AUTHOR=Ma Jichun , Wen Xiangmei , Xu Zijun , Xia Peihui , Jin Ye , Lin Jiang , Qian Jun 

TITLE=Predicting the influence of Circ_0059706 expression on prognosis in patients with acute myeloid leukemia using classical statistics and machine learning

JOURNAL=Frontiers in Genetics

VOLUME=13

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.961142

DOI=10.3389/fgene.2022.961142

ISSN=1664-8021

ABSTRACT=<p><bold>Background:</bold> Various circular RNA (circRNA) molecules are abnormally expressed in acute myeloid leukemia (AML), and associated with disease occurrence and development, as well as patient prognosis. The roles of <italic>circ_0059706</italic>, a circRNA derived from <italic>ID1</italic>, in AML remain largely unclear.</p><p><bold>Results:</bold> Here, we reported <italic>circ_0059706</italic> expression in <italic>de novo</italic> AML and its association with prognosis. We found that <italic>circ_0059706</italic> expression was significantly lower in AML patients than in controls (<italic>p</italic> &lt; 0.001). Survival analysis of patients with AML divided into two groups according to high and low <italic>circ_0059706</italic> expression showed that overall survival (OS) of patients with high <italic>circ_0059706</italic> expression was significantly longer than that of those with low expression (<italic>p</italic> &lt; 0.05). Further, female patients with AML and those aged &gt;60 years old in the high <italic>circ_0059706</italic> expression group had longer OS than male patients and those younger than 60 years. Multiple regression analysis showed that <italic>circ_0059706</italic> was an independent factor-affecting prognosis of all patients with AML. To evaluate the prospects for application of <italic>circ_0059706</italic> in machine learning predictions, we developed seven types of algorithm. The gradient boosting (GB) model exhibited higher performance in prediction of 1-year prognosis and 3-year prognosis, with AUROC 0.796 and 0.847. We analyzed the importance of variables and found that <italic>circ_0059706</italic> expression level was the first important variables among all 26 factors included in the GB algorithm, suggesting the importance of <italic>circ_0059706</italic> in prediction model. Further, overexpression of <italic>circ_0059706</italic> inhibited cell growth and increased apoptosis of leukemia cells <italic>in vitro</italic>.</p><p><bold>Conclusion:</bold> These results provide evidence that high expression of <italic>circ_0059706</italic> is propitious for patient prognosis and suggest <italic>circ_0059706</italic> as a potential new biomarker for diagnosis and prognosis evaluation in AML, with high predictive value and good prospects for application in machine learning algorithms.</p>