Machine learning methods for prioritizing novel candidate disease-causing variants

Dr. Imane Boudellioua

ucjournals

Abstract: Recent advances in Next Generation Sequencing (NGS) technologies have generated massive amounts of genomic data which in turn is bringing the promise that personalized medicine will soon become widely available. As a result, there is an increasing pressure to develop computational tools to interpret genomic data produced at diagnostic labs. Artificial intelligence algorithms can significantly contribute towards analyzing genomic data. In this talk, we discuss opportunities and challenges of incorporating artificial intelligence for the molecular diagnosis of rare diseases. We also present a suite of machine learning based tools, PVP[1], DeepPVP[2], and OligoPVP[3], that we developed for interrogating patients’ genomes to identify candidate causal genomic variants of Mendelian and oligogenic diseases. These methods incorporate genotype-phenotype relations by exploiting semantic technologies and automated reasoning inferred throughout a cross-species phenotypic ontology network obtained from human, mouse, and zebra fish studies. We further discuss a retrospective study using our proposed methods on a set of real patients’ exomes suffering from congenital hypothyroidism. We show that our methods successfully outperformed several state-of-the-art methods, and provide a promising tool for accurate variant prioritization for Mendelian diseases. Finally, we discuss some limitations and future steps for extending the applicability of our proposed methods to identify the genetic underpinning for Mendelian and oligogenic diseases.

Keywords: Variant prioritization, gene-phenotype associations, NGS data analysis, precision diagnostics

 

References: [1] Boudellioua I, Mahamad Razali RB, Kulmanov M, Hashish Y, Bajic VB, et al. (2017) Semantic prioritization of novel causative genomic variants. PLOS Computational Biology 13(4): e1005500. [2] Boudellioua, I., Kulmanov, M., Schofield, P. et al. DeepPVP: phenotype-based prioritization of causative variants using deep learning. BMC Bioinformatics 20, 65 (2019).. [3] Boudellioua, I., Kulmanov, M., Schofield, P.N. et al. OligoPVP: Phenotype-driven analysis of individual genomic information to prioritize oligogenic disease variants. Scientific Reports, 8, 14681 (2018).

Biography: Dr. Imane Boudellioua is a Senior Researcher at the Biotechnology Research Center at Technology Innovation Institute in Abu Dhabi, UAE. Previously, she was an Assistant Professor in the Information and Computer Science Department at King Fahd University of Petroleum and Minerals, and one of the founding female faculty members at KFUPM. She holds a PhD degree in Computer Science from King Abdullah University of Science and Technology, where she was awarded KAUST Discovery Scholarship, KAUST MSc/PhD Fellowship, and KAUST Provost Award. She is the recipient of 2020 KACSTAlMarai Prize for Scientific Creativity for her PhD thesis on machine learning methods for the prioritization of candidate causative genomic variants of Mendelian and oligogenic diseases. She is also one of the winners of KAUST TAQADAM Accelerator Program for her startup, GenomeFit, providing AIempowered genetic diagnostics services. Her research interests are in computational genomics, and the application of machine learning and data mining in the biomedical field.

Tags:

Healthcare Conference, Nursing & Health Sciences, Healthcare Simulation, Home Care Nursing Services, Advanced Healthcare, Types of Nursing in Healthcare, Public Health Nursing, Healthcare Leadership, Healthcare Management, Hospital Management, Internal Medicine, Pharmacology, Psychiatry and Mental Health, Healthcare Quality, Family Medicine, Child Health Advanced Nursing Practices during Pandemic, Nurse Protection during Pandemics, Oncology Nursing, Cardiac Nursing, Gynacology and Obstetrics Nursing, Nursing Education, Global Healthcare, Family Nursing, Men in Nursing, Nursing Care, Women Health Nursing, Infection Control, Healthcare Quality improvement, Tele Healthcare, Digital Healthcare, Healthcare Services, Healthcare Marketing

Upcoming UCG Conference;

Related Articles
↑
Exit mobile version