RESUMEN
Genome-wide association studies have shown that common genetic variants associated with complex diseases are mostly located in non-coding regions, which may not be causal. In addition, the limited number of validated non-coding functional variants makes it difficult to develop an effective supervised learning model. Therefore, improving the accuracy of predicting non-coding causal variants has become critical. This study aims to build a transfer learning-based machine learning method for predicting regulatory variants to overcome the problem of limited sample size. This paper presents a supervised learning method transfer support vector machine (TSVM) for massively parallel reporter assays (MPRA) validated regulatory variants prediction. First, uses a convolutional neural network to extract features with transfer learning. Second, the extracted features are selected by random forest method. Third, the selected features are used to train support vector machine for classification. We performed scale sensitivity experiments on the MPRA dataset and validated the effectiveness of transfer learning. The model achieves the Mcc of 0.326 and the AUC of 0.720, which are higher than the state-of-the-art method.
Asunto(s)
Biología Computacional , Máquina de Vectores de Soporte , Biología Computacional/métodos , Humanos , Variación Genética/genética , Algoritmos , Estudio de Asociación del Genoma Completo/métodosRESUMEN
Macrophages form a crucial bridge between the innate and adaptive immune response. One of their most important functions is to recognize infectious microorganisms. Toll-like receptors (TLRs) are key elements in pathogen recognition, and among them, TLR2 and TLR4 are most discussed. However, expression patterns of TLRs during myeloid cell differentiation to macrophage are unknown. In this study, we examined differentiation in the model human myeloid cell line, HL-60, treated with phorbol 12-myristate 13-acetate (PMA) or VitD(3). Expression of TLR2, TLR4, and CD14 were measured by reverse transcription-PCR, RNase protection assay, and fluorescence-activated cell sorter assays. After treatment by PMA (1, 10, and 100 nM) for 12, 24, and 48 h, expression of TLR2 and CD14 mRNA was increased in a time- and dose-dependent manner. However, VitD(3) only induced expression of CD14 but not TLR2 in HL-60 cells. TLR4 was expressed constitutively before differentiation and increased slightly after that. Thus, PMA-mediated differentiation of HL-60 cells to macrophages is associated largely with TLR2 expression and, to a much lesser extent, with TLR4. Furthermore, up-regulation of TLR2 and CD14 mRNA expression by PMA was abrogated by a protein kinase C inhibitor, Calphostine C, suggesting the up-regulation of TLR2 and CD14 mRNA is dependent on the activation of protein kinase C. Coexpression of CD14/TLR2 and/or CD14/TLR4 may be essential but not sufficient for the production of tumor necrosis factor-alpha in response to lipopolysaccharide in our system.