MLb-LDLr
| Autor: | Sonia Arrasate, Kepa B. Uribe, Unai Galicia-Garcia, Shifa Jebari-Benslaiman, Helena Ostolaza, César Martín, Fernando Civeira, Humberto González-Díaz, Ana Cenarro, José Angel Fernández-Higuero, Asier Larrea-Sebal, Asier Benito-Vicente |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
LNN
linear neural networks Disease Cascade screening Familial hypercholesterolemia Biology Machine learning computer.software_genre FH familial hypercholesterolemia LDL low-density lipoprotein machine learning software medicine Missense mutation pathogenicity EGS expert-guided selection ML machine learning Gene AUROC area under the receiver operating curve familial hypercholesterolemia business.industry nutritional and metabolic diseases LDL receptor ESEA Excel Solver Evolutionary algorithm prediction ANN artificial neural network Pathogenicity medicine.disease LDLr low-density lipoprotein receptor UTR untranslated region RBF radial basis function MLb-LDLr machine-learning–based low-density lipoprotein receptor software lipids (amino acids peptides and proteins) Artificial intelligence Preclinical Research MLP multilayer perceptron Cardiology and Cardiovascular Medicine business computer LDA linear discriminant analysis |
| Zdroj: | JACC: Basic to Translational Science |
| ISSN: | 2452-302X |
| Popis: | Visual Abstract Highlights • A machine-learning model has been developed to improve accuracy on predicting the activity of missense LDLr mutations. • ClinVar was used as database, and the model function was defined by using specific characteristics of the LDLr. • A high-score prediction ML model with specificity of 92.5% and sensitivity of 91.6% has been developed to predict pathogenicity of LDLr variants. • Implementation of high-predicting capacity software constitutes a valuable approach for assessing pathogenicity of LDLr variants to help in the early diagnosis and management of FH disease. • An open-access predictive software (MLb-LDLr) is provided to the scientific community. Summary Untreated familial hypercholesterolemia (FH) leads to atherosclerosis and early cardiovascular disease. Mutations in the low-density lipoprotein receptor (LDLr) gene constitute the major cause of FH, and the high number of mutations already described in the LDLr makes necessary cascade screening or in vitro functional characterization to provide a definitive diagnosis. Implementation of high-predicting capacity software constitutes a valuable approach for assessing pathogenicity of LDLr variants to help in the early diagnosis and management of FH disease. This work provides a reliable machine learning model to accurately predict the pathogenicity of LDLr missense variants with specificity of 92.5% and sensitivity of 91.6%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|