION DATE	Tuesday 17th January 2023

KEY WORDS SEARCH	Data analytics, Biomedical data, Health data, Model calibration, AI, Time series analysis, Modelling, Image analysis

AI and Data Science Methods for Life and Health Sciences - 2023 entry