RESUMO
INTRODUCTION: BRCA tumour testing is a crucial tool for personalised therapy of patients with ovarian cancer. Since different next-generation sequencing (NGS) platforms and BRCA panels are available, the NGS Italian Network proposed to assess the robustness of different technologies. METHODS: Six centres, using four different technologies, provided raw data of 284 cases, including 75 cases with pathogenic/likely pathogenic variants, for a revision blindly performed by an external bioinformatic platform. RESULTS: The third-party revision assessed that all the 284 raw data reached good quality parameters. The variant calling analysis confirmed all the 75 pathogenic/likely pathogenic variants, including challenging variants, achieving a concordance rate of 100% regardless of the panel, instrument and bioinformatic pipeline adopted. No additional variants were identified in the reanalysis of a subset of 41 cases. CONCLUSIONS: BRCA tumour testing performed with different technologies in different centres, may achieve the realibility and reproducibility required for clinical diagnostic procedures.
Assuntos
Proteína BRCA1/genética , Proteína BRCA2/genética , Biomarcadores Tumorais/genética , Heterogeneidade Genética , Testes Genéticos , Neoplasias Ovarianas/genética , Biologia Computacional , Feminino , Sequenciamento de Nucleotídeos em Larga Escala , Humanos , Itália , Variações Dependentes do Observador , Neoplasias Ovarianas/patologia , Valor Preditivo dos Testes , Reprodutibilidade dos Testes , Fluxo de TrabalhoRESUMO
This paper proposes a parameterized Support Vector Machine (ParaSVM) approach for modeling the Drug Concentration to Time (DCT) curves. It combines the merits of Support Vector Machine (SVM) algorithm that considers various patient features and an analytical model that approximates the predicted DCT points and enables curve calibrations using occasional real Therapeutic Drug Monitoring (TDM) measurements. The RANSAC algorithm is applied to construct the parameter library for the relevant basis functions. We show an example of using ParaSVM to build DCT curves and then calibrate them by TDM measurements on imatinib case study.
Assuntos
Monitoramento de Medicamentos , Preparações Farmacêuticas/metabolismo , Máquina de Vetores de Suporte , Algoritmos , Antineoplásicos/metabolismo , Antineoplásicos/uso terapêutico , Benzamidas/metabolismo , Benzamidas/uso terapêutico , Humanos , Mesilato de Imatinib , Leucemia Mielogênica Crônica BCR-ABL Positiva/tratamento farmacológico , Piperazinas/metabolismo , Piperazinas/uso terapêutico , Medicina de Precisão , Pirimidinas/metabolismo , Pirimidinas/uso terapêutico , Fatores de TempoRESUMO
Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. In this paper, we focus on the prediction of drug concentrations using Support Vector Machines (S VM) and the analysis of the influence of each feature to the prediction results. Our study shows that SVM-based approaches achieve similar prediction results compared with pharmacokinetic model. The two proposed example-based SVM methods demonstrate that the individual features help to increase the accuracy in the predictions of drug concentration with a reduced library of training data.