| 36 |
2026 |
MOCDT: multi-cancer detection and tissue-of-origin classification via cfDNA multi-modal integration
MOCDT: multi-cancer detection and tissue-of-origin classification via cfDNA multi-modal integration
Abstract
Circulating tumor DNA (ctDNA) contains rich molecular information that can be leveraged for both cancer detection and tissue-of-origin (TOO) prediction. However, effectively integrating multiple cfDNA-derived modalities, including methylation, copy number variation (CNV), and fragment size ratio (FSR), remains challenging. To address this issue, the authors developed MOCDT (Multi-Omics Cancer Detection and Tissue-of-Origin), a deep learning framework that integrates multi-modal cfDNA features through a clinically relevant two-stage workflow consisting of cancer detection followed by tissue-of-origin classification.
Purpose
The study aimed to:
Develop a robust deep learning framework capable of integrating multiple cfDNA modalities, including methylation, CNV, and fragmentomics data.
Improve the accuracy of blood-based multi-cancer detection.
Accurately identify the tissue of origin for detected cancers.
Overcome limitations of existing multi-omics approaches, such as modality imbalance, insufficient exploitation of inter-patient relationships, and inadequate learning of tissue-specific biological features.
Results
Study Cohort
Total participants: 1,423 individuals
Included healthy controls and patients with eight cancer types:
Colorectal cancer
Gastric cancer
Liver cancer
Pancreatic cancer
Lung cancer
Breast cancer
Ovarian cancer
Prostate cancer
Cancer Detection Performance
MOCDT achieved strong performance in distinguishing cancer patients fr|om healthy individuals:
Metric
Performance
Specificity
95.74%
Sensitivity
96.22%
Accuracy
96.09%
The proposed framework outperformed several existing multi-omics integration methods, including MOGONET, MoGCN, and MO-GCAN.
Tissue-of-Origin Classification Performance
Metric
Performance
Top-1 Accuracy
75.20%
Top-2 Accuracy
86.79%
Top-3 Accuracy
91.06%
These results indicate that the correct cancer type was included among the top three predicted tissue origins in over 91% of cases.
Biological Interpretation
Latent-space analyses demonstrated that MOCDT successfully learned tissue-specific molecular patterns rather than relying solely on generic cancer-associated signals. This finding supports the biological interpretability of the model and its ability to distinguish among different cancer origins.
Conclusions
MOCDT is an effective multi-modal deep learning framework that integrates methylation, CNV, and fragmentomics features fr|om cfDNA for both cancer detection and tissue-of-origin classification. The model demonstrated:
High sensitivity and specificity for cancer detection.
Strong tissue-of-origin prediction performance.
Effective learning of tissue-specific biological characteristics.
A clinically applicable two-stage workflow suitable for multi-cancer early detection (MCED).
Overall, the study suggests that integrating multiple cfDNA-derived signals through advanced artificial intelligence approaches can significantly enhance the performance of liquid biopsy-based cancer screening and tissue-of-origin prediction, supporting the future development of non-invasive multi-cancer early detection strategies.
|
Bioinformatics |
リンクを見る
|
| 35 |
2026 |
Preoperative Circulating Tumor DNA Detection and Risk Stratification in Esophageal Squamous Cell Carcinoma
Abstract
Preoperative circulating tumor DNA (ctDNA) detection may help identify patients with early-stage esophageal squamous cell carcinoma (ESCC) who harbor occult nodal metastasis or are at high risk of recurrence.
In this cohort study of 74 patients with clinical stage I (T1b) or stage II (T2N0) ESCC who underwent upfront curative surgery without neoadjuvant therapy, tumor-informed ctDNA sequencing was performed on preoperative plasma samples.
Preoperative ctDNA positivity was significantly associated with both pathologic nodal upstaging and worse survival outcomes (recurrence-free survival and overall survival).
Incorporation of ctDNA status into guideline-based risk prediction models substantially improved the ability to predict occult lymph node metastasis, particularly in the T2N0 subgroup.
The findings suggest that ctDNA may be a valuable preoperative biomarker for refining risk stratification and informing treatment decisions in early-stage ESCC.
Purpose
The purpose of this study was to determine whether preoperative detection of circulating tumor DNA (ctDNA) in patients with early-stage esophageal squamous cell carcinoma
(clinical T1b or T2N0 ESCC) is associated with (1) pathologic nodal upstaging (occult lymph node metastasis discovered after surgery) and (2) postoperative recurrence and survival outcomes.
The study also aimed to evaluate whether adding ctDNA status to existing guideline-based risk models could improve the prediction of occult nodal metastasis, particularly in patients with T2N0 disease
where clinical decision-making regarding neoadjuvant therapy remains uncertain.
Results
- A total of 74 patients were included: 50 fr|om Samsung Medical Center and 24 fr|om Yonsei University Severance Hospital, all with clinical stage T1b or T2N0 ESCC who underwent surgery without neoadjuvant therapy.- Preoperative ctDNA was detected in 36 patients (48.6%) — 27 (54.0%) in the SMC cohort and 9 (37.5%) in the YUSH cohort. Detection was more frequent among patients with clinical T2N0 than T1b disease.- During a median follow-up of 37.7 months, ctDNA-positive patients had significantly worse recurrence-free survival (RFS) (HR, 4.15; P = .005) and overall survival (OS) (HR, 4.02; P = .006) compared with ctDNA-negative patients.- In the T2N0 subgroup specifically, ctDNA positivity showed very high positive predictive value for occult nodal metastasis, reaching 100% in the SMC cohort and 88.9% in the YUSH cohort.- In multivariable analysis, ctDNA positivity remained strongly associated with pathologic nodal metastasis (OR, ~19.98; P < .001), outperforming standard guideline-based risk factors
(tumor size ≥ 3 cm, lymphovascular invasion, poor differentiation).- Incorporating ctDNA status into predictive models significantly improved the area under the ROC curve for predicting occult nodal metastasis (e.g., fr|om 0.66 to 0.91 in the SMC cohort).
Conclusions
Preoperative ctDNA detection in patients with early-stage ESCC was significantly associated with occult nodal metastasis and poorer survival outcomes.
Among patients with clinical T2N0 disease, ctDNA may serve as a complementary biomarker to current guideline-based risk criteria for refining preoperative risk stratification.
Incorporating ctDNA status into clinical models could help clinicians identify high-risk patients who might benefit fr|om neoadjuvant treatment escalation and
support more personalized therapeutic strategies in early-stage ESCC. Prospective validation of ctDNA-guided treatment approaches is needed before clinical implementation.
|
JAMA Surgery |
リンクを見る
|
| 34 |
2025 |
Pairwise analysis of plasma cell-free DNA before and after palliative second-line paclitaxel plus ramucirumab treatment in patients with metastatic gastric cancer
Abstract
Background
This study compared plasma cell-free DNA (cfDNA) and tumor tissue DNA (ttDNA) to explore the clinical applicability of cfDNA in patients with metastatic gastric cancer (mGC) receiving palliative second-line paclitaxel + ramucirumab treatment.
Methods
Targeted sequencing of 106 genes was conducted using germline DNA and cfDNA at baseline (baseline-cfDNA) and progressive disease (PD-cfDNA). The results were compared with those of ttDNA-based cancer panel data.
Results
Of 76 consecutive patients, 46 (27 males; median age 57.5 [range, 32–73] years) who had all three samples were included. Combined analysis of ttDNA and baseline-cfDNA revealed that TP53 (58.7%) was the most frequently mutated gene, followed by CDH1 (26.1%), KRAS (21.7%), and APC (13.0%). For these genes, the sensitivity and positive predictive value of baseline-cfDNA over ttDNA were 71.8% and 51.9%, respectively. When baseline-cfDNA and PD-cfDNA results were combined, 34 patients (73.9%) were found to have additional mutations compared with ttDNA results alone. PD-cfDNA analysis revealed 14 novel pathogenic mutations in ten patients (21.7%). At baseline, patients with a high circulating tumor DNA fraction concentration showed a significantly shorter progression-free survival (PFS) (P = 0.016) in univariable and multivariable analyses. High maximal variant allele frequency (VAF) (P = 0.022), high sum of VAF (P = 0.028), and high TP53 VAF (P = 0.022) were associated with worse PFS in univariable analysis.
Conclusions
Although cfDNA alone cannot replace ttDNA entirely, cfDNA analysis revealed additional mutations. Notably, PD-cfDNA analysis revealed novel pathogenic mutations that emerged during treatment. Moreover, the baseline circulating tumor DNA fraction concentration and VAF values were associated with longer PFS.
|
Gastric Cancer |
リンクを見る
|
| 33 |
2025 |
Blood Circulating Tumor DNA‐based Genomic Profiling and Serial Analysis in Patients With Advanced Biliary Tract Cancer
Abstract
Background/Aim: This study aimed to identify mutation profile similarities between tissue and circulating tumor DNA (ctDNA) and to explore driver mutations as potential prognostic or predictive biomarkers or druggable targets in patients with advanced biliary tract cancer (BTC).
Patients and Methods: We prospectively enrolled 18 patients with advanced BTC and analyzed next-generation sequencing data fr|om 60 ctDNA samples using AlphaLiquid® 100. This assay screens up to 118 genes for single-nucleotide variants (SNVs) and insertion or deletions (INDELs), 27 genes for copy number alterations (CNAs), and 10 genes for fusions. We examined the intra-patient tissue-ctDNA concordance and studied the association between ctDNA variant allele frequency (VAF) and survival.
Results: A total of seven gallbladder cancer cases, six intrahepatic cholangiocarcinoma cases, and five extrahepatic cholangiocarcinoma cases were observed. Among these cases, tumor tissues were available for 16 patients. Genetic alterations were detected in 88% (14/16) of tissue DNA samples and 89% (16/18) of samples with ctDNA at baseline. The most common genes altered in ctDNA were TP53 (n=11), ERBB3 (n=3), and KRAS (n=3). There was a 29% overlap in somatic SNVs/INDELs and a 60% overlap in CNAs between tissue DNA and ctDNA, while no fusion variant was detected. The sensitivity and positive predictive value of ctDNA for all types of somatic mutations were 47% and 43%, respectively. Among the 14 patients whose serial ctDNA was analyzed, 10 showed changes in ctDNA. A high pre-treatment VAF (>4.0%) was associated with poor overall survival.
Conclusion: ctDNA sequencing can successfully identify molecular genetic alterations in patients with advanced BTC, providing insights into potential biomarkers and therapeutic targets.
|
Anticancer Research |
リンクを見る
|
| 32 |
2026 |
Enhanced multicancer screening assay through whole-genome methylation sequencing-based multimodal cell-free DNA analysis
Abstract
This study developed a multimodal cfDNA-based multicancer detection assay combining whole-genome methylation sequencing with machine learning analysis.
The model integrated methylation and fragmentomic features and demonstrated high performance across eight cancer types, achieving 93.2% sensitivity and 95% specificity. It also showed strong early-stage detection capability, with over 92% sensitivity for stage I and II cancers.
The assay further achieved 85.7% accuracy in predicting tissue of origin, highlighting its potential for improving multicancer early detection and cancer screening.
Introduction
Cancer remains a leading cause of death worldwide, highlighting the urgent need for accurate and noninvasive early detection methods. Current screening approaches are often invasive, expensive and limited in detecting multiple cancer types, especially cancers without established screening guidelines.
Liquid biopsy using cell-free DNA (cfDNA) has emerged as a promising strategy for multicancer early detection (MCED). Recent advances in sequencing technologies have enabled analysis of methylation, copy number variation (CNV) and fragmentomic features fr|om circulating tumor DNA (ctDNA). However, existing MCED methods still face challenges in achieving high sensitivity for early-stage cancers due to the low abundance of ctDNA.
To overcome these limitations, this study developed a multimodal MCED framework integrating four cfDNA features: average methylation fraction (AMF), CNV, fragment size ratio (FSR) and fragment size distribution (FSD). Using an ensemble machine learning model, the study evaluated detection performance across eight major cancer types and assessed tissue-of-origin prediction accuracy. The findings demonstrate the potential of combining multiple cfDNA characteristics to improve noninvasive early cancer detection.
Materials and methods
This study analyzed plasma cfDNA samples fr|om patients with eight cancer types—colorectal, gastric, liver, pancreatic, lung, breast, ovarian and prostate cancer—as well as healthy controls. Blood samples were collected before treatment, and cfDNA was extracted fr|om plasma for analysis.
Whole-genome methylation sequencing was performed using the IMBdx AlphaLiquid screening platform, followed by extensive NGS preprocessing and quality control. The study evaluated four major cfDNA features: average methylation fraction (AMF), copy number variation (CNV), fragment size distribution (FSD) and fragment size ratio (FSR). Cancer-specific methylation markers and genomic alterations were identified using statistical filtering and machine learning-based optimization.
Single-feature models were first developed for each cfDNA characteristic using machine learning algorithms such as random forest, logistic regression and support vector machines. These models were then integrated into an ensemble framework combining methylation, genomic and fragmentomic signals along with demographic factors including age and sex. The final multimodal model was trained to detect cancer signals and predict tissue of origin while maintaining high specificity. Statistical analyses were performed using R and Python with rigorous validation procedures.
Results
The study analyzed 1,415 samples, including 1,034 cancer samples fr|om eight cancer types and 381 healthy controls. More than half of the cancer cases were stage I–II, enabling robust evaluation of early cancer detection performance.
Unsupervised clustering analyses using methylation, copy number variation (CNV), and fragmentomic features showed clear separation between healthy individuals and cancer patients, especially in advanced-stage disease. Distinct cancer-specific methylation signatures and fragmentomic patterns were identified, supporting the complementary value of integrating multiple cfDNA features.
Among single-feature models, average methylation fraction (AMF) showed the highest overall sensitivity (85.3%), particularly for early-stage cancers. CNV, fragment size ratio (FSR), and fragment size distribution (FSD) also contributed meaningful diagnostic information across different cancer types.
The multimodal ensemble model integrating AMF, CNV, FSR, and FSD achieved strong overall performance with 93.2% sensitivity and 95% specificity. Importantly, sensitivity remained high for early-stage cancers, reaching 92.3% for stage I and 92.2% for stage II disease. Sensitivity was especially high for colorectal, breast, and gastric cancers, while also demonstrating strong detection capability for difficult-to-screen cancers such as pancreatic, ovarian, and prostate cancer.
For tissue-of-origin (TOO) prediction, the model achieved 72.9% top-1 accuracy and 85.7% top-2 accuracy across the eight cancer types. The ensemble framework successfully leveraged complementary methylation, genomic, and fragmentomic signals to improve both cancer detection and tissue classification performance.
Discussion
This study demonstrated that a multimodal cfDNA analysis framework integrating methylation (AMF), copy number variation (CNV), and fragmentomic features (FSR and FSD) can significantly improve multicancer early detection (MCED). The ensemble model achieved high sensitivity (93.2%) and specificity (95%), outperforming several existing cfDNA-based cancer screening approaches.
The model showed particularly strong performance for early-stage cancers, highlighting the importance of combining complementary cfDNA features. AMF effectively detected early epigenetic alterations, while CNV and fragmentomic analyses contributed additional discriminatory power, especially in later-stage disease. The multimodal strategy also improved tissue-of-origin prediction accuracy.
Despite these promising results, challenges remain for cancers with low ctDNA abundance, such as ovarian and prostate cancer, and for certain stage III cancers affected by variable ctDNA shedding. The authors also acknowledged limitations related to single-cohort validation and emphasized the need for large-scale prospective external validation studies.
Overall, the findings support the potential clinical utility of multimodal cfDNA analysis as a scalable and noninvasive approach for improving early cancer detection and future cancer screening strategies.
Data availability
The raw data for this study were generated by IMBdx Inc. Data supporting the findings of this study are available fr|om the corresponding author upon reasonable request. Data access may be subject to institutional and ethical regulations.
|
Experimental & Molecular Medicine |
リンクを見る
|
