RankProd Combined with Genetic Algorithm Optimized Artificial Neural Network Establishes a Diagnostic and Prognostic Prediction Model that Revealed C1QTNF3 as a Biomarker for Prostate Cancer

Biobanks and biomarkers: Their current and future role in biomedical research

The importance and utility of biobanks has increased exponentially since their inception and creation. Initially used as part of translational research, they now contribute over 40% of data for all cancer research papers in the United States of America and play a crucial role in all aspects of healthcare. Multiple classification systems exist but a simplified approach is to either classify as population-based or disease-oriented entities. Whilst historically publicly funded institutions, there has been a significant increase in industry funded entities across the world which has changed the dynamic of biobanks offering new possibilities but also new challenges. Biobanks face legal questions over data sharing and intellectual property as well as ethical and sustainability questions particularly as the world attempts to move to a low-carbon economy. International collaboration is required to address some of these challenges but this in itself is fraught with complexity and difficulty. This review will examine the current utility of biobanks in the modern healthcare setting as well as the current and future challenges these vital institutions face.

From molecular mechanisms of prostate cancer to translational applications: based on multi-omics fusion analysis and intelligent medicine

Prostate cancer is the most common cancer in men worldwide and has a high mortality rate. The complex and heterogeneous development of prostate cancer has become a core obstacle in the treatment of prostate cancer. Simultaneously, the issues of overtreatment in early-stage diagnosis, oligometastasis and dormant tumor recognition, as well as personalized drug utilization, are also specific concerns that require attention in the clinical management of prostate cancer. Some typical genetic mutations have been proved to be associated with prostate cancer's initiation and progression. However, single-omic studies usually are not able to explain the causal relationship between molecular alterations and clinical phenotypes. Exploration from a systems genetics perspective is also lacking in this field, that is, the impact of gene network, the environmental factors, and even lifestyle behaviors on disease progression. At the meantime, current trend emphasizes the utilization of artificial intelligence (AI) and machine learning techniques to process extensive multidimensional data, including multi-omics. These technologies unveil the potential patterns, correlations, and insights related to diseases, thereby aiding the interpretable clinical decision making and applications, namely intelligent medicine. Therefore, there is a pressing need to integrate multidimensional data for identification of molecular subtypes, prediction of cancer progression and aggressiveness, along with perosonalized treatment performing. In this review, we systematically elaborated the landscape from molecular mechanism discovery of prostate cancer to clinical translational applications. We discussed the molecular profiles and clinical manifestations of prostate cancer heterogeneity, the identification of different states of prostate cancer, as well as corresponding precision medicine practices. Taking multi-omics fusion, systems genetics, and intelligence medicine as the main perspectives, the current research results and knowledge-driven research path of prostate cancer were summarized.

Regulation of iron metabolism in HEC-1A endometrium cells by macrophage-derived factors and fractalkine

Macrophages in the endometrium promote receptivity and implantation by secreting proinflammatory cytokines and other factors like fractalkine (FKN). Macrophages are closely linked to regulating iron homeostasis and can modulate iron availability in the tissue microenvironment. It has been revealed that the iron metabolism of the mother is crucial in fertility. Iron metabolism is strictly controlled by hepcidin, the principal iron regulatory protein. The inflammatory cytokines can modulate hepcidin synthesis and, therefore, the iron metabolism of the endometrium. It was proven recently that FKN, a unique chemokine, is implicated in maternal-fetal communication and may contribute to endometrial receptivity and implantation. In the present study, we investigated the effect of activated THP-1 macrophages and FKN on the iron metabolism of the HEC-1A endometrial cells. We established a noncontact coculture with or without recombinant human FKN supplementation to study the impact of the macrophage-derived factors and FKN on the regulation of hepcidin synthesis and iron release and storage of endometrial cells. Based on our findings, the conditioned medium of the activated macrophages could modify hepcidin synthesis via the nuclear factor kappa-light-chain-enhancer of activated B cells, the signal transducer and activator of transcription 3, and the transferrin receptor 2/bone morphogenetic protein 6/suppressor of mothers against decapentaplegic 1/5/8 signaling pathways, and FKN could alter this effect on the endometrial cells. It was also revealed that the conditioned macrophage medium and FKN modulated the iron release and storage of HEC-1A cells. FKN signaling may be involved in the management of iron trafficking of the endometrium by the regulation of hepcidin. It can contribute to the iron supply for fetal development at the early stage of the pregnancy.

Assessment of Prostate and Bladder Cancer Genomic Biomarkers Using Artificial Intelligence: a Systematic Review

PURPOSE OF REVIEW

The aim of the systematic review is to assess AI's capabilities in the genetics of prostate cancer (PCa) and bladder cancer (BCa) to evaluate target groups for such analysis as well as to assess its prospects in daily practice.

