Shicai Liu

Background: Gastrointestinal cancer is a common malignant tumor with high incidence and poor prognosis. Accurate prediction of prognosis can improve the treatment of cancer patients, but the clinical features currently used provide insufficient information. This study aimed to establish an efficient survival prediction model for gastrointestinal cancer based on gene expression and clinical data. Methods: Based on the gastrointestinal cancer samples in The Cancer Genome Atlas, we established efficient gastrointestinal cancer survival prediction models with gene expression profiling data as input molecular features. A series of bioinformatics methods were applied to conduct a comprehensive analysis of the identified gastrointestinal cancer-related genes. The molecular mechanism by which newly identified gastrointestinal cancer-related genes mediate cancer occurrence was preliminarily explored. Results: Random forest-based model (I) had an accuracy of 94.98% with Mathew’s correlation coefficient (MCC) of 0.8995. Support vector machine-based model (II) had an accuracy of 94.98% with MCC of 0.9000. We found a significant difference in survival between the two subtypes (S1 and S2, 3-year survival rates ≥75% and ≤45%, respectively). These subtypes have independent predictive value for patient survival. The models constructed in this study exhibit inherent interpretability. Twenty key genes related to gastrointestinal cancer were successfully identified. The comprehensive functional analysis in this study provides important clues for elucidating the potential mechanisms of action of the selected cancer-related genes in tumor initiation and progression. Most importantly, we conducted drug target predictions for these genes and successfully identified potential targeted drugs for seven genes (NR3C1, HNF4A, DNAAF9, CDX2, ATP2B4, RBMS3, LIFR). Conclusions: The findings of this study hold significant implications for predicting survival and treatment decisions in gastrointestinal cancer.

Cancer database is a systematic collection and analysis of various human cancer information at the genomic and molecular levels, which can be used to understand the mechanisms of cancer occurrence and development, and facilitate the diagnosis and treatment of cancer. Gastrointestinal (GI) cancer is one of the leading causes of incidence and mortality worldwide. The progress and development of high-throughput sequencing technology have led to the emergence of a large amount of cancer-related omics data, such as genomics, transcriptomics, and proteomics, laying a data foundation for the diagnosis and treatment of cancer. These omics data are stored in various databases. Public resources promote the progress of scientific research. High-throughput sequencing technology and the era of big data have created a need for collaboration and data sharing in order to effectively utilize this new knowledge. This article provided comprehensive information on 54 publicly accessible databases containing GI cancer-related information, including 44 general databases and 10 specific databases designed for GI cancer. Moreover, we discussed the challenges faced in the construction of GI cancer database and future research directions. We hope that such an introduction can raise awareness and promote the full and effective utilization of these data resources, thereby improving the management of patients with GI cancer.

BACKGROUND The early diagnosis rate of pancreatic ductal adenocarcinoma (PDAC) is low and the prognosis is poor. It is important to develop an interpretable noninvasive early diagnostic model in clinical practice. AIM To develop an interpretable noninvasive early diagnostic model for PDAC using plasma extracellular vesicle long RNA (EvlRNA). METHODS The diagnostic model was constructed based on plasma EvlRNA data. During the process of establishing the model, EvlRNA-index was introduced, and four algorithms were adopted to calculate EvlRNA-index. After the model was successfully constructed, performance evaluation was conducted. A series of bioinformatics methods were adopted to explore the potential mechanism of EvlRNA-index as the input feature of the model. And the relationship between key characteristics and PDAC were explored at the single-cell level. RESULTS A novel interpretable machine learning framework was developed based on plasma EvlRNA. In this framework, a two-layer classifier was established. A new concept was proposed: EvlRNA-index. Based on EvlRNA-index, a cancer diagnostic model was established, and a good diagnostic effect was achieved. The accuracy of PDACandCPvsHealth-Probabilistic PCA Index-SVM (PDAC and chronic pancreatitis vs health-probabilistic principal component analysis index-support vector machine) (1-18) was 91.51%, with Mathew’s correlation coefficient 0.7760 and area under the curve 0.9560. In the second layer of the model, the accuracy of PDACvsCP-Probabilistic PCA Index-RF (PDAC vs chronic pancreatitis-probabilistic principal component analysis index-random forest) (2-17) was 93.83%, with Mathew’s correlation coefficient 0.8422 and area under the curve 0.9698. Forty-nine PDAC-related genes were identified, among which 16 were known, inferring that the remaining ones were also PDAC-related genes. CONCLUSION An interpretable two-layer machine learning framework was proposed for early diagnosis and prediction of PDAC based on plasma EvlRNA, providing new insights into the clinical value of EvlRNA.

At present, cancer is still an important factor threatening human health. Colorectal cancer (CRC) is one of the top three most common cancers worldwide and one of the deadliest malignancies in humans. The latest data showed that CRC incidence and mortality rank third and second, respectively, among global malignancies. Early and accurate diagnosis is crucial to reduce the morbidity, mortality and improve survival of patients with CRC, but the current early diagnostic methods have limitations. The effectiveness and compliance of diagnostic methods have a certain impact on whether people choose screening. In this editorial, we explore strategies for the early diagnosis of CRC, including stool-based, blood-based, direct visualization, and imaging examinations.

Comprehensive analysis of clinical and biological value of ING family genes in liver cancer

Objectives: More convenient and effective non-invasive diagnostic methods are essential for the detection and prognosis of cancer. This study aimed to mine the information in plasma cfDNA to find novel biomarkers for the diagnosis of esophageal cancer (ESCA). Methods: Blood samples were collected from esophageal cancer patients and healthy individuals. SALP-seq method was used to construct libraries and sequence cfDNA samples from 40 esophageal cancer patients and 10 normal cfDNA samples, and mutation analysis was performed. Results: Esophageal cancer related mutational signatures and 52 mutated genes were identified. Many of these genes are known cancer-related genes. Mutations in these genes were also found in 11 additional ESCA cfDNA samples. Conclusion: SALP-seq based cfDNA mutation analysis can obtain reliable and verifiable biomarkers for ESCA. These biomarkers provide a novel reference for the diagnosis of esophageal cancer, as well as offer novel insights into understanding the cellular and molecular mechanisms of esophageal carcinogenesis. Finally, our method provides a new avenue to explore novel cancer biomarkers.

With the rapid development of science and technology, cell-free DNA (cfDNA) is rapidly becoming an important biomarker for tumor diagnosis, monitoring and prognosis, and this cfDNA-based liquid biopsy technology has great potential to become an important part of precision medicine. cfDNA is the total amount of free DNA in the systemic circulation, including DNA fragments derived from tumor cells and all other somatic cells. Tumor cells release fragments of DNA into the bloodstream, and this source of cfDNA is called circulating tumor DNA (ctDNA). cfDNA detection has become a major focus in the field of tumor research in recent years, which provides a new opportunity for non-invasive diagnosis and prognosis of cancer. In this paper, we discuss the limitations of the study on the origin and dynamics analysis of ctDNA, and how to solve these problems in the future. Although the future faces major challenges, it also contains great potential.

A liquid biopsy is a minimally invasive or non-invasive method to analyze a range of tumor material in blood or other body fluids, including circulating tumor cells (CTCs), cell-free DNA (cfDNA), messenger RNA (mRNA), microRNA (miRNA), and exosomes, which is a very promising technology. Among these cancer biomarkers, plasma cfDNA is the most widely used in clinical practice. Compared with a tissue biopsy of traditional cancer diagnosis, in assessing tumor heterogeneity, a liquid biopsy is more reliable because all tumor sites release cfDNA into the blood. Therefore, a cfDNA liquid biopsy is less invasive and comprehensive. Moreover, the development of next-generation sequencing technology makes cfDNA sequencing more sensitive than a tissue biopsy, with higher clinical applicability and wider application. In this publication, we aim to review the latest perspectives of cfDNA liquid biopsy clinical significance and application in cancer diagnosis, treatment, and prognosis. We introduce the sequencing techniques and challenges of cfDNA detection, analysis, and clinical applications, and discuss future research directions.

Background: The advancement of bioinformatics and machine learning has facilitated the diagnosis of cancer and the discovery of omics-based biomarkers. Objective: Our study employed a novel data-driven approach to classifying the normal samples and different types of gastrointestinal cancer samples, to find potential biomarkers for effective diagnosis and prognosis assessment of gastrointestinal cancer patients. Methods: Different feature selection methods were used, and the diagnostic performance of the proposed biosignatures was benchmarked using support vector machine (SVM) and random forest (RF) models. Results: All models showed satisfactory performance in which Multilabel-RF appeared to be the best. The accuracy of the Multilabel-RF based model was 83.12%, with precision, recall, F1, and Hamming- Loss of 79.70%, 68.31%, 0.7357 and 0.1688, respectively. Moreover, proposed biomarker signatures were highly associated with multifaceted hallmarks in cancer. Functional enrichment analysis and impact of the biomarker candidates in the prognosis of the patients were also examined. Conclusion: We successfully introduced a solid workflow based on multi-label learning with High- Throughput Omics for diagnosis of cancer and identification of novel biomarkers. Novel transcriptome biosignatures that may improve the diagnostic accuracy in gastrointestinal cancer are introduced for further validations in various clinical settings.

The effective non-invasive diagnosis and prognosis are critical for cancer treatment. The plasma cell-free DNA (cfDNA) provides a good material for cancer liquid biopsy and its worth in this field is increasingly explored. Here we describe a new pipeline for effectively finding new cfDNA-based biomarkers for cancers by combining SALP-seq and machine learning. Using the pipeline, 30 cfDNA samples from 26 esophageal cancer (ESCA) patients and 4 healthy people were analyzed as an example. As a result, 103 epigenetic markers (including 54 genome-wide and 49 promoter markers) and 37 genetic markers were identified for this cancer. These markers provide new biomarkers for ESCA diagnosis, prognosis and therapy. Importantly, these markers, especially epigenetic markers, not only shed important new insights on the regulatory mechanisms of this cancer, but also could be used to classify the cfDNA samples. We therefore developed a new pipeline for effectively finding new cfDNA-based biomarkers for cancers by combining SALP-seq and machine learning. In this study, we also discovered new clinical worth of cfDNA distinct from other reported characters.