RESUMEN
The revolutionary CRISPR-Cas9 technology has revolutionized genetic engineering, and it holds immense potential for therapeutic interventions. However, the presence of off-target mutations and mismatch capacity poses significant challenges to its safe and precise implementation. In this study, we explore the implications of off-target effects on critical gene regions, including exons, introns, and intergenic regions. Leveraging a benchmark dataset and using innovative data preprocessing techniques, we have put forth the advantages of categorical encoding over one-hot encoding in training machine learning classifiers. Crucially, we use latent class analysis (LCA) to uncover subclasses within the off-target range, revealing distinct patterns of gene region disruption. Our comprehensive approach not only highlights the critical role of model complexity in CRISPR applications but also offers a transformative off-target scoring procedure based on ML classifiers and LCA. By bridging the gap between traditional target-off scoring and comprehensive model analysis, our study advances the understanding of off-target effects and opens new avenues for precision genome editing in diverse biological contexts. This work represents a crucial step toward ensuring the safety and efficacy of CRISPR-based therapies, underscoring the importance of responsible genetic manipulation for future therapeutic applications.
Asunto(s)
Sistemas CRISPR-Cas , Repeticiones Palindrómicas Cortas Agrupadas y Regularmente Espaciadas , Edición Génica , Mutación , ARN Guía de Sistemas CRISPR-Cas , ARN Guía de Sistemas CRISPR-Cas/genética , Edición Génica/métodos , Humanos , Exones , Intrones , Aprendizaje AutomáticoRESUMEN
AIMS: To develop a deep learning model, with the aid of ChatGPT, for thyroid nodules, utilizing ultrasound images. The cytopathology of the fine needle aspiration biopsy (FNAB) serves as the baseline. MATERIAL AND METHODS: After securing IRB approval, a retrospective study was conducted, analyzing thyroid ultrasound images and FNAB results from 1,061 patients between January 2017 and January 2022. Detailed examinations of their demographic profiles, imaging characteristics, and cytological features were conducted. The images were used for training a deep learning model to identify various thyroid pathologies. ChatGPT assisted in developing this model by aiding in code writing, preprocessing, model optimization, and troubleshooting. RESULTS: The model demonstrated an accuracy of 0.81 on the testing set, within a 95% confidence interval of 0.76 to 0.87. It presented remarkable results across thyroid subgroups, particularly in the benign category, with high precision (0.78) and recall (0.96), yielding a balanced F1-score of 0.86. The malignant category also displayed high precision (0.82) and recall (0.92), with an F1-score of 0.87. CONCLUSIONS: The study demonstrates the potential of artificial intelligence, particularly ChatGPT, in aiding the creation of robust deep learning models for medical image analysis.
Asunto(s)
Aprendizaje Profundo , Neoplasias de la Tiroides , Nódulo Tiroideo , Humanos , Nódulo Tiroideo/diagnóstico por imagen , Nódulo Tiroideo/patología , Estudios Retrospectivos , Inteligencia Artificial , Sensibilidad y Especificidad , Ultrasonografía/métodos , Inteligencia , Neoplasias de la Tiroides/patologíaRESUMEN
This retrospective cohort study deals with evaluating severity of COVID-19 cases on the first symptoms and blood-test results of infected patients admitted to Emergency Department of Koc University Hospital (Istanbul, Turkey). To figure out remarkable hematological characteristics and risk factors in the prognosis evaluation of COVID-19 cases, the hybrid machine learning (ML) approaches integrated with feature selection procedure based Genetic Algorithms and information complexity were used in addition to the multivariate statistical analysis. Specifically, COVID-19 dataset includes demographic features, symptoms, blood test results and disease histories of total 166 inpatients with different age and gender groups. Analysis results point out that the hybrid ML methods has brought out potential risk factors on the severity of COVID-19 cases and their impacts on the prognosis evaluation, accurately.