Three Steps Novel Machine Learning Method Classifies Uncertain MEFV Gene Variants DOI Creative Commons
Mustafa Tarık Alay, İbrahim Demir, Murat Ki̇ri̇şçi̇

и другие.

Research Square (Research Square), Год журнала: 2023, Номер unknown

Опубликована: Июль 20, 2023

Abstract Introduction: The International Study Group for Systemic Autoinflammatory Diseases (INSAID) consensus criteria revealed that the clinical outcomes of more than half MEFV gene variants are uncertain. In this study, we estabilished a novel approach accurate classification by using optimal number amino acid prediction scores and machine-learning algorithms. Our goal was to determine while also reducing uncertainties. Material-Methods: We extracted from infevers database ,and point mutations were included, others excluded study. then determined in silico instruments our model. On training dataset, implemented seven machine learning algorithms on with known effects. evaluated effectiveness model three steps: First, performed dataset those accuracy greater 90 percent. Second, compared results existing studies. Third, functional level. Results included 266 381 four computational tools algorithm classified Likely pathogenic (LP) an 96.6% classifying 97.6% Benign (LB) variants. Among methods used classify variants, method yielded most datasets. Most predictors LB higher 90% however, LP showed wide range variety between 2% − 62.5%. Disease-causing frequently located domains. Functional level evaluation compatible results. Discussion comparison indicated variant is biggest problem classification, might be candidate solving 96.67% accuracy. Considering 60% effects unresolved, evaluating conjunction manifestations patients significantly simplifies interpretation unknown

Язык: Английский

Neuronal wires and novel epileptic gene studies: Methods and mechanism of brain network and - Recent update DOI
Meenakshi Sundari Rajendran, Rajkumar Prabhakaran,

Rathi Muthaiyan Ahalliya

и другие.

Human Gene, Год журнала: 2023, Номер 37, С. 201186 - 201186

Опубликована: Май 24, 2023

Язык: Английский

Процитировано

0
Three Steps Novel Machine Learning Method Classifies Uncertain MEFV Gene Variants DOI Creative Commons
Mustafa Tarık Alay, İbrahim Demir, Murat Ki̇ri̇şçi̇

и другие.

Research Square (Research Square), Год журнала: 2023, Номер unknown

Опубликована: Июль 20, 2023

Abstract Introduction: The International Study Group for Systemic Autoinflammatory Diseases (INSAID) consensus criteria revealed that the clinical outcomes of more than half MEFV gene variants are uncertain. In this study, we estabilished a novel approach accurate classification by using optimal number amino acid prediction scores and machine-learning algorithms. Our goal was to determine while also reducing uncertainties. Material-Methods: We extracted from infevers database ,and point mutations were included, others excluded study. then determined in silico instruments our model. On training dataset, implemented seven machine learning algorithms on with known effects. evaluated effectiveness model three steps: First, performed dataset those accuracy greater 90 percent. Second, compared results existing studies. Third, functional level. Results included 266 381 four computational tools algorithm classified Likely pathogenic (LP) an 96.6% classifying 97.6% Benign (LB) variants. Among methods used classify variants, method yielded most datasets. Most predictors LB higher 90% however, LP showed wide range variety between 2% − 62.5%. Disease-causing frequently located domains. Functional level evaluation compatible results. Discussion comparison indicated variant is biggest problem classification, might be candidate solving 96.67% accuracy. Considering 60% effects unresolved, evaluating conjunction manifestations patients significantly simplifies interpretation unknown

Язык: Английский

Процитировано

0