Machine learning-based acceleration of monogenic disease diagnosis
Abstract/Contents
- Abstract
- Monogenic diseases are genetic diseases caused by mutations to single genes in the human genome. There are currently over 5,000 described monogenic diseases with a known causative gene, and thousands more likely monogenic diseases with an unknown causative gene. Patients with monogenic diseases are affected by a wide spectrum of disease-associated phenotypic abnormalities such as intellectual disability, developmental delays, skin, heart, or facial abnormalities. A handful of monogenic diseases occur fairly frequently: e.g., sickle cell anemia, which affects up to 3% of newborns in some parts of Africa, and cystic fibrosis, which occurs in one out of approximately 3,000 white infants in the United States. However, most monogenic diseases are very rare, occurring at a frequency of less than 1 in 10,000 newborns. Since they are individually so rare, physicians may not recognize the symptoms immediately, making rare monogenic diseases hard to diagnose. This leads to so-called diagnostic odysseys, where patients seek an explanation for their symptoms for months or years. With the rise of genome sequencing, diagnosis of a monogenic disease is becoming more and more synonymous with identifying the causative gene in the patient's genome. Diagnosis, in particular by identification of the causative gene, can help predict the course of the disease, treatment options, provide a sense of closure to the patient and their relatives, and in the age of gene editing even provide a first hope for a cure. In this dissertation, I present multiple computational methods that accelerate the diagnosis of patients with suspected monogenic disease. I describe the computational discovery of a novel disease-causing mutation, the automatic curation of monogenic disease-related data directly from the primary literature and patient medical records, and novel computational methods for accelerating the discovery of causative genes directly from patient data. I hope that the findings presented here will help patients affected with monogenic diseases, their relatives, physicians, and genetic counselors, to achieve the best possible care.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2019; ©2019 |
Publication date | 2019; 2019 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Birgmeier, Johannes |
---|---|
Degree supervisor | Bejerano, Gill, 1970- |
Thesis advisor | Bejerano, Gill, 1970- |
Thesis advisor | Bernstein, Jonathan A |
Thesis advisor | Jurafsky, Dan, 1962- |
Degree committee member | Bernstein, Jonathan A |
Degree committee member | Jurafsky, Dan, 1962- |
Associated with | Stanford University, Computer Science Department. |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Johannes Birgmeier. |
---|---|
Note | Submitted to the Computer Science Department. |
Thesis | Thesis Ph.D. Stanford University 2019. |
Location | electronic resource |
Access conditions
- Copyright
- © 2019 by Johannes Birgmeier
Also listed in
Loading usage metrics...