Network regularised Cox regression and multiplex network models to predict disease comorbidities and survival of cancer
Institution:
1. Computer Laboratory, University of Cambridge, Cambridge CB3 0FD, UK;2. Bone Biology, Garvan Institute of Medical Research, Australia;1. Department of Mechanical Engineering, Graduate University of Advanced Technology, Kerman, Iran;2. Department of Mechanical Engineering, Shahid Bahonar University of Kerman, Kerman, Iran;3. Department of Medical Physics, School of Medicine, Kerman University of Medical Sciences, Kerman, Iran;4. Istituto Italiano di Tecnologia, Graphene Labs, Genova, Italy;5. ISOF – Istituto per la Sintesi Organica e la Fotoreattività, Consiglio Nazionale delle Ricerche, Bologna, Italy;6. Laboratorio MIST.E-R Bologna, Bologna, Italy;7. Department of Materials Science, University of Patras, Rio Patras, Greece;8. Institute of Chemical Engineering Sciences, Foundation of Research and Technology-Hellas, Platani, Patras Acahaias, Greece;9. Laboratory of Bio-Inspired & Graphene Nanomechanics, Department of Civil, Environmental and Mechanical Engineering, Università di Trento, Trento, Italy;10. Center for Materials and Microsystems, Fondazione Bruno Kessler, Povo (Trento), Italy;11. School of Engineering & Materials Science, Queen Mary University of London, London, UK;1. Department of Clinical & Chemical Pathology, Kasr Al-Ainy, School of Medicine, Cairo University, Egypt;2. Endemic Medicine Department, Liver Unit, Cairo University Center of Hepatic Fibrosis (CUC-HF), Faculty of Medicine, Cairo University, Egypt;1. Department of Biomedical Engineering, Columbia University, Mail Code 8904, 1210 Amsterdam Avenue, New York, NY 10027, USA;2. Department of Biomedical Engineering, Duke University, 136 Hudson Hall, P. O. Box 90281, Durham, NC 27708, USA;3. Department of Biomedical Engineering, Khalifa University, P. O. Box 127788, Abu Dhabi, United Arab Emirates;4. Center for Biomaterials, Biomedical Research Institute, Korea Institute of Science and Technology, Seoul, South Korea
Abstract:
In cancer genomics, gene expression levels provide important molecular signatures for all types of cancer, and this could be very useful for predicting the survival of cancer patients. However, the main challenge of gene expression data analysis is high dimensionality, and microarray is characterised by few number of samples with large number of genes. To overcome this problem, a variety of penalised Cox proportional hazard models have been proposed. We introduce a novel network regularised Cox proportional hazard model and a novel multiplex network model to measure the disease comorbidities and to predict survival of the cancer patient. Our methods are applied to analyse seven microarray cancer gene expression datasets: breast cancer, ovarian cancer, lung cancer, liver cancer, renal cancer and osteosarcoma. Firstly, we applied a principal component analysis to reduce the dimensionality of original gene expression data. Secondly, we applied a network regularised Cox regression model on the reduced gene expression datasets. By using normalised mutual information method and multiplex network model, we predict the comorbidities for the liver cancer based on the integration of diverse set of omics and clinical data, and we find the diseasome associations (disease–gene association) among different cancers based on the identified common significant genes. Finally, we evaluated the precision of the approach with respect to the accuracy of survival prediction using ROC curves. We report that colon cancer, liver cancer and renal cancer share the CXCL5 gene, and breast cancer, ovarian cancer and renal cancer share the CCND2 gene. Our methods are useful to predict survival of the patient and disease comorbidities more accurately and helpful for improvement of the care of patients with comorbidity. Software in Matlab and R is available on our GitHub page: https://github.com/ssnhcom/NetworkRegularisedCox.git.
