Your browser doesn't support javascript.
loading
HyperFoods: Machine intelligent mapping of cancer-beating molecules in foods.
Veselkov, Kirill; Gonzalez, Guadalupe; Aljifri, Shahad; Galea, Dieter; Mirnezami, Reza; Youssef, Jozef; Bronstein, Michael; Laponogov, Ivan.
Affiliation
  • Veselkov K; Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, SW7 2AZ, UK. kirill.veselkov04@imperial.ac.uk.
  • Gonzalez G; Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, SW7 2AZ, UK.
  • Aljifri S; Department of Computing, Faculty of Engineering, Imperial College London, London, SW7 2AZ, UK.
  • Galea D; Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, SW7 2AZ, UK.
  • Mirnezami R; Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, SW7 2AZ, UK.
  • Youssef J; Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, SW7 2AZ, UK.
  • Bronstein M; Kitchen Theory, London, EN5 4LG, UK.
  • Laponogov I; Department of Computing, Faculty of Engineering, Imperial College London, London, SW7 2AZ, UK.
Sci Rep ; 9(1): 9237, 2019 07 03.
Article in En | MEDLINE | ID: mdl-31270435
Recent data indicate that up-to 30-40% of cancers can be prevented by dietary and lifestyle measures alone. Herein, we introduce a unique network-based machine learning platform to identify putative food-based cancer-beating molecules. These have been identified through their molecular biological network commonality with clinically approved anti-cancer therapies. A machine-learning algorithm of random walks on graphs (operating within the supercomputing DreamLab platform) was used to simulate drug actions on human interactome networks to obtain genome-wide activity profiles of 1962 approved drugs (199 of which were classified as "anti-cancer" with their primary indications). A supervised approach was employed to predict cancer-beating molecules using these 'learned' interactome activity profiles. The validated model performance predicted anti-cancer therapeutics with classification accuracy of 84-90%. A comprehensive database of 7962 bioactive molecules within foods was fed into the model, which predicted 110 cancer-beating molecules (defined by anti-cancer drug likeness threshold of >70%) with expected capacity comparable to clinically approved anti-cancer drugs from a variety of chemical classes including flavonoids, terpenoids, and polyphenols. This in turn was used to construct a 'food map' with anti-cancer potential of each ingredient defined by the number of cancer-beating molecules found therein. Our analysis underpins the design of next-generation cancer preventative and therapeutic nutrition strategies.
Subject(s)

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Artificial Intelligence / Food Analysis / Neoplasms / Antineoplastic Agents Type of study: Prognostic_studies Limits: Humans Language: En Journal: Sci Rep Year: 2019 Type: Article

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Artificial Intelligence / Food Analysis / Neoplasms / Antineoplastic Agents Type of study: Prognostic_studies Limits: Humans Language: En Journal: Sci Rep Year: 2019 Type: Article