Development of fecal microbial diagnostic marker sets of colorectal cancer using natural language processing method.

BACKGROUND: Cancer screening and early detection greatly increase the chances of successful treatment. However, most cancer types lack effective early screening biomarkers. In recent years, natural language processing (NLP)-based text-mining methods have proven effective in searching the scientific literature and identifying promising associations between potential biomarkers and disease, but unfortunately few are widely used. METHODS: In this study, we used an NLP-enabled text-mining system, MarkerGenie, to identify potential stool bacterial markers for early detection and screening of colorectal cancer. After filtering markers based on text-mining results, we validated bacterial markers using multiplex digital droplet polymerase chain reaction (ddPCR). Classifiers were built based on ddPCR results, and sensitivity, specificity, and area under the curve (AUC) were used to evaluate the performance. RESULTS: A total of 7 of the 14 bacterial markers showed significantly increased abundance in the stools of colorectal cancer patients. A five-bacteria classifier for colorectal cancer diagnosis was built, and achieved an AUC of 0.852, with a sensitivity of 0.692 and specificity of 0.935. When combined with the fecal immunochemical test (FIT), our classifier achieved an AUC of 0.959 and increased the sensitivity of FIT (0.929 vs. 0.872) at a specificity of 0.900. CONCLUSIONS: Our study provides a valuable case example of the use of NLP-based marker mining for biomarker identification.

Endoscopic image classification algorithm based on Poolformer.

Image desmoking is a significant aspect of endoscopic image processing, effectively mitigating visual field obstructions without the need for additional surgical interventions. However, current smoke removal techniques tend to apply comprehensive video enhancement to all frames, encompassing both smoke-free and smoke-affected images, which not only escalates computational costs but also introduces potential noise during the enhancement of smoke-free images. In response to this challenge, this paper introduces an approach for classifying images that contain surgical smoke within endoscopic scenes. This classification method provides crucial target frame information for enhancing surgical smoke removal, improving the scientific robustness, and enhancing the real-time processing capabilities of image-based smoke removal method. The proposed endoscopic smoke image classification algorithm based on the improved Poolformer model, augments the model's capacity for endoscopic image feature extraction. This enhancement is achieved by transforming the Token Mixer within the encoder into a multi-branch structure akin to ConvNeXt, a pure convolutional neural network. Moreover, the conversion to a single-path topology during the prediction phase elevates processing speed. Experiments use the endoscopic dataset sourced from the Hamlyn Centre Laparoscopic/Endoscopic Video Dataset, augmented by Blender software rendering. The dataset comprises 3,800 training images and 1,200 test images, distributed in a 4:1 ratio of smoke-free to smoke-containing images. The outcomes affirm the superior performance of this paper's approach across multiple parameters. Comparative assessments against existing models, such as mobilenet_v3, efficientnet_b7, and ViT-B/16, substantiate that the proposed method excels in accuracy, sensitivity, and inference speed. Notably, when contrasted with the Poolformer_s12 network, the proposed method achieves a 2.3% enhancement in accuracy, an 8.2% boost in sensitivity, while incurring a mere 6.4 frames per second reduction in processing speed, maintaining 87 frames per second. The results authenticate the improved performance of the refined Poolformer model in endoscopic smoke image classification tasks. This advancement presents a lightweight yet effective solution for the automatic detection of smoke-containing images in endoscopy. This approach strikes a balance between the accuracy and real-time processing requirements of endoscopic image analysis, offering valuable insights for targeted desmoking process.

Postoperative circulating tumor DNA detection and CBLB mutations are prognostic biomarkers for gastric cancer.

BACKGROUND: Several studies have demonstrated that circulating tumor DNA (ctDNA) can be used to predict the postoperative recurrence of several cancers. However, there are few studies on the use of ctDNA as a prognosis tool for gastric cancer (GC) patients. OBJECTIVE: This study aims to determine whether ctDNA could be used as a prognostic biomarker in GC patients through multigene-panel sequencing. METHODS: Using next-generation sequencing (NGS) Multigene Panels, the mutational signatures associated with the prognosis of GC patients were identified. We calculated the survival probability with Kaplan-Meier and used the Log-rank test to compare survival curves between ctDNA-positive and ctDNA-negative groups. Potential application of radiology combined with tumor plasma biomarker analysis of ctDNA in GC patients was carried out. RESULTS: Disease progression is more likely in ctDNA-positive patients as characterized clinically by a generally higher T stage and a poorer therapeutic response (P < 0.05). ctDNA-positive patients also had worse overall-survival (OS: P = 0.203) and progression-free survival (PFS: P = 0.037). The combined analysis of ctDNA, radiological, and serum biomarkers in four patients indicated that ctDNA monitoring can be a good complement to radiological and plasma tumor markers for GC patients. Kaplan-Meier analysis using a cohort of GC patients in the TCGA database showed that patients with CBLB mutations had shorter OS and PFS than wild-type patients (OS: P = 0.0036; PFS: P = 0.0027). CONCLUSIONS: This study confirmed the utility and feasibility of ctDNA in the prognosis monitoring of gastric cancer.

miR­873 inhibits colorectal cancer cell proliferation by targeting TRAF5 and TAB1.

MicroRNA-873 (miR­873) has been reported to be dysregulated in a variety of malignancies, however, the biological function and underlying molecular mechanism of miR­873 in colorectal cancer (CRC) remain unclear. In the present study we found that the expression levels of miR­873 were markedly decreased in CRC cell lines and tissues from patients. Statistical analysis revealed that miR­873 expression was inversely correlated with the disease stage of CRC. Kaplan­Meier survival analysis revealed that patients with CRC with lower miR­873 expression had shorter overall survival rates. Additionally, downregulation of miR­873 enhanced the proliferation of CRC cells, while upregulation of miR­873 reduced this proliferation. Furthermore, we found that tumor necrosis factor (TNF) receptor-associated factor 5 (TRAF5) and TGF­ß activated kinase 1 (MAP3K7) binding protein 1 (TAB1) were direct targets of miR­873 in CRC cells. A luciferase assay revealed that ectopic expression of miR­873 significantly reduced nuclear factor κB (NF­κB) luciferase activity, while ectopic expression of miR­873 inhibitor enhanced luciferase activity, suggesting that downregulation of miR­873 can activate NF­κB signaling. Therefore, our findings established a tumor-suppressive role for miR­873 in the inhibition of CRC progression, which may be employed as a novel prognostic marker and as an effective therapeutic target for CRC.