Login / Signup

Predicting anticancer hyperfoods with graph convolutional networks.

Guadalupe GonzalezShunwang GongIvan LaponogovMichael BronsteinKirill Veselkov
Published in: Human genomics (2021)
We introduce an end-to-end graph convolutional model to predict cancer-beating molecules within food. The introduced model outperforms the existing baseline approach, and shows interpretability, paving the way to the future of a personalized nutritional science approach allowing the development of nutrition strategies for cancer prevention and/or therapeutics.
Keyphrases
  • papillary thyroid
  • neural network
  • squamous cell
  • small molecule
  • convolutional neural network
  • physical activity
  • squamous cell carcinoma
  • childhood cancer
  • young adults
  • climate change
  • deep learning