kANNa · Knowledge graph completion using Artificial Neural Networks for Herb-Drug Interaction discovery
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2019-04-01 → 2021-03-31
- EU contribution
- €185,076
- Participants
- 1
- Scheme
- MSCA-IF-EF-ST
Lines connect the coordinator with its partners.
Results in brief
Knowledge graph completion using Artificial Neural Networks for Herb-Drug Interaction discovery
Herbal medicinal products are commonly used in combination with conventional drugs, therefore there is an increased risk of serious interactions between them. In Eastern Europe 51.8% of women use herbal medicines in pregnancy and in Germany 70% of the population reported using “natural medicines”, often as a complement to conventional forms of therapy. This raises concerns especially in pharmacovigilance, a field of study concerned with the identification, evaluation and prevention of adverse drug reactions. While the effects of certain herbal drugs such as St John’s Wort are well understood, there is still little information on possible interactions for many drugs and herbal products. For this reason, the European Medicines Agency (EMA) is actively monitoring medical literature to identify adverse reactions for a predefined list of herbs to populate its pharmacovigilance database. But their list is far from being exhaustive and manual curation does not scale up in the face of an increasingly frequent publication rate. Take for example the case of kanna (sceletium tortuosum), a plant used for its effects against anxiety. Because of its neuro-receptor activities there are plausible concerns that it might interact with psychiatric drugs or cardiac medication. Although clinical evidence is still limited, understanding interaction mechanisms by comparing with similar plants can inform risk assessment. The main objective of the kANNa project is to automatically extract facts about herb-drug interactions from unstructured text through information extraction, combining and linking extracted information with rich information already available in general-purpose and domain-specific knowledge bases. To achieve this, the kANNa research program pursues the following measurable objectives: (i) Integrate information extraction into the process of monitoring herb-drug interactions from medical literature; (ii) Enhance additional knowledge acquisition from sparse, incomplete, and unreliable evidence; (iii) Provide support for clinical decision making and promote collaboration and reuse over the acquired knowledge base.
Data: CORDIS, © European Union
Project objective
With the growing popularity of herbal drugs an increasing number of scientific studies report information about herb-drug interactions that can significantly alter the effects of a drug. Keeping up with the current publication rate is not feasible, therefore there is a clear need for computational methods for early detection of herb-drug interactions that will enable better public and physician understanding of herbal products. But the costs of manually representing knowledge about herb-drug interactions in a machine processable way are prohibitive, therefore domain expertise has to be leveraged indirectly from domain-specific corpora using Information Extraction. This Marie Curie European Fellowship proposes a Deep Learning approach based on Artificial Neural Networks (ANN) and Information Extraction to monitor medical literature and construct a knowledge base of herb-drug interactions together with supporting evidence in the form of interaction mechanisms. To cope with the problem of incorrect or missing information we will consolidate the resulting knowledge graph using knowledge graph completion that predicts the probability of existence or correctness of typed edges in the graph. Advanced graph visualization techniques will be employed to develop intuitive interfaces for analyzing and comparing herb-drug interactions and underlying mechanisms. The Fellowship is expected to increase knowledge on clinically significant herb-drug interactions which will contribute to improved public safety. The Host will provide training on Deep Learning approaches for knowledge extraction which will open opportunities for a senior researcher position, in turn the Fellow will transfer Natural Language Processing skills and European collaborations to the host.
Original text from CORDIS.
Participants
- UNIVERSITE DE BORDEAUX · BordeauxCoordinatorFrance
Links
Data: CORDIS, © European Union