¹û¶³Ó°Ôº

Aims:

The overall aim of this module is to introduce machine learning students to the field of bioinformatics (computational biology) and show how machine learning techniques can be employed in this area. The module is aimed at students who have no previous knowledge of biology and so the aim of Part 1 of the course is to give a basic introduction to molecular biology as a background for bioinformatics. Part 2 will concentrate on classical bioinformatics applications, particularly those which make good use of pattern recognition and machine learning methods. Part 3 will cover more recent bioinformatics areas, including high-throughput –omics techniques, and gene expression analysis.

Intended learning outcomes:

On successful completion of the module, a student will be able to:

1. Have a basic knowledge of modern molecular biology and genomics.
2. Understand the advantages and disadvantages of different machine learning techniques in bioinformatics and how the relative merits of different approaches can be evaluated by correct benchmarking techniques.
3. Understand how theoretical approaches can be used to model and analyse complex biological systems.

Indicative content:

The following are indicative of the topics the module will typically cover:

Part 1:

• Introduction to Basic Cell Chemistry: Cell chemistry and macromolecules. Biochemical pathways e.g., Glycolysis. Protein structure and functions.
• Cell Structure and Function: Cell components. Different types of cell. Chromosome structure and organisation. Cell division.
• The Hereditary Material: DNA structure, replication and protein synthesis. Structure and roles of RNA. Genetic code. Mechanism of protein synthesis: transcription and translation. Mutation.
• Recombinant DNA Technology: Restriction enzymes. Hybridisation techniques. Gene cloning. Polymerase chain reaction.
• Genomics and Structural Genomics: Genes, genomes, mapping and DNA sequencing.

Part 2:

• Biological Databases: Overview of the use and maintenance of different databases in common use in biology.
• Gene Prediction: Methods for analysing genomic DNA to identify genes. Techniques: neural networks and HMMs.
• Detecting Distant Homology: Methods for inferring remote relationships between genes and proteins. Techniques: dynamic programming, HMMs, hierarchical clustering.
• Protein Structure Prediction: Methods for predicting the secondary and tertiary structure of proteins. Techniques: deep neural networks, sequence-to-sequence models and stochastic global optimization.

Part 3:

• Introduction to high-throughput –omics techniques and data sources and data representations.
• Transcriptomics: basic principles of transcriptomics experimental design. An introduction to RNAseq technologies and analysis methods.
• An introduction to data standards in transcriptomics data
• Computational Techniques and machine learning in analysing transcriptomics data: differential gene detection, hierarchical clustering, dimensionality reduction, k-NN classification, neural networks.

Requisites:

To be eligible to select the module delivery Postgraduate (FHEQ Level 7) as an optional or elective, a student must: (1) be registered on a programme and year of study for which it is formally available; (2) be familiar with the principles of techniques such as neural networks, Support Vector Machines, and Hidden Markov Models; and (3) be able to program machine learning applications using a standard machine learning framework such as MATLAB.

To be eligible to select the module delivery Undergraduate (FHEQ Level 7) as an optional or elective, a student must additionally have taken at least one introductory machine learning module, for example Supervised Learning (COMP0078), Introduction to Machine Learning (COMP0088), Introduction to Deep Learning (COMP0090), or Machine Learning for Domain Specialists (COMP0142).