A qualitative transcriptional signature for the early diagnosis of colorectal cancer

Integrated analysis of diverse cancer types reveals a breast cancer-specific serum miRNA biomarker through relative expression orderings analysis

PURPOSE

Serum microRNA (miRNA) holds great potential as a non-invasive biomarker for diagnosing breast cancer (BrC). However, most diagnostic models rely on the absolute expression levels of miRNAs, which are susceptible to batch effects and challenging for clinical transformation. Furthermore, current studies on liquid biopsy diagnostic biomarkers for BrC mainly focus on distinguishing BrC patients from healthy controls, needing more specificity assessment.

METHODS

We collected a large number of miRNA expression data involving 8465 samples from GEO, including 13 different cancer types and non-cancer controls. Based on the relative expression orderings (REOs) of miRNAs within each sample, we applied the greedy, LASSO multiple linear regression, and random forest algorithms to identify a qualitative biomarker specific to BrC by comparing BrC samples to samples of other cancers as controls.

RESULTS

We developed a BrC-specific biomarker called 7-miRPairs, consisting of seven miRNA pairs. It demonstrated comparable classification performance in our analyzed machine learning algorithms while requiring fewer miRNA pairs, accurately distinguishing BrC from 12 other cancer types. The diagnostic performance of 7-miRPairs was favorable in the training set (accuracy = 98.47%, specificity = 98.14%, sensitivity = 99.25%), and similar results were obtained in the test set (accuracy = 97.22%, specificity = 96.87%, sensitivity = 98.02%). KEGG pathway enrichment analysis of the 11 miRNAs within the 7-miRPairs revealed significant enrichment of target mRNAs in pathways associated with BrC.

CONCLUSION

Our study provides evidence that utilizing serum miRNA pairs can offer significant advantages for BrC-specific diagnosis in clinical practice by directly comparing serum samples with BrC to other cancer types.

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.

Identification of an Individualized Prognostic Biomarker for Serous Ovarian Cancer: A Qualitative Model

Serous ovarian cancer is the most common type of ovarian epithelial cancer and usually has a poor prognosis. The objective of this study was to construct an individualized prognostic model for predicting overall survival in serous ovarian cancer. Based on the relative expression orderings (Ea > Eb/Ea ≤ Eb) of gene pairs closely associated with serous ovarian prognosis, we tried constructing a potential individualized qualitative biomarker by the greedy algorithm and evaluated the performance in independent validation datasets. We constructed a prognostic biomarker consisting of 20 gene pairs (SOV-P20). The overall survival between high- and low-risk groups stratified by SOV-P20 was statistically significantly different in the training and independent validation datasets from other platforms (p < 0.05, Wilcoxon test). The average area under the curve (AUC) values of the training and three validation datasets were 0.756, 0.590, 0.630, and 0.680, respectively. The distribution of most immune cells between high- and low-risk groups was quite different (p < 0.001, Wilcoxon test). The low-risk patients tended to show significantly better tumor response to chemotherapy than the high-risk patients (p < 0.05, Fisher’s exact test). SOV-P20 achieved the highest mean index of concordance (C-index) (0.624) compared with the other seven existing prognostic signatures (ranging from 0.511 to 0.619). SOV-P20 is a promising prognostic biomarker for serous ovarian cancer, which will be applicable for clinical predictive risk assessment.

Identification of cancer risk assessment signature in patients with chronic obstructive pulmonary disease and exploration of the potential key genes

It is essential to assess the cancer risk for patients with chronic obstructive pulmonary disease (COPD). Comparing gene expression data from patients with lung cancer (a total of 506 samples) and those with cancer-adjacent normal lung tissues (a total of 370 samples), we generated a qualitative transcriptional signature consisting of 2046 gene pairs. The signature was verified in an evaluation dataset comprising 18 subjects with severe disease and 52 subjects with moderate disease (Wilcoxon rank-sum test; p = 7.33 × 10^-5). Similar results were obtained in other independent datasets. Among the gene pairs in the signature, 326 COPD stage-related gene pairs were identified based on Spearman's rank correlation tests and those gene pairs comprised 368 unique genes. Of these 368 genes, 16 genes were significantly dysregulated in COPD rat model data compared with control data. Some of these genes (Dhx16, Upf2, Notch3, Sec61a1, Dyrk2, and Hmmr) were altered when the COPD rat model was treated with traditional Chinese medicines (TCM), including Bufei Yishen formula, Bufei Jianpi formula, and Yiqi Zishen formula. Overall, the signature could predict the cancer incidence-risk of COPD and the identified key genes might provide guidance regarding both the treatment of COPD using TCM and the prevention of cancer in patients with COPD. KEY MESSAGESA cancer risk assessment signature was identified in patients with COPD.The signature is insensitive to batch effects and is well verified.COPD key genes identified in this study might play a crucial role in TCM treatment and cancer prevention.

