Identification of biomarkers for esophageal squamous cell carcinoma using feature selection and decision tree methods

A two-stage hybrid biomarker selection method based on ensemble filter and binary differential evolution incorporating binary African vultures optimization

BACKGROUND

In the field of genomics and personalized medicine, it is a key issue to find biomarkers directly related to the diagnosis of specific diseases from high-throughput gene microarray data. Feature selection technology can discover biomarkers with disease classification information.

RESULTS

We use support vector machines as classifiers and use the five-fold cross-validation average classification accuracy, recall, precision and F1 score as evaluation metrics to evaluate the identified biomarkers. Experimental results show classification accuracy above 0.93, recall above 0.92, precision above 0.91, and F1 score above 0.94 on eight microarray datasets.

METHOD

This paper proposes a two-stage hybrid biomarker selection method based on ensemble filter and binary differential evolution incorporating binary African vultures optimization (EF-BDBA), which can effectively reduce the dimension of microarray data and obtain optimal biomarkers. In the first stage, we propose an ensemble filter feature selection method. The method combines an improved fast correlation-based filter algorithm with Fisher score. obviously redundant and irrelevant features can be filtered out to initially reduce the dimensionality of the microarray data. In the second stage, the optimal feature subset is selected using an improved binary differential evolution incorporating an improved binary African vultures optimization algorithm. The African vultures optimization algorithm has excellent global optimization ability. It has not been systematically applied to feature selection problems, especially for gene microarray data. We combine it with a differential evolution algorithm to improve population diversity.

CONCLUSION

Compared with traditional feature selection methods and advanced hybrid methods, the proposed method achieves higher classification accuracy and identifies excellent biomarkers while retaining fewer features. The experimental results demonstrate the effectiveness and advancement of our proposed algorithmic model.

Ensemble learning for predicting ex vivo human placental barrier permeability

Background

The placental barrier protects the fetus from exposure to some toxicants and is vital for drug development and risk assessment of environmental chemicals. However, in vivo experiments for assessing the placental barrier permeability of chemicals is not ethically acceptable. Although ex vivo placental perfusion methods provide good alternatives for the assessment of placental barrier permeability, the application to a large number of test chemicals could be time- and resource-consuming. Computational prediction models for ex vivo placental barrier permeability are therefore desirable.

Methods

A total of 87 chemicals and corresponding 1444 physicochemical properties were divided into training and test datasets. Three types of algorithms including linear regression, random forest, and ensemble models were applied to develop prediction models for ex vivo placental barrier permeability.

Results

Among the tested models, the ensemble model integrating the previous two methods performed best for predicting ex vivo human placental barrier permeability with correlation coefficients of 0.887 and 0.825 when considering the applicability domain. An additional test on seven newly curated chemicals from the literature showed a good correlation coefficient of 0.879 which was further improved to 0.921 by considering the variation of experiments.

Conclusion

In this study, the first valid predicting model for ex vivo human placental barrier permeability was developed following the OECD guideline. The model is expected to be useful for assessing the human placental barrier permeability and can be integrated with developmental toxicity prediction models for investigating the toxic effects of chemicals on the fetus.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04937-y.

Bioinformatics Characterization of Candidate Genes Associated with Gene Network and miRNA Regulation in Esophageal Squamous Cell Carcinoma Patients

The present study aimed to identify potential therapeutic targets for esophageal squamous cell carcinoma (ESCC). The gene expression profile GSE161533 contained 84 samples, in that 28 tumor tissues and 28 normal tissues encoded as ESCC patients were retrieved from the Gene Expression Omnibus database. The obtained data were validated and screened for differentially expressed genes (DEGs) between normal and tumor tissues with the GEO2R tool. Next, the protein–protein network (PPI) was constructed using the (STRING 2.0) and reconstructed with Cytoscape 3.8.2, and the top ten hub genes (HGsT10) were predicted using the Maximal Clique Centrality (MCC) algorithm of the CytoHubba plugin. The identified hub genes were mapped in GSE161533, and their expression was determined and compared with The Cancer Genome Atlas (TCGA.) ESCC patient’s samples. The overall survival rate for HGsT10 wild and mutated types was analyzed with the Gene Expression Profiling Interactive Analysis2 (GEPIA2) server and UCSC Xena database. The functional and pathway enrichment analysis was performed using the WebGestalt database with the reference gene from lumina human ref 8.v3.0 version. The promoter methylation for the HGsT10 was identified using the UALCAN server. Additionally, the miRNA-HGsT10 regulatory network was constructed to identify the top ten hub miRNAs (miRT10). Finally, we identified the top ten novel driving genes from the DEGs of GSE161533 ESCC patient’s sample using a multi-omics approach. It may provide new insights into the diagnosis and treatment for the ESCC affected patients early in the future.

