Integrated Machine Learning and Bioinformatic Analyses Constructed a Novel Stemness-Related Classifier to Predict Prognosis and Immunotherapy Responses for Hepatocellular Carcinoma Patients

Analysis and identification of mRNAsi‑related expression signatures via RNA sequencing in lung cancer

High stemness index scores are associated with poor survival in patients with lung cancer. Studies on the mRNA expression-based stemness index (mRNAsi) are typically conducted using tumor tissues; however, mRNAsi-related expression signatures based on cell-free RNA (cfRNA) are yet to be comprehensively investigated. The present study aimed to elucidate the gene expression profiles of tumor stemness in lung cancer tissues and corresponding cfRNAs in blood, and to assess their links with immune infiltration. Tumor tissue, paracancerous tissue, peripheral blood and lymph node samples were collected from patients with stage I-III non-small cell lung cancer and RNA sequencing was performed. The TCGAbiolinks package was used to calculate the mRNAsi for each of these four types of sample. Weighted gene co-expression network analysis and differentially expressed gene analyses were performed to investigate mRNAsi-related genes, and pathway enrichment analysis was performed using the Kyoto Encyclopedia of Genes and Genomes (KEGG) orthology-based annotation system. In addition, the STAR-Fusion tool was used to detect fusion variants, and CIBERSORT was used to analyze the correlations of stemness signatures in tissues and blood with immune cell infiltration. The mRNAsi values in peripheral blood and lymph nodes were found to be higher than those in cancer tissues. 'Hematopoietic cell lineage' was the only KEGG pathway enriched in mRNAsi-related genes in both lung cancer tissues and peripheral blood. In addition, the protein tyrosine phosphatase receptor type C associated protein gene was the only gene commonly associated with the mRNAsi in these two types of sample. The expression of mRNAsi-related genes was increased in the dendritic and Treg cells in tumor tissues, but was elevated in Treg and CD8 cells in the blood. In conclusion, cfRNAs in the blood exhibit unique stemness signatures that have potential for use in the diagnosis of lung cancer.

Interpretable machine learning based on CT-derived extracellular volume fraction to predict pathological grading of hepatocellular carcinoma

PURPOSE

To develop a non-invasive auxiliary assessment method based on CT-derived extracellular volume (ECV) to predict the pathological grading (PG) of hepatocellular carcinoma (HCC).

METHODS

The study retrospectively analyzed 238 patients who underwent HCC resection surgery between January 2013 and April 2023. Six machine learning algorithms were employed to construct predictive models for HCC PG: logistic regression, extreme gradient boosting, Light Gradient Boosting Machine (LightGBM), random forest, adaptive boosting, and Gaussian naive Bayes. Model performance was evaluated using receiver operating characteristic curve analysis, including area under the curve (AUC), sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and F1 score. Calibration plots were used for visual evaluation of model calibration. Clinical decision curve analysis was performed to assess potential clinical utility by calculating net benefit.

RESULTS

166 patients from Hospital A were allocated to the training set, while 72 patients from Hospital B (constituting 30.25% of the total sample) were assigned to the test set. The model achieved an AUC of 1.000 (95%CI: 1.000-1.000) in the training set and 0.927 (95%CI: 0.837-0.999) in the validation set, respectively. Ultimately, the model achieved an AUC of 0.909 (95%CI: 0.837-0.980) in the test set, with an accuracy of 0.778, sensitivity of 0.906, specificity of 0.789, negative predictive value of 0.556, and F1 score of 0.908.

CONCLUSION

This study successfully developed and validated a non-invasive auxiliary assessment method based on CT-derived ECV to predict the HCC PG, providing important supplementary information for clinical decision-making.

Machine learning and single-cell analysis identify the mitophagy-associated gene TOMM22 as a potential diagnostic biomarker for intervertebral disc degeneration

Background

Mitophagy selectively eliminates potentially cytotoxic and damaged mitochondria and effectively prevents excessive cytotoxicity from damaged mitochondria, thereby attenuating inflammatory and oxidative responses. However, the potential role of mitophagy in intervertebral disc degeneration remains to be elucidated.

Methods

The GSVA method, two machine learning methods (SVM-RFE algorithm and random forest), the CIBERSORT and MCPcounter methods, as well as the consensus clustering method and the WGCNA algorithm were used to analyze the involvement of mitophagy in intervertebral disc degeneration, the diagnostic value of mitophagy-associated genes in intervertebral disc degeneration, and the infiltration of immune cells, and identify the gene modules that were closely related to mitophagy. Single-cell analysis was used to detect mitophagy scores and TOMM22 expression, and pseudo-temporal analysis was used to explore the function of TOMM22 in nucleus pulposus cells. In addition, TOMM22 expression was compared between human normal and degenerated intervertebral disc tissue samples by immunohistochemistry and PCR.

Results

This study identified that the mitophagy pathway score was elevated in intervertebral disc degeneration compared with the normal condition. A strong link was present between mitophagy genes and immune cells, which may be used to typify intervertebral disc degeneration. The single-cell level showed that mitophagy-associated gene TOMM22 was highly expressed in medullary cells of the disease group. Further investigations indicated the upregulation of TOMM22 expression in late-stage nucleus pulposus cells and its role in cellular communication. In addition, human intervertebral disc tissue samples established that TOMM22 levels were higher in disc degeneration samples than in normal samples.

Conclusions

Our findings revealed that mitophagy may be used in the diagnosis of intervertebral disc degeneration and its typing, and TOMM22 is a molecule in this regard and may act as a potential diagnostic marker in intervertebral disc degeneration.

Construction of a pathomics model for predicting mRNAsi in lung adenocarcinoma and exploration of biological mechanism

Objective

This study aimed to predict the level of stemness index (mRNAsi) and survival prognosis of lung adenocarcinoma (LUAD) using pathomics model.

Methods

From The Cancer Genome Atlas (TCGA) database, 327 LUAD patients were randomly assigned to a training set (n = 229) and a validation set (n = 98) for pathomics model development and evaluation. PyRadiomics was used to extract pathomics features, followed by feature selection using the mRMR-RFE algorithm. In the training set, Gradient Boosting Machine (GBM) was utilized to establish a model for predicting mRNAsi in LUAD. The model's predictive performance was evaluated using ROC curves, calibration curves, and decision curve analysis (DCA). Prognostic analysis was conducted using Kaplan-Meier curves and cox regression. Additionally, gene enrichment analysis, tumor microenvironment analysis, and tumor mutational burden (TMB) analysis were performed to explore the biological mechanisms underlying the pathomics prediction model.

Results

Multivariable cox analysis (HR = 1.488, 95 % CI 1.012-2.187, P = 0.043) identified mRNAsi as a prognostic risk factor for LUAD. A total of 465 pathomics features were extracted from TCGA-LUAD histopathological images, and ultimately, the most representative 8 features were selected to construct the predictive model. ROC curves demonstrated the significant predictive value of the model for mRNAsi in both the training set (AUC = 0.769) and the validation set (AUC = 0.757). Calibration curves and Hosmer-Lemeshow goodness-of-fit test showed good consistency between the model's prediction of mRNAsi levels and the actual values. DCA indicated a good net benefit of the model. The prediction of mRNAsi levels by the pathomics model is represented using the pathomics score (PS). PS was strongly associated with the prognosis of LUAD (HR = 1.496, 95 % CI 1.008-2.222, P = 0.046). Signaling pathways related to DNA replication and damage repair were significantly enriched in the high PS group. Prediction of immune therapy response indicated significantly reduced Dysfunction in the high PS group (P < 0.001). The high PS group exhibited higher TMB values (P < 0.001).

Conclusions

The predictive model constructed based on pathomics features can forecast the mRNAsi and survival risk of LUAD. This model holds promise to aid clinical practitioners in identifying high-risk patients and devising more optimized treatment plans for patients by jointly employing therapeutic strategies targeting cancer stem cells (CSCs).

Integrated machine learning screened glutamine metabolism-associated biomarker SLC1A5 to predict immunotherapy response in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) stands as one of the most prevalent malignancies. While PD-1 immune checkpoint inhibitors have demonstrated promising therapeutic efficacy in HCC, not all patients exhibit a favorable response to these treatments. Glutamine is a crucial immune cell regulatory factor, and tumor cells exhibit glutamine dependence. In this study, HCC patients were divided into two subtypes (C1 and C2) based on glutamine metabolism-related genes via consensus clustering. The C1 pattern, in contrast to C2, was associated with a lower survival probability among HCC patients. Additionally, the C1 pattern exhibited higher proportions of patients with advanced tumor stages. The activity of C1 in glutamine metabolism and transport is significantly enhanced, while its oxidative phosphorylation activity is reduced. And, C1 was mainly involved in the progression-related pathway of HCC. Furthermore, C1 exhibited high levels of immunosuppressive cells, cytokine-receptor interactions and immune checkpoint genes, suggesting C1 as an immunosuppressive subtype. After stepwise selection based on integrated four machine learning methods, SLC1A5 was finally identified as the pivotal gene that distinguishes the subtypes. The expression of SLC1A5 was significantly positively correlated with immunosuppressive status. SLC1A5 showed the most significant correlation with macrophage infiltration, and this correlation was confirmed through the RNA-seq data of CLCA project and our cohort. Low-SLC1A5-expression samples had better immunogenicity and responsiveness to immunotherapy. As expected, SubMap and survival analysis indicated that individuals with low SLC1A5 expression were more responsive to anti-PD1 therapy. Collectively, this study categorized HCC patients based on glutamine metabolism-related genes and proposed two subclasses with different clinical traits, biological behavior, and immune status. Machine learning was utilized to identify the hub gene SLC1A5 for HCC classification, which also could predict immunotherapy response.

