Abstract 7293: Serum fusion gene transcripts to predict liver cancer

Abstract

Abstract Hepatocellular carcinoma (HCC) is the most common type of liver cancers and one of the most lethal malignancies for human. Early diagnosis of HCC is crucial in reducing the mortality of the disease. In this report, we analyzed a panel of 9 fusion transcripts in the serum samples from 136 individuals (61 HCC patients and 75 individuals without HCC) using TaqMan qRT-PCR. Our results showed that 7 fusion genes were frequently detected in the serum samples of HCC patients, including MAN2A1-FER (100%), SLC45A2-AMACR (62.3%), ZMPSTE24-ZMYM4 (62.3%), Pten-NOLC1 (57.4%), CCNH-C5orf30 (55.7%), STAMBPL1-FAS (26.2%) and PCMTD1-SNTG1 (16.4%). We then divided the samples into training and testing cohorts based on the sample collection time: 82 individuals with samples collected before 2016 as the training cohort while 54 individuals with sample collected after 2015 as the testing cohort. Machine learning models was constructed based on the combination of different fusion genes with various cutoffs to predict the occurrence of HCC in the training cohort using leave-one-out-cross-validation approach. One of the machine learning models called 4-fusion genes logistic regression model (MAN2A1-FER<40, CCNH-C5orf30<38, SLC45A2-AMACR<41, Pten-NOLC1<40) produced a 91.5% accuracy, with a sensitivity of 87.1% and specificity of 94.1% in the training cohort. The same model generated an accuracy of 83.3%, with a sensitivity of 73.3% and specificity of 95.8% in testing cohort. When the training and testing cohorts were combined, the model produced an accuracy of 86%. When serum α-fetal protein (AFP) level was incorporated into the machine learning model, we found a 2-fusion gene+AFP logistic regression model (MAN2A1-FER<40, CCNH-C5orf30<38, AFP) generated an accuracy of 94.8% in the training cohort with a sensitivity of 93.5% and specificity of 96.3%. The same model generated 95% accuracy in both the testing cohort and the combined cohorts in the validation. Cancer treatment reduced most of the serum fusion transcript levels, reflecting the reduction of the tumor load. As a result, serum fusion gene machine learning models may serve as important tools in screening HCC and monitoring the impact of HCC treatment. Citation Format: Jian-Hua Luo, Yan-Ping Yu, Silvia Liu, David Geller. Serum fusion gene transcripts to predict liver cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7293.