DIscBIO: A User-Friendly Pipeline for Biomarker Discovery in Single-Cell Transcriptomics

The growing attention toward the benefits of single-cell RNA sequencing (scRNA-seq) is leading to a myriad of computational packages for the analysis of different aspects of scRNA-seq data. For researchers without advanced programing skills, it is very challenging to combine several packages in order to perform the desired analysis in a simple and reproducible way. Here we present DIscBIO, an open-source, multi-algorithmic pipeline for easy, efficient and reproducible analysis of cellular sub-populations at the transcriptomic level. The pipeline integrates multiple scRNA-seq packages and allows biomarker discovery with decision trees and gene enrichment analysis in a network context using single-cell sequencing read counts through clustering and differential analysis. DIscBIO is freely available as an R package. It can be run either in command-line mode or through a user-friendly computational pipeline using Jupyter notebooks. We showcase all pipeline features using two scRNA-seq datasets. The first dataset consists of circulating tumor cells from patients with breast cancer. The second one is a cell cycle regulation dataset in myxoid liposarcoma. All analyses are available as notebooks that integrate in a sequential narrative R code with explanatory text and output data and images. R users can use the notebooks to understand the different steps of the pipeline and will guide them to explore their scRNA-seq data. We also provide a cloud version using Binder that allows the execution of the pipeline without the need of downloading R, Jupyter or any of the packages used by the pipeline. The cloud version can serve as a tutorial for training purposes, especially for those that are not R users or have limited programing skills. However, in order to do meaningful scRNA-seq analyses, all users will need to understand the implemented methods and their possible options and limitations.

Functional genetic variants of RUVBL1 predict overall survival of Chinese patients with epithelial ovarian cancer

To date, the 5-year overall survival of epithelial ovarian cancer (EOC) remains poor. Because studies suggest that RUVBL1 may be a chemotherapeutic target for the treatment of cancer, in this study, therefore, we investigated the role of potentially functional single nucleotide polymorphisms (SNPs) of RUVBL1 in the survival of Chinese patients with EOC, and we subsequently performed functional prediction and validation of the identified significant SNPs. We found that RUVBL1 rs1057156 A>G and RUVBL1 rs149652370 A>G were associated with survival of EOC patients in the multivariate Cox proportional hazards regression analysis. Specifically, the RUVBL1 rs149652370 AG genotype was associated with a shorter progression-free survival ([adjusted hazards ratio (HR)] = 3.32, 95% confidence interval (CI) = 1.76-6.25 and P = 2.01E-04), compared with the AA genotype. The RUVBL1 rs1057156 AG (only nine had GG) genotype was also associated with a poor overall survival (adjusted HR = 1.73, 95% CI = 1.19-2.52, P = 0.004), compared with the AA genotype. Further experiments showed that the RUVBL1 rs1057156 A>G change lowered its binding affinity to microRNA-4294 and led to upregulation of the RUVBL1 expression. We further found that overexpression of RUVBL1 promoted cell proliferation and metastatic potential. Overall, RUVBL1 enhanced EOC cell proliferation, invasion and migration presumably by stimulating the process of glycolysis. Thus, this study provides evidence that functional variants of RUVBL1 may regulate its gene expression, a possible mechanism affecting survival of EOC patients and that RUVBL1 may be a potential chemotherapeutic target for the treatment of EOC patients.

Epigenetic Alterations in Oesophageal Cancer: Expression and Role of the Involved Enzymes

Oesophageal cancer is a life-threatening disease, accounting for high mortality rates. The poor prognosis of this malignancy is mostly due to late diagnosis and lack of effective therapies for advanced disease. Epigenetic alterations may constitute novel and attractive therapeutic targets, owing to their ubiquity in cancer and their reversible nature. Herein, we offer an overview of the most important studies which compared differences in expression of enzymes that mediate epigenetic alterations between oesophageal cancer and normal mucosa, as well as in vitro data addressing the role of these genes/proteins in oesophageal cancer. Furthermore, The Cancer Genome Atlas database was interrogated for the correlation between expression of these epigenetic markers and standard clinicopathological features. We concluded that most epigenetic players studied thus far are overexpressed in tumours compared to normal tissue. Furthermore, functional assays suggest an oncogenic role for most of those enzymes, supporting their potential as therapeutic targets in oesophageal cancer.

Telomerase and Telomeres in Endometrial Cancer

Telomeres at the termini of human chromosomes are shortened with each round of cell division due to the “end replication problem” as well as oxidative stress. During carcinogenesis, cells acquire or retain mechanisms to maintain telomeres to avoid initiation of cellular senescence or apoptosis and halting cell division by critically short telomeres. The unique reverse transcriptase enzyme complex, telomerase, catalyzes the maintenance of telomeres but most human somatic cells do not have sufficient telomerase activity to prevent telomere shortening. Tissues with high and prolonged replicative potential demonstrate adequate cellular telomerase activity to prevent telomere erosion, and high telomerase activity appears to be a critical feature of most (80–90%) epithelial cancers, including endometrial cancer. Endometrial cancers regress in response to progesterone which is frequently used to treat advanced endometrial cancer. Endometrial telomerase is inhibited by progestogens and deciphering telomere and telomerase biology in endometrial cancer is therefore important, as targeting telomerase (a downstream target of progestogens) in endometrial cancer may provide novel and more effective therapeutic avenues. This review aims to examine the available evidence for the role and importance of telomere and telomerase biology in endometrial cancer.

Discovery of Pyrazolo[4,3-c]quinolines Derivatives as Potential Anti-Inflammatory Agents through Inhibiting of NO Production

The synthesis and anti-inflammatory effects of certain pyrazolo[4,3-c]quinoline derivatives 2a–2r are described. The anti-inflammatory activities of these derivatives were evaluated by means of inhibiting nitric oxide (NO) production in lipopolysaccharide (LPS)-induced RAW 264.7 cells. Among them, 3-amino-4-(4-hydroxyphenylamino)-1H-pyrazolo[4,3-c]-quinoline (2i) and 4-(3-amino-1H-pyrazolo[4,3-c]quinolin-4-ylamino)benzoic acid (2m) exhibited significant inhibition of LPS-stimulated NO production with a potency approximately equal to that of the positive control, 1400 W. Important structure features were analyzed by quantitative structure–activity relationship (QSAR) analysis to give better insights into the structure determinants for predicting the inhibitory effects on the accumulation of nitric oxide for RAW 264.7 cells in response to LPS. In addition, our results indicated that their anti-inflammatory effects involve the inhibition of inducible nitric oxide synthase (iNOS) and cyclooxygenase 2 (COX-2) protein expression. Further studies on the structural optimization are ongoing.

Exploration of gene functions for esophageal squamous cell carcinoma using network-based guilt by association principle

Gene networks have been broadly used to predict gene functions based on guilt by association (GBA) principle. Thus, in order to better understand the molecular mechanisms of esophageal squamous cell carcinoma (ESCC), our study was designed to use a network-based GBA method to identify the optimal gene functions for ESCC. To identify genomic bio-signatures for ESCC, microarray data of GSE20347 were first downloaded from a public functional genomics data repository of Gene Expression Omnibus database. Then, differentially expressed genes (DEGs) between ESCC patients and controls were identified using the LIMMA method. Afterwards, construction of differential co-expression network (DCN) was performed relying on DEGs, followed by gene ontology (GO) enrichment analysis based on a known confirmed database and DEGs. Eventually, the optimal gene functions were predicted using GBA algorithm based on the area under the curve (AUC) for each GO term. Overall, 43 DEGs and 67 GO terms were gained for subsequent analysis. GBA predictions demonstrated that 13 GO functions with AUC>0.7 had a good classification ability. Significantly, 6 out of 13 GO terms yielded AUC>0.8, which were determined as the optimal gene functions. Interestingly, there were two GO categories with AUC>0.9, which included cell cycle checkpoint (AUC=0.91648), and mitotic sister chromatid segregation (AUC=0.91597). Our findings highlight the clinical implications of cell cycle checkpoint and mitotic sister chromatid segregation in ESCC progression and provide the molecular foundation for developing therapeutic targets.

Overexpression of ATPase Na+/+ transporting alpha 1 polypeptide, ATP1A1, correlates with clinical diagnosis and progression of esophageal squamous cell carcinoma

This study aims to identify new upregulated genes related to secretory or membranous proteins to help detect esophageal squamous cell carcinoma (ESCC). First, we performed microarray-based screening of esophageal tumors from both N-nitrosomethylbenzylamine- and arecoline-induced F344 rats and seventeen human ESCC specimens. Candidate genes were validated by quantitative PCR (qPCR) and immunohistochemical (IHC) staining of ESCC tissues. Among the paired cancer and adjacent normal tissues from 14 ESCC patients, 10 pairs (71.4%) had overexpression of ATP1A1 (ATPase Na+/K+ transporting alpha 1 polypeptide) by qPCR (P = 0.0052). ATP1A1 protein expression was re-confirmed by tissue arrays in 243 ESCC tissues and 126 adjacent normal tissues and by ELISA in 78 serum specimens of ESCC patients. ATP1A1 was 12.3 times (adjusted odds ratio=12.3, 95% CI = 7.2-21.0) more likely to be overexpressed in cancer tissues than in normal tissues. ATP1A1 expression was also correlated to tumor stage. Patients with higher serum ATP1A1 levels had a 2.9-fold (95% CI = 1.1-7.4) risk of late-stage disease (stages III-IV vs. I-II). Downregulation of ATP1A1 expression inhibited the migration and invasion ability of ESCC cell lines in vitro. We concluded that the overexpression of ATP1A1 is strongly associated with the presence and severity of ESCC.

Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach

Understanding the biological factors that are characteristic of metastasis in melanoma remains a key approach to improving treatment. In this study, we seek to identify a gene signature of metastatic melanoma. We configured a new network-based computational pipeline, combined with a machine learning method, to mine publicly available transcriptomic data from melanoma patient samples. Our method is unbiased and scans a genome-wide protein-protein interaction network using a novel formulation for network scoring. Using this, we identify the most influential, differentially expressed nodes in metastatic as compared to primary melanoma. We evaluated the shortlisted genes by a machine learning method to rank them by their discriminatory capacities. From this, we identified a panel of 6 genes, ALDH1A1, HSP90AB1, KIT, KRT16, SPRR3 and TMEM45B whose expression values discriminated metastatic from primary melanoma (87% classification accuracy). In an independent transcriptomic data set derived from 703 primary melanomas, we showed that all six genes were significant in predicting melanoma specific survival (MSS) in a univariate analysis, which was also consistent with AJCC staging. Further, 3 of these genes, HSP90AB1, SPRR3 and KRT16 remained significant predictors of MSS in a joint analysis (HR = 2.3, P = 0.03) although, HSP90AB1 (HR = 1.9, P = 2 × 10-4) alone remained predictive after adjusting for clinical predictors.

