Artificial Intelligence in genomics

Genomics requires the analysis of vast quantities of digital data, so tools which can achieve this quickly and effectively are highly valued.

Artificial intelligence (AI) is already in widespread use in genomics, creating computer systems capable of complex problem-solving or decision-making, and innovation in this field continues at a very rapid pace.

Predictive AI models can make predictions or classifications based on previously processed data. Generative AI models (such as ChatGPT) can make ‘new’ content based on patterns learned from existing data. Both of these types of models can be useful in genomics, with appropriate safeguards.

Some current examples include:

• Analysing images of tissue samples to find, diagnose and treat cancers more effectively
• Repurposing existing drugs that might be effective for other health conditions
• Helping to identify possible genetic drivers for conditions in understudied parts of the genome – although this still needs human expertise to confirm a diagnosis.

You might find this short article on AI in genomics helpful.

As in other disciplines, there is much debate about the responsible use of AI in medicine and health science.

It is essential that research organisations include ethical considerations and equity in the design and delivery of their research, and that governing bodies invest in addressing the social and ethical implications

Katrina Costa (quote from the YourGenome website).

Patients, research participants and their advocates should be part of those deliberations. For example, this report from NHS Genomic AI Network, 2024, was the result of a dialogue with 100 people, many of whom were representing patient groups, see here.

Discussion:

What types of AI uses do you think are acceptable and unacceptable for large scale health data and biobanks? Where should the limits be? Who should make the decisions about what is or is not OK?

Please leave your opinion in the comments section, and see if you agree or disagree with other learners. Like the comments that you agree with.

In the next step, we will discuss the ethical issues that are specifically relevant to genomics in more depth.