Google Research has introduced DeepSomatic, an open-source machine learning model that accelerates the analysis of genes to support cancer research.
Created in collaboration with UC Santa Cruz and Children’s Mercy, DeepSomatic utilizes convolutional neural networks to identify inherited and somatic genetic variants, including mutations that drive cancer growth.
The model has demonstrated outstanding performance in identifying complex variants, particularly insertions and deletions, in challenging cancer samples, such as pediatric leukemia and glioblastoma.
The model and high-quality training dataset are both available for public use, allowing scientists worldwide to contribute to advancing cancer research.
Google describes DeepSomatic as part of its goal to make foundational breakthroughs in AI that have concrete, real-world effects for researchers and patients.
You may also want to check out some of our other recent updates.
Wanna know what’s trending online every day? Subscribe to Vavoza Insider to access the latest business and marketing insights, news, and trends daily with unmatched speed and conciseness! 🗞️