Artificial intelligence applied to 'omics data in liver disease: towards a personalised approach for diagnosis, prognosis and treatment

Advancements in omics technologies and artificial intelligence (AI) methodologies are fuelling our progress towards personalised diagnosis, prognosis and treatment strategies in hepatology. This review provides a comprehensive overview of the current landscape of AI methods used for analysis of omics data in liver diseases. We present an overview of the prevalence of different omics levels across various liver diseases, as well as categorise the AI methodology used across the studies. Specifically, we highlight the predominance of transcriptomic and genomic profiling and the relatively sparse exploration of other levels such as the proteome and methylome, which represent untapped potential for novel insights. Publicly available database initiatives such as The Cancer Genome Atlas and The International Cancer Genome Consortium have paved the way for advancements in the diagnosis and treatment of hepatocellular carcinoma. However, the same availability of large omics datasets remains limited for other liver diseases. Furthermore, the application of sophisticated AI methods to handle the complexities of multiomics datasets requires substantial data to train and validate the models and faces challenges in achieving bias-free results with clinical utility. Strategies to address the paucity of data and capitalise on opportunities are discussed. Given the substantial global burden of chronic liver diseases, it is imperative that multicentre collaborations be established to generate large-scale omics data for early disease recognition and intervention. Exploring advanced AI methods is also necessary to maximise the potential of these datasets and improve early detection and personalised treatment strategies.

Identification of effective diagnostic genes and immune cell infiltration characteristics in small cell lung cancer by integrating bioinformatics analysis and machine learning algorithms

OBJECTIVES

To identify potential diagnostic markers for small cell lung cancer (SCLC) and investigate the correlation with immune cell infiltration.

METHODS

GSE149507 and GSE6044 were used as the training group, while GSE108055 served as validation group A and GSE73160 served as validation group B. Differentially expressed genes (DEGs) were identified and analyzed for functional enrichment. Machine learning (ML) was used to identify candidate diagnostic genes for SCLC. The area under the receiver operating characteristic curves was applied to assess diagnostic efficacy. Immune cell infiltration analyses were carried out.

RESULTS

There were 181 DEGs identified. The gene ontology analysis showed that DEGs were enriched in 455 functional annotations, some of which were associated with immunity. The kyoto encyclopedia of genes and genomes analysis revealed that there were 9 signaling pathways enriched. The disease ontology analysis indicated that DEGs were related to 116 diseases. The gene set enrichment analysis results displayed multiple items closely related to immunity. ZWINT and NRCAM were screened using ML and further validated as diagnostic genes. Significant differences were observed in SCLC with normal lung tissue samples among immune cell infiltration characteristics. Strong associations were found between the diagnostic genes and immune cell infiltration.

CONCLUSION

This study identified 2 diagnostic genes, ZWINT and NRCAM, that were related to immune cell infiltration by integrating bioinformatics analysis and ML algorithms. These genes could serve as potential diagnostic biomarkers and provide possible molecular targets for immunotherapy in SCLC.

Potential therapeutic targets for pelvic organ prolapse: insights from key genes related to blood vessel development

Objective

Pelvic organ prolapse (POP) is a disease in which pelvic floor support structures are dysfunctional due to disruption of the extracellular matrix (ECM). The vascular system is essential for maintaining ECM homeostasis. Therefore, this study explored the potential mechanism of blood vessel development-related genes (BVDRGs) in POP.

Methods

POP-related datasets and BVDRGs were included in this study. Differentially expressed genes (DEGs) between the POP and control groups were first identified in the GSE12852 and GSE208271 datasets, and DE-BVDRGs were identified by determining the intersection of these DEGs and BVDRGs. Subsequently, the feature genes were evaluated by machine learning. Feature genes with consistent expression trends in the GSE12852 and GSE208271 datasets were considered key genes. Afterward, the overall diagnostic efficacy of key genes in POP was evaluated through receiver operating characteristic (ROC) curve analysis. Based on the key genes, enrichment analysis, immune infiltration analysis and regulatory network construction were performed to elucidate the molecular mechanisms underlying the functions of the key genes in POP.

Results

A total of 888 DEGs1 and 643 DEGs2 were identified in the GSE12852 and GSE208271 datasets, and 26 candidate genes and 4 DE-BVDRGs were identified. Furthermore, Hyaluronan synthase 2 (HAS2), Matrix metalloproteinase 19 (MMP19) and Plexin Domain Containing 1 (PLXDC1) were identified as key genes in POP and had promising value for diagnosing POP (AUC > 0.8). Additional research revealed that the key genes were predominantly implicated in immune cell activation, chemotaxis, and cytokine release via the chemokine signaling pathway, the Nod-like receptor signaling pathway, and the Toll-like receptor signaling pathway. Analysis of immune cell infiltration confirmed a decrease in the proportion of plasma cells in POP, and MMP19 expression showed a significant negative correlation with plasma cell numbers. In addition, regulatory network analysis revealed that MALAT1 (a lncRNA) targeted hsa-miR-503-5p, hsa-miR-23a-3p and hsa-miR-129-5p to simultaneously regulate three key genes.

Conclusion

We identified three key BVDRGs (HAS2, MMP19 and PLXDC1) related to the ECM in POP, providing markers for diagnostic studies and investigations of the molecular mechanism of POP.

Lasso-Cox interpretable model of AFP-negative hepatocellular carcinoma

BACKGROUND

In AFP-negative hepatocellular carcinoma patients, markers for predicting tumor progression or prognosis are limited. Therefore, our objective is to establish an optimal predicet model for this subset of patients, utilizing interpretable methods to enhance the accuracy of HCC prognosis prediction.

METHODS

We recruited a total of 508 AFP-negative HCC patients in this study, modeling with randomly divided training set and validated with validation set. At the same time, 86 patients treated in different time periods were used as internal validation. After comparing the cox model with the random forest model based on Lasso regression, we have chosen the former to build our model. This model has been interpreted with SHAP values and validated using ROC, DCA. Additionally, we have reconfirmed the model's effectiveness by employing an internal validation set of independent periods. Subsequently, we have established a risk stratification system.

RESULTS

The AUC values of the Lasso-Cox model at 1, 2, and 3 years were 0.807, 0.846, and 0.803, and the AUC values of the Lasso-RSF model at 1, 2, and 3 years were 0.783, 0.829, and 0.776. Lasso-Cox model was finally used to predict the prognosis of AFP-negative HCC patients in this study. And BCLC stage, gamma-glutamyl transferase (GGT), diameter of tumor, lung metastases (LM), albumin (ALB), alkaline phosphatase (ALP), and the number of tumors were included in the model. The validation set and the separate internal validation set both indicate that the model is stable and accurate. Using risk factors to establish risk stratification, we observed that the survival time of the low-risk group, the middle-risk group, and the high-risk group decreased gradually, with significant differences among the three groups.

CONCLUSION

The Lasso-Cox model based on AFP-negative HCC showed good predictive performance for liver cancer. SHAP explained the model for further clinical application.

Screening and experimental validation of diagnostic gene in ulcerative colitis with anti-TNF-α therapy

In clinical practice, the diagnosis of ulcerative colitis (UC) mainly relies on a comprehensive analysis of a series of signs and symptoms of patients. The current biomarkers for diagnosis of UC and prognostic prediction of anti-TNF-α therapy are inaccurate. The present study aimed to perform an integrative analysis of gene expression profiles in patients with UC. A total of seven datasets from the GEO database that met our strict inclusion criteria were included. After identifying differentially expressed genes (DEGs) between UC patients and healthy individuals, the diagnostic and prognostic utility of the DEGs were then analyzed via least absolute shrinkage and selection operator and support-vector machine recursive feature elimination. Subgroup analyses of the treated and untreated groups, as well as the treatment-response group and non-response group, were also performed. Furthermore, the relationship between the expressions of UC-related genes and infiltration of immune cells in the course of treatment was also investigated. Immunohistochemical (IHC) assay was used to verify the gene expression in inflamed UC tissues. When considering all the applied methods, DUOX2, PI3, S100P, MMP7, and S100A8 had priority to be defined as the characteristic genes among DEGs. The area under curve (AUC) of the five genes, which were all consistently over-expressed, based on an external validation dataset, were all above 0.94 for UC diagnosis. Four of the five genes (DUOX2, PI3, MMP7, and S100A8) were down-regulated between treatment-responsive and nonresponsive patients. A significant difference was also observed concerning the infiltration of immune cells, including macrophage and neutrophil, between the two groups (treatment responsive and nonresponsive). The changes in the expression of DUOX2 and MMP7 based on the IHC assay were highly consistent with the results obtained in the current study. This confirmed the mild to moderate diagnostic and predictive value of DUOX2 and MMP7 in patients with UC. The conducted analyses showed that the expression profile of the five identified biomarkers accurately detects UC, whereas four of the five genes evidently predicted the response to anti-TNF-α therapy.

Systemic analysis of the prognostic significance and interaction network of miR-26b-3p in cholangiocarcinoma

MicroRNAs (miRNAs) reportedly play significant roles in the progression of various cancers and hold huge potential as both diagnostic tools and therapeutic targets. Given the ongoing uncertainty surrounding the precise functions of several miRNAs in cholangiocarcinoma (CCA), this research undertakes a comprehensive analysis of CCA data sourced from Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) databases. The present study identified a novel miRNA, specifically miR-26b-3p, which exhibited prognostic value for individuals with CCA. Notably, miR-26b-3p was upregulated within CCA samples, with an inverse correlation established with patient prognosis (Hazard Ratio = 8.19, p = 0.018). Through a combination of functional enrichment analysis, analysis of the LncRNA-miR-26b-3p-mRNA interaction network, and validation by qRT PCR and western blotting, this study uncovered the potential of miR-26b-3p in potentiating the malignant progression of CCA via regulation of essential genes (including PSMD14, XAB2, SLC4A4) implicated in processes such as endoplasmic reticulum (ER) stress and responses to misfolded proteins. Our findings introduce novel and valuable insights that position miR-26b-3p-associated genes as promising biomarkers for the diagnosis and treatment of CCA.

