A qualitative signature for early diagnosis of hepatocellular carcinoma based on relative expression orderings

Applications of gene pair methods in clinical research: advancing precision medicine

The rapid evolution of high-throughput sequencing technologies has revolutionized biomedical research, producing vast amounts of gene expression data that hold immense potential for biological discovery and clinical applications. Effectively mining these large-scale, high-dimensional data is crucial for facilitating disease detection, subtype differentiation, and understanding the molecular mechanisms underlying disease progression. However, the conventional paradigm of single-gene profiling, measuring absolute expression levels of individual genes, faces critical limitations in clinical implementation. These include vulnerability to batch effects and platform-dependent normalization requirements. In contrast, emerging approaches analyzing relative expression relationships between gene pairs demonstrate unique advantages. By focusing on binary comparisons of two genes' expression magnitudes, these methods inherently normalize experimental variations while capturing biologically stable interaction patterns. In this review, we systematically evaluate gene pair-based analytical frameworks. We classify eleven computational approaches into two fundamental categories: expression value-based methods quantifying differential expression patterns, and rank-based methods exploiting transcriptional ordering relationships. To bridge methodological development with practical implementation, we establish a reproducible analytical pipeline incorporating feature selection, classifier construction, and model evaluation modules using real-world benchmark datasets from pulmonary tuberculosis studies. These findings position gene pair analysis as a transformative paradigm for mining high-dimensional omics data, with direct implications for precision biomarker discovery and mechanistic studies of disease progression.

Bulk and single-cell transcriptome reveal the immuno-prognostic subtypes and tumour microenvironment heterogeneity in HCC

BACKGROUND & AIMS

Accumulating evidences suggest tumour microenvironment (TME) profoundly influence clinical outcome in hepatocellular carcinoma (HCC). Existing immune subtypes are susceptible to batch effects, and integrative analysis of bulk and single-cell transcriptome is helpful to recognize immune subtypes and TME in HCC.

METHODS

Based on the relative expression ordering (REO) of 1259 immune-related genes, an immuno-prognostic signature was developed and validated in 907 HCC samples from five bulk transcriptomic cohorts, including 72 in-house samples. The machine learning models based on subtype-specific gene pairs with stable REOs were constructed to jointly predict immuno-prognostic subtypes in single-cell RNA-seq data and validated in another single-cell data. Then, cancer characteristics, immune landscape, underlying mechanism and therapeutic benefits between subtypes were analysed.

RESULTS

An immune-related signature with 29 gene pairs stratified HCC samples individually into two risk subgroups (C1 and C2), which was an independent prognostic factor for overall survival. The machine learning models verified the immune subtypes from five bulk cohorts to two single-cell transcriptomic data. Integrative analysis revealed that C1 had poorer outcomes, higher CNV burden and malignant scores, higher sensitivity to sorafenib, and exhibited an immunosuppressive phenotype with more regulators, e.g., myeloid-derived suppressor cells (MDSCs), Mø_SPP1, while C2 was characterized with better outcomes, higher metabolism, more benefit from immunotherapy, and displayed active immune with more effectors, e.g., tumour infiltrating lymphocyte and dendritic cell. Moreover, both two single-cell data revealed the crosstalk of SPP1-related L-R pairs between cancer and immune cells, especially SPP1-CD44, might lead to immunosuppression in C1.

CONCLUSIONS

The REO-based immuno-prognostic subtypes were conducive to individualized prognosis prediction and treatment options for HCC. This study paved the way for understanding TME heterogeneity between immuno-prognostic subtypes of HCC.

A pyroptosis-related lncRNA-based prognostic index for hepatocellular carcinoma by relative expression orderings

Background

Hepatocellular carcinoma (HCC) is an invasive malignant tumor, and pyroptosis makes an important contribution to the pathology and progression of liver cancer. Many prognostic models have been proposed for HCC based on the quantitative expression level of candidate genes, which are unsuitable for clinical application due to their vulnerability against experimental batch effects. The aim of this study was to develop a novel pyroptosis-related long non-coding RNA (lncRNA)-based prognostic index (PLPI) for HCC based on relative expression orderings (REOs).

Methods

Firstly, the pyroptosis-related lncRNAs were identified through the Wilcoxon rank-sum test and gene co-expression analyses. Then, the novel prognostic model PLPI was constructed by pyroptosis-related lncRNA pairs, which were identified by multiple machine learning algorithms. Gene set enrichment, somatic mutation, and drug sensitivity analyses were conducted to measure the differences between high- and low-risk patients. Multiple immune analyses were used to explore the association between PLPI and the immunological microenvironment.

Results

In this study, a novel prognostic model PLPI based on 10 pyroptosis-related lncRNA pairs was constructed, which was proven to be an independent prognostic risk factor. The receiver operating characteristic (ROC) curves showed that the model had a good prognostic ability in the training, testing, and external set, respectively [5-year area under the curve (AUC) =0.73, 5-year AUC =0.81, 4-year AUC =0.79]. The results of survival, somatic mutation, and immune analyses showed that the patients in the low-risk group had a better prognosis, lower rates of somatic mutation, and better immune cell infiltration. Personalized chemotherapeutic drugs were also identified for the patients with HCC.

