Drug-drug interaction (DDI) prediction is a challenging problem in pharmacology and clinical application, and effectively identifying potential DDIs during clinical trials is critical for patients and society. Most of existing computational models with AI techniques often concentrate on integrating multiple data sources and combining popular embedding methods together. Yet, researchers pay less attention to the potential correlations between drug and other entities such as targets and genes. Moreover, recent studies also adopted knowledge graph (KG) for DDI prediction. Yet, this line of methods learn node latent embedding directly, but they are limited in obtaining the rich neighborhood information of each entity in KG. To address the above limitations, we propose an end-to-end framework, called Knowledge Graph Neural Network (KGNN), to resolve the DDI prediction. Our framework can effectively capture drug and its potential neighborhoods by mining their associated relations in KG. To extract both high-order structures and semantic relations of the KG, we learn from the neighborhoods for each entity in KG as their local receptive, and then integrate neighborhood information with bias from representation of the current entity. This way, the receptive field can be naturally extended to multiple hops away to model highorder topological information and to obtain drugs potential long-distance correlations. We have implemented our method and conducted experiments based on several widely-used datasets. Empirical results show that KGNN outperforms the classic and state-of-the-art models.

/pdf/kgnn-knowledge-graph-neural-network-for-drug-drug-43s9p5pwcp.pdf

KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction

Developing multi-agent systems with a FIPA-compliant agent framework

Knowledge graphs can support many biomedical applications. These graphs represent biomedical concepts and relationships in the form of nodes and edges. In this review, we discuss how these graphs are constructed and applied with a particular focus on how machine learning approaches are changing these processes. Biomedical knowledge graphs have often been constructed by integrating databases that were populated by experts via manual curation, but we are now seeing a more robust use of automated systems. A number of techniques are used to represent knowledge graphs, but often machine learning methods are used to construct a low-dimensional representation that can support many different applications. This representation is designed to preserve a knowledge graph’s local and/or global structure. Additional machine learning methods can be applied to this representation to make predictions within genomic, pharmaceutical, and clinical domains. We frame our discussion first around knowledge graph construction and then around unifying representational learning techniques and unifying applications. Advances in machine learning for biomedicine are creating new opportunities across many domains, and we note potential avenues for future work with knowledge graphs that appear particularly promising.

https://greenelab.github.io/knowledge-graph-review/manuscript.pdf

Constructing knowledge graphs and their biomedical applications.

Multi-scale approach from mechatronic to Cyber-Physical Systems for the design of manufacturing systems

A system built in terms of autonomous agents may require even greater correctness assurance than one which is merely reacting to the immediate control of its users. Agents make substantial decisions for themselves, so thorough testing is an important consideration. However, autonomy also makes testing harder; by their nature, autonomous agents may react in different ways to the same inputs over time, because, for instance they have changeable goals and knowledge. For this reason, we argue that testing of autonomous agents requires a procedure that caters for a wide range of test case contexts, and that can search for the most demanding of these test cases, even when they are not apparent to the agents' developers. In this paper, we address this problem, introducing and evaluating an approach to testing autonomous agents that uses evolutionary optimization to generate demanding test cases.

/pdf/evolutionary-testing-of-autonomous-software-agents-4c2n2g6bcb.pdf

Evolutionary testing of autonomous software agents

Current approaches to identifying drug-drug interactions (DDIs), include safety studies during drug development and post-marketing surveillance after approval, offer important opportunities to identify potential safety issues, but are unable to provide complete set of all possible DDIs. Thus, the drug discovery researchers and healthcare professionals might not be fully aware of potentially dangerous DDIs. Predicting potential drug-drug interaction helps reduce unanticipated drug interactions and drug development costs and optimizes the drug design process. Methods for prediction of DDIs have the tendency to report high accuracy but still have little impact on translational research due to systematic biases induced by networked/paired data. In this work, we aimed to present realistic evaluation settings to predict DDIs using knowledge graph embeddings. We propose a simple disjoint cross-validation scheme to evaluate drug-drug interaction predictions for the scenarios where the drugs have no known DDIs. We designed different evaluation settings to accurately assess the performance for predicting DDIs. The settings for disjoint cross-validation produced lower performance scores, as expected, but still were good at predicting the drug interactions. We have applied Logistic Regression, Naive Bayes and Random Forest on DrugBank knowledge graph with the 10-fold traditional cross validation using RDF2Vec, TransE and TransD. RDF2Vec with Skip-Gram generally surpasses other embedding methods. We also tested RDF2Vec on various drug knowledge graphs such as DrugBank, PharmGKB and KEGG to predict unknown drug-drug interactions. The performance was not enhanced significantly when an integrated knowledge graph including these three datasets was used. We showed that the knowledge embeddings are powerful predictors and comparable to current state-of-the-art methods for inferring new DDIs. We addressed the evaluation biases by introducing drug-wise and pairwise disjoint test classes. Although the performance scores for drug-wise and pairwise disjoint seem to be low, the results can be considered to be realistic in predicting the interactions for drugs with limited interaction information.