CDKL3 is a promising biomarker for diagnosis and prognosis prediction in patients with hepatocellular carcinoma

Cyclin-dependent kinase-like 3 (CDKL3) has been identified as an oncogene in certain types of tumors. Nonetheless, its function in hepatocellular carcinoma (HCC) is poorly understood. In this study, we conducted a comprehensive analysis of CDKL3 based on data from the HCC cohort of The Cancer Genome Atlas (TCGA). Our analysis included gene expression, diagnosis, prognosis, functional enrichment, tumor microenvironment and metabolic characteristics, tumor burden, mRNA expression-based stemness, alternative splicing, and prediction of therapy response. Additionally, we performed a cell counting kit-8 assay, TdT-mediated dUTP nick-end Labeling staining, migration assay, wound healing assay, colony formation assay, and nude mouse experiments to confirm the functional relevance of CDKL3 in HCC. Our findings showed that CDKL3 was significantly upregulated in HCC patients compared to controls. Various bioinformatic analyses suggested that CDKL3 could serve as a potential marker for HCC diagnosis and prognosis. Furthermore, CDKL3 was found to be involved in various mechanisms linked to the development of HCC, including copy number variation, tumor burden, genomic heterogeneity, cancer stemness, and alternative splicing of CDKL3. Notably, CDKL3 was also closely correlated with tumor immune cell infiltration and the expression of immune checkpoint markers. Additionally, CDKL3 was shown to independently function as a risk predictor for overall survival in HCC patients by multivariate Cox regression analysis. Furthermore, the knockdown of CDKL3 significantly inhibited cell proliferation in vitro and in vivo, indicating its role as an oncogene in HCC. Taken together, our findings suggest that CDKL3 shows promise as a biomarker for the detection and treatment outcome prediction of HCC patients.

Establishing and clinically validating a machine learning model for predicting unplanned reoperation risk in colorectal cancer

BACKGROUND

Colorectal cancer significantly impacts global health, with unplanned reoperations post-surgery being key determinants of patient outcomes. Existing predictive models for these reoperations lack precision in integrating complex clinical data.

AIM

To develop and validate a machine learning model for predicting unplanned reoperation risk in colorectal cancer patients.

METHODS

Data of patients treated for colorectal cancer (n = 2044) at the First Affiliated Hospital of Wenzhou Medical University and Wenzhou Central Hospital from March 2020 to March 2022 were retrospectively collected. Patients were divided into an experimental group (n = 60) and a control group (n = 1984) according to unplanned reoperation occurrence. Patients were also divided into a training group and a validation group (7:3 ratio). We used three different machine learning methods to screen characteristic variables. A nomogram was created based on multifactor logistic regression, and the model performance was assessed using receiver operating characteristic curve, calibration curve, Hosmer-Lemeshow test, and decision curve analysis. The risk scores of the two groups were calculated and compared to validate the model.

RESULTS

More patients in the experimental group were ≥ 60 years old, male, and had a history of hypertension, laparotomy, and hypoproteinemia, compared to the control group. Multiple logistic regression analysis confirmed the following as independent risk factors for unplanned reoperation (P < 0.05): Prognostic Nutritional Index value, history of laparotomy, hypertension, or stroke, hypoproteinemia, age, tumor-node-metastasis staging, surgical time, gender, and American Society of Anesthesiologists classification. Receiver operating characteristic curve analysis showed that the model had good discrimination and clinical utility.

CONCLUSION

This study used a machine learning approach to build a model that accurately predicts the risk of postoperative unplanned reoperation in patients with colorectal cancer, which can improve treatment decisions and prognosis.

Histamine-related genes participate in the establishment of an immunosuppressive microenvironment and impact the immunotherapy response in hepatocellular carcinoma

Chronic inflammation is pivotal in the pathogenesis of hepatocellular carcinoma (HCC). Histamine is a biologically active substance that amplifies the inflammatory and immune response and serves as a neurotransmitter. However, knowledge of histamine's role in HCC and its effects on immunotherapy remains lacking. We focused on histamine-related genes to investigate their potential role in HCC. The RNA-seq data and clinical information regarding HCC were obtained from The Cancer Genome Atlas (TCGA). After identifying the differentially expressed genes, we constructed a signature using the univariate Cox proportional hazard regression and least absolute shrinkage and selection operator (LASSO) analyses. The signature's predictive performance was evaluated using a receiver operating characteristic curve (ROC) analysis. Furthermore, drug sensitivity, immunotherapy effects, and enrichment analyses were conducted. Histamine-related gene expression in HCC was confirmed using quantitative real-time polymerase chain reaction (qRT-PCR). A histamine-related gene prognostic signature (HRGPS) was developed in TCGA. Time-dependent ROC and Kaplan-Meier survival analyses demonstrated the signature's strong predictive power. Importantly, patients in high-risk groups exhibited a higher frequency of TP53 mutations, elevated immune checkpoint-related gene expression, and increased infiltration of immunosuppressive cells-indicating a potentially favorable response to immunotherapy. In addition, drug sensitivity analysis revealed that the signature could effectively predict chemotherapy efficacy and sensitivity. qRT-PCR results validated histamine-related gene overexpression in HCC. Our findings demonstrate that inhibiting histamine-related genes and signaling pathways can impact the therapeutic effect of anti-PD-1/PD-L1. The precise predictive ability of our signature in determining the response to different therapeutic options highlights its potential clinical significance.

Identification and validation of immune-related gene signature models for predicting prognosis and immunotherapy response in hepatocellular carcinoma

Background

This study seeks to enhance the accuracy and efficiency of clinical diagnosis and therapeutic decision-making in hepatocellular carcinoma (HCC), as well as to optimize the assessment of immunotherapy response.

Methods

A training set comprising 305 HCC cases was obtained from The Cancer Genome Atlas (TCGA) database. Initially, a screening process was undertaken to identify prognostically significant immune-related genes (IRGs), followed by the application of logistic regression and least absolute shrinkage and selection operator (LASSO) regression methods for gene modeling. Subsequently, the final model was constructed using support vector machines-recursive feature elimination (SVM-RFE). Following model evaluation, quantitative polymerase chain reaction (qPCR) was employed to examine the gene expression profiles in tissue samples obtained from our cohort of 54 patients with HCC and an independent cohort of 231 patients, and the prognostic relevance of the model was substantiated. Thereafter, the association of the model with the immune responses was examined, and its predictive value regarding the efficacy of immunotherapy was corroborated through studies involving three cohorts undergoing immunotherapy. Finally, the study uncovered the potential mechanism by which the model contributed to prognosticating HCC outcomes and assessing immunotherapy effectiveness.

Results

SVM-RFE modeling was applied to develop an OS prognostic model based on six IRGs (CMTM7, HDAC1, HRAS, PSMD1, RAET1E, and TXLNA). The performance of the model was assessed by AUC values on the ROC curves, resulting in values of 0.83, 0.73, and 0.75 for the predictions at 1, 3, and 5 years, respectively. A marked difference in OS outcomes was noted when comparing the high-risk group (HRG) with the low-risk group (LRG), as demonstrated in both the initial training set (P <0.0001) and the subsequent validation cohort (P <0.0001). Additionally, the SVMRS in the HRG demonstrated a notable positive correlation with key immune checkpoint genes (CTLA-4, PD-1, and PD-L1). The results obtained from the examination of three cohorts undergoing immunotherapy affirmed the potential capability of this model in predicting immunotherapy effectiveness.

Conclusions

The HCC predictive model developed in this study, comprising six genes, demonstrates a robust capability to predict the OS of patients with HCC and immunotherapy effectiveness in tumor management.

Bioinformatics Analysis Reveals HIST1H2BH as a Novel Diagnostic Biomarker for Atrial Fibrillation-Related Cardiogenic Thromboembolic Stroke

Atrial fibrillation (AF) is a significant precursor to cerebral embolism. Our study sought to unearth new diagnostic biomarkers for atrial fibrillation-related cerebral embolism (AF-CE) by meticulously examining multiple GEO datasets and meta-analysis. The gene expression omnibus (GEO) database provided RNA sequencing data associated with AF and stroke. We began by pinpointing genes with varied expressions in AF-CE patient blood samples. A meta-analysis was subsequently undertaken using several RNA sequencing datasets to verify these genes. LASSO regression discerned key genes for AF-CE, with their diagnostic prowess verified through ROC curve examination. Active signaling pathways within stroke patients were discerned via GO and KEGG enrichment, with PPI interactions detailing gene interplay. Differential gene analysis revealed an upregulation of sixteen genes and a downregulation of four in stroke patient blood samples. Eight genes showcased varied expression in the meta-analysis. LASSO regression zeroed in on five of these, culminating in HIST1H2BH's identification as a characteristic gene. HIST1H2BH's prowess in predicting AF-CE was confirmed through ROC. Integrin signaling, platelet activation, ECM interactions, and the PI3K-Akt pathway were found active in stroke victims. HIST1H2BH's interaction with the notably upregulated ITGA2B was spotlighted by PPI. Additionally, HIST1H2BH exhibited links with NK cells and eosinophils. HIST1H2BH emerges as an insightful diagnostic beacon for AF-CE. Its presence, post AF, potentially modulates pathways, accentuating platelet activation and consequent thrombus generation, leading to cerebral embolism.

Letter: Presence of progression or absence of response? Alternative trial designs for immunotherapy of advanced hepatocellular carcinoma. Authors' reply

This article is linked to Jost‐Brinkmann et al papers. To view these articles, visit https://doi.org/10.1111/apt.17441 and https://doi.org/10.1111/apt.17985

Novel candidate genes for environmental stresses response in Synechocystis sp. PCC 6803 revealed by machine learning algorithms

Cyanobacteria have developed acclimation strategies to adapt to harsh environments, making them a model organism. Understanding the molecular mechanisms of tolerance to abiotic stresses can help elucidate how cells change their gene expression patterns in response to stress. Recent advances in sequencing techniques and bioinformatics analysis methods have led to the discovery of many genes involved in stress response in organisms. The Synechocystis sp. PCC 6803 is a suitable microorganism for studying transcriptome response under environmental stress. Therefore, for the first time, we employed two effective feature selection techniques namely and support vector machine recursive feature elimination (SVM-RFE) and LASSO (Least Absolute Shrinkage Selector Operator) to pinpoint the crucial genes responsive to environmental stresses in Synechocystis sp. PCC 6803. We applied these algorithms of machine learning to analyze the transcriptomic data of Synechocystis sp. PCC 6803 under distinct conditions, encompassing light, salt and iron stress conditions. Seven candidate genes namely sll1862, slr0650, sll0760, slr0091, ssl3044, slr1285, and slr1687 were selected by both LASSO and SVM-RFE algorithms. RNA-seq analysis was performed to validate the efficiency of our feature selection approach in selecting the most important genes. The RNA-seq analysis revealed significantly high expression for five genes namely sll1862, slr1687, ssl3044, slr1285, and slr0650 under ion stress condition. Among these five genes, ssl3044 and slr0650 could be introduced as new potential candidate genes for further confirmatory genetic studies, to determine their roles in their response to abiotic stresses.

Cellular senescence gene TACC3 associated with colorectal cancer risk via genetic and DNA methylated alteration

Cell senescence genes play a vital role in the pathogenesis of colorectal cancer, a process that may involve the triggering of genetic variations and reversible phenotypes caused by epigenetic modifications. However, the specific regulatory mechanisms remain unclear. Using CellAge and The Cancer Genome Atlas databases and in-house RNA-seq data, DNA methylation-modified cellular senescence genes (DMCSGs) were validated by Support Vector Machine and correlation analyses. In 1150 cases and 1342 controls, we identified colorectal cancer risk variants in DMCSGs. The regulatory effects of gene, variant, and DNA methylation were explored through dual-luciferase and 5-azacytidine treatment experiments, complemented by multiple database analyses. Biological functions of key gene were evaluated via cell proliferation assays, SA-β-gal staining, senescence marker detection, and immune infiltration analyses. The genetic variant rs4558926 in the downstream of TACC3 was significantly associated with colorectal cancer risk (OR = 1.35, P = 3.22 × 10-4). TACC3 mRNA expression increased due to rs4558926 C > G and decreased DNA methylation levels. The CpG sites in the TACC3 promoter region were regulated by rs4558926. TACC3 knockdown decreased proliferation and senescence in colorectal cancer cells. In addition, subjects with high-TACC3 expression presented an immunosuppressive microenvironment. These findings provide insights into the involvement of genetic variants of cellular senescence genes in the development and progression of colorectal cancer.

Application of artificial intelligence in the prediction of immunotherapy efficacy in hepatocellular carcinoma: Current status and prospects

Artificial Intelligence (AI) has increased as a potent tool in medicine, with promising oncology applications. The emergence of immunotherapy has transformed the treatment terrain for hepatocellular carcinoma (HCC), offering new hope to patients with this challenging malignancy. This article examines the role and future of AI in forecasting the effectiveness of immunotherapy in HCC. We highlight the potential of AI to revolutionize the prediction of therapy response, thus improving patient selection and clinical outcomes. The article further outlines the challenges and future research directions in this emerging field.

Up-regulation of RAN by MYBL2 maintains osteosarcoma cancer stem-like cells population during heterogeneous tumor generation

Intratumor heterogeneity is one of the major features of cancers, leading to aggressive disease and treatment failure. Cancer stem-like cells (CSCs) are believed to give rise to the heterogeneous cell types within tumors. Hence, understanding the regulatory mechanism underlying the recurrence process of heterogeneous tumor by CSCs could facilitate the development of CSC-targeted therapies. Here, utilizing single-cell transcriptomics, we present the molecular profile of osteosarcoma CSCs-derived heterogeneous tumors consisting of CSC clusters, osteoprogenitor and differentiated cell types, such as pre-osteoblasts, osteoblasts and chondroblasts. Furthermore, by constructing the comprehensive map of modulated genes during CSCs self-renewal and differentiation, we identify RAN exhibiting specific peak expression in osteosarcoma CSCs clusters which is transcriptionally up-regulated by MYBL2. Functionality, MYBL2-RAN pathway promotes the CSCs self-renewal by enhancing the nuclear accumulation of MYC protein, which in turn boosts the overexpression of RAN as a positive feedback. Importantly, blockage of MYBL2-RAN pathway sensitizes CSCs to cisplatin treatment and synergistically enhanced the cisplatin-induced cytotoxicity. Both MYBL2 and RAN are highly expressed in clinical osteosarcoma tissues which indicate poor prognosis. Collectively, our study provides advanced insights into the regeneration process of heterogeneous tumor originating from CSCs and highlights the MYBL2-RAN pathway as a promising target for CSC-based therapy in osteosarcoma.

Creation of a machine learning-based prognostic prediction model for various subtypes of laryngeal cancer

Depending on the source of the blastophore, there are various subtypes of laryngeal cancer, each with a unique metastatic risk and prognosis. The forecasting of their prognosis is a pressing issue that needs to be resolved. This study comprised 5953 patients with glottic carcinoma and 4465 individuals with non-glottic type (supraglottic and subglottic). Five clinicopathological characteristics of glottic and non-glottic carcinoma were screened using univariate and multivariate regression for CoxPH (Cox proportional hazards); for other models, 10 (glottic) and 11 (non-glottic) clinicopathological characteristics were selected using least absolute shrinkage and selection operator (LASSO) regression analysis, respectively; the corresponding survival models were established; and the best model was evaluated. We discovered that RSF (Random survival forest) was a superior model for both glottic and non-glottic carcinoma, with a projected concordance index (C-index) of 0.687 for glottic and 0.657 for non-glottic, respectively. The integrated Brier score (IBS) of their 1-year, 3-year, and 5-year time points is, respectively, 0.116, 0.182, 0.195 (glottic), and 0.130, 0.215, 0.220 (non-glottic), demonstrating the model's effective correction. We represented significant variables in a Shapley Additive Explanations (SHAP) plot. The two models are then combined to predict the prognosis for two distinct individuals, which has some effectiveness in predicting prognosis. For our investigation, we established separate models for glottic carcinoma and non-glottic carcinoma that were most effective at predicting survival. RSF is used to evaluate both glottic and non-glottic cancer, and it has a considerable impact on patient prognosis and risk factor prediction.

Fine particulate matter (PM2.5) induces the stem cell-like properties of hepatocellular carcinoma by activating ROS/Nrf2/Keap1-mediated autophagy

Exposure to fine particulate matter (PM2.5) has been linked to an increased incidence and mortality of hepatocellular carcinoma (HCC). However, the impact of PM2.5 exposure on HCC progression and the underlying mechanisms remain largely unknown. This study aimed to investigate the effects of PM2.5 exposure on the stem cell-like properties of HCC cells. Our findings indicate that PM2.5 exposure significantly enhances the stemness of HCC cells (p < 0.01). Subsequently, male nude mice were divided into two groups (n = 8/group for tumor-bearing assay, n = 5/group for metastasis assay) for control and PM2.5 exposure. In vivo assays revealed that exposure to PM2.5 promoted the growth, metastasis, and epithelial-mesenchymal transition (EMT) of HCC cells (p < 0.01). Further exploration demonstrated that PM2.5 enhances the stemness of HCC cells by inducing cellular reactive oxygen species (ROS) generation (p < 0.05). Mechanistic investigation indicated that elevated intracellular ROS inhibited kelch-like ECH-associated protein 1 (Keap1) levels, promoting the upregulation and nucleus translocation of NFE2-like bZIP transcription factor 2 (Nrf2). This, in turn, induced autophagy activation, thereby promoting the stemness of HCC cells (p < 0.01). Our present study demonstrates the adverse effects of PM2.5 exposure on HCC development and highlights the mechanism of ROS/Nrf2/Keap1-mediated autophagy. For the first time, we reveal the impact of PM2.5 exposure on the poor prognosis-associated cellular phenotype of HCC and its underlying mechanism, which is expected to provide new theoretical basis for the improvement of public health.

Long non-coding RNAFOXD1-AS1 modulated CTCs epithelial-mesenchymal transition and immune escape in hepatocellular carcinoma in vitro by sponging miR-615-3p

BACKGROUND

Hepatocellular carcinoma (HCC) is widely recognized as a globally prevalent malignancy. Immunotherapy is a promising therapy for HCC patients. Increasing evidence suggests that lncRNAs are involved in HCC progression and immunotherapy.

AIM

The study reveals the mechanistic role of long non-coding RNA (lncRNA) FOXD1-AS1 in regulating migration, invasion, circulating tumor cells (CTCs), epithelial-mesenchymal transition (EMT), and immune escape in HCC in vitro.

METHODS

This study employed real-time PCR (RT-qPCR) to measure FOXD1-AS1, miR-615-3p, and programmed death-ligand 1 (PD-L1). The interactions of FOXD1-AS1, miR-615-3p, and PD-L1 were validated via dual-luciferase reporter gene and ribonucleoprotein immunoprecipitation (RIP) assay. In vivo experimentation involves BALB/c mice and BALB/c nude mice to investigate the impact of HCC metastasis.

RESULTS

The upregulation of lncRNA FOXD1-AS1 in malignant tissues significantly correlates with poor prognosis. The investigation was implemented on the impact of lncRNA FOXD1-AS1 on the migratory, invasive, and EMT of HCC cells. It has been observed that the lncRNA FOXD1-AS1 significantly influences the generation and metastasis of MCTC in vivo analysis. In mechanistic analysis, lncRNA FOXD1-AS1 enhanced immune escape in HCC via upregulation of PD-L1, which acted as a ceRNA by sequestering miR-615-3p. Additionally, lncRNA FOXD1-AS1 was found to modulate the EMT of CTCs through the activation of the PI3K/AKT pathway.

CONCLUSION

This study presents compelling evidence supporting the role of lncRNA FOXD1-AS1 as a miRNA sponge that sequesters miR-655-3p and protects PD-L1 from suppression.

Identification and validation of CCR5 linking keloid with atopic dermatitis through comprehensive bioinformatics analysis and machine learning

There is sufficient evidence indicating that keloid is strongly associated with atopic dermatitis (AD) across ethnic groups. However, the molecular mechanism underlying the association is not fully understood. The aim of this study is to discover the underlying mechanism of the association between keloid and AD by integrating comprehensive bioinformatics techniques and machine learning methods. The gene expression profiles of keloid and AD were downloaded from the Gene Expression Omnibus (GEO) database. A total of 449 differentially expressed genes (DEGs) were found to be shared in keloid and AD using the training datasets of GEO (GSE158395 and GSE121212). The hub genes were identified using the protein-protein interaction network and Cytoscape software. 20 of the most significant hub genes were selected, which were mainly involved in the regulation of the inflammatory and immune response. Through two machine learning algorithms of LASSO and SVM-RFE, CCR5 was identified as the most important key gene. Subsequently, upregulated CCR5 gene expression was confirmed in validation GEO datasets (GSE188952 and GSE32924) and clinical samples of keloid and AD. Immune infiltration analysis showed that T helper (Th) 1, 2 and 17 cells were significantly enriched in the microenvironment of both keloid and AD. Positive correlations were found between CCR5 and Th1, Th2 and Th17 cells. Finally, two TFs of CCR5, NR3C2 and YY1, were identified, both of which were downregulated in keloid and AD tissues. Our study firstly reveals that keloid and AD shared common inflammatory and immune pathways. Moreover, CCR5 plays a key role in the pathogenesis association between keloid and AD. The common pathways and key genes may shed light on further mechanism research and targeted therapy, and may provide therapeutic interventions of keloid with AD.

Signature construction and molecular subtype identification based on liver-specific genes for prediction of prognosis, immune activity, and anti-cancer drug sensitivity in hepatocellular carcinoma

BACKGROUND

Liver specific genes (LSGs) are crucial for hepatocyte differentiation and maintaining normal liver function. A deep understanding of LSGs and their heterogeneity in hepatocellular carcinoma (HCC) is necessary to provide clues for HCC diagnosis, prognosis, and treatment.

METHODS

The bulk and single-cell RNA-seq data of HCC were downloaded from TCGA, ICGC, and GEO databases. Through unsupervised cluster analysis, LSGs-based HCC subtypes were identified in TCGA-HCC samples. The prognostic effects of the subtypes were investigated with survival analyses. With GSVA and Wilcoxon test, the LSGs score, stemness score, aging score, immune score and stromal score of the samples were estimated and compared. The HCC subtype-specific genes were identified. The subtypes and their differences were validated in ICGC-HCC samples. LASSO regression analysis was used for key gene selection and risk model construction for HCC overall survival. The model performance was estimated and validated. The key genes were validated for their heterogeneities in HCC cell lines with quantitative real-time PCR and at single-cell level. Their dysregulations were investigated at protein level. Their correlations with HCC response to anti-cancer drugs were estimated in HCC cell lines.

RESULTS

We identified three LSGs-based HCC subtypes with different prognosis, tumor stemness, and aging level. The C1 subtype with low LSGs score and high immune score presented a poor survival, while the C2 subtype with high LSGs score and immune score indicated an enduring survival. Although no significant survival difference between C2 and C3 HCCs was shown, the C2 HCCs presented higher immune score and stroma score. The HCC subtypes and their differences were confirmed in ICGC-HCC dataset. A five-gene prognostic signature for HCC survival was constructed. Its good performance was shown in both the training and validation datasets. The five genes presented significant heterogeneities in different HCC cell lines and hepatocyte subclusters. Their dysregulations were confirmed at protein level. Furthermore, their significant associations with HCC sensitivities to anti-cancer drugs were shown.

CONCLUSIONS

LSGs-based HCC subtype classification and the five-gene risk model might provide useful clues not only for HCC stratification and risk prediction, but also for the development of more personalized therapies for effective HCC treatment.

Prognostic Factors for Mortality in Hepatocellular Carcinoma at Diagnosis: Development of a Predictive Model Using Artificial Intelligence

BACKGROUND

Hepatocellular carcinoma (HCC) accounts for 75% of primary liver tumors. Controlling risk factors associated with its development and implementing screenings in risk populations does not seem sufficient to improve the prognosis of these patients at diagnosis. The development of a predictive prognostic model for mortality at the diagnosis of HCC is proposed.

METHODS

In this retrospective multicenter study, the analysis of data from 191 HCC patients was conducted using machine learning (ML) techniques to analyze the prognostic factors of mortality that are significant at the time of diagnosis. Clinical and analytical data of interest in patients with HCC were gathered.

RESULTS

Meeting Milan criteria, Barcelona Clinic Liver Cancer (BCLC) classification and albumin levels were the variables with the greatest impact on the prognosis of HCC patients. The ML algorithm that achieved the best results was random forest (RF).

CONCLUSIONS

The development of a predictive prognostic model at the diagnosis is a valuable tool for patients with HCC and for application in clinical practice. RF is useful and reliable in the analysis of prognostic factors in the diagnosis of HCC. The search for new prognostic factors is still necessary in patients with HCC.

Diagnostic potential of NRG1 in benign nerve sheath tumors and its influence on the PI3K-Akt signaling and tumor immunity

OBJECTIVE

Benign nerve sheath tumors (BNSTs) present diagnostic challenges due to their heterogeneous nature. This study aimed to determine the significance of NRG1 as a novel diagnostic biomarker in BNST, emphasizing its involvement in the PI3K-Akt pathway and tumor immune regulation.

METHODS

Differential genes related to BNST were identified from the GEO database. Gene co-expression networks, protein-protein interaction networks, and LASSO regression were utilized to pinpoint key genes. The CIBERSORT algorithm assessed immune cell infiltration differences, and functional enrichment analyses explored BNST signaling pathways. Clinical samples helped establish PDX models, and in vitro cell lines to validate NRG1's role via the PI3K-Akt pathway.

RESULTS

Nine hundred eighty-two genes were upregulated, and 375 downregulated in BNST samples. WGCNA revealed the brown module with the most significant difference. Top hub genes included NRG1, which was also determined as a pivotal gene in disease characterization. Immune infiltration showed significant variances in neutrophils and M2 macrophages, with NRG1 playing a central role. Functional analyses confirmed NRG1's involvement in key pathways. Validation experiments using PDX models and cell lines further solidified NRG1's role in BNST.

CONCLUSION

NRG1 emerges as a potential diagnostic biomarker for BNST, influencing the PI3K-Akt pathway, and shaping the tumor immune microenvironment.

Integrated bioinformatics analysis of SEMA3C in tongue squamous cell carcinoma using machine-learning strategies

Tongue squamous cell carcinoma (TSCC) is an aggressive oral cancer with a high incidence of metastasis and poor prognosis. We aim to identify and verify potential biomarkers for TSCC using bioinformatics analysis. To begin with, we examined clinical and RNA expression information of individuals with TSCC from the Gene Expression Omnibus (GEO) database. Differential expression analysis and functional analysis were conducted. Multiple machine-learning strategies were next employed to screen and determine the hub gene, and receiver operating characteristic (ROC) analysis was used to assess diagnostic value. Semaphorin3C (SEMA3C) was identified as a critical biomarker, presenting high diagnostic accuracy for TSCC. In the validation cohorts, SEMA3C exhibited high expression levels in TSCC. The high expression of SEMA3C was a poor prognostic factor in TSCC by the Kaplan-Meier curve. Based on the Gene Ontology (GO) analysis, SEMA3C was mapped in terms related to cell adhesion, positive regulation of JAK-STAT, positive regulation of stem cell maintenance, and positive regulation of NF-κB activity. Single-cell RNA sequencing (ScRNA-seq) analysis showed cells expressing SEMA3C were predominantly tumor cells. Then, we further verified that SEMA3C had high expression in TSCC clinical samples. In addition, the knockdown of SEMA3C suppressed the proliferation, migration, and invasion of TSCC cells in vitro. This study is the first to report the involvement of SEMA3C in TSCC, suggesting that upregulated SEMA3C could be a novel and critical potential biomarker for future predictive diagnostics, prevention, prognostic assessment, and personalized medical services in TSCC.

Development and validation of a novel stemness-related prognostic model for neuroblastoma using integrated machine learning and bioinformatics analyses

Background

Neuroblastoma (NB) is a common solid tumor in children, with a dismal prognosis in high-risk cases. Despite advancements in NB treatment, the clinical need for precise prognostic models remains critical, particularly to address the heterogeneity of cancer stemness which plays a pivotal role in tumor aggressiveness and patient outcomes. By utilizing machine learning (ML) techniques, we aimed to explore the cancer stemness features in NB and identify stemness-related hub genes for future investigation and potential targeted therapy.

Methods

The public dataset GSE49710 was employed as the training set for acquire gene expression data and NB sample information, including age, stage, and MYCN amplification status and survival. The messenger RNA (mRNA) expression-based stemness index (mRNAsi) was calculated and patients were grouped according to their mRNAsi value. Stemness-related hub genes were identified from the differentially expressed genes (DEGs) to construct a gene signature. This was followed by evaluating the relationship between cancer stemness and the NB immune microenvironment, and the development of a predictive nomogram. We assessed the prognostic outcomes including overall survival (OS) and event-free survival, employing machine learning methods to measure predictive accuracy through concordance indices and validation in an independent cohort E-MTAB-8248.