Conclusions

The novel PLPI not only greatly predicted the prognosis of patients with HCC but could also offer novel ideas and approaches for the therapeutic management of HCC.

Development of machine learning-based predictors for early diagnosis of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) remains a formidable malignancy that significantly impacts human health, and the early diagnosis of HCC holds paramount importance. Therefore, it is imperative to develop an efficacious signature for the early diagnosis of HCC. In this study, we aimed to develop early HCC predictors (eHCC-pred) using machine learning-based methods and compare their performance with existing methods. The enhancements and advancements of eHCC-pred encompassed the following: (i) utilization of a substantial number of samples, including an increased representation of cirrhosis tissues without HCC (CwoHCC) samples for model training and augmented numbers of HCC and CwoHCC samples for model validation; (ii) incorporation of two feature selection methods, namely minimum redundancy maximum relevance and maximum relevance maximum distance, along with the inclusion of eight machine learning-based methods; (iii) improvement in the accuracy of early HCC identification, elevating it from 78.15 to 97% using identical independent datasets; and (iv) establishment of a user-friendly web server. The eHCC-pred is freely accessible at http://www.dulab.com.cn/eHCC-pred/ . Our approach, eHCC-pred, is anticipated to be robustly employed at the individual level for facilitating early HCC diagnosis in clinical practice, surpassing currently available state-of-the-art techniques.

Bioinformatics and machine learning driven key genes screening for hepatocellular carcinoma

Liver cancer, a global menace, ranked as the sixth most prevalent and third deadliest cancer in 2020. The challenge of early diagnosis and treatment, especially for hepatocellular carcinoma (HCC), persists due to late-stage detections. Understanding HCC's complex pathogenesis is vital for advancing diagnostics and therapies. This study combines bioinformatics and machine learning, examining HCC comprehensively. Three datasets underwent meticulous scrutiny, employing various analytical tools such as Gene Ontology (GO) function and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis, protein interaction assessment, and survival analysis. These rigorous investigations uncovered twelve pivotal genes intricately linked with HCC's pathophysiological intricacies. Among them, CYP2C8, CYP2C9, EPHX2, and ESR1 were significantly positively correlated with overall patient survival, while AKR1B10 and NQO1 displayed a negative correlation. Moreover, the Adaboost prediction model yielded an 86.8 % accuracy, showcasing machine learning's potential in deciphering complex dataset patterns for clinically relevant predictions. These findings promise to contribute valuable insights into the elusive mechanisms driving liver cancer (HCC). They hold the potential to guide the development of more precise diagnostic methods and treatment strategies in the future. In the fight against this global health challenge, unraveling HCC's intricacies is of paramount importance.

SIMarker: Cellular similarity detection and its application to diagnosis and prognosis of liver cancer

BACKGROUND

The emergence of single-cell technology offers a unique opportunity to explore cellular similarity and heterogeneity between precancerous diseases and solid tumors. However, there is lacking a systematic study for identifying and characterizing similarities at single-cell resolution.

METHODS

We developed SIMarker, a computational framework to detect cellular similarities between precancerous diseases and solid tumors based on gene expression at single-cell resolution. Taking hepatocellular carcinoma (HCC) as a case study, we quantified the cellular and molecular connections between HCC and cirrhosis. Core analysis modules of SIMarker is publicly available at https://github.com/xmuhuanglab/SIMarker ("SIM" means "similarity" and "Marker" means "biomarkers).

RESULTS

We found PGA5+ hepatocytes in HCC showed cirrhosis-like characteristics, including similar transcriptional programs and gene regulatory networks. Consequently, the genes constituting the gene expression program of these cirrhosis-like subpopulations were designated as cirrhosis-like signatures (CLS). Strikingly, our utilization of CLS enabled the development of diagnosis and prognosis biomarkers based on within-sample relative expression orderings of gene pairs. These biomarkers achieved high precision and concordance compared with previous studies.

CONCLUSIONS

Our work provides a systematic method to investigate the clinical translational significance of cellular similarities between HCC and cirrhosis, which opens avenues for identifying similar paradigms in other categories of cancers and diseases.

Clinical data mining: challenges, opportunities, and recommendations for translational applications

Clinical data mining of predictive models offers significant advantages for re-evaluating and leveraging large amounts of complex clinical real-world data and experimental comparison data for tasks such as risk stratification, diagnosis, classification, and survival prediction. However, its translational application is still limited. One challenge is that the proposed clinical requirements and data mining are not synchronized. Additionally, the exotic predictions of data mining are difficult to apply directly in local medical institutions. Hence, it is necessary to incisively review the translational application of clinical data mining, providing an analytical workflow for developing and validating prediction models to ensure the scientific validity of analytic workflows in response to clinical questions. This review systematically revisits the purpose, process, and principles of clinical data mining and discusses the key causes contributing to the detachment from practice and the misuse of model verification in developing predictive models for research. Based on this, we propose a niche-targeting framework of four principles: Clinical Contextual, Subgroup-Oriented, Confounder- and False Positive-Controlled (CSCF), to provide guidance for clinical data mining prior to the model's development in clinical settings. Eventually, it is hoped that this review can help guide future research and develop personalized predictive models to achieve the goal of discovering subgroups with varied remedial benefits or risks and ensuring that precision medicine can deliver its full potential.

