Abstract 1214P
Background
HRR gene alterations are enriched in prostate cancer (PC) and are associated with sensitivity to PARP inhibitors. Homozygous deletion (HD), which accounts for up to 15% of HRR gene alterations in PC, is an important type of pathogenic alteration. However, the reliable detection of HD is technically challenging. Here we introduced a novel machine learning based method for HD detection in formalin-fixed paraffin-embedded (FFPE) PC tissues.
Methods
HD/non-HD simulation events (∼30000) of varying tumor cellularity and fragment size were constructed using the sequencing data of matched tumor and wild type cell lines tested by AmoyDx HRD Complete NGS panel. Seven artificial features were calculated based on genomic segment depth and minor allele frequency of single nucleotide polymorphisms, tumor cellularity and tumor ploidy. The feature data were fed into the xgboost with 10-StratifiedKFold to generate HD recognition model (training :validation datasets=7:3). Analytical performance was assessed with reference cell lines: specificity with wildtype cell lines, sensitivity with gradient HD-positive cell lines (tumor cellularity: 20%, 30%, 40%, 50%) with varying DNA input (30ng, 50ng, 100ng), reproducibility of intra- and inter-runs, and anti-interference against hemoglobin, triglycerides, xylene, paclitaxel, and ethanol. Clinical performance was evaluated using FFPE PC tissues.
Results
The trained HD model achieved 99.8% accuracy in the in silico validation dataset. Analytical validation demonstrated: 100% specificity; 100% sensitivity at gene level with 30% tumor cellularity and at exon level with 40% tumor cellularity with 100ng DNA input; 100% reproducibility; strong anti-interference capability with all HD events detected and no false positives. 132 FFPE PC tissues showed high consistency with a second validated NGS assay (PPA 100%, NPA 98.4%, OPA 98.5%).
Conclusions
A machine learning based method was successfully developed and adopted in multiple NGS assays to detect HD of HRR genes in PC tissues. It provides a reliable approach to effectively identify PC patients with HRR HD.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Janssen.
Disclosure
J. Wang, P. Cheng, W. Xu, Z. Huang, X. Chen, S. Liu, Y. Guo, W. Shi, S. Yang: Financial Interests, Personal, Full or part-time Employment: Amoy Diagnostics. X. Ye, U. Singh, K. Bell, K. Urtishak, L. Luo, X. Lyu, L. Zhou: Financial Interests, Institutional, Full or part-time Employment: Janssen Research & Development.
Resources from the same session
1251P - Development of a deep learning algorithm for lung cancer diagnosis using methylation and fragment size profiles of cfDNA
Presenter: Jiyoung Huh
Session: Poster session 14
1252P - Quantitative cell signaling activity profiling of solid tumors to support personalized treatment in the FINPROVE basket trial: Presentation of skin tumor data
Presenter: Diederick Keizer
Session: Poster session 14
1253P - Analytic validation and implementation of OncoDEEP: A pan-cancer comprehensive genomic profiling NGS assay for assessing homologous recombination deficiency (HRD)
Presenter: Marcel Trautmann
Session: Poster session 14
1254P - Retrospective analysis of brain OMX: Diagnostic tool for structural (T1) and functional connectome (RS-FMRI) analysis of brain
Presenter: Swarnambiga Ayyachamy
Session: Poster session 14
1255P - Evaluating GPT-4 as an academic support tool for clinicians: A comparative analysis of case records from the literature
Presenter: Marcos Aurelio Fonseca Magalhaes Filho
Session: Poster session 14
1256P - Value of detection of peripheral blood circRNA based on digital PCR in the diagnosis of lung adenocarcinoma
Presenter: Jihong Zhou
Session: Poster session 14
1257P - Double heterozygous prevalence in hereditary cancer syndromes in Northern Mexico population
Presenter: Carlos Burciaga Flores
Session: Poster session 14
1258P - Does FDG PET-based radiomics have an added value for prediction of overall survival in non-small cell lung cancer?
Presenter: Andrea Ciarmiello
Session: Poster session 14
1260TiP - Enhancing lung nodule discrimination with a novel cfDNA test: The cancer signature ensemble (CSE) approach
Presenter: Young-Chul Kim
Session: Poster session 14
1773P - ICECaP-2: Validation of metastasis-free survival (MFS) as a surrogate for overall survival (OS) in localized prostate cancer (LPC) in a more contemporary era
Presenter: Wanling Xie
Session: Poster session 14