Results

Based on mRNAsi, we categorized NB patients into two groups to explore the association between varying levels of stemness and their clinical outcomes. High mRNAsi was linked to the advanced International Neuroblastoma Staging System (INSS) stage, amplified MYCN, and elder age. High mRNAsi patients had a significantly poorer prognosis than low mRNAsi cases. According to the multivariate Cox analysis, the mRNAsi was an independent risk factor of prognosis in NB patients. After least absolute shrinkage and selection operator (LASSO) regression analysis, four key genes (ERCC6L, DUXAP10, NCAN, DIRAS3) most related to mRNAsi scores were discovered and a risk model was built. Our model demonstrated a significant prognostic capacity with hazard ratios (HR) ranging from 18.96 to 41.20, P values below 0.0001, and area under the receiver operating characteristic curve (AUC) values of 0.918 in the training set, suggesting high predictive accuracy which was further confirmed by external verification. Individuals with a low four-gene signature score had a favorable outcome and better immune responses. Finally, a nomogram for clinical practice was constructed by integrating the four-gene signature and INSS stage.

Conclusions

Our findings confirm the influence of CSC features in NB prognosis. The newly developed NB stemness-related four-gene signature prognostic signature could facilitate the prognostic prediction, and the identified hub genes may serve as promising targets for individualized treatments.

Application of data science and bioinformatics in RNA therapeutics

Nowadays, information technology (IT) has been holding a significant role in daily life worldwide. The trajectory of data science and bioinformatics promises pioneering personalized therapies, reshaping medical landscapes and patient care. For RNA therapy to reach more patients, a comprehensive understanding of the application of data science and bioinformatics to this therapy is essential. Thus, this chapter has summarized the application of data science and bioinformatics in RNA therapeutics. Data science applications in RNA therapy, such as data integration and analytics, machine learning, and drug development, have been discussed. In addition, aspects of bioinformatics such as RNA design and evaluation, drug delivery system simulation, and databases for personalized medicine have also been covered in this chapter. These insights have shed light on existing evidence and opened potential future directions. From there, scientists can elevate RNA-based therapeutics into an era of tailored treatments and revolutionary healthcare.

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

ChatGPT in Occupational Medicine: A Comparative Study with Human Experts

The objective of this study is to evaluate ChatGPT's accuracy and reliability in answering complex medical questions related to occupational health and explore the implications and limitations of AI in occupational health medicine. The study also provides recommendations for future research in this area and informs decision-makers about AI's impact on healthcare. A group of physicians was enlisted to create a dataset of questions and answers on Italian occupational medicine legislation. The physicians were divided into two teams, and each team member was assigned a different subject area. ChatGPT was used to generate answers for each question, with/without legislative context. The two teams then evaluated human and AI-generated answers blind, with each group reviewing the other group's work. Occupational physicians outperformed ChatGPT in generating accurate questions on a 5-point Likert score, while the answers provided by ChatGPT with access to legislative texts were comparable to those of professional doctors. Still, we found that users tend to prefer answers generated by humans, indicating that while ChatGPT is useful, users still value the opinions of occupational medicine professionals.

Online COVID-19 diagnosis prediction using complete blood count: an innovative tool for public health

BACKGROUND

COVID-19, caused by SARS-CoV-2, presents distinct diagnostic challenges due to its wide range of clinical manifestations and the overlapping symptoms with other common respiratory diseases. This study focuses on addressing these difficulties by employing machine learning (ML) methodologies, particularly the XGBoost algorithm, to utilize Complete Blood Count (CBC) parameters for predictive analysis.

METHODS

We performed a retrospective study involving 2114 COVID-19 patients treated between December 2022 and January 2023 at our healthcare facility. These patients were classified into fever (1057 patients) and pneumonia groups (1057 patients), based on their clinical symptoms. The CBC data were utilized to create predictive models, with model performance evaluated through metrics like Area Under the Receiver Operating Characteristics Curve (AUC), accuracy, sensitivity, specificity, and precision. We selected the top 10 predictive variables based on their significance in disease prediction. The data were then split into a training set (70% of patients) and a validation set (30% of patients) for model validation.

RESULTS

We identified 31 indicators with significant disparities. The XGBoost model outperformed others, with an AUC of 0.920 and high precision, sensitivity, specificity, and accuracy. The top 10 features (Age, Monocyte%, Mean Platelet Volume, Lymphocyte%, SIRI, Eosinophil count, Platelet count, Hemoglobin, Platelet Distribution Width, and Neutrophil count.) were crucial in constructing a more precise predictive model. The model demonstrated strong performance on both training (AUC = 0.977) and validation (AUC = 0.912) datasets, validated by decision curve analysis and calibration curve.

CONCLUSION

ML models that incorporate CBC parameters offer an innovative and effective tool for data analysis in COVID-19. They potentially enhance diagnostic accuracy and the efficacy of therapeutic interventions, ultimately contributing to a reduction in the mortality rate of this infectious disease.

WGCNA combined with machine learning to find potential biomarkers of liver cancer

The incidence of hepatocellular carcinoma (HCC) has been increasing in recent years. With the development of various detection technologies, machine learning is an effective method to screen disease characteristic genes. In this study, weighted gene co-expression network analysis (WGCNA) and machine learning are combined to find potential biomarkers of liver cancer, which provides a new idea for future prediction, prevention, and personalized treatment. In this study, the "limma" software package was used. P < .05 and log2 |fold-change| > 1 is the standard screening differential genes, and then the module genes obtained by WGCNA analysis are crossed to obtain the key module genes. Gene Ontology and Kyoto Gene and Genome Encyclopedia analysis was performed on key module genes, and 3 machine learning methods including lasso, support vector machine-recursive feature elimination, and RandomForest were used to screen feature genes. Finally, the validation set was used to verify the feature genes, the GeneMANIA (http://www.genemania.org) database was used to perform protein-protein interaction networks analysis on the feature genes, and the SPIED3 database was used to find potential small molecule drugs. In this study, 187 genes associated with HCC were screened by using the "limma" software package and WGCNA. After that, 6 feature genes (AADAT, APOF, GPC3, LPA, MASP1, and NAT2) were selected by RandomForest, Absolute Shrinkage and Selection Operator, and support vector machine-recursive feature elimination machine learning algorithms. These genes are also significantly different on the external dataset and follow the same trend as the training set. Finally, our findings may provide new insights into targets for diagnosis, prevention, and treatment of HCC. AADAT, APOF, GPC3, LPA, MASP1, and NAT2 may be potential genes for the prediction, prevention, and treatment of liver cancer in the future.

Targeting NAD+ metabolism of hepatocellular carcinoma cells by lenvatinib promotes M2 macrophages reverse polarization, suppressing the HCC progression

BACKGROUND

Lowered nicotinamide adenine dinucleotide (NAD+) levels in tumor cells drive tumor hyperprogression during immunotherapy, and its restoration activates immune cells. However, the effect of lenvatinib, a first-line treatment for unresectable hepatocellular carcinoma (HCC), on NAD+ metabolism in HCC cells, and the metabolite crosstalk between HCC and immune cells after targeting NAD+ metabolism of HCC cells remain unelucidated.

METHODS

Liquid chromatography-tandem mass spectrometry (LC-MS/MS) and ultra-high-performance liquid chromatography multiple reaction monitoring-mass spectrometry (UHPLC-MRM-MS) were used to detect and validate differential metabolites. RNA sequencing was used to explore mRNA expression in macrophages and HCC cells. HCC mouse models were used to validate the effects of lenvatinib on immune cells and NAD+ metabolism. The macrophage properties were elucidated using cell proliferation, apoptosis, and co-culture assays. In silico structural analysis and interaction assays were used to determine whether lenvatinib targets tet methylcytosine dioxygenase 2 (TET2). Flow cytometry was performed to assess changes in immune cells.

RESULTS

Lenvatinib targeted TET2 to synthesize and increase NAD+ levels, thereby inhibiting decomposition in HCC cells. NAD+ salvage increased lenvatinib-induced apoptosis of HCC cells. Lenvatinib also induced CD8+ T cells and M1 macrophages infiltration in vivo. And lenvatinib suppressed niacinamide, 5-Hydroxy-L-tryptophan and quinoline secretion of HCC cells, and increased hypoxanthine secretion, which contributed to proliferation, migration and polarization function of macrophages. Consequently, lenvatinib targeted NAD+ metabolism and elevated HCC-derived hypoxanthine to enhance the macrophages polarization from M2 to M1. Glycosaminoglycan binding disorder and positive regulation of cytosolic calcium ion concentration were characteristic features of the reverse polarization.

CONCLUSIONS

Targeting HCC cells NAD+ metabolism by lenvatinib-TET2 pathway drives metabolite crosstalk, leading to M2 macrophages reverse polarization, thereby suppressing HCC progression. Collectively, these novel insights highlight the role of lenvatinib or its combination therapies as promising therapeutic alternatives for HCC patients with low NAD+ levels or high TET2 levels.

Identification of Molecular Markers Predicting the Outcome of Anti-thrombotic Therapy After Percutaneous Coronary Intervention in Patients with Acute Coronary Syndrome and Atrial fibrillation: Evidence from a Meta-analysis and Experimental Study

Acute coronary syndrome (ACS) and atrial fibrillation (AF) often coexist in clinical practice, and patients with these conditions often have a critical illness with high risk of both ischemia and bleeding. This study aims to report potential molecular markers for predicting the efficacy based on a meta-analysis of microarray data from the GEO database. In 40 patients with acute coronary syndrome (ACS) and atrial fibrillation (AF) treated with PCI, P2RX1's effects on platelet aggregation, medication resistance, and predictive value were examined. Twenty up-regulated genes in peripheral blood samples of ACS and AF patients were down-regulated after PCI, while 7 down-regulated genes were up-regulated. ACS affected eight potential genes. P2RX1, one of the four LASSO analysis-retrieved disease characteristic genes, accurately predicted AF patients' thrombosis risk and PCI's anti-thrombotic impact. Therefore, P2RX1 may be a molecular marker to predict the effect of anti-thrombotic therapy in patients with ACS and AF after PCI.

