Abstract 623P
Background
Cancer ranks second globally in causes of death, accounting for 21% of all fatalities. However, many types of cancer can be cured if diagnosed and treated during early stages. We propose a liquid biopsy cancer analysis method that uses deep learning and a methylation-sensitive restriction enzyme digestion followed by sequencing method to detect and classify the most common cancers worldwide at early stages.
Methods
We developed a selective methylation sensitive restriction enzyme sequencing (MRE-Seq) method combined with a prediction model based on deep neural network (DNN) learning on data from 63,266 CpG sites to identify global hypomethylation patterns. The methylation dataset was made from 96 colon cancer samples, 95 lung cancer samples, 122 gastric cancer samples, 136 breast cancer samples, and 183 control samples. To eliminate batch bias, the ANOVA test was performed during feature selection. A DNN was adopted as a classifier, and 5-fold cross validation was performed to verify the classification performance.
Results
Across four cancer types, colorectal cancer had the highest predictive performance at 0.98, followed by breast cancer at 0.97, gastric cancer at 0.96, and lung cancer at 0.93. At 95% specificity, the sensitivity for detecting early-stage cancers varied widely, with lung cancer at 50% and breast cancer at 83%. Two different metrics were used to evaluate the model's performance. The cancer classifier (performance in detecting cancer) had a sensitivity of 95.1% and a specificity of 66.7%, indicating better performance in correctly identifying cancer samples. The cancer type classifier (performance in classifying the cancer type) utilized the precision metric to evaluate the accuracy of cancer classification. Notably, breast cancer achieved the highest precision at 95.8%, followed by lung cancer at 83.3%, gastric cancer at 79.1%, and colon cancer at 69.0%.
Conclusions
The proposed classification model based on the MRE-Seq method can reliably identify cancer and normal samples and differentiate between different cancer types using only methylation information obtained from patient's blood. This approach could be used in clinical practices to help medical experts diagnose cancer earlier and at the individual level.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
612P - Is the juice worth the squeeze? Overall survival gain per unit treatment time as a metric of clinical benefit of systemic treatment in incurable cancers
Presenter: Vodathi Bamunuarachchi
Session: Poster Display
Resources:
Abstract
613P - Differences in the interactions with pharmaceutical companies between medical oncologists and infectious diseases physicians
Presenter: Hui Ling Yeoh
Session: Poster Display
Resources:
Abstract
614P - The role of PD-L1 expression in prognosis of osteosarcoma patients: A systematic review and meta-analysis
Presenter: Alexander Purnomo
Session: Poster Display
Resources:
Abstract
615P - Pulmonary resectable metastases of osteosarcoma with apatinib and chemotherapy (PROACH): An open-label, single-arm phase II clinical trial
Presenter: Qiyuan Bao
Session: Poster Display
Resources:
Abstract
616P - Incidence of cardiotoxicity after high cumulative dose of anthracyclines in adult patients with advanced soft tissue sarcomas: A systematic review and meta-analysis
Presenter: Paula Franco
Session: Poster Display
Resources:
Abstract
617P - The risk of acute myeloid leukaemia in patients with Ewing's sarcoma and trend analysis: A SEER-based study 2000-2020
Presenter: Mohamed Abdalla
Session: Poster Display
Resources:
Abstract
618P - Adult renal Ewing’s sarcoma/primitive neuroectodermal tumor: A 20-year retrospective review of molecular histopathological profiles, and clinical outcomes
Presenter: Josh Thomas Georgy
Session: Poster Display
Resources:
Abstract
619P - Single-cell and bulk RNA-seq analyses decode the renal microenvironment induced by polystyrene microplastics in mice receiving high-fat diet
Presenter: Wangrui Liu
Session: Poster Display
Resources:
Abstract
620P - A unique circulating microRNA pairs signature serves as a superior tool for early diagnosis of pan-cancer
Presenter: Dongyu Li
Session: Poster Display
Resources:
Abstract
621P - Effective identification of primary liver cancer from cirrhosis or chronic hepatitis virus infection using eight methylated plasma DNA markers: Marker discovery, phase I pilot, and phase II clinical validation
Presenter: Tian Yang
Session: Poster Display
Resources:
Abstract