RECENT FINDINGS

In total, our analysis included 27 articles: 10 articles have reported on PCa and 17 on BCa, respectively. The AI algorithms added clinical value and demonstrated promising results in several fields, including cancer detection, assessment of cancer development risk, risk stratification in terms of survival and relapse, and prediction of response to a specific therapy. Besides clinical applications, genetic analysis aided by the AI shed light on the basic urologic cancer biology. We believe, our results of the AI application to the analysis of PCa, BCa data sets will help to identify new targets for urological cancer therapy. The integration of AI in genomic research for screening and clinical applications will evolve with time to help personalizing chemotherapy, prediction of survival and relapse, aid treatment strategies such as reducing frequency of diagnostic cystoscopies, and clinical decision support, e.g., by predicting immunotherapy response. These factors will ultimately lead to personalized and precision medicine thereby improving patient outcomes.

Systematic review and integrated analysis of prognostic gene signatures for prostate cancer patients

Prostate cancer (PC) is one of the most common cancers in men and becoming the second leading cause of cancer fatalities. At present, the lack of effective strategies for prognosis of PC patients is still a problem to be solved. Therefore, it is significant to identify potential gene signatures for PC patients' prognosis. Here, we summarized 71 different prognostic gene signatures for PC and concluded 3 strategies for signature construction after extensive investigation. In addition, 14 genes frequently appeared in 71 different gene signatures, which enriched in mitotic and cell cycle. This review provides extensive understanding and integrated analysis of current prognostic signatures of PC, which may help researchers to construct gene signatures of PC and guide future clinical treatment.

Fatty-Acid-Binding Proteins: From Lipid Transporters to Disease Biomarkers

Fatty-acid-binding proteins (FABPs) serve a crucial role in the metabolism and transport of fatty acids and other hydrophobic ligands as an intracellular protein family. They are also recognized as a critical mediator in the inflammatory and ischemic pathways. FABPs are found in a wide range of tissues and organs, allowing them to contribute to various disease/injury developments that have not been widely discussed. We have collected and analyzed research journals that have investigated the role of FABPs in various diseases. Through this review, we discuss the findings on the potential of FABPs as biomarkers for various diseases in different tissues and organs, looking at their expression levels and their roles in related diseases according to available literature data. FABPs have been reported to show significantly increased expression levels in various tissues and organs associated with metabolic and inflammatory diseases. Therefore, FABPs are a promising novel biomarker that needs further development to optimize disease diagnosis and prognosis methods along with previously discovered markers.

Artificial intelligence and allied subsets in early detection and preclusion of gynecological cancers

Gynecological cancers including breast, cervical, ovarian, uterine, and vaginal, pose the greatest threat to world health, with early identification being crucial to patient outcomes and survival rates. The application of machine learning (ML) and artificial intelligence (AI) approaches to the study of gynecological cancer has shown potential to revolutionize cancer detection and diagnosis. The current review outlines the significant advancements, obstacles, and prospects brought about by AI and ML technologies in the timely identification and accurate diagnosis of different types of gynecological cancers. The AI-powered technologies can use genomic data to discover genetic alterations and biomarkers linked to a particular form of gynecologic cancer, assisting in the creation of targeted treatments. Furthermore, it has been shown that the potential benefits of AI and ML technologies in gynecologic tumors can greatly increase the accuracy and efficacy of cancer diagnosis, reduce diagnostic delays, and possibly eliminate the need for needless invasive operations. In conclusion, the review focused on the integrative part of AI and ML based tools and techniques in the early detection and exclusion of various cancer types; together with a collaborative coordination between research clinicians, data scientists, and regulatory authorities, which is suggested to realize the full potential of AI and ML in gynecologic cancer care.

Fatty acid binding protein 5 regulates docetaxel sensitivity in taxane-resistant prostate cancer cells

Prostate cancer is a leading cause of cancer-related deaths in men in the United States. Although treatable when detected early, prostate cancer commonly transitions to an aggressive castration-resistant metastatic state. While taxane chemotherapeutics such as docetaxel are mainstay treatment options for prostate cancer, taxane resistance often develops. Fatty acid binding protein 5 (FABP5) is an intracellular lipid chaperone that is upregulated in advanced prostate cancer and is implicated as a key driver of its progression. The recent demonstration that FABP5 inhibitors produce synergistic inhibition of tumor growth when combined with taxane chemotherapeutics highlights the possibility that FABP5 may regulate other features of taxane function, including resistance. Employing taxane-resistant DU145-TXR cells and a combination of cytotoxicity, apoptosis, and cell cycle assays, our findings demonstrate that FABP5 knockdown sensitizes the cells to docetaxel. In contrast, docetaxel potency was unaffected by FABP5 knockdown in taxane-sensitive DU145 cells. Taxane-resistance in DU145-TXR cells stems from upregulation of the P-glycoprotein ATP binding cassette subfamily B member 1 (ABCB1). Expression analyses and functional assays confirmed that FABP5 knockdown in DU145-TXR cells markedly reduced ABCB1 expression and activity, respectively. Our study demonstrates a potential new function for FABP5 in regulating taxane sensitivity and the expression of a major P-glycoprotein efflux pump in prostate cancer cells.

