Project description:Objective: The objective of this study was to estimate the accuracy of transcriptome-based classifier in differential diagnosis of uterine leiomyoma and leiomyosarcoma. Methods: We manually selected 114 normal uterine tissue and 31 leiomyosarcoma samples from publicly available transcriptome data in UCSC Xena as training/validation sets. We developed pre-processing procedure and gene selection method to sensitively find genes of larger variance in leiomyosarcoma than normal uterine tissues. Through our method, twenty genes were selected to build transcriptome-based classifier. The prediction accuracies of deep feedforward neural network (DNN), support vector machine (SVM), Random Forest (RF), and Gradient Boosting (GB) models were examined. We interpret the biological functionality of selected genes via network-based analysis using Gene-Mania. To validate the performance of trained model, we additionally collected 35 clinical samples of leiomyosarcoma and leiomyoma as a test set (18 + 17 as 1st and 2nd test sets). Results: We discovered genes expressed in a highly variable way in leiomyosarcoma while these genes are expressed in a conserved way in normal uterine samples. These genes were mainly associated with DNA replication, cell cycle, and DNA damage checkpoint. Among evaluated machine learning classifiers, the DNN had the highest accuracy and average AUC value in training data set. As gene selection and model training were made in leiomyosarcoma and uterine normal tissue, proving discriminant of ability between leiomyosarcoma and leiomyoma is necessary. Thus, further validation of trained model was conducted in newly collected clinical samples of leiomyosarcoma and leiomyoma. The DNN classifier performed AUC of 0.917 and 0.914 supporting that the selected genes in conjunction with DNN classifier are well discriminating the difference between leiomyosarcoma and leiomyoma in clinical sample. Conclusion: The transcriptome-based classifier accurately distinguished uterine leiomyoma from leiomyosarcoma.

Project description:Uterine leiomyosarcoma (LMS) is the worst malignancy among the gynecologic cancers. Uterine leiomyoma (LM) is a benign tumor of myometrial origin and is the most common among women of childbearing age. Because the symptoms of women with LMS such as abnormal vaginal bleeding, palpable pelvic mass, and pelvic pain resemble with those of women with LM, it is difficult to preoperatively distinguish LMS and LM only by ultrasound and pelvic MRI. While histopathological diagnosis after hysterectomy is the current major means to distinguish them postoperatively, unusual histologic variants of LM tend to be misdiagnosed as LMS. Furthermore, the low incidence of LMS has been preventing elucidating its causal mechanisms and developing effective diagnoses and treatments. Therefore, development of molecular diagnosis as an alternative or confirmatory means helps diagnosing LMS more accurately. We adopted omics-based technologies to identify genome-wide features to distinguish LMS from LM, and revealed that copy-number, gene expression, and DNA methylation profiles successfully distinguished between these tumors. LMS was found to possess features typically observed in malignant solid tumors, such as extensive chromosomal abnormalities, overexpression of cell cycle –related genes, and hypomethylation spreading through large genomic regions as well as frequent hypermethylation at polycomb group target gene and cadherin gene loci. We also identified candidate expression and DNA methylation markers, which will help establishing diagnostic tests using conventional quantitative assays. While the identified omics-signatures and certain markers specific to LMS need to be further validated in larger numbers of LM and LMS samples, our results demonstrate the practical feasibility of establishing a postoperative diagnostic test to distinguish LMS from LM with high accuracy, and also suggest the future possibility of developing preoperative and non-invasive diagnostic methods.

Dataset Information

Genomic, epigenomic, and transcriptomic profiling towards identifying omics-features and specific biomarkers that distinguish uterine leiomyosarcoma and leiomyoma at molecular levels

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets