Search

Knowledge graph embedding models have gained significant attention in AI research. The aim of knowledge graph embedding is to embed the graphs into a vector space in which the structure of the graph is preserved. Recent works have shown that the inclusion of background knowledge, such as logical rules, can improve the performance of embeddings in downstream machine learning tasks. However, so far, most existing models do not allow the inclusion of rules. We address the challenge of including rules and present a new neural based embedding model (LogicENN). We prove that LogicENN can learn every ground truth of encoded rules in a knowledge graph. To the best of our knowledge, this has not been proved so far for the neural based family of embedding models. Moreover, we derive formulae for the inclusion of various rules, including (anti-)symmetric, inverse, irreflexive and transitive, implication, composition, equivalence, and negation. Our formulation allows avoiding grounding for implication and equivalence relations. Our experiments show that LogicENN outperforms the existing models in link prediction.

[2]M. Nayyeri, B. Xiong, M. Mohammadi, M. M. Akter, M. M. Alam, J. Lehmann ~. . In

Mahmoud M Habibullah,1,2 Syam Mohan,3,4 Nabeel Kashan Syed,5 Hafiz A Makeen,5 Qazi Mohammad Sajid Jamal,6 Hani Alothaid,7 Farkad Bantun,8 Alaa Alhazmi,1,2 Ali Hakamy,2,9 Yahia A Kaabi,1 Ghalia Samlan,10 Mohtashim Lohani,11 Neelaveni Thangavel,12 Mohamed Ahmed Al-Kasim5 1Department of Medical Laboratory Technology, Faculty of Applied Medical Sciences, Jazan University, Jazan, Saudi Arabia; 2SMIRES for Consultation in Specialized Medical Laboratories, Jazan University, Jazan, Saudi Arabia; 3Substance Abuse and Toxicology Research Center, Jazan University, Jazan, Saudi Arabia; 4School of Health Science, University of Petroleum and Energy Studies, Dehradun, Uttarakhand, India; 5Pharmacy Practice Research Unit, Department of Clinical Pharmacy, Faculty of Pharmacy, Jazan University, Jazan, Saudi Arabia; 6Department of Health Informatics, College of Public Health and Health Informatics, Qassim University, Al Bukayriyah, Saudi Arabia; 7Department of Basic Sciences, Faculty of Applied Medical Sciences, Al-Baha University, Al-Baha, Saudi Arabia; 8Department of Microbiology, Faculty of Medicine, Umm Al-Qura University, Makkah, Saudi Arabia; 9Respiratory Therapy Department, Faculty of Applied Medical Sciences, Jazan University, Jazan, Saudi Arabia; 10Department of Food Science and Nutrition, College of Food and Agriculture Sciences, King Saud University, Riyadh, Saudi Arabia; 11Emergency Medical Services Department, Faculty of Applied Medical Sciences, Jazan University, Jazan, Saudi Arabia; 12Department of Pharmaceutical Chemistry, Faculty of Pharmacy, Jazan University, Jazan, Saudi ArabiaCorrespondence: Mahmoud M Habibullah, Department of Medical Laboratory Technology, Faculty of Applied Medical Sciences, Jazan University, Al Maarefah Road, Jazan, Saudi Arabia, Tel +966 556644205, Email mhabibullah@jazanu.edu.saIntroduction: Numerous drugs with potent toxicity against cancer cells are available for treating malignancies, but therapeutic efficacies are limited due to their inefficient tumor targeting and deleterious effects on non-cancerous tissue. Therefore, two improvements are mandatory for improved chemotherapy 1) novel delivery techniques that can target cancer cells to deliver anticancer drugs and 2) methods to specifically enhance drug efficacy within tumors. The loading of inert drug carriers with anticancer agents and peptides which are able to bind (target) tumor-related proteins to enhance tumor drug accumulation and local cytotoxicity is a most promising approach.Objective: To evaluate the anticancer efficacy of Chitosan nanoparticles loaded with human growth hormone hGH fragment 176– 191 peptide plus the clinical chemotherapeutic doxorubicin in comparison with Chitosan loaded with doxorubicin alone.Methods: Two sets of in silico experiments were performed using molecular docking simulations to determine the influence of hGH fragment 176– 191 peptide on the anticancer efficacy of doxorubicin 1) the binding affinities of hGH fragment 176– 191 peptide to the breast cancer receptors, 2) the effects of hGH fragment 176– 191 peptide binding on doxorubicin binding to these same receptors. Further, the influence of hGH fragment 176– 191 peptide on the anticancer efficacy of doxorubicin was validated using viability assay in Human MCF-7 breast cancer cells.Results: In silico analysis suggested that addition of the hGH fragment to doxorubicin-loaded Chitosan nanoparticles can enhance doxorubicin binding to multiple breast cancer protein targets, while photon correlation spectroscopy revealed that the synthesized dual-loaded Chitosan nanoparticles possess clinically favorable particle size, polydispersity index, as well as zeta potential.Conclusion: These dual-loaded Chitosan nanoparticles demonstrated greater anti-proliferative activity against a breast cancer cell line (MCF-7) than doxorubicin-loaded Chitosan. This dual-loading strategy may enhance the anticancer potency of doxorubicin and reduce the clinical side effects associated with non-target tissue exposure.Keywords: anticancer potency, nanoparticles, cytotoxicity, docking analysis