Gene variations related to the hepatocellular carcinoma: Results from a field synopsis and Bayesian revaluation

Hepatocellular carcinoma (HCC) is considered as the second cause of cancer-related deaths worldwide. Genetic variations are associated with HCC risk, an issue that has been the subject of several meta-analyses. However, meta-analyses have an important limitation on the likelihood of false positive data. Henceforth, this study aimed to assess the level of noteworthiness in the meta-analyses by means of a Bayesian approach. A systematic search was performed for meta-analyses with associations between gene polymorphisms and HCC. The calculations for the False-Positive Rate Probability (FPRP) and the Bayesian False Discovery Probability (BFDP) were performed to assess the noteworthiness with a statistical power of 1.2 and 1.5 of Odds Ratio at a prior probability of 10^-3 and 10^-5. The quality of studies was evaluated by the Venice criteria. As additional analyses, the gene-gene and protein-protein networks were designed for these genes and products. As results, we found 33 meta-analytic studies on 45 polymorphisms occurring in 35 genes. A total of 1,280 values for FPRP and BFDP were obtained. Seventy-five for FPRP (5.86%) and 95 for BFDP (14.79%) were noteworthy. In conclusion, the polymorphisms in CCND1, CTLA4, EGF, IL6, IL12A, KIF1B, MDM2, MICA, miR-499, MTHFR, PNPLA3, STAT4, TM6SF2, and XPD genes were considered as noteworthy biomarkers for HCC risk.

Prognosis and Personalized Treatment Prediction in Different Mutation-Signature Hepatocellular Carcinoma

Introduction

Mutation patterns have been extensively explored to decipher the etiologies of hepatocellular carcinoma (HCC). However, the study and potential clinical role of mutation patterns to stratify high-risk patients and optimize precision therapeutic strategies remain elusive in HCC.

Methods

Using exon-sequencing data in public (n=362) and in-house (n=30) cohorts, mutation signatures were extracted to decipher relationships with the etiology and prognosis in HCC. The proteomics (n=159) and cell-line transcriptome data (n=1019) were collected to screen the implication of sensitive drugs. A novel multi-step machine-learning framework was then performed to construct a classification predictor, including recognizing stable reversed gene pairs, establishing a robust prediction model, and validating the robustness of the predictor in five independent cohorts (n=900).

Results

Two heterogeneous mutation signature clusters were identified, and a high-risk prognosis cluster was recognized for further analysis. Notably, mutation signature cluster 1 (MSC1) was featured by activated anti-tumor immune and metabolism dysfunctional states, higher genomic instability (high TMB, SNV neoantigen, indel neoantigens, and total neoantigens), and a dismal prognosis. Notably, MSC performed as an independent risk factor than clinical traits (eg, stage, vascular invasion). Additionally, afatinib and canertinib were recognized which might have potential therapeutic implications in MSC1, and the targets of these drugs presented a higher expression in both gene and protein levels in HCC.

Discussion

Our studies may provide a promising platform for improving prognosis and tailoring therapy in HCC.

lncRNA pair as candidate diagnostic signature for colorectal cancer based on the within-sample relative expression levels

Background

Early diagnosis of colorectal cancer could significantly improve the prognosis and reduce mortality. However, indeterminate diagnosis is often met in pathology diagnosis in biopsy samples. Abnormal expression of long non-coding RNA (lncRNA) is associated with the initiation and progression of colorectal cancer. It is of great value and clinical significance to explore lncRNAs as candidate diagnostic biomarkers in colorectal cancer.

Methods

Based on the within-sample relative expression levels of lncRNA pairs, we identified a group of candidate diagnostic biomarkers for colorectal cancer. In addition, we validated it in independent datasets produced by different laboratories and different platforms. We also tested it in colorectal cancer tissue samples using quantitative real-time polymerase chain reaction (RT-qPCR).

Results

A biomarker consisting of six lncRNA pairs including nine lncRNAs was identified for the diagnosis of colorectal cancer. For a total of 950 cancer samples and 247 non-cancer samples, both of the sensitivity and specificity could achieve approximately 90%. For adenoma samples, the accuracy could achieve 73%. For normal tissues from inflammatory bowel disease patients, 93% (14/15) were correctly classified as non-cancer. Furthermore, the lncRNA pair biomarker showed excellent performance in all clinical stages; even in the early stage, the accuracy could achieve 87% and 82% in stage I and II. Meanwhile, the biomarker was also robust to the microsatellite instability status. More importantly, we measured the biomarker in 35 colorectal cancer and 30 cancer-adjacent tissue samples using quantitative real-time polymerase chain reaction (RT-qPCR). The accuracy could achieve 93.3% (70/75). Specially, even in early-stage tumors (I and II), the accuracy could also achieve 90.9% (30/33). The enrichment analysis revealed that these lncRNAs were involved in highly associated cancer pathways and immune-related pathways. Immune analysis showed that these marker lncRNAs were associated with multiple immune cells, implying that they might be involved in the regulation of immune cell functions in colorectal cancer. Most of the biomarker lncRNAs were also differentially expressed between the mutant group and wild-type group of colorectal cancer driver genes.

