Background: Gastric cancer (GC) is one of the leading causes of cancer-related deaths globally, with a 5-year survival rate of less than 40%. While immune checkpoint inhibitors have provided promising therapeutic options for advanced GC, only a small proportion of patients benefit. In this study, we developed a deep learning model using whole-slide images to predict prognoses and sensitivity to immune checkpoint inhibitors in GC patients by predicting a novel marker. Methods: Formalin-fixed, paraffin-embedded whole-slide images from 292 patients in the Cancer Genome Atlas-Stomach Adenocarcinoma cohort were analyzed. Tumor regions were identified using a ResNet50-based tumor detection model and validated in HiESD dataset. Tiles classified as malignant were extracted for subsequent analysis. Risk score prediction models were developed using convolutional neural networks, clustering-constrained attention multiple-instance learning (CLAM), and dual-stream multiple-instance learning (DSMIL). Attention heatmap visualization was used to interpret tumor microenvironment (TME) features and a multi-model classification framework utilizing a support vector machine (SVM) was developed to assess the impact of clinical variables in model performances. The results were evaluated using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, and F1 score. Results: The tumor detection model achieved an AUROC of 0.99 on the training set, 0.92 on the test set, and 0.87 on external test set. Among risk score prediction models, DSMIL demonstrated the highest performance, with an AUROC of 0.73 and accuracy of 0.73 on the training set and AUROC of 0.70 and accuracy of 0.68 on the internal test set. High-risk patients exhibited worse survival outcomes and lower immunotherapy response rates compared with low-risk patients. Feature attribution analysis using attention heatmaps confirmed that the model prioritized TME components, specifically regions with dense lymphocytic infiltration. The muti-modal analysis showed that the image features alone were superior to the model combining image features with clinicopathological data. Conclusion: Deep learning models leveraging whole-slide images show potential in predicting prognoses and immunotherapy responses in GC. By integrating tumor-specific and tumor microenvironmental features, this approach offers a scalable, objective tool for personalized treatment planning, improving precision oncology strategies.

Background: Hypoxia and immune components significantly shape the tumor microenvironment and influence prognosis and immunotherapy response in gastric cancer (GC). This study aimed to develop hypoxia- and immune-related gene signatures for prognostic evaluation in GC. Methods: Transcriptomic data from TCGA-STAD were integrated with hypoxia- and immune-related genes from InnateDB and MSigDB. A prognostic gene signature was constructed using Cox regression analyses and validated on an independent GSE84437 cohort and single-cell RNA dataset. We further analyzed immune cell infiltration, molecular characteristics of different risk groups, and their association with immunotherapy response. Single-cell RNA-seq data from the TISCH database were used to explore gene expression patterns across cell types. Results: Five genes (TGFB3, INHA, SERPINE1, GPC3, SRPX) were identified. The risk score effectively stratified patients by prognosis, with the high-risk group showing lower overall survival and lower T-cell expression. The gene signature had an association with immune suppression, ARID1A mutation, EMT features, and poorer response to immunotherapy. Gene signature, especially SRPX was enriched in fibroblasts. Conclusions: We developed a robust hypoxia- and immune-related gene signature that predicts prognosis and may help guide immunotherapy strategies for GC patients.

Background/Objectives: Cell-free DNA (cfDNA) fragmentomics from low-coverage whole-genome sequencing (lcWGS) is a promising approach for non-invasive cancer detection. However, most existing methods summarize millions of cfDNA fragments into handcrafted sample-level features before classification, potentially discarding informative patterns carried by individual molecules. We aimed to develop and benchmark a framework that learns directly from fragment-level signals. Methods: We developed FragMIL, a fragment-token multiple-instance learning framework that represents each cfDNA molecule as a learnable token integrating end-motif, genomic-position, and fragment-length information, and aggregates thousands of fragment tokens into a patient-level cancer score. FragMIL was evaluated on 934 samples from three public lcWGS cohorts (pan-cancer, lung cancer, and hepatocellular carcinoma) using five repeated subject-level splits, a 288-configuration design-space benchmark, and comparison with four established fragmentomic approaches (coverage, DELFI, end motif, and fragment size). Results: FragMIL achieved the highest mean areas under the receiver operating characteristic curve (AUROCs) in every cohort, with 0.963 ± 0.009, 0.802 ± 0.009, and 0.910 ± 0.015 in the DELFI/Cristiano 2019, LUCAS/Mathios 2021, and Jiang 2015 cohorts, respectively. End-motif encoding provided the strongest standalone discriminative signal, whereas the optimal fragment pool was cohort-dependent, with open chromatin region fragments performing best for pan-cancer detection and tumor-enriched fragments for disease-specific cohorts. Performance was retained across cancer stages and cancer types. Conclusions: Preserving molecule-level fragmentomic information improves cancer detection, supporting fragment-token learning as a promising framework for next-generation cfDNA fragmentomics.