Predicting anticancer hyperfoods with graph convolutional networks

Graph Neural Networks in Cancer and Oncology Research: Emerging and Future Trends

Next-generation cancer and oncology research needs to take full advantage of the multimodal structured, or graph, information, with the graph data types ranging from molecular structures to spatially resolved imaging and digital pathology, biological networks, and knowledge graphs. Graph Neural Networks (GNNs) efficiently combine the graph structure representations with the high predictive performance of deep learning, especially on large multimodal datasets. In this review article, we survey the landscape of recent (2020-present) GNN applications in the context of cancer and oncology research, and delineate six currently predominant research areas. We then identify the most promising directions for future research. We compare GNNs with graphical models and "non-structured" deep learning, and devise guidelines for cancer and oncology researchers or physician-scientists, asking the question of whether they should adopt the GNN methodology in their research pipelines.

Genomic-driven nutritional interventions for radiotherapy-resistant rectal cancer patient

Radiotherapy response of rectal cancer patients is dependent on a myriad of molecular mechanisms including response to stress, cell death, and cell metabolism. Modulation of lipid metabolism emerges as a unique strategy to improve radiotherapy outcomes due to its accessibility by bioactive molecules within foods. Even though a few radioresponse modulators have been identified using experimental techniques, trying to experimentally identify all potential modulators is intractable. Here we introduce a machine learning (ML) approach to interrogate the space of bioactive molecules within food for potential modulators of radiotherapy response and provide phytochemically-enriched recipes that encapsulate the benefits of discovered radiotherapy modulators. Potential radioresponse modulators were identified using a genomic-driven network ML approach, metric learning and domain knowledge. Then, recipes from the Recipe1M database were optimized to provide ingredient substitutions maximizing the number of predicted modulators whilst preserving the recipe's culinary attributes. This work provides a pipeline for the design of genomic-driven nutritional interventions to improve outcomes of rectal cancer patients undergoing radiotherapy.

Dietary Oncopharmacognosy as a Crosswalk between Precision Oncology and Precision Nutrition

While diet and nutrition are modifiable risk factors for many chronic and infectious diseases, their role in cancer prevention and control remains under investigation. The lack of clarity of some diet-cancer relationships reflects the ongoing debate about the relative contribution of genetic factors, environmental exposures, and replicative errors in stem cell division as determinate drivers of cancer risk. In addition, dietary guidance has often been based upon research assuming that the effects of diet and nutrition on carcinogenesis would be uniform across populations and for various tumor types arising in a specific organ, i.e., that one size fits all. Herein, we present a paradigm for investigating precision dietary patterns that leverages the approaches that led to successful small-molecule inhibitors in cancer treatment, namely understanding the pharmacokinetics and pharmacodynamics of small molecules for targeting carcinogenic mechanisms. We challenge the scientific community to refine the paradigm presented and to conduct proof-in-concept experiments that integrate existing knowledge (drug development, natural products, and the food metabolome) with developments in artificial intelligence to design and then test dietary patterns predicted to elicit drug-like effects on target tissues for cancer prevention and control. We refer to this precision approach as dietary oncopharmacognosy and envision it as the crosswalk between the currently defined fields of precision oncology and precision nutrition with the goal of reducing cancer deaths.

East Wind, West Wind: Toward the modernization of traditional Chinese medicine

Traditional Chinese medicine (TCM) has used herbal remedies for more than 2,000 years. The use of complimentary therapies has increased dramatically during the last years, especially in the West, and the incorporation and modernization of TCM in current medical practice is gaining momentum. We reflect on the main bottlenecks in the modernization of arcane Chinese herbal medicine: lack of standardization, safety concerns and poor quality of clinical trials, as well as the ways these are being overcome. Progress in these areas will facilitate the implementation of an efficacy approach, in which only successful clinical trials lead to the molecular characterization of active compounds and their mechanism of action. Traditional pharmacological methodologies will produce novel leads and drugs, and we describe TCM successes such as the discovery of artemisinin as well as many others still in the pipeline. Neurodegenerative diseases, such as Parkinson's and Alzheimer's disease, cancer and cardiovascular disease are the main cause of mortality in the Western world and, with an increasing old population in South East Asia, this trend will also increase in the Far East. TCM has been used for long time for treating these diseases in China and other East Asian countries. However, the holistic nature of TCM requires a paradigm shift. By changing our way of thinking, from "one-target, one-drug" to "network-target, multiple-component-therapeutics," network pharmacology, together with other system biology methodologies, will pave the way toward TCM modernization.