The Role of Pontin and Reptin in Cellular Physiology and Cancer Etiology

Pontin (RUVBL1, TIP49, TIP49a, Rvb1) and Reptin (RUVBL2, TIP48, TIP49b, Rvb2) are highly conserved ATPases of the AAA+ (ATPases Associated with various cellular Activities) superfamily and are involved in various cellular processes that are important for oncogenesis. First identified as being upregulated in hepatocellular carcinoma and colorectal cancer, their overexpression has since been shown in multiple cancer types such as breast, lung, gastric, esophageal, pancreatic, kidney, bladder as well as lymphatic, and leukemic cancers. However, their exact functions are still quite unknown as they interact with many molecular complexes with vastly different downstream effectors. Within the nucleus, Pontin and Reptin participate in the TIP60 and INO80 complexes important for chromatin remodeling. Although not transcription factors themselves, Pontin and Reptin modulate the transcriptional activities of bona fide proto-oncogenes such as MYC and β-catenin. They associate with proteins involved in DNA damage repair such as PIKK complexes as well as with the core complex of Fanconi anemia pathway. They have also been shown to be important for cell cycle progression, being involved in assembly of telomerase, mitotic spindle, RNA polymerase II, and snoRNPs. When the two ATPases localize to the cytoplasm, they were reported to promote cancer cell invasion and metastasis. Due to their various roles in carcinogenesis, it is not surprising that Pontin and Reptin are proving to be important biomarkers for diagnosis and prognosis of various cancers. They are also current targets for the development of new therapeutic anticancer drugs.

Identification of informative features for predicting proinflammatory potentials of engine exhausts

BACKGROUND

The immunotoxicity of engine exhausts is of high concern to human health due to the increasing prevalence of immune-related diseases. However, the evaluation of immunotoxicity of engine exhausts is currently based on expensive and time-consuming experiments. It is desirable to develop efficient methods for immunotoxicity assessment.

METHODS

To accelerate the development of safe alternative fuels, this study proposed a computational method for identifying informative features for predicting proinflammatory potentials of engine exhausts. A principal component regression (PCR) algorithm was applied to develop prediction models. The informative features were identified by a sequential backward feature elimination (SBFE) algorithm.

RESULTS

A total of 19 informative chemical and biological features were successfully identified by SBFE algorithm. The informative features were utilized to develop a computational method named FS-CBM for predicting proinflammatory potentials of engine exhausts. FS-CBM model achieved a high performance with correlation coefficient values of 0.997 and 0.943 obtained from training and independent test sets, respectively.

CONCLUSIONS

The FS-CBM model was developed for predicting proinflammatory potentials of engine exhausts with a large improvement on prediction performance compared with our previous CBM model. The proposed method could be further applied to construct models for bioactivities of mixtures.

Discovery of Indeno[1,2-c]quinoline Derivatives as Potent Dual Antituberculosis and Anti-Inflammatory Agents

A series of indeno[1,2-c]quinoline derivatives were designed, synthesized and evaluated for their anti-tuberculosis (anti-TB) and anti-inflammatory activities. The minimum inhibitory concentration (MIC) of the newly synthesized compound was tested against Mycobacterium tuberculosis H₃₇R_V. Among the tested compounds, (E)-N′-[6-(4-hydroxypiperidin-1-yl)-11H-indeno[1,2-c]quinolin-11-ylidene]isonicotino-hydrazide (12), exhibited significant activities against the growth of M. tuberculosis (MIC values of 0.96 μg/mL) with a potency approximately equal to that of isoniazid (INH), an anti-TB drug. Important structure features were analyzed by quantitative structure–activity relationship (QSAR) analysis to give better insights into the structure determinants for predicting the anti-TB activity. The anti-inflammatory activity was induced by superoxide anion generation and neutrophil elastase (NE) release using the formyl-l-methionyl-l-leucyl-l-phenylalanine (fMLF)-activated human neutrophils method. Results indicated that compound 12 demonstrated a potent dual inhibitory effect on NE release and superoxide anion generation with IC₅₀ values of 1.76 and 1.72 μM, respectively. Our results indicated that compound 12 is a potential lead compound for the discovery of dual anti-TB and anti-inflammatory drug candidates. In addition, 6-[3-(hydroxymethyl)piperidin-1-yl]-9-methoxy-11H-indeno[1,2-c]quinolin-11-one (4g) showed a potent dual inhibitory effect on NE release and superoxide anion generation with IC₅₀ values of 0.46 and 0.68 μM, respectively, and is a potential lead compound for the discovery of anti-inflammatory drug candidates.

