You are here

580b57fcd9996e24bc43c53e   LinkedIn Logo 500x500   Facebook logo square   Instagram icon

event icon
Date
07.02.25
Start time
09:00
End time
17:00
Online

*** This course contributes to the Royal Society of Biology's Industry Skills Certificate


An Introduction to Computational biology, Machine learning and Artificial Intelligence


Overview

Advances in biology such as the sequencing of the human genome and advances in imaging techniques have led to an explosion of data in the biosciences. One of the challenges with the analysis of such data is the volume, resolution and complexity of the data generated; plus, the quality of the data. These issues from a bioinformatics perspective are often typified by the criticism that different data sets do not yield consistent results. This would indicate that often such individual data sets have high levels of noise and thus do not have sufficient cases to achieve a sufficient statistical power. Thus, analysis of such data requires careful consideration, paying attention to the non-linearity of biological systems, the interaction of molecular entities in pathways, the fluidity of biological systems and the need for determination of consistent entities across multiple data sets.

These challenges can be addressed through appropriate application of computational methods such as artificial intelligence and machine learning. These techniques have significant advantages, in that they can cope with nonlinearity, complexity, high dimensionality and false discovery in biological data and generate solutions that have real world application. There has however been significant hype around the terms. Often techniques are applied inappropriately, are not fit for purpose or are inappropriately badged as machine learning or artificial Intelligence. This course sets out to demystify the terms offering practical solutions to the application of machine learning and artificial intelligence to solving biomedical problems. The strength and limitations of the approaches are discussed and practical solutions provided in a form accessible to non-computer scientists.


Aims

The broad aims of the course are to:
  • provide intellectually challenging and professionally relevant training at the forefront of bioinformatics, machine learning, Artificial Intelligence and computational biology; accessible to non-computer scientists and led by academic experts
  • develop the theoretical, practical and strategic skills needed to collect, understand, manage and analyse data
  • provide understanding of and signposting to methodologies and resources that allow application of computational biology and machine learning techniques. Have a practical knowledge of the computational and artificial intelligence methods applicable to biological data
  • provide a critical understanding of these methodologies and approaches and their advantages and limitations
  • introduce the key data types encountered and sources of data
  • to provide an understanding of the basis and application of approaches including:
  1. artificial neural networks
  2. shallow versus deep learning
  3. support vector machines
  4. random forests
  5. Ordination and clustering techniques

Who is the course for?

Biological and medical scientists who wish to explore the opportunities offered by Artificial Intelligence, Machine Learning and Computational Biology. No prior knowledge of these subjects will be required and the purpose of the course is to offer a practical point of access to these techniques in an practical user friendly form.

Learning outcomes

Knowledge and understanding
  1. Understand approaches through which biological data is obtained and may be exploited in the fields of biotechnology, medicine and related disciplines
  2. Practical application of machine learning methods to solve biological/medical data problems through data mining, construction of classification models and data analytics
  3. Demonstrate understanding and reasoned application of Artificial Intelligence and Machine learning methods in analysis of biological/medical data
  4. Critically evaluate the results generated through use of relevant scientific databases and web-based tools
Skills, qualities and attributes
  1. Select, format and apply appropriate analysis methods for use with real experimental data

Course tutor

Research experience relevant to this project:
Professor Graham Ball has 26 years' experience in the application of artificial intelligence and machine learning to biological problems. He has developed numerous approaches combining ML and statistical approaches for classification and systems biology. He has supervised 9 students (as 1st supervisor, 23 as second supervisor) from a biological background to PhD award in a machine learning discipline and well as over 80 Biosciences master's students. He has regularly run international bioinformatics/ Machine learning and Computational biology courses (France, India, China) annually for the last 15 years. He has lead numerous projects in the biomarker discovery and systems biology space over the last 20 years.

Current research interests have focused on the development and application of bioinformatic algorithms using Artificial Neural Networks (ANNs) to medical diagnostics and statistics including:
  • Cancer systems biology and bioinformatics
  • Biomarker Discovery and Drug target discovery through application of machine learning to biological “Big Data”
  • Plant based systems for identification of molecular drivers of phenotype.
  • Species distributions and ecological factors governing species abundance and decline.
  • Machine learning based image assessment and classification of Immunohistochemical cores, MRI images and freshwater invertebrate taxa.

Certification and Continuing Professional Development (CPD)

A certificate of attendance will be provided after the event. We evaluate all of our training events, to make sure that we maintain a high quality of training.

This event has been approved by the Royal Society of Biology for purposes of CPD and can be counted as 24 CPD points.

Professional Registers

This course supports registers competencies and has been identified as supporting competency development for: Registered Scientist (RSci).
Competency area:
  • Application of knowledge and understanding


Fees

Members - £120 + VAT
Non-members - £240 + VAT

Get in touch with training@rsb.org.uk to access these rates:
  • Members of Member Organisations, SCAS members - £180 + VAT
  • Non-members who have completed a membership application and made payment - £120 + VAT


Contact

For further information about this course please contact Tia Salter, Training and Registers Officer at training@rsb.org.uk.

Special requirements

If you have accessibility requirements, please let us know during your booking, and we will do what we can to accommodate your needs.

Refunds

Unfortunately, the Royal Society of Biology is unable to offer refunds on training courses that have been attended. We do, of course, welcome and encourage any feedback from a course and will continue to improve the service we offer.

Terms and Conditions

By booking to attend this event, you are confirming you have agreed to the RSB's Terms and Conditions which can be found here.