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
601P - Pembrolizumab in patients of Chinese descent with microsatellite instability-high/mismatch repair deficient advanced solid tumors: KEYNOTE-158
Presenter: Xiaohua Wu
Session: Poster Display
Resources:
Abstract
602P - COLUMBUS 7-year update: A randomized, open-label, phase III trial of encorafenib (Enco) + binimetinib (Bini) vs vemurafenib (Vemu) or Enco in patients (Pts) with BRAF V600-mutant melanoma
Presenter: Andrew Haydon
Session: Poster Display
Resources:
Abstract
603P - An individualised postoperative radiological surveillance schedule for IDH-wildtype glioblastoma patients (HK-GBM Registry)
Presenter: Jason Chak Yan Li
Session: Poster Display
Resources:
Abstract
604P - Cabozantinib versus placebo in patients with radioiodine-refractory differentiated thyroid cancer who progressed after prior VEGFR-targeted therapy: Outcomes from COSMIC-311 by BRAF status
Presenter: Marcia Brose
Session: Poster Display
Resources:
Abstract
606P - BRAF and NRAS mutations are associated with poor prognosis in Asians with acral-lentiginous and nodular cutaneous melanoma
Presenter: Sumadi Lukman Anwar
Session: Poster Display
Resources:
Abstract
607P - Single institutional outcomes of radiotherapy and systemic therapy for melanoma brain metastases in Japan
Presenter: Naoya Yamazaki
Session: Poster Display
Resources:
Abstract
608P - The efficacy of immune checkpoint inhibitors and targeted therapy in mucosal melanomas: A systematic review and meta-analysis
Presenter: Andrea Teo
Session: Poster Display
Resources:
Abstract
609P - The association between thyroid function abnormalities and vitiligo induced by pembrolizumab regarding prognosis in patients with advanced melanoma
Presenter: Moez Mobarek
Session: Poster Display
Resources:
Abstract
610P - Analyzing the clinical benefit of the evidence presented at these congresses and utilizing a standardized scale to quantify it will significantly enhance our understanding of the studies showcased, allowing for more objective evaluation and interpretation
Presenter: Charles Jeffrey Tan
Session: Poster Display
Resources:
Abstract
611P - ESMO-magnitude of clinical benefit scale (MCBS) scores for phase III trials of adjuvant and curative therapies at the 2022 ASCO annual meeting (ASCO22)
Presenter: Thi Thao Vi Luong
Session: Poster Display
Resources:
Abstract