/pdf/evaluation-of-knowledge-graph-embedding-approaches-for-drug-1hgdx67o28.pdf

Evaluation of knowledge graph embedding approaches for drug-drug interaction prediction in realistic settings

In this paper, a new agent development platform, which includes built-in features for semantic web based multi agent system development, is introduced. All agents and services in the platform use semantic web standards to represent their internal knowledge and semantic web query languages are used to query them. Semantic web services can be discovered and dynamically invoked. The directory service is implemented in a way to support semantic matching of agent capabilities. The ontology service allows ontology translation based on defined mappings between platform ontologies and external ontologies. With these features already integrated, the agent development platform that is developed simplifies the semantic web based multi-agent system development.

SEAGENT: a platform for developing semantic web based multi agent systems

In this paper, we discuss the development of a multi agent system working on the Semantic Web environment by using a new framework called SEAGENT. SEAGENT is a new agent development framework and platform, which includes built-in features for semantic web based multi agent system development. These features provide semantic supports such as a new specific content language for transferring semantic knowledge, specifically designed agent's internal architecture to handle semantic knowledge, a new directory facilitator architecture based on semantic service matching engine and ontology management service to provide ontology translations within the platform's ontologies. The implemented case study shows the effectiveness of these features in terms of semantically enriched multi agent system development.

Developing multi agent systems on semantic web environment using SEAGENT platform

Current approaches to identifying drug-drug interactions (DDIs), which involve clinical evaluation of drugs and post-marketing surveillance, are unable to provide complete, accurate information, nor do they alert the public to potentially dangerous DDIs before the drugs reach the market. Predicting potential drug-drug interaction helps reduce unanticipated drug interactions and drug development costs and optimizes the drug design process. Many bioinformatics databases have begun to present their data as Linked Open Data (LOD), a graph data model, using Semantic Web technologies. The knowledge graphs provide a powerful model for defining the data, in addition to making it possible to use underlying graph structure for extraction of meaningful information. In this work, we have applied Knowledge Graph (KG) Embedding approaches to extract feature vector representation of drugs using LOD to predict potential drug-drug interactions. We have investigated the effect of different embedding methods on the DDI prediction and showed that the knowledge embeddings are powerful predictors and comparable to current state-of-the-art methods for inferring new DDIs. We have applied Logistic Regression, Naive Bayes and Random Forest on Drugbank KG with the 10-fold traditional cross validation (CV) using RDF2Vec, TransE and TransD. RDF2Vec with uniform weighting surpass other embedding methods.

/pdf/evaluation-of-knowledge-graph-embedding-approaches-for-drug-bj1hr3kmmt.pdf

Evaluation of Knowledge Graph Embedding Approaches for Drug-Drug Interaction Prediction using Linked Open Data

Classification and addressing, and geographical origin of different olive oils is of great importance due to their differentiation in quality, and for commercial concerns. In this study, quantification of sterols, fatty acids, and triacylglycerol composition of forty-nine olive oils collected from six different locations of western part of Turkey (Izmir, Manisa, Aydin, Mugla, Bursa, and Edremit Bay) were performed by using chromatographic methods. Data for those olive oil samples were compiled, and classified with the artificial neural network (ANN) modelling and principal components analysis (PCA). The analytical results included resourceful information about determining geographical origin and traceability of olive oil in Turkey by using ANN and PCA. The ANN model for sterol composition showed the highest accuracy with 85.71%. The FAME and TAG profiles followed this with 83.67 and 81.63% accuracy respectively. However, Izmir and Manisa regions have poor sensitivity values with all ANN models since they are geographically very close to each other. Furthermore, the PCA results of the sterol composition have provided separation and clustering between locations. β-sitosterol, campesterol, stigmasterol and 24-metilen cholesterol have an important role in determining the separation of the locations of origin. While separation of the Bursa location has been under the pressure of FAME composition, the TAGs have been effective on the clustering of the Aydin and Edremit Bay. In conclusion, the geographical authentication of Turkish olive oils can be done with high accuracy by using ANN and PCA.

Özgür Gümüs

Papers

Evaluation of knowledge graph embedding approaches for drug-drug interaction prediction in realistic settings

SEAGENT: a platform for developing semantic web based multi agent systems

Developing multi agent systems on semantic web environment using SEAGENT platform

Evaluation of Knowledge Graph Embedding Approaches for Drug-Drug Interaction Prediction using Linked Open Data

Classification of olive oils using chromatography, principal component analysis and artificial neural network modelling