A multimodal model fusing multiphase contrast-enhanced CT and clinical characteristics for predicting lymph node metastases of pancreatic cancer

Objective. To develop a multimodal model that combines multiphase contrast-enhanced computed tomography (CECT) imaging and clinical characteristics, including experts’ experience, to preoperatively predict lymph node metastasis (LNM) in pancreatic cancer patients. Methods. We proposed a new classifier fusion strategy (CFS) based on a new evidential reasoning (ER) rule (CFS-nER) by combining nomogram weights into a previous ER rule-based CFS. Three kernelled support tensor machine-based classifiers with plain, arterial, and venous phases of CECT as the inputs, respectively, were constructed. They were then fused based on the CFS-nER to construct a fusion model of multiphase CECT. The clinical characteristics were analyzed by univariate and multivariable logistic regression to screen risk factors, which were used to construct correspondent risk factor-based classifiers. Finally, the fusion model of the three phases of CECT and each risk factor-based classifier were fused further to construct the multimodal model based on our CFS-nER, named MMM-nER. This study consisted of 186 patients diagnosed with pancreatic cancer from four clinical centers in China, 88 (47.31%) of whom had LNM. Results. The fusion model of the three phases of CECT performed better overall than single and two-phase fusion models; this implies that the three considered phases of CECT were supplementary and complemented one another. The MMM-nER further improved the predictive performance, which implies that our MMM-nER can complement the supplementary information between CECT and clinical characteristics. The MMM-nER had better predictive performance than based on previous classifier fusion strategies, which presents the advantage of our CFS-nER. Conclusion. We proposed a new CFS-nER, based on which the fusion model of the three phases of CECT and MMM-nER were constructed and performed better than all compared methods. MMM-nER achieved an encouraging performance, implying that it can assist clinicians in noninvasively and preoperatively evaluating the lymph node status of pancreatic cancer.

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.

Two novel qualitative transcriptional signatures robustly applicable to non-research-oriented colorectal cancer samples with low-quality RNA

Currently, due to the low quality of RNA caused by degradation or low abundance, the accuracy of gene expression measurements by transcriptome sequencing (RNA‐seq) is very challenging for non‐research‐oriented clinical samples, majority of which are preserved in hospitals or tissue banks worldwide with complete pathological information and follow‐up data. Molecular signatures consisting of several genes are rarely applied to such samples. To utilize these resources effectively, 45 stage II non‐research‐oriented samples which were formalin‐fixed paraffin‐embedded (FFPE) colorectal carcinoma samples (CRC) using RNA‐seq have been analysed. Our results showed that although gene expression measurements were significantly affected, most cancer features, based on the relative expression orderings (REOs) of gene pairs, were well preserved. We then developed two REO‐based signatures, which consisted of 136 gene pairs for early diagnosis of CRC, and 4500 gene pairs for predicting post‐surgery relapse risk of stage II and III CRC. The performance of our signatures, which included hundreds or thousands of gene pairs, was more robust for non‐research‐oriented clinical samples, compared to that of two published concise REO‐based signatures. In conclusion, REO‐based signatures with relatively more gene pairs could be robustly applied to non‐research‐oriented CRC samples.

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.

