Open Access. Powered by Scholars. Published by Universities.®
Medical Biomathematics and Biometrics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
-
- C.elegan (1)
- CRISPR-Cas9 (1)
- Contact-map (1)
- Covariance (1)
- DEEPCON (1)
-
- DEEPCON-PRE (1)
- Deep (1)
- Engineering (1)
- Evaluation (1)
- Feature (1)
- Folding (1)
- Gene (1)
- Genetics (1)
- Gum disease (1)
- Hereditary Gingival Fibromatosis (1)
- Inter-residue (1)
- Layer (1)
- Learning (1)
- Machine (1)
- Matrix (1)
- Microinjection (1)
- Mutation (1)
- Nematode (1)
- Network (1)
- Neural (1)
- Precision (1)
- Protein (1)
- ResPRE (1)
- SOS1 (1)
- Validation (1)
Articles 1 - 2 of 2
Full-Text Articles in Medical Biomathematics and Biometrics
Genetic Analysis Of Hereditary Gingival Fibromatosis Associated Sos1 Missense Variants Of Uncertain Significance In Caenorhabditis Elegans, Himani Patel
Theses
Hereditary gingival fibromatosis (HGF) is a disease that can present as benign overgrowth of gingival tissue in the mouth. The overgrowth can enclose the entire mouth and teeth in severe cases or present itself in a concentrated area. Researchers have identified that mutations in the SOS1 gene can be responsible for HGF. This disease can impair basic functions related to the mouth. Eating, smiling, speaking can all be affected. Additionally, excess inflammation can cause periodontal disease because of the difficulty in maintaining proper oral health. Periodontal disease can lead to severe bone loss which can lead to complete loss of …
Deepcon-Pre: Improved Protein Contact Map Prediction Using Inverse Covariance And Deep Residual Networks, Nachammai Palaniappan
Deepcon-Pre: Improved Protein Contact Map Prediction Using Inverse Covariance And Deep Residual Networks, Nachammai Palaniappan
Theses
As with most domains where machine learning methods are applied, correct feature engineering is critical when developing deep learning algorithms for solving the protein folding problem. Unlike the domains such as computer vision and natural language processing, feature engineering is not rigorously studied towards solving the protein folding problem. A recent research has highlighted that input features known as precision matrix are most informative for predicting inter-residue contact map, the key for building three-dimensional models. In this work, we study the significance of the precision matrix feature when very deep residual networks are trained. Using a standard dataset of 3456 …