Identification of consensus biomarkers for predicting non-genotoxic hepatocarcinogens

The assessment of non-genotoxic hepatocarcinogens (NGHCs) is currently relying on two-year rodent bioassays. Toxicogenomics biomarkers provide a potential alternative method for the prioritization of NGHCs that could be useful for risk assessment. However, previous studies using inconsistently classified chemicals as the training set and a single microarray dataset concluded no consensus biomarkers. In this study, 4 consensus biomarkers of A2m, Ca3, Cxcl1, and Cyp8b1 were identified from four large-scale microarray datasets of the one-day single maximum tolerated dose and a large set of chemicals without inconsistent classifications. Machine learning techniques were subsequently applied to develop prediction models for NGHCs. The final bagging decision tree models were constructed with an average AUC performance of 0.803 for an independent test. A set of 16 chemicals with controversial classifications were reclassified according to the consensus biomarkers. The developed prediction models and identified consensus biomarkers are expected to be potential alternative methods for prioritization of NGHCs for further experimental validation.

Downregulation of RUVBL1 inhibits proliferation of lung adenocarcinoma cells by G1/S phase cell cycle arrest via multiple mechanisms

Lung cancer remains a leading cause of cancer-related mortality and morbidity worldwide, of which non-small cell lung cancer (NSCLC) accounts for 80 %. RUVBL1 is a highly conserved eukaryotic AAA+ adenosine 5'-triphosphatase (ATPase) that has many functions highly relevant to cancer. We therefore attempted to determine the potential role of RUVBL1 in the biogenesis of lung adenocarcinoma and obtained some interesting results. Our study revealed that RUVBL1 expression was higher in lung adenocarcinoma specimens than in those of adjacent non-tumor tissues and in lung cancer cell lines than in normal lung cell lines. RUVBL1 knockdown via siRNA reduced proliferation and caused G1/S phase cell cycle arrest in lung adenocarcinoma cell lines. The G1/S phase cell cycle arrest triggered by RUVBL1 downregulation could be attributed, at least in part, to repression of the AKT/GSK-3β/cyclin D1 pathway and probably to the activation of IRE1α-mediated endoplasmic reticulum (ER) stress. We thus demonstrated for the first time that a knockdown of RUVBL1 could effectively inhibit the proliferation of lung adenocarcinoma A549 and H292 cells through the induction of G1/S phase cell cycle arrest via multiple mechanisms. These observations strongly suggested that RUVBL1 should be considered a promising target for the prevention or therapy of lung adenocarcinoma.

Plasma matrix metalloproteinase 1 improves the detection and survival prediction of esophageal squamous cell carcinoma

This study aimed to identify noninvasive protein markers capable of detecting the presence and prognosis of esophageal squamous-cell carcinoma (ESCC). Analyzing microarray expression data collected from 17-pair ESCC specimens, we identified one protein, matrix metalloproteinase-1 (MMP1), as a possibly useful marker. Plasma MMP1 was then measured by enzyme-linked immunosorbent assay (ELISA) in 210 ESCC patients and 197 healthy controls. ESCC patients had higher mean levels of MMP1 than controls (8.7 ± 7.5 vs. 6.7 ± 4.9 ng/mL, p < 0.0001). Using the highest quartile level (9.67 ng/mL) as cut-off, we found a 9.0-fold risk of ESCC in those with higher plasma MMP1 after adjusting for covariates (95% confidence interval = 2.2, 36.0). Heavy smokers and heavy drinkers with higher plasma MMP1 had 61.4- and 31.0 times the risk, respectively, than non-users with lower MMP1. In the survival analysis, compared to those with MMP1 ≤ 9.67 ng/mL, ESCC patients with MMP1 > 9.67 ng/mL had a 48% increase in the risk of ESCC death (adjusted hazard ratio = 1.48; 95% CI = 1.04-2.10). In conclusion, plasma MMP1 may serve as a noninvasive marker of detecting the presence and predicting the survival of ESCC.