Conclusion

We identified and validated six lncRNA pairs including nine lncRNAs as a biomarker for assisting in the diagnosis of colorectal cancer.

Metabolism-Related Gene Pairs to Predict the Clinical Outcome and Molecular Characteristics of Early Hepatocellular Carcinoma

Recurrence is the main factor affecting the prognosis of early hepatocellular carcinoma (HCC), which is not accurately evaluated by clinical indicators. The metabolic heterogeneity of HCC hints at the possibility of constructing a stratification model to predict the clinical outcome. On the basis of the relative expression orderings of 2939 metabolism-related genes, an individualized signature with 10 metabolism-related gene pairs (10-GPS) was developed from 250 early HCC samples in the discovery datasets, which stratified HCC patients into the high- and low-risk subgroups with significantly different survival rates. The 10-GPS was validated in 311 public transcriptomic samples from two independent validation datasets. A nomogram that included the 10-GPS, age, gender, and stage was constructed for eventual clinical evaluation. The low-risk group was characterized by lower proliferation, higher metabolism, increased activated immune microenvironment, and lower TIDE scores, suggesting a better response to immunotherapy. The high-risk group displayed hypomethylation, higher copy number alterations, mutations, and more overexpression of immune-checkpoint genes, which might jointly lead to poor outcomes. The prognostic accuracy of the 10-GPS was further validated in 47 institutional transcriptomic samples and 101 public proteomic samples. In conclusion, the 10-GPS is a robust predictor of the clinical outcome for early HCC patients and could help evaluate prognosis and characterize molecular heterogeneity.

A novel qualitative signature based on lncRNA pairs for prognosis prediction in hepatocellular carcinoma

Background

Prognostic assessment is imperative for clinical management of patients with hepatocellular carcinoma (HCC). Most reported prognostic signatures are based on risk scores summarized from quantitative expression level of candidate genes, which are vulnerable against experimental batch effects and impractical for clinical application. We aimed to develop a robust qualitative signature to assess individual survival risk for HCC patients.

Methods

Long non-coding RNA (lncRNA) pairs correlated with overall survival (OS) were identified and an optimal combination of lncRNA pairs based on the majority voting rule was selected as a classification signature to predict the overall survival risk in the cancer genome atlas (TCGA). Then, the signature was further validated in two external datasets. Besides, biomolecular characteristics, immune infiltration status, and chemotherapeutics efficacy of different risk groups were further compared. Finally, we performed key lncRNA screening and validated it in vitro.

Results

A signature consisting of 50 lncRNA pairs (50-LPS) was identified in TCGA and successfully validated in external datasets. Patients in the high-risk group, when at least 25 of the 50-LPS voted for high risk, had significantly worse OS than the low-risk group. Multivariate Cox, receiver operating characteristic (ROC) curve and decision curve analyses (DCA) demonstrated that the 50-LPS was an independent prognostic factor and more powerful than other available clinical factors in OS prediction. Comparison analyses indicated that different risk groups had distinct biomolecular characteristics, immune infiltration status, and chemotherapeutics efficacy. TDRKH-AS1 was confirmed as a key lncRNA and associated with cell growth of HCC.

Conclusions

The 50-LPS could not only predict the prognosis of HCC patients robustly and individually, but also provide theoretical basis for therapy. Besides, TDRKH-AS1 was identified as a key lncRNA in the proliferation of HCC. The 50-LPS might guide personalized therapy for HCC patients in clinical practice.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12935-022-02507-z.

Stratification of patients with clear cell renal cell carcinoma to facilitate drug repositioning

Clear cell renal cell carcinoma (ccRCC) is the most common histological type of kidney cancer and has high heterogeneity. Stratification of ccRCC is important since distinct subtypes differ in prognosis and treatment. Here, we applied a systems biology approach to stratify ccRCC into three molecular subtypes with different mRNA expression patterns and prognosis of patients. Further, we developed a set of biomarkers that could robustly classify the patients into each of the three subtypes and predict the prognosis of patients. Then, we reconstructed subtype-specific metabolic models and performed essential gene analysis to identify the potential drug targets. We identified four drug targets, including SOAT1, CRLS1, and ACACB, essential in all the three subtypes and GPD2, exclusively essential to subtype 1. Finally, we repositioned mitotane, an FDA-approved SOAT1 inhibitor, to treat ccRCC and showed that it decreased tumor cell viability and inhibited tumor cell growth based on in vitro experiments.

•

Three consistent molecular ccRCC subtypes were found to guide patients' prognoses

•

REOs-based biomarker was developed to robustly classify patients at individual level

•

SOAT1 is identified as a common drug target for all ccRCC subtypes

•

Mitotane was repositioned treatment of ccRCC via inhibiting SOAT1

Qualitative diagnostic signature for pancreatic ductal adenocarcinoma based on the within-sample relative expression orderings

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) accounts for about 90% of pancreatic cancer, which is one of the most aggressive malignant neoplasms with a 9.3% five-year survival rate. The pathological biopsy is the current golden standard for confirming suspicious lesions of PDAC, but it is not entirely reliable because of the insufficient sampling amount and inaccurate sampling location. Therefore, developing a robust signature to aid the accurate diagnosis of PDAC is critical.

METHODS

Based on the within-sample relative expression orderings of gene pairs, we identified a qualitative signature to discriminate both PDAC and adjacent samples from both chronic pancreatitis and normal samples in the training datasets and validated it in other independent datasets produced by different laboratories with different measuring platforms.

RESULTS

A six-gene-pair signature was identified in the training data and validated in eight independent datasets. For surgical samples, 96.63% of 356 PDAC tissues, 100% of 11 pancreatitis tissues of non-cancer patients, and 23 of 24 normal pancreatic tissues were correctly classified. Especially, 59 of 60 cancer-adjacent normal tissues of PDAC patients were correctly identified as PDAC. For biopsy samples, all of 11 PDAC biopsy tissues were correctly classified as PDAC.

CONCLUSION

The signature can distinguish both PDAC and PDAC-adjacent normal tissues from both chronic pancreatitis and normal tissues of non-cancer patients even when the sampling locations are inaccurate, which can aid the diagnosis of PDAC.

A Qualitative Transcriptional Signature for the Risk Assessment of Precancerous Colorectal Lesions

It is meaningful to assess the risk of cancer incidence among patients with precancerous colorectal lesions. Comparing the within-sample relative expression orderings (REOs) of colorectal cancer patients measured by multiple platforms with that of normal colorectal tissues, a qualitative transcriptional signature consisting of 1,840 gene pairs was identified in the training data. Within an evaluation dataset of 16 active and 18 inactive (remissive) ulcerative colitis subjects, the median incidence risk score of colorectal carcinoma was 0.6402 in active ulcerative colitis subjects, significantly higher than that in remissive subjects (0.3114). Evaluation of two other independent datasets yielded similar results. Moreover, we found that the score significantly positively correlated with the degree of dysplasia in the case of colorectal adenomas. In the merged dataset, the median incidence risk score was 0.9027 among high-grade adenoma samples, significantly higher than that among low-grade adenomas (0.8565). In summary, the developed incidence risk score could well predict the incidence risk of precancerous colorectal lesions and has value in clinical application.

M1 Macrophage-Derived Exosomal MicroRNA-326 Suppresses Hepatocellular Carcinoma Cell Progression Via Mediating NF-κB Signaling Pathway

Accumulating evidence has shown that microRNA (miR) derived from M1 macrophage-derived exosomes can regulate the progression of hepatocellular carcinoma (HCC). However, the effect of miR-326 derived from M1 macrophage-derived exosomes on HCC has not been reported. Therefore, the objective of the present study was to explore the mechanism of exosomal miR-326 from M1 macrophages in regulating HCC cell progression. RT-qPCR detected miR-326 expression in HCC cell lines. miR-326 expression in HCC was altered by transfection, and the effect of miR-326 on CD206 and NF-κB expression, cell proliferation, colony formation, migration, apoptosis and invasion was detected. Subsequently, exosomes were isolated from M1 macrophages. RT-qPCR identified miR-326 expression in M1 macrophage-derived exosomes. miR-326 expression in M1 macrophage-derived exosomes was changed by transfection. M1 macrophage-derived exosomes were co-cultured with HCC cells to figure out their effects on the biological progress of HCC cells. Finally, in vivo experiments were performed to verify the in vitro results. MiR-326 was decreased in HCC cells and enriched in M1 macrophage-derived exosomes. Up-regulating miR-326 would inhibit HCC cell proliferation, colony formation, migration, invasion, and CD206 and NF-κB expression and promoted apoptosis, and inhibited the growth of HCC tumors in vivo, while down-regulating miR-326 showed opposite effects. M1 macrophage-derived exosomes inhibited HCC cell proliferation, colony formation, migration, invasion, and CD206 and NF-κB expression and enhanced apoptosis, while overexpression of miR-326 enhanced the effect of M1 macrophage-derived exosomes on HCC cells. It is revealed that M1 macrophages-derived exosomal miR-326 suppresses proliferation, migration and invasion as well as advances apoptosis of HCC through down-regulating NF-κB expression.

Qualitative Transcriptional Signature for the Pathological Diagnosis of Pancreatic Cancer

It is currently difficult for pathologists to diagnose pancreatic cancer (PC) using biopsy specimens because samples may have been from an incorrect site or contain an insufficient amount of tissue. Thus, there is a need to develop a platform-independent molecular classifier that accurately distinguishes benign pancreatic lesions from PC. Here, we developed a robust qualitative messenger RNA signature based on within-sample relative expression orderings (REOs) of genes to discriminate both PC tissues and cancer-adjacent normal tissues from non-PC pancreatitis and healthy pancreatic tissues. A signature comprising 12 gene pairs and 17 genes was built in the training datasets and validated in microarray and RNA-sequencing datasets from biopsy samples and surgically resected samples. Analysis of 1,007 PC tissues and 257 non-tumor samples from nine databases indicated that the geometric mean of sensitivity and specificity was 96.7%, and the area under receiver operating characteristic curve was 0.978 (95% confidence interval, 0.947–0.994). For 20 specimens obtained from endoscopic biopsy, the signature had a diagnostic accuracy of 100%. The REO-based signature described here can aid in the molecular diagnosis of PC and may facilitate objective differentiation between benign and malignant pancreatic lesions.

Early Diagnosis of Pancreatic Ductal Adenocarcinoma by Combining Relative Expression Orderings With Machine-Learning Method

Pancreatic ductal adenocarcinoma (PDAC) is an aggressive and lethal cancer deeply affecting human health. Diagnosing early-stage PDAC is the key point to PDAC patients' survival. However, the biomarkers for diagnosing early PDAC are inexact in most cases. Therefore, it is highly desirable to identify an effective PDAC diagnostic biomarker. In the current work, we designed a novel computational approach based on within-sample relative expression orderings (REOs). A feature selection technique called minimum redundancy maximum relevance was used to pick out optimal REOs. We then compared the performances of different classification algorithms for discriminating PDAC and its adjacent normal tissues from non-PDAC tissues. The support vector machine algorithm is the best one for identifying early PDAC diagnostic biomarker. At first, a signature composed of nine gene pairs was acquired from microarray gene expression data sets. These gene pairs could produce satisfactory classification accuracy up to 97.53% in fivefold cross-validation. Subsequently, two types of data from diverse platforms, namely, microarray and RNA-Seq, were used to validate this signature. For microarray data, all (100.00%) of 115 PDAC tissues and all (100.00%) of 31 PDAC adjacent normal tissues were correctly recognized as PDAC. In addition, 88.24% of 17 non-PDAC (normal or pancreatitis) tissues were correctly classified. For the RNA-Seq data, all (100.00%) of 177 PDAC tissues and all (100.00%) of 4 PDAC adjacent normal tissues were correctly recognized as PDAC. Validation results demonstrated that the signature had a good cross-platform effect for early detection of PDAC. This work developed a new robust signature that might be a promising biomarker for early PDAC diagnosis.

A qualitative transcriptional signature for predicting the biochemical recurrence risk of prostate cancer patients after radical prostatectomy

BACKGROUND

The qualitative transcriptional characteristics, the within-sample relative expression orderings (REOs) of genes, are highly robust against batch effects and sample quality variations. Hence, we develop a qualitative transcriptional signature based on REOs to predict the biochemical recurrence risk of prostate cancer (PCa) patients after radical prostatectomy.

METHODS

Gene pairs with REOs significantly correlated with the biochemical recurrence-free survival (BFS) were identified from 131 PCa samples in the training data set. From these gene pairs, we selected a qualitative transcriptional signature based on the within-sample REOs of gene pairs which could predict the recurrence risk of PCa patients after radical prostatectomy.

RESULTS

A signature consisting of 74 gene pairs, named 74-GPS, was developed for predicting the recurrence risk of PCa patients after radical prostatectomy based on the majority voting rule that a sample was assigned as high risk when at least 37 gene pairs of the 74-GPS voted for high risk; otherwise, low risk. The signature was validated in six independent datasets produced by different platforms. In each of the validation datasets, the Kaplan-Meier survival analysis showed that the average BFS of the low-risk group was significantly better than that of the high-risk group. Analyses of multiomics data of PCa samples from TCGA suggested that both the epigenomic and genomic alternations could cause the reproducible transcriptional differences between the two different prognostic groups.

CONCLUSIONS

The proposed qualitative transcriptional signature can robustly stratify PCa patients after radical prostatectomy into two groups with different recurrence risk and distinct multiomics characteristics. Hence, 74-GPS may serve as a helpful tool for guiding the management of PCa patients with radical prostatectomy at the individual level.

Early Diagnosis of Hepatocellular Carcinoma Using Machine Learning Method

Hepatocellular carcinoma (HCC) is a serious cancer which ranked the fourth in cancer-related death worldwide. Hence, more accurate diagnostic models are urgently needed to aid the early HCC diagnosis under clinical scenarios and thus improve HCC treatment and survival. Several conventional methods have been used for discriminating HCC from cirrhosis tissues in patients without HCC (CwoHCC). However, the recognition successful rates are still far from satisfactory. In this study, we applied a computational approach that based on machine learning method to a set of microarray data generated from 1091 HCC samples and 242 CwoHCC samples. The within-sample relative expression orderings (REOs) method was used to extract numerical descriptors from gene expression profiles datasets. After removing the unrelated features by using maximum redundancy minimum relevance (mRMR) with incremental feature selection, we achieved “11-gene-pair” which could produce outstanding results. We further investigated the discriminate capability of the “11-gene-pair” for HCC recognition on several independent datasets. The wonderful results were obtained, demonstrating that the selected gene pairs can be signature for HCC. The proposed computational model can discriminate HCC and adjacent non-cancerous tissues from CwoHCC even for minimum biopsy specimens and inaccurately sampled specimens, which can be practical and effective for aiding the early HCC diagnosis at individual level.

An absolute human stemness index associated with oncogenic dedifferentiation

The progression of cancer is accompanied by the acquisition of stemness features. Many stemness evaluation methods based on transcriptional profiles have been presented to reveal the relationship between stemness and cancer. However, instead of absolute stemness index values-the values with certain range-these methods gave the values without range, which makes them unable to intuitively evaluate the stemness. Besides, these indices were based on the absolute expression values of genes, which were found to be seriously influenced by batch effects and the composition of samples in the dataset. Recently, we have showed that the signatures based on the relative expression orderings (REOs) of gene pairs within a sample were highly robust against these factors, which makes that the REO-based signatures have been stably applied in the evaluations of the continuous scores with certain range. Here, we provided an absolute REO-based stemness index to evaluate the stemness. We found that this stemness index had higher correlation with the culture time of the differentiated stem cells than the previous stemness index. When applied to the cancer and normal tissue samples, the stemness index showed its significant difference between cancers and normal tissues and its ability to reveal the intratumor heterogeneity at stemness level. Importantly, higher stemness index was associated with poorer prognosis and greater oncogenic dedifferentiation reflected by histological grade. All results showed the capability of the REO-based stemness index to assist the assignment of tumor grade and its potential therapeutic and diagnostic implications.

A qualitative transcriptional signature for predicting microsatellite instability status of right-sided Colon Cancer

Background

Microsatellite instability (MSI) accounts for about 15% of colorectal cancer and is associated with prognosis. Today, MSI is usually detected by polymerase chain reaction amplification of specific microsatellite markers. However, the instability is identified by comparing the length of microsatellite repeats in tumor and normal samples. In this work, we developed a qualitative transcriptional signature to individually predict MSI status for right-sided colon cancer (RCC) based on tumor samples.

Results

Using RCC samples, based on the relative expression orderings (REOs) of gene pairs, we extracted a signature consisting of 10 gene pairs (10-GPS) to predict MSI status for RCC through a feature selection process. A sample is predicted as MSI when the gene expression orderings of at least 7 gene pairs vote for MSI; otherwise the microsatellite stability (MSS). The classification performance reached the largest F-score in the training dataset. This signature was verified in four independent datasets of RCCs with the F-scores of 1, 0.9630, 0.9412 and 0.8798, respectively. Additionally, the hierarchical clustering analyses and molecular features also supported the correctness of the reclassifications of the MSI status by 10-GPS.

Conclusions

The qualitative transcriptional signature can be used to classify MSI status of RCC samples at the individualized level.

A qualitative transcriptional signature for the early diagnosis of colorectal cancer

Currently, using biopsy specimens for the early diagnosis of colorectal cancer (CRC) is not entirely reliable due to insufficient sampling amount and inaccurate sampling location. Thus, it is necessary to develop a signature that can accurately identify patients with CRC under these clinical scenarios. Based on the relative expression orderings of genes within individual samples, we developed a qualitative transcriptional signature to discriminate CRC tissues, including CRC adjacent normal tissues from non-CRC individuals. The signature was validated using multiple microarray and RNA sequencing data from different sources. In the training data, a signature consisting of 7 gene pairs was identified. It was well validated in both biopsy and surgical resection specimens from multiple datasets measured by different platforms. For biopsy specimens, 97.6% of 42 CRC tissues and 94.5% of 163 non-CRC (normal or inflammatory bowel disease) tissues were correctly classified. For surgically resected specimens, 99.5% of 854 CRC tissues and 96.3% of 81 CRC adjacent normal tissues were correctly identified as CRC. Notably, we additionally measured 33 CRC biopsy specimens by the Affymetrix platform and 13 CRC surgical resection specimens, with different proportions of tumor epithelial cells, ranging from 40% to 100%, by the RNA sequencing platform, and all these samples were correctly identified as CRC. The signature can be used for the early diagnosis of CRC, which is also suitable for minimum biopsy specimens and inaccurately sampled specimens, and thus has potential value for clinical application.

Development and validation of a CIMP-associated prognostic model for hepatocellular carcinoma

BACKGROUND

CpG island methylator phenotype (CIMP), a common biological phenomenon characterized by a subset of concurrently methylated genes, can have an influence on the progression of multiple cancers. However, the potential mechanism of CIMP in hepatocarcinogenesis and its clinical relevance remains only partially understood.

METHODS

We used a methylation array from the cancer genome atlas (TCGA) to stratify HCC patients into different CIMP subtypes, and evaluated their correlation with clinical characteristics. In addition, mutation, CNV, and transcriptome profiles were also utilized to evaluate the distinctive genomic patterns correlated with CIMP. Finally, a CIMP-associated prognostic model (CPM) was trained and validated using four independent datasets.

FINDINGS

A subgroup of patients was identified as having CIMP-H, which was associated with worse OS and DFS. Gene enrichment analysis indicated that the terms "liver cancer with EPCAM up", "tumor invasiveness up", "methyltransferase complex", and "translational initiation" were enriched in CIMP-H subgroup. Notably, somatic mutation analysis indicated that CIMP-H patients presented with a higher mutation burden of BRD4, DDIAS and NOX1. Moreover, four CPM associated genes could significantly categorize patients into low- and high-risk groups in the training dataset and another 3 independent validation datasets. Finally, a nomogram incorporating a classifier based on four mRNAs, pathological M stage and CIMP status was established, which showed a favorable discriminating ability and might contribute to clinical decision-making for HCC.

INTERPRETATION

Our work highlights the potential clinical application value of CPM in predicting the overall survival of HCC patients and the mechanisms underlying the role of CIMP in hepatocarcinogenesis. FUND: This work was supported by the State Key Project on Infectious Diseases of China (2018ZX10723204-003), the National Nature Science Foundation of China (Nos. 81874065, 81500565, 81874149, 81572427, and 81401997), the Hepato-Biliary-Pancreatic Malignant Tumor Investigation Fund of Chen Xiao-ping Foundation for the Development of Science and Technology of Hubei Province (CXPJJH11800001-2018356).

A Qualitative Transcriptional Signature for Predicting Recurrence Risk of Stage I-III Bladder Cancer Patients After Surgical Resection

Background: Previously reported transcriptional signatures for predicting the prognosis of stage I-III bladder cancer (BLCA) patients after surgical resection are commonly based on risk scores summarized from quantitative measurements of gene expression levels, which are highly sensitive to the measurement variation and sample quality and thus hardly applicable under clinical settings. It is necessary to develop a signature which can robustly predict recurrence risk of BLCA patients after surgical resection.

Methods: The signature is developed based on the within-sample relative expression orderings (REOs) of genes, which are qualitative transcriptional characteristics of the samples.

Results: A signature consisting of 12 gene pairs (12-GPS) was identified in training data with 158 samples. In the first validation dataset with 114 samples, the low-risk group of 54 patients had a significantly better overall survival than the high-risk group of 60 patients (HR = 3.59, 95% CI: 1.34~9.62, p = 6.61 × 10⁻⁰³). The signature was also validated in the second validation dataset with 57 samples (HR = 2.75 × 10⁰⁸, 95% CI: 0~Inf, p = 0.05). Comparison analysis showed that the transcriptional differences between the low- and high-risk groups were highly reproducible and significantly concordant with DNA methylation differences between the two groups.

Conclusions: The 12-GPS signature can robustly predict the recurrence risk of stage I-III BLCA patients after surgical resection. It can also aid the identification of reproducible transcriptional and epigenomic features characterizing BLCA metastasis.

A robust qualitative transcriptional signature for the correct pathological diagnosis of gastric cancer

BACKGROUND

Currently, pathological examination of gastroscopy biopsy specimens is the gold standard for gastric cancer (GC) diagnosis. However, it has a false-negative rate of 10-20% due to inaccurate sampling locations and/or insufficient sampling amount. A signature should be developed to aid the early diagnosis of GC using biopsy specimens even when they are sampled from inaccurate locations.

METHODS

We extracted a robust qualitative transcriptional signature, based on the within-sample relative expression orderings (REOs) of gene pairs, to discriminate both GC tissues and adjacent-normal tissues from non-GC gastritis, intestinal metaplasia and normal gastric tissues.

RESULTS

A signature consisting of two gene pairs for GC diagnosis was identified and validated in data of both biopsy specimens and surgical resection specimens pooled from publicly available datasets measured by different laboratories with different platforms. For gastroscopy biopsy specimens, 96.20% of 79 non-GC tissues were correctly identified as non-GC, and 96.84% of 158 GC tissues and six of seven adjacent-normal tissues were correctly identified as GC. For surgical resection specimens, 98.37% of 2560 GC tissues and 97.28% of 221 adjacent-normal tissues were correctly identified as GC. Especially, 97.67% of the 257 GC patients at stage I were exactly diagnosed as GC. We additionally measured 21 GC tissues from seven different GC patients, each with three specimens sampled from three tumor locations with different proportions of the tumor epithelial cell. All these GC tissues were correctly identified as GC, even when the proportion of the tumor epithelial cell was as low as 14%.

CONCLUSIONS

The qualitative transcriptional signature can distinguish both GC and adjacent-normal tissues from normal, gastritis and intestinal metaplasia tissues of non-GC patients even using inaccurately sampled biopsy specimens, which can be applied robustly at the individual level to aid the early GC diagnosis.