Network pharmacology and bioinformatics to identify the molecular mechanisms of Gleditsiae Spina against colorectal cancer

Objective

In this study, network pharmacology, bioinformatics and molecular docking were used to explore the active phytochemicals, hub genes, and potential molecular mechanisms of Gleditsiae Spina in treating of colorectal cancer..

Methods

The targets of Gleditsiae Spina, and targets related to CRC were derived from databases. We identified the hub genes for Gleditsiae Spina anti-colorectal cancer following the protein-protein-interaction (PPI) network. Furthermore, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment were used to analyze the hub genes from a macro perspective. Finally, we verified the hub genes by molecular docking, GEPIA, HPA, and starBase database.

Results

We identified nine active phytochemicals and 36 intersection targets. The GO enrichment analysis results showed that Gleditsiae Spina may be involved in gene targets affecting multiple biological processes, including response to radiation, response to ionizing radiation, cyclin-dependent protein kinase holoenzyme complex, serine/threonine protein kinase complex, cyclin-dependent protein serine/threonine kinase regulator activity and protein kinase regulator activity. KEGG enrichment analysis results indicated that the P53 signaling pathway, IL-17 signaling pathway, Toll-like receptor signaling pathway, PI3K-Akt signaling pathway, and JAK-STAT signaling pathway were mainly related to the effect of Gleditsiae Spina on colorectal cancer. Molecular docking analysis suggested that the active phytochemicals of Gleditsiae Spina could combine well with hub genes (PTGS1, PIK3CG, CCND1, CXCL8 and ADRB2).

Conclusion

This study provides clues for further study of anti-CRC phytochemicals as well as their mechanisms of provides a basis for their development model.

Stemness signature and targeted therapeutic drugs identification for Triple Negative Breast Cancer

Triple-negative breast cancer (TNBC) is the most aggressive subtype of breast cancer and carries the worst prognosis, characterized by the lack of progesterone, estrogen, and HER2 gene expression. This study aimed to analyze cancer stemness-related gene signature to determine patients' risk stratification and prognosis feature with TNBC. Here one-class logistic regression (OCLR) algorithm was applied to compute the stemness index of TNBC patients. Cox and LASSO regression analysis was performed on stemness-index related genes to establish 16 genes-based prognostic signature, and their predictive performance was verified in TCGA and METABERIC merged data cohort. We diagnosed the expression level of prognostic genes signature in the tumor immune microenvironment, analyzed the TNBC scRNA-seq GSE176078 dataset, and further validated the expression level of prognostic genes using the HPA database. Finally, the small molecular compounds targeted at the anti-tumor effect of predictive genes were screened by molecular docking; this novel stemness-based prognostic genes signature study could facilitate the prognosis of patients with TNBC and thus provide a feasible therapeutic target for TNBC.

Prognostic clinical phenotypes associated with tumor stemness in the immune microenvironment of T-cell exhaustion for hepatocellular carcinoma

T-cell exhaustion (TEX) and high heterogeneity of cancer stem cells (CSCs) are associated with progression, metastasis, and treatment resistance in hepatocellular carcinoma (HCC). Here, we aim to characterize TEX-stemness-related genes (TEXSRGs) and screen for HCC patients who are more sensitive to immunotherapy. The immune cell abundance identifier (ImmuCellAI) was utilized to precisely evaluate the abundance of TEX and screen TEX-related genes. The stemness index (mRNAsi) of samples was analyzed through the one-class logistic regression (OCLR) algorithm. Application of the non-negative matrix decomposition algorithm (NMF) for subtype identification of HCC samples. The different subtypes were assessed for differences in prognosis, tumor microenvironment (TME) landscape, and immunotherapy treatment response. Then, the TEXSRGS-score, which can accurately forecast the survival outcome of HCC patients, was built by LASSO-Cox and multivariate Cox regression, and experimentally validated for the most important TEXSRGs. We also analyzed the expression of TEXSRGs and the infiltration of CD8+ T cells in clinical samples using qRT-PCR and immunohistochemistry (IHC). Based on 146 TEXSRGs, we found two distinct clinical phenotypes with different TEX infiltration abundance, tumor stemness index, enrichment pathways, mutational landscape, and immune cell infiltration through the non-negative matrix decomposition algorithm (NMF), which were confirmed in the ICGC dataset. Utilizing eight TEXSRGs linked to clinical outcome, we created a TEXSRGs-score model to further improve the clinical applicability. Patients can be divided into two groups with substantial differences in the characteristics of immune cell infiltration, TEX infiltration abundance, and survival outcomes. The results of qRT-PCR and IHC analysis showed that PAFAH1B3, ZIC2, and ESR1 were differentially expressed in HCC and normal tissues and that patients with high TEXSRGs-scores had higher TEX infiltration abundance and tumor stemness gene expression. Regarding immunotherapy reaction and immune cell infiltration, patients with various TEXSRGs-score levels had various clinical traits. The outcome and immunotherapy efficacy of patients with low TEXSRGs-score was favorable. In conclusion, we identified two clinical subtypes with different prognoses, TEX infiltration abundance, tumor cell stemness index, and immunotherapy response based on TEXSRGs, and developed and validated a TEXSRGs-score capable of accurately predicting survival outcomes in HCC patients by comprehensive bioinformatics analysis. We believe that the TEXSRGs-score has prospective clinical relevance for prognostic assessment and may help physicians select prospective responders in preference to current immune checkpoint inhibitors (ICIs).

Machine learning-based prediction models for parathyroid carcinoma using pre-surgery cognitive function and clinical features

Patients with parathyroid carcinoma (PC) are often diagnosed postoperatively, due to incomplete resection during the initial surgery, resulting in poor outcomes. The aim of our study was to investigate the pre-surgery indicators of PC and try to develop a predictive model for PC utilizing machine learning. Evaluation of pre-surgery neuropsychological function and confirmation of pathology were carried out in 133 patients with primary hyperparathyroidism in Beijing Chaoyang Hospital from December 2019 to January 2023. Patients were randomly divided into a training cohort (n = 93) and a validating cohort (n = 40). Analysis of the clinical dataset, two machine learning including the extreme gradient boosting (XGBoost) and the least absolute shrinkage and selection operator (LASSO) regression were utilized to develop the prediction model for PC. Logistic regression analysis was also conducted for comparison. Significant differences in elevated parathyroid hormone and decreased serum phosphorus in PC compared to (BP). The lower score of MMSE and MOCA was observed in PC and a cutoff of MMSE < 24 was the optimal threshold to stratify PC from BP (area under the curve AUC 0.699 vs 0.625). The predicted probability of PC by machine learning was similar to the observed probability in the test set, whereas the logistic model tended to overpredict the possibility of PC. The XGBoost model attained a higher AUC than the logistic algorithms and LASSO models. (0.835 vs 0.683 vs 0.607). Preoperative cognitive function may be a probable predictor for PC. The cognitive function-based prediction model based on the XGBoost algorithm outperformed LASSO and logistic regression, providing valuable preoperative assistance to surgeons in clinical decision-making for patients suspected PC.

Machine Learning in Cardio-Oncology: New Insights from an Emerging Discipline

A growing body of evidence on a wide spectrum of adverse cardiac events following oncologic therapies has led to the emergence of cardio-oncology as an increasingly relevant interdisciplinary specialty. This also calls for better risk-stratification for patients undergoing cancer treatment. Machine learning (ML), a popular branch discipline of artificial intelligence that tackles complex big data problems by identifying interaction patterns among variables, has seen increasing usage in cardio-oncology studies for risk stratification. The objective of this comprehensive review is to outline the application of ML approaches in cardio-oncology, including deep learning, artificial neural networks, random forest and summarize the cardiotoxicity identified by ML. The current literature shows that ML has been applied for the prediction, diagnosis and treatment of cardiotoxicity in cancer patients. In addition, role of ML in gender and racial disparities for cardiac outcomes and potential future directions of cardio-oncology are discussed. It is essential to establish dedicated multidisciplinary teams in the hospital and educate medical professionals to become familiar and proficient in ML in the future.

Machine learning model of imipenem-resistant Klebsiella pneumoniae based on MALDI-TOF-MS platform: An observational study

Background and Aim

Machine learning is an important branch and supporting technology of artificial intelligence, we established four machine learning model for the drug sensitivity of Klebsiella pneumoniae to imipenem based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF-MS) and compared their diagnostic effect.

Methods

The data of MALDI-TOF-MS and imipenem sensitivity of 174 cases of K. pneumoniae isolated from clinical specimens in the laboratory of microbiology department of Tianjin Haihe Hospital from 2019 January to 2020 December were collected. The mass spectrometry and imipenem sensitivity of 70 cases of imipenem-sensitive and 70 resistant cases were randomly selected to establish the training set model, 17 cases of sensitive and 17 cases of resistant cases were randomly selected to establish the test set model. Mass spectral peak data were subjected to orthogonal partial least squares discriminant analysis (OPLS-DA), the training set data model was established by machine learning least absolute shrinkage and selection operator (LASSO) algorithm, logistic regression (LR) algorithm, support vector machines (SVM) algorithm, neural network (NN) algorithm, the area under the curve (AUC) and confusion matrix of training set and test set model were calculated and selected by Grid search and 3-fold Cross-validation respectively, the accuracy of the prediction model was verified by test set confusion matrix.

Results

The R²Y and Q² of OPLS-DA were 0.546 and 0.0178. The AUC of the best training set and test set models were 0.9726 and 0.9100, 1.0000 and 0.8581, 0.8462 and 0.6263, 1.0000 and 0.7180 evaluated by LASSO, LR, SVM and NN model respectively. The accuracy of the LASSO, LR, SVM and NN model were 87%, 79%, 62%, and 68% in test set, respectively.

Conclusion

The LASSO prediction model of K. pneumoniae sensitivity to imipenem established in this study has a high accuracy rate and has potential clinical decision support ability.

Unleashing the efficacy of immune checkpoint inhibitors for advanced hepatocellular carcinoma: factors, strategies, and ongoing trials

Hepatocellular carcinoma (HCC) is a prevalent primary liver cancer, representing approximately 85% of cases. The diagnosis is often made in the middle and late stages, necessitating systemic treatment as the primary therapeutic option. Despite sorafenib being the established standard of care for advanced HCC in the past decade, the efficacy of systemic therapy remains unsatisfactory, highlighting the need for novel treatment modalities. Recent breakthroughs in immunotherapy have shown promise in HCC treatment, particularly with immune checkpoint inhibitors (ICIs). However, the response rate to ICIs is currently limited to approximately 15%-20% of HCC patients. Recently, ICIs demonstrated greater efficacy in "hot" tumors, highlighting the urgency to devise more effective approaches to transform "cold" tumors into "hot" tumors, thereby enhancing the therapeutic potential of ICIs. This review presented an updated summary of the factors influencing the effectiveness of immunotherapy in HCC treatment, identified potential combination therapies that may improve patient response rates to ICIs, and offered an overview of ongoing clinical trials focusing on ICI-based combination therapy.

Refining Liver Biopsy in Hepatocellular Carcinoma: An In-Depth Exploration of Shifting Diagnostic and Therapeutic Applications

The field of hepatocellular carcinoma (HCC) has faced significant change on multiple levels in the past few years. The increasing emphasis on the various HCC phenotypes and the emergence of novel, specific therapies have slowly paved the way for a personalized approach to primary liver cancer. In this light, the role of percutaneous liver biopsy of focal lesions has shifted from a purely confirmatory method to a technique capable of providing an in-depth characterization of any nodule. Cancer subtype, gene expression, the mutational profile, and tissue biomarkers might soon become widely available through biopsy. However, indications, expectations, and techniques might suffer changes as the aim of the biopsy evolves from providing minimal proof of the disease to high-quality specimens for extensive analysis. Consequently, a revamped position of tissue biopsy is expected in HCC, following the reign of non-invasive imaging-only diagnosis. Moreover, given the advances in techniques that have recently reached the spotlight, such as liquid biopsy, concomitant use of all the available methods might gather just enough data to improve therapy selection and, ultimately, outcomes. The current review aims to discuss the changing role of liver biopsy and provide an evidence-based rationale for its use in the era of precision medicine in HCC.

Machine learning-based identification of glycosyltransferase-related mRNAs for improving outcomes and the anti-tumor therapeutic response of gliomas

Background: Glycosyltransferase participates in glycosylation modification, and glycosyltransferase alterations are involved in carcinogenesis, progression, and immune evasion, leading to poor outcomes. However, in-depth studies on the influence of glycosyltransferase on clinical outcomes and treatments are lacking. Methods: The analysis of differentially expressed genes was performed using the Gene Expression Profiling Interactive Analysis 2 database. A total of 10 machine learning algorithms were introduced, namely, random survival forest, elastic network, least absolute shrinkage and selection operator, Ridge, stepwise Cox, CoxBoost, partial least squares regression for Cox, supervised principal components, generalized boosted regression modeling, and survival support vector machine. Gene Set Enrichment Analysis was performed to explore signaling pathways regulated by the signature. Cell-type identification by estimating relative subsets of RNA transcripts was used for estimating the fractions of immune cell types. Results: Here, we analyzed the genomic and expressive alterations in glycosyltransferase-related genes in gliomas. A combination of 80 machine learning algorithms was introduced to establish the glycosyltransferase-related mRNA signature (GRMS) based on 2,030 glioma samples from The Cancer Genome Atlas Program, Chinese Glioma Genome Atlas, Rembrandt, Gravendeel, and Kamoun cohorts. The GRMS was identified as an independent hazardous factor for overall survival and exhibited stable and robust performance. Notably, gliomas in the high-GRMS subgroup exhibited abundant tumor-infiltrating lymphocytes and tumor mutation burden values, increased expressive levels of hepatitis A virus cellular receptor 2 and CD274, and improved progression-free survival when subjected to anti-tumor immunotherapy. Conclusion: The GRMS may act as a powerful and promising biomarker for improving the clinical prognosis of glioma patients.

Integrated analysis revealing a novel stemness-metabolism-related gene signature for predicting prognosis and immunotherapy response in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a malignant lethal tumor and both cancer stem cells (CSCs) and metabolism reprogramming have been proven to play indispensable roles in HCC. This study aimed to reveal the connection between metabolism reprogramming and the stemness characteristics of HCC, established a new gene signature related to stemness and metabolism and utilized it to assess HCC prognosis and immunotherapy response. The clinical information and gene expression profiles (GEPs) of 478 HCC patients came from the Gene Expression Omnibus (GEO) and the Cancer Genome Atlas (TCGA). The one-class logistic regression (OCLR) algorithm was employed to calculate the messenger ribonucleic acid expression-based stemness index (mRNAsi), a new stemness index quantifying stemness features. Differentially expressed analyses were done between high- and low-mRNAsi groups and 74 differentially expressed metabolism-related genes (DEMRGs) were identified with the help of metabolism-related gene sets from Molecular Signatures Database (MSigDB). After integrated analysis, a risk score model based on the three most efficient prognostic DEMRGs, including Recombinant Phosphofructokinase Platelet (PFKP), phosphodiesterase 2A (PDE2A) and UDP-glucuronosyltransferase 1A5 (UGT1A5) was constructed and HCC patients were divided into high-risk and low-risk groups. Significant differences were found in pathway enrichment, immune cell infiltration patterns, and gene alterations between the two groups. High-risk group patients tended to have worse clinical outcomes and were more likely to respond to immunotherapy. A stemness-metabolism-related model composed of gender, age, the risk score model and tumor-node-metastasis (TNM) staging was generated and showed great discrimination and strong ability in predicting HCC prognosis and immunotherapy response.

From Reductionistic Approach to Systems Immunology Approach for the Understanding of Tumor Microenvironment

The tumor microenvironment (TME) is a complex and dynamic ecosystem that includes a variety of immune cells mutually interacting with tumor cells, structural/stromal cells, and each other. The immune cells in the TME can have dual functions as pro-tumorigenic and anti-tumorigenic. To understand such paradoxical functions, the reductionistic approach classifies the immune cells into pro- and anti-tumor cells and suggests the therapeutic blockade of the pro-tumor and induction of the anti-tumor immune cells. This strategy has proven to be partially effective in prolonging patients' survival only in a fraction of patients without offering a cancer cure. Recent advances in multi-omics allow taking systems immunology approach. This essay discusses how a systems immunology approach could revolutionize our understanding of the TME by suggesting that internetwork interactions of the immune cell types create distinct collective functions independent of the function of each cellular constituent. Such collective function can be understood by the discovery of the immunological patterns in the TME and may be modulated as a therapeutic means for immunotherapy of cancer.

Prognosis prediction and comparison between pancreatic signet ring cell carcinoma and pancreatic duct adenocarcinoma: a retrospective observational study

Background

Pancreatic signet ring cell carcinoma (PSRCC) is a rare and aggressive cancer that has been reported primarily as case reports. Due to limited large-scale epidemiological and prognostic analyses, the outcomes of PSRCC patients varies greatly in the absence of recognized first-line treatment strategies. This study aimed to compare the clinical features, treatment, and prognosis of PSRCC and pancreatic ductal cell carcinoma (PDAC), the most common subtype of pancreatic cancer, and to establish predictive models for these subtypes.

Methods

The data on PSRCC and PDAC patients from 1998 to 2018 was obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Thereafter, the clinical, demographic, and treatment characteristics of the two groups and the differences and influencing factors of the two groups were evaluated by propensity score matching (PSM), Kaplan-Meier survival curves, Cox risk regression analyses, and least absolute shrinkage and selection operator (LASSO) analysis. Next, prognosis models were constructed and validated by KM and ROC analysis. Finally, a nomogram was constructed, based on the results of these analyses, to predict survival outcomes of PSRCC and PDAC patients.

Results

A total of 84,789 patients (432 PSRCC and 84357 PDAC patients) were included in this study. The results of the study revealed that, compared to the PDAC patients, PSRCC patients were more likely to be male, aged between 58-72 years, have larger tumor masses, and less likely to undergo chemotherapy. Before PSM, the overall survival and cancer-specific survival of the PSRCC group were significantly lower than those PDAC group, but there was no difference in the prognosis of the two groups after PSM. Additionally, lymph node ratio (LNR), log odds of positive lymph node (LODDS), tumor size, age, T-stage, marital status, and summary stage were found to be independent prognostic factors for PSRCC. Lastly, the prediction model and nomogram based on these prognostic factors could accurately predict the survival rate of the patients in SEER datasets and external validation datasets.

Conclusion

The prognosis of PSRCC and PDAC patients is similar under the same conditions; however, PSRCC patients may have more difficulty in receiving better treatment, thus resulting in their poor prognosis.

Early warning and diagnosis of liver cancer based on dynamic network biomarker and deep learning

Background

Early detection of complex diseases like hepatocellular carcinoma remains challenging due to their network-driven pathology. Dynamic network biomarkers (DNB) based on monitoring changes in molecular correlations may enable earlier predictions. However, DNB analysis often overlooks disease heterogeneity.

Methods

We integrated DNB analysis with graph convolutional neural networks (GCN) to identify critical transitions during hepatocellular carcinoma development in a mouse model. A DNB-GCN model was constructed using transcriptomic data and gene expression levels as node features.

Results

DNB analysis identified a critical transition point at 7 weeks of age despite histological examinations being unable to detect cancerous changes at that time point. The DNB-GCN model achieved 100% accuracy in classifying healthy and cancerous mice, and was able to accurately predict the health status of newly introduced mice.

Conclusion

The integration of DNB analysis and GCN demonstrates potential for the early detection of complex diseases by capturing network structures and molecular features that conventional biomarker discovery methods overlook. The approach warrants further development and validation.