Identification of Tamoxifen-Resistant Breast Cancer Cell Lines and Drug Response Signature

Breast cancer cell lines are frequently used to elucidate the molecular mechanisms of the disease. However, a large proportion of cell lines are affected by problems such as mislabeling and cross-contamination. Therefore, it is of great clinical significance to select optimal breast cancer cell lines models. Using tamoxifen survival-related genes from breast cancer tissues as the gold standard, we selected the optimal cell line model to represent the characteristics of clinical tissue samples. Moreover, using relative expression orderings of gene pairs, we developed a gene pair signature that could predict tamoxifen therapy outcomes. Based on 235 consistently identified survival-related genes from datasets GSE17705 and GSE6532, we found that only the differentially expressed genes (DEGs) from the cell line dataset GSE26459 were significantly reproducible in tissue samples (binomial test, p = 2.13E-07). Finally, using the consistent DEGs from cell line dataset GSE26459 and tissue samples, we used the transcriptional qualitative feature to develop a two-gene pair (TOP2A, SLC7A5; NMU, PDSS1) for predicting clinical tamoxifen resistance in the training data (logrank p = 1.98E-07); this signature was verified using an independent dataset (logrank p = 0.009909). Our results indicate that the cell line model from dataset GSE26459 provides a good representation of the characteristics of clinical tissue samples; thus, it will be a good choice for the selection of drug-resistant and drug-sensitive breast cancer cell lines in the future. Moreover, our signature could predict tamoxifen treatment outcomes in breast cancer patients.

Early diagnosis and treatment for Sjögren's syndrome: current challenges, redefined disease stages and future prospects

There are some challenges and unmet needs in the early diagnosis and management of Sjögren's syndrome (SjS) such as prominent glandular dysfunction at diagnosis and long diagnostic delay. Those challenges are partly attributed to the lack of a good knowledge of the early stages of SjS, which is a major obstacle to delivering appropriate care to SjS patients. Findings from both clinical and experimental studies suggest the plausibility of a redefined SjS course consisting of 4 stages, which includes initiation stage, preclinical stage, asymptomatic SjS stage and overt SjS stage. More studies focusing on the pathological processes and changes during the early stages of SjS are needed. To enable early diagnosis and treatment for SjS, more useful biomarkers of the early stages of SjS need to be identified, and individuals at high risk of SjS development need to be identified. Appropriate screening can be performed to facilitate the early diagnosis of SjS among those high-risk individuals.

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.

Identification of the origin of brain metastases based on the relative methylation orderings of CpG sites

Accurate diagnosis of the origin of brain metastases (BMs) is crucial for tailoring an effective therapy to improve patients' prognosis. BMs of unknown origin account for approximately 2-14% of patients with BMs. Hence, the aim of this study was to identify the original cancer type of BMs based on their DNA methylation profiles. The DNA methylation profiles of glioma (GM), BM, and seven other types of primary cancers were collected. In comparison with GM, the reversal CpG site pairs were identified for each of the seven other types of primary cancers based on the within-sample relative methylation orderings (RMOs) of the CpG sites. Then, using the reversal CpG site pairs, GMs were distinguished from BMs and the seven other types of primary cancers. All 61 of the GM samples were correctly identified as GM. The cancer type was also identified for the non-GM samples. For the seven other types of primary cancers, greater than 93% of samples of each cancer type were correctly identified as their corresponding cancer type, except for breast cancer, which had an 88% accuracy. For 133 BM samples, 132 BM samples were identified as non-GM, and 95% of the 133 BM samples were correctly classified into their corresponding original cancer types. The RMO-based method can accurately identify the origin of BMs, which is important for precision treatment.

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.

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.

GINS complex subunit 4, a prognostic biomarker and reversely mediated by Krüppel-like factor 4, promotes the growth of colorectal cancer

GINS complex subunit 4 (GINS4) is essential for DNA replication initiation and elongation in the G₁ /S phase cell cycle in eukaryotes, however, its functional roles and molecular mechanisms remain unclear in many aspects. Our study was designed to investigate the clinical significance, biological function, and molecular mechanism of GINS4 in colorectal cancer (CRC). First, we confirmed that GINS4 expression was significantly overexpressed in CRC cells and tissues. The immunohistochemical results in tissue microarray from 106 CRC patients showed that a high level of GINS4 expression was positively correlated with advanced T stage, higher tumor TNM stage, and poor differentiation. The results from univariate and multivariate survival analysis models based on 106 CRC patients revealed that GINS4 might serve as an independent prognostic indicator for overall survival and disease-free survival of CRC patients. Moreover, downregulated GINS4 can inhibit growth and the cell cycle and accelerate cell apoptosis progression in vitro as well as inhibit tumorigenesis in vivo. Besides, our results also indicated that Krüppel-like factor 4 (KLF4) can negatively regulate GINS4 expression at the transcriptional level and the KLF/GINS4 pathway might play a vital role in the growth and prognosis of CRC.

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.