Artificial Intelligence in Urooncology: What We Have and What We Expect

INTRODUCTION

Artificial intelligence is transforming healthcare by driving innovation, automation, and optimization across various fields of medicine. The aim of this study was to determine whether artificial intelligence (AI) techniques can be used in the diagnosis, treatment planning, and monitoring of urological cancers.

METHODOLOGY

We conducted a thorough search for original and review articles published until 31 May 2022 in the PUBMED/Scopus database. Our search included several terms related to AI and urooncology. Articles were selected with the consensus of all authors.

RESULTS

Several types of AI can be used in the medical field. The most common forms of AI are machine learning (ML), deep learning (DL), neural networks (NNs), natural language processing (NLP) systems, and computer vision. AI can improve various domains related to the management of urologic cancers, such as imaging, grading, and nodal staging. AI can also help identify appropriate diagnoses, treatment options, and even biomarkers. In the majority of these instances, AI is as accurate as or sometimes even superior to medical doctors.

CONCLUSIONS

AI techniques have the potential to revolutionize the diagnosis, treatment, and monitoring of urologic cancers. The use of AI in urooncology care is expected to increase in the future, leading to improved patient outcomes and better overall management of these tumors.

Eye Melanoma Diagnosis System using Statistical Texture Feature Extraction and Soft Computing Techniques

BACKGROUND

Eye melanoma is deforming in the eye, growing and developing in tissues inside the middle layer of an eyeball, resulting in dark spots in the iris section of the eye, changes in size, the shape of the pupil, and vision.

OBJECTIVE

The current study aims to diagnose eye melanoma using a gray level co-occurrence matrix (GLCM) for texture extraction and soft computing techniques, leading to the disease diagnosis faster, time-saving, and prevention of misdiagnosis resulting from the physician's manual approach.

MATERIAL AND METHODS

In this experimental study, two models are proposed for the diagnosis of eye melanoma, including backpropagation neural networks (BPNN) and radial basis functions network (RBFN). The images used for training and validating were obtained from the eye-cancer database.

RESULTS

Based on our experiments, our proposed models achieve 92.31% and 94.70% recognition rates for GLCM+BPNN and GLCM+RBFN, respectively.

CONCLUSION

Based on the comparison of our models with the others, the models used in the current study outperform other proposed models.

Susceptibility identification for seasonal influenza A/H3N2 based on baseline blood transcriptome

Introduction

Influenza susceptibility difference is a widely existing trait that has great practical significance for the accurate prevention and control of influenza.

Methods

Here, we focused on the human susceptibility to the seasonal influenza A/H3N2 of healthy adults at baseline level. Whole blood expression data for influenza A/H3N2 susceptibility from GEO were collected firstly (30 symptomatic and 19 asymptomatic). Then to explore the differences at baseline, a suite of systems biology approaches - the differential expression analysis, co-expression network analysis, and immune cell frequencies analysis were utilized.

Results

We found the baseline condition, especially immune condition between symptomatic and asymptomatic, was different. Co-expression module that is positively related to asymptomatic is also related to immune cell type of naïve B cell. Function enrichment analysis showed significantly correlation with "B cell receptor signaling pathway", "immune response-activating cell surface receptor signaling pathway" and so on. Also, modules that are positively related to symptomatic are also correlated to immune cell type of neutrophils, with function enrichment analysis showing significantly correlations with "response to bacterium", "inflammatory response", "cAMP-dependent protein kinase complex" and so on. Responses of symptomatic and asymptomatic hosts after virus exposure show differences on resisting the virus, with more effective frontline defense for asymptomatic hosts. A prediction model was also built based on only baseline transcription information to differentiate symptomatic and asymptomatic population with accuracy of 0.79.

Discussion

The results not only improve our understanding of the immune system and influenza susceptibility, but also provide a new direction for precise and targeted prevention and therapy of influenza.

Pediatric Crohn's disease diagnosis aid via genomic analysis and machine learning

Introduction

Determination of pediatric Crohn's disease (CD) remains a major diagnostic challenge. However, the rapidly emerging field of artificial intelligence has demonstrated promise in developing diagnostic models for intractable diseases.

Methods

We propose an artificial neural network model of 8 gene markers identified by 4 classification algorithms based on Gene Expression Omnibus database for diagnostic of pediatric CD.

Results

The model achieved over 85% accuracy and area under ROC curve value in both training set and testing set for diagnosing pediatric CD. Additionally, immune infiltration analysis was performed to address why these markers can be integrated to develop a diagnostic model.

Conclusion

This study supports further clinical facilitation of precise disease diagnosis by integrating genomics and machine learning algorithms in open-access database.

Establishment and analysis of a disease risk prediction model for the systemic lupus erythematosus with random forest

Systemic lupus erythematosus (SLE) is a latent, insidious autoimmune disease, and with the development of gene sequencing in recent years, our study aims to develop a gene-based predictive model to explore the identification of SLE at the genetic level. First, gene expression datasets of SLE whole blood samples were collected from the Gene Expression Omnibus (GEO) database. After the datasets were merged, they were divided into training and validation datasets in the ratio of 7:3, where the SLE samples and healthy samples of the training dataset were 334 and 71, respectively, and the SLE samples and healthy samples of the validation dataset were 143 and 30, respectively. The training dataset was used to build the disease risk prediction model, and the validation dataset was used to verify the model identification ability. We first analyzed differentially expressed genes (DEGs) and then used Lasso and random forest (RF) to screen out six key genes (OAS3, USP18, RTP4, SPATS2L, IFI27 and OAS1), which are essential to distinguish SLE from healthy samples. With six key genes incorporated and five iterations of 10-fold cross-validation performed into the RF model, we finally determined the RF model with optimal mtry. The mean values of area under the curve (AUC) and accuracy of the models were over 0.95. The validation dataset was then used to evaluate the AUC performance and our model had an AUC of 0.948. An external validation dataset (GSE99967) with an AUC of 0.810, an accuracy of 0.836, and a sensitivity of 0.921 was used to assess the model's performance. The external validation dataset (GSE185047) of all SLE patients yielded an SLE sensitivity of up to 0.954. The final high-throughput RF model had a mean value of AUC over 0.9, again showing good results. In conclusion, we identified key genetic biomarkers and successfully developed a novel disease risk prediction model for SLE that can be used as a new SLE disease risk prediction aid and contribute to the identification of SLE.

Single-cell transcriptomics reveals cell type diversity of human prostate

Extensive studies have been performed to describe the phenotypic changes occurring during malignant transformation of the prostate. However, the cell types and associated changes that contribute to the development of prostate diseases and cancer remain elusive, largely due to the heterogeneous composition of prostatic tissues. Here, we conduct a comprehensive evaluation of four human prostate tissues by single-cell RNA sequencing (scRNA-seq) to analyze their cellular compositions. We identify 18 clusters of cell types, each with distinct gene expression profiles and unique features; of these, one cluster of epithelial cells (Ep) is found to be associated with immune function. In addition, we characterize a special cluster of fibroblasts and aberrant signaling changes associated with prostate cancer (PCa). Moreover, we provide insights into the epithelial changes that occur during the cellular senescence and aging. These results expand our understanding of the unique functional associations between the diverse prostatic cell types and the contributions of specific cell clusters to the malignant transformation of prostate tissues and PCa development.

Cancer glycomics offers potential biomarkers and therapeutic targets in the framework of 3P medicine

Glycosylation is one of the most important post-translational modifications (PTMs) in a protein, and is the most abundant and diverse biopolymer in nature. Glycans are involved in multiple biological processes of cancer initiation and progression, including cell-cell interactions, cell-extracellular matrix interactions, tumor invasion and metastasis, tumor angiogenesis, and immune regulation. As an important biomarker, tumor-associated glycosylation changes have been extensively studied. This article reviews recent advances in glycosylation-based biomarker research, which is useful for cancer diagnosis and prognostic assessment. Truncated O-glycans, sialylation, fucosylation, and complex branched structures have been found to be the most common structural patterns in malignant tumors. In recent years, immunochemical methods, lectin recognition-based methods, mass spectrometry (MS)-related methods, and fluorescence imaging-based in situ methods have greatly promoted the discovery and application potentials of glycomic and glycoprotein biomarkers in various cancers. In particular, MS-based proteomics has significantly facilitated the comprehensive research of extracellular glycoproteins, increasing our understanding of their critical roles in regulating cellular activities. Predictive, preventive and personalized medicine (PPPM; 3P medicine) is an effective approach of early prediction, prevention and personalized treatment for different patients, and it is known as the new direction of medical development in the 21st century and represents the ultimate goal and highest stage of medical development. Glycosylation has been revealed to have new diagnostic, prognostic