Motivation Predicting the binding between T-cell receptor (TCR) and peptide presented by HLA molecule is a highly challenging task and a key bottleneck in the development of immunotherapy. Existing prediction tools, despite exhibiting good performance on the datasets they were built with, suffer from low true positive rates when used to predict epitopes capable of eliciting T-cell responses in patients. Therefore, an improved tool for TCR-peptide prediction built upon a large dataset combining existing publicly available data is still needed. Results We collected data from five public databases (IEDB, TBAdb, VDJdb, McPAS-TCR, and 10X) to form a dataset of > 3 million TCR-peptide pairs, 3.27% of which were binding interactions. We proposed epiTCR, a Random Forest-based method dedicated to predicting the TCR-peptide interactions. epiTCR used simple input of TCR CDR3β sequences and antigen sequences, which are encoded by flattened BLOSUM62. epiTCR performed with AUC (0.98) and higher sensitivity (0.94) than other existing tools (NetTCR, Imrex, ATM-TCR, and pMTnet), while maintaining comparable prediction specificity (0.9). We identified seven epitopes that contributed to 98.67% of false positives predicted by epiTCR and exerted similar effects on other tools. We also demonstrated a considerable influence of peptide sequences on prediction, highlighting the need for more diverse peptides in a more balanced dataset. In conclusion, epiTCR is among the most well-performing tools thanks to the use of combined data from public sources and its use will contribute to the quest in identifying neoantigens for precision cancer immunotherapy. Availability epiTCR is available on GitHub (https://github.com/ddiem-ri-4D/epiTCR). Supplementary information Supplementary data are available at Bioinformatics online.

No abstract

Aims: Early detection of colorectal cancer (CRC) provides substantially better survival rates. This study aimed to develop a blood-based screening assay named SPOT-MAS (‘screen for the presence of tumor by DNA methylation and size’) for early CRC detection with high accuracy. Methods: Plasma cell-free DNA samples from 159 patients with nonmetastatic CRC and 158 healthy controls were simultaneously analyzed for fragment length and methylation profiles. We then employed a deep neural network with fragment length and methylation signatures to build a classification model. Results: The model achieved an area under the curve of 0.989 and a sensitivity of 96.8% at 97% specificity in detecting CRC. External validation of our model showed comparable performance, with an area under the curve of 0.96. Conclusion: SPOT-MAS based on integration of cancer-specific methylation and fragmentomic signatures could provide high accuracy for early-stage CRC detection.

IntroductionBreast cancer causes the most cancer-related death in women and is the costliest cancer in the US regarding medical service and prescription drug expenses. Breast cancer screening is recommended by health authorities in the US, but current screening efforts are often compromised by high false positive rates. Liquid biopsy based on circulating tumor DNA (ctDNA) has emerged as a potential approach to screen for cancer. However, the detection of breast cancer, particularly in early stages, is challenging due to the low amount of ctDNA and heterogeneity of molecular subtypes.MethodsHere, we employed a multimodal approach, namely Screen for the Presence of Tumor by DNA Methylation and Size (SPOT-MAS), to simultaneously analyze multiple signatures of cell free DNA (cfDNA) in plasma samples of 239 nonmetastatic breast cancer patients and 278 healthy subjects.ResultsWe identified distinct profiles of genome-wide methylation changes (GWM), copy number alterations (CNA), and 4-nucleotide oligomer (4-mer) end motifs (EM) in cfDNA of breast cancer patients. We further used all three signatures to construct a multi-featured machine learning model and showed that the combination model outperformed base models built from individual features, achieving an AUC of 0.91 (95% CI: 0.87-0.95), a sensitivity of 65% at 96% specificity.DiscussionOur findings showed that a multimodal liquid biopsy assay based on analysis of cfDNA methylation, CNA and EM could enhance the accuracy for the detection of early- stage breast cancer.

Aim: This study exploited hepatocellular carcinoma (HCC)-specific circulating DNA methylation profiles to improve the accuracy of a current screening assay for HCC patients in high-risk populations. Methods: Differentially methylated regions in cell-free DNA between 58 nonmetastatic HCC and 121 high-risk patients with liver cirrhosis or chronic hepatitis were identified and used to train machine learning classifiers. Results: The model could distinguish HCC from high-risk non-HCC patients in a validation cohort, with an area under the curve of 0.84. Combining these markers with the three serum biomarkers (AFP, lectin-reactive AFP, des-γ-carboxy prothrombin) in a commercial test, μTASWako®, achieved an area under the curve of 0.87 and sensitivity of 68.8% at 95.8% specificity. Conclusion: HCC-specific circulating DNA methylation markers may be added to the available assay to improve the early detection of HCC.