Plasma Extracellular Vesicle Long RNA in Diagnosis and Prediction in Small Cell Lung Cancer

Predicting high sensitivity C-reactive protein levels and their associations in a large population using decision tree and linear regression

High-sensitivity C-reactive protein (hs-CRP) is a biomarker of inflammation predicting the incidence of different health pathologies. In this study, we aimed to evaluate the association between hematological and demographic factors with hs-CRP levels using decision tree (DT) and linear regression (LR) modeling. This study was conducted on a population of 9704 males and females aged 35 to 65 years recruited from the Mashhad Stroke and Heart Atherosclerotic Disorder (MASHAD) cohort study. We utilized a data mining approach to construct a predictive model of hs-CRP measurements, employing the DT methodology. DT model was used to predict hs-CRP level using biochemical factors and clinical features. A total of 9,704 individuals were included in the analysis, with 57% of them being female. Except for fasting blood glucose (FBG), hypertension (HTN), and Type 2 diabetes mellites (T2DM), all variables showed significant differences between the two groups. The results of the LR models showed that variables such as anxiety score, depression score, Systolic Blood Pressure, Cardiovascular disease, and HTN were significant in predicting hs-CRP levels. In the DT models, depression score, FBG, cholesterol, and anxiety score were identified as the most important factors in predicting hs-CRP levels. DT model was able to predict hs-CRP level with an accuracy of 72.1% in training and 71.4% in testing of both genders. The proposed DT model appears to be able to predict the hs-CRP levels based on anxiety score, depression scores, fasting blood glucose, systolic blood pressure, and history of cardiovascular diseases.

StructmRNA a BERT based model with dual level and conditional masking for mRNA representation

In this study, we introduce StructmRNA, a new BERT-based model that was designed for the detailed analysis of mRNA sequences and structures. The success of DNABERT in understanding the intricate language of non-coding DNA with bidirectional encoder representations is extended to mRNA with StructmRNA. This new model uses a special dual-level masking technique that covers both sequence and structure, along with conditional masking. This enables StructmRNA to adeptly generate meaningful embeddings for mRNA sequences, even in the absence of explicit structural data, by capitalizing on the intricate sequence-structure correlations learned during extensive pre-training on vast datasets. Compared to well-known models like those in the Stanford OpenVaccine project, StructmRNA performs better in important tasks such as predicting RNA degradation. Thus, StructmRNA can inform better RNA-based treatments by predicting the secondary structures and biological functions of unseen mRNA sequences. The proficiency of this model is further confirmed by rigorous evaluations, revealing its unprecedented ability to generalize across various organisms and conditions, thereby marking a significant advance in the predictive analysis of mRNA for therapeutic design. With this work, we aim to set a new standard for mRNA analysis, contributing to the broader field of genomics and therapeutic development.

Artificial intelligence-based evaluation of prognosis in cirrhosis

Cirrhosis represents a significant global health challenge, characterized by high morbidity and mortality rates that severely impact human health. Timely and precise prognostic assessments of liver cirrhosis are crucial for improving patient outcomes and reducing mortality rates as they enable physicians to identify high-risk patients and implement early interventions. This paper features a thorough literature review on the prognostic assessment of liver cirrhosis, aiming to summarize and delineate the present status and constraints associated with the application of traditional prognostic tools in clinical settings. Among these tools, the Child-Pugh and Model for End-Stage Liver Disease (MELD) scoring systems are predominantly utilized. However, their accuracy varies significantly. These systems are generally suitable for broad assessments but lack condition-specific applicability and fail to capture the risks associated with dynamic changes in patient conditions. Future research in this field is poised for deep exploration into the integration of artificial intelligence (AI) with routine clinical and multi-omics data in patients with cirrhosis. The goal is to transition from static, unimodal assessment models to dynamic, multimodal frameworks. Such advancements will not only improve the precision of prognostic tools but also facilitate personalized medicine approaches, potentially revolutionizing clinical outcomes.

Plasma extracellular vesicle long RNA profiling identifies a predictive signature for immunochemotherapy efficacy in lung squamous cell carcinoma

Introduction

The introduction of Immune Checkpoint Inhibitors (ICIs) has marked a paradigm shift in treating Lung Squamous Cell Carcinoma (LUSC), emphasizing the urgent need for precise molecular biomarkers to reliably forecast therapeutic efficacy. This study aims to identify potential biomarkers for immunochemotherapy efficacy by focusing on plasma extracellular vesicle (EV)-derived long RNAs (exLRs).

Methods

We enrolled 78 advanced LUSC patients undergoing first-line immunochemotherapy. Plasma samples were collected, and exLR sequencing was conducted to establish baseline profiles. A retrospective analysis was performed on 42 patients to identify differentially expressed exLRs. Further validation of the top differentially expressed exLRs was conducted using quantitative reverse transcription PCR (qRT-PCR). Univariate Cox analysis was applied to determine the prognostic significance of these exLRs. Based on these findings, we developed a predictive signature (p-Signature).

Results

In the retrospective analysis of 42 patients, we identified 460 differentially expressed exLRs, with pathways related to leukocyte migration notably enriched among non-responders. Univariate Cox analysis revealed 45 exLRs with prognostic significance. The top 6 protein-coding exLRs were validated using qRT-PCR, identifying CXCL8, SSH3, and SDHAF1 as differentially expressed between responders and non-responders. The p-Signature, comprising these three exLRs, demonstrated high accuracy in distinguishing responders from non-responders, with an Area Under the Curve (AUC) of 0.904 in the retrospective cohort and 0.812 in the prospective cohort.

Discussion

This study highlighted the potential of plasma exLR profiles in predicting LUSC treatment efficacy. Intriguingly, lower p-Signature scores were associated with increased abundance of activated CD4+ and CD8+ T cells, indicating a more robust immune environment. These findings suggest that the p-Signature could serve as a valuable tool in guiding personalized and effective therapeutic strategies for LUSC.

Exploring the Role of Vitamin D, Vitamin D-Dependent Proteins, and Vitamin D Receptor Gene Variation in Lung Cancer Risk

Lung cancer has an unfavorable prognosis with a rate of low overall survival, caused by the difficulty of diagnosis in the early stages and resistance to therapy. In recent years, there have been new therapies that use specific molecular targets and are effective in increasing the survival chances of advanced cancer. Therefore, it is necessary to find more specific biomarkers that can identify early changes in carcinogenesis and allow the earliest possible treatment. Vitamin D (VD) plays an important role in immunity and carcinogenesis. Furthermore, the vitamin D receptor (VDR) regulates the expression of various genes involved in the physiological functions of the human organism. The genes encoding the VDR are extremely polymorphic and vary greatly between human populations. To date, there are significant associations between VDR polymorphism and several types of cancer, but the data on the involvement of VDR polymorphism in lung cancer are still conflicting. Therefore, in this review, our aim was to investigate the relationship between VDR single-nucleotide polymorphisms in humans and the degree of risk for developing lung cancer. The studies showcased different gene polymorphisms to be associated with an increased risk of lung cancer: TaqI, ApaI, BsmI, FokI, and Cdx2. In addition, there is a strong positive correlation between VD deficiency and lung cancer development. Still, due to a lack of awareness, the assessment of VD status and VDR polymorphism is rarely considered for the prediction of lung cancer evolution and their clinical applicability, despite the fact that studies have shown the highest risk for lung cancer given by TaqI gene polymorphisms and that VDR polymorphisms are associated with more aggressive cancer evolution.

A liquid biopsy signature of circulating extracellular vesicles-derived RNAs predicts response to first line chemotherapy in patients with metastatic colorectal cancer

BACKGROUND

Colorectal cancer (CRC) is one of the most threatening tumors in the world, and chemotherapy remains dominant in the treatment of metastatic CRC (mCRC) patients. The purpose of this study was to develop a biomarker panel to predict the response of the first line chemotherapy in mCRC patients.

METHODS

Totally 190 mCRC patients treated with FOLFOX or XEOLX chemotherapy in 3 different institutions were included. We extracted the plasma extracellular vesicle (EV) RNA, performed RNA sequencing, constructed a model and generated a signature through shrinking the number of variables by the random forest algorithm and the least absolute shrinkage and selection operator (LASSO) algorithm in the training cohort (n = 80). We validated it in an internal validation cohort (n = 62) and a prospective external validation cohort (n = 48).

RESULTS

We established a signature consisted of 22 EV RNAs which could identify responders, and the area under the receiver operating characteristic curve (AUC) values was 0.986, 0.821, and 0.816 in the training, internal validation, and external validation cohort respectively. The signature could also identify the progression-free survival (PFS) and overall survival (OS). Besides, we constructed a 7-gene signature which could predict tumor response to first-line oxaliplatin-containing chemotherapy and simultaneously resistance to second-line irinotecan-containing chemotherapy.

CONCLUSIONS

The study was first to develop a signature of EV-derived RNAs to predict the response of the first line chemotherapy in mCRC with high accuracy using a non-invasive approach, indicating that the signature could help to select the optimal regimen for mCRC patients.