Search

Background Recent efforts in the field of nutritional science have allowed the discovery of disease-beating molecules within foods based on the commonality of bioactive food molecules to FDA-approved drugs. The pioneering work in this field used an unsupervised network propagation algorithm to learn the systemic-wide effect on the human interactome of 1962 FDA-approved drugs and a supervised algorithm to predict anticancer therapeutics using the learned representations. Then, a set of bioactive molecules within foods was fed into the model, which predicted molecules with cancer-beating potential.The employed methodology consisted of disjoint unsupervised feature generation and classification tasks, which can result in sub-optimal learned drug representations with respect to the classification task. Additionally, due to the disjoint nature of the tasks, the employed approach proved cumbersome to optimize, requiring testing of thousands of hyperparameter combinations and significant computational resources.To overcome the technical limitations highlighted above, we represent each drug as a graph (human interactome) with its targets as binary node features on the graph and formulate the problem as a graph classification task. To solve this task, inspired by the success of graph neural networks in graph classification problems, we use an end-to-end graph neural network model operating directly on the graphs, which learns drug representations to optimize model performance in the prediction of anticancer therapeutics. Results The proposed model outperforms the baseline approach in the anticancer therapeutic prediction task, achieving an F1 score of 67.99%±2.52% and an AUPR of 73.91%±3.49%. It is also shown that the model is able to capture knowledge of biological pathways to predict anticancer molecules based on the molecules’ effects on cancer-related pathways. Conclusions 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.

We engineered a machine learning approach, MSHub, to enable auto-deconvolution of gas chromatography–mass spectrometry (GC–MS) data. We then designed workflows to enable the community to store, process, share, annotate, compare and perform molecular networking of GC–MS data within the Global Natural Product Social (GNPS) Molecular Networking analysis platform. MSHub/GNPS performs auto-deconvolution of compound fragmentation patterns via unsupervised non-negative matrix factorization and quantifies the reproducibility of fragmentation patterns across samples., Fil: Aksenov, Alexander A. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Aksenov, Alexander A. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Laponogov, Ivan. South Kensington Campus. Imperial College London. Department of Surgery and Cancer; Reino Unido, Fil: Zhang, Zheng. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Doran, Sophie L. F. South Kensington Campus. Imperial College London. Department of Surgery and Cancer; Reino Unido, Fil: Belluomo, Ilaria. South Kensington Campus. Imperial College London. Department of Surgery and Cancer; Reino Unido, Fil: Veselkov, Dennis. Intelligify Limited. Reino Unido. South Kensington Campus. Imperial College. Department of Computing; Reino Unido, Fil: Bittremieux, Wout. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Bittremieux, Wout. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Bittremieux, Wout. University of Antwerp. Department of Computer Science; Belgica, Fil: Nothias, Louis Felix. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Nothias, Louis Felix. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Nothias-Esposito, Mélissa. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Nothias-Esposito, Mélissa. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Maloney, Katherine N. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Maloney, Katherine N. Point Loma Nazarene University. Department of Chemistry; Estados Unidos, Fil: Misra, Biswapriya B. Wake Forest School of Medicine. Section of Molecular Medicine. Department of Internal Medicine. Center for Precision Medicine; Estados Unidos, Fil: Melnik, Alexey V. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Smirnov, Aleksandr. University of North Carolina at Charlotte. Department of Bioinformatics and Genomics; Estados Unidos, Fil: Du, Xiuxia. University of North Carolina at Charlotte. Department of Bioinformatics and Genomics; Estados Unidos, Fil: Jones, Kenneth L. University of North Carolina at Charlotte. Department of Bioinformatics and Genomics; Estados Unidos, Fil: Dorrestein, Kathleen. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Dorrestein, Kathleen. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Panitchpakdi, Morgan. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Ernst, Madeleine. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Ernst, Madeleine. Statens Serum Institut. Danish Center for Neonatal Screening. Department of Congenital Disorders. Section for Clinical Mass Spectrometry; Dinamarca, Fil: van der Hooft, Justin J. J. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: van der Hooft, Justin J. J. Wageningen University. Bioinformatics Group; Países Bajos, Fil: Gonzalez, Mabel. Universidad de los Andes. Department of Chemistry; Colombia, Fil: Carazzone, Chiara. Universidad de los Andes. Department of Chemistry; Colombia, Fil: Amézquita, Adolfo. Universidad de los Andes. Department of Biological Sciences; Colombia, Fil: Callewaert, Chris. Center for Microbial Ecology and Technology; Belgica, Fil: Callewaert, Chris. University of California. Department of Pediatrics; Estados Unidos, Fil: Morton, James T. University of California. Department of Pediatrics; Estados Unidos, Fil: Morton, James T. Simons Foundation. Flatiron Institute. Center for Computational Biology; Estados Unidos, Fil: Quinn, Robert A. Michigan State University. Department of Biochemistry and Molecular Biology; Estados Unidos, Fil: Bouslimani, Amina. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Bouslimani, Amina. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Orio, Andrea Albarracín. Universidad Católica de Córdoba. IRNASUS. CONICET. Facultad de Ciencias Agropecuarias; Argentina, Fil: Petras, Daniel. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Petras, Daniel. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Smania, Andrea M. Universidad Nacional de Córdoba. Facultad de Ciencias Químicas. Departamento de Química Biológica Ranwel Caputto; Argentina, Fil: Smania, Andrea M. Centro de Investigaciones en Química Biológica de Córdoba. Universidad Nacional de Córdoba. CONICET; Argentina, Fil: Couvillion, Sneha P. Pacific Northwest National Laboratory. Biological Sciences Division; Estados Unidos, Fil: Burnet, Meagan C. Pacific Northwest National Laboratory. Biological Sciences Division; Estados Unidos, Fil: Nicora, Carrie D. Pacific Northwest National Laboratory. Biological Sciences Division; Estados Unidos, Fil: Zink, Erika. Pacific Northwest National Laboratory. Biological Sciences Division; Estados Unidos, Fil: Metz, Thomas O. Pacific Northwest National Laboratory. Biological Sciences Division; Estados Unidos, Fil: Artaev, Viatcheslav. LECO Corporation; Estados Unidos, Fil: Humston-Fulmer, Elizabeth. LECO Corporation; Estados Unidos, Fil: Gregor, Rachel. Ben-Gurion University of the Negev. Department of Chemistry and the National Institute for Biotechnology in the Negev; Israel, Fil: Meijler, Michael M. Ben-Gurion University of the Negev. Department of Chemistry and the National Institute for Biotechnology in the Negev; Israel, Fil: Mizrahi, Itzhak. Ben-Gurion University of the Negev. Department of Life Sciences and the National Institute for Biotechnology in the Negev; Israel, Fil: Eyal, Stav. Ben-Gurion University of the Negev. Department of Life Sciences and the National Institute for Biotechnology in the Negev; Israel, Fil: Anderson, Brooke. University of California. Division of Biological Sciences; Estados Unidos, Fil: Dutton, Rachel. University of California. Division of Biological Sciences; Estados Unidos, Fil: Lugan, Raphaël. Université d’Avignon et des Pays du Vaucluse, Agrosciences. UMR Qualisud; Francia, Fil: Boulch, Pauline Le. Université d’Avignon et des Pays du Vaucluse, Agrosciences. UMR Qualisud; Francia, Fil: Guitton, Yann. INRAe. Oniris. Laboratoire d’Etude des Résidus et Contaminants dans les Aliments (LABERCA); Francia, Fil: Prevost, Stephanie. INRAe. Oniris. Laboratoire d’Etude des Résidus et Contaminants dans les Aliments (LABERCA); Francia, Fil: Poirier, Audrey. INRAe. Oniris. Laboratoire d’Etude des Résidus et Contaminants dans les Aliments (LABERCA); Francia, Fil: Dervilly, Gaud. INRAe. Oniris. Laboratoire d’Etude des Résidus et Contaminants dans les Aliments (LABERCA); Francia, Fil: Le Bizec, Bruno. Oniris. Laboratoire d’Etude des Résidus et Contaminants dans les Aliments (LABERCA); Francia, Fil: Fait, Aaron. Ben Gurion University of the Negev. Sede Boqer Campus. The Jacob Blaustein Institutes for Desert Research. The French Associates Institute for Agriculture and Biotechnology of Dryland; Israel, Fil: Persi, Noga Sikron. Ben Gurion University of the Negev. Sede Boqer Campus. The Jacob Blaustein Institutes for Desert Research. The French Associates Institute for Agriculture and Biotechnology of Dryland; Israel, Fil: Song, Chao. Ben Gurion University of the Negev. Sede Boqer Campus. The Jacob Blaustein Institutes for Desert Research. The French Associates Institute for Agriculture and Biotechnology of Dryland; Israel, Fil: Gashu, Kelem. Ben Gurion University of the Negev. Sede Boqer Campus. The Jacob Blaustein Institutes for Desert Research. The French Associates Institute for Agriculture and Biotechnology of Dryland; Israel, Fil: Coras, Roxana. University of California. Department of Medicine. Division of Rheumatology; Estados Unidos, Fil: Guma, Monica. University of California. Department of Medicine. Division of Rheumatology; Estados Unidos, Fil: Manasson, Julia. New York University School of Medicine. Department of Medicine. Division of Rheumatology; Estados Unidos, Fil: Scher, Jose U. New York University School of Medicine. Department of Medicine. Division of Rheumatology; Estados Unidos, Fil: Barupal, Dinesh Kumar. Icahn School of Medicine at Mount Sinai. Department of Environmental Medicine and Public Health; Estados Unidos, Fil: Alseekh, Saleh. Max Planck Institute for Molecular Plant Physiology; Alemania, Fil: Alseekh, Saleh. Center of Plant Systems Biology and Biotechnology (CPSBB); Bulgaria, Fil: Fernie, Alisdair R. Max Planck Institute for Molecular Plant Physiology; Alemania, Fil: Fernie, Alisdair R. Center of Plant Systems Biology and Biotechnology (CPSBB); Bulgaria, Fil: Mirnezami, Reza. Royal Free Hospital NHS Foundation Trust. Department of Colorectal Surgery; Reino Unido, Fil: Vasiliou, Vasilis. Yale University. Yale School of Public Health. Department of Environmental Health Sciences; Estados Unidos, Fil: Schmid, Robin. University of Münster. Institute of Inorganic and Analytical Chemistry; Alemania, Fil: Borisov, Roman S. A.V. Topchiev Institute of Petrochemical Synthesis RAS; Rusia, Fil: Kulikova, Larisa N. Рeoples’ Friendship University of Russia (RUDN University); Rusia, Fil: Knight, Rob. University of California. Department of Pediatrics; Estados Unidos, Fil: Knight, Rob. University of California. UCSD Center for Microbiome Innovation; Estados Unidos, Fil: Knight, Rob. University of California. Department of Bioengineering; Estados Unidos, Fil: Wang, Mingxun. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Wang, Mingxun. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Hanna, George B. South Kensington Campus. Imperial College London. Department of Surgery and Cancer; Reino Unido, Fil: Dorrestein, Pieter C. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences; Estados Unidos, Fil: Dorrestein, Pieter C. University of California. Skaggs School of Pharmacy and Pharmaceutical Sciences. Collaborative Mass Spectrometry Innovation Center; Estados Unidos, Fil: Dorrestein, Pieter C. University of California. Department of Pediatrics; Estados Unidos, Fil: Veselkov, Kirill. South Kensington Campus. Imperial College London. Department of Surgery and Cancer; Reino Unido

Recent research efforts have shown the possibility to discover anticancer drug-like molecules in food from their effect on protein-protein interaction networks, opening a potential pathway to disease-beating diet design. We formulate this task as a graph classification problem on which graph neural networks (GNNs) have achieved state-of-the-art results. However, GNNs are difficult to train on sparse low-dimensional features according to our empirical evidence. Here, we present graph augmented features, integrating graph structural information and raw node attributes with varying ratios, to ease the training of networks. We further introduce a novel neural network architecture on graphs, the Graph Attentional Autoencoder (GAA) to predict food compounds with anticancer properties based on perturbed protein networks. We demonstrate that the method outperforms the baseline approach and state-of-the-art graph classification models in this task.

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.

A workshop on research gaps and opportunities for Precision Medicine in Pancreatic Disease was sponsored by the National Institute of Diabetes and Digestive Kidney Diseases on July 24, 2019, in Pittsburgh. The workshop included an overview lecture on precision medicine in cancer and 4 sessions: (1) general considerations for the application of bioinformatics and artificial intelligence; (2) omics, the combination of risk factors and biomarkers; (3) precision imaging; and (4) gaps, barriers, and needs to move from precision to personalized medicine for pancreatic disease. Current precision medicine approaches and tools were reviewed, and participants identified knowledge gaps and research needs that hinder bringing precision medicine to pancreatic diseases. Most critical were (a) multicenter efforts to collect large-scale patient data sets from multiple data streams in the context of environmental and social factors; (b) new information systems that can collect, annotate, and quantify data to inform disease mechanisms; (c) novel prospective clinical trial designs to test and improve therapies; and (d) a framework for measuring and assessing the value of proposed approaches to the health care system. With these advances, precision medicine can identify patients early in the course of their pancreatic disease and prevent progression to chronic or fatal illness.