Researchers have used unsupervised machine learning to predict disease-causing properties in more than 36 million genetic variants across more than 3,200 disease-related genes.

In the process theyve advanced the classification of more than 256,000 genetic variants whose propertieshelpful, harmful or neitherhave been unknown.

The work was conducted at Harvard Medical School and Oxford University. The resulting study is posted online in Nature.

Quantifying the pathogenicity of protein variants in human disease-related genes would have a marked effect on clinical decisions, yet the overwhelming majority (over 98%) of these variants still have unknown consequences, write co-lead authors Jonathan Frazer, Mafalda Dias and colleagues to contextualize their pursuit.

In principle, computational methods could support the large-scale interpretation of genetic variants, they add. However, state-of-the-art methods have relied on training machine learning models on known disease labels.

For the current project, the team sought to overcome this limitation by modeling the distribution of sequence variation across organismsand over vast swaths of time.

In so doing, they hypothesized, they would isolate fitness-maintaining features in protein sequences.

Calling their model EVE for evolutionary model of variant effect, the authors report their technique proved more accurate than labeled-data AI approaches.

Whats more, it can equal or improve upon predictions from more commonly used approaches.

The team states their work with EVE suggests models of evolutionary information can provide valuable independent evidence for variant interpretation that will be widely useful in research and clinical settings.

Here is the original post:
AI predicts gathering disease with a deep dive into evolutionary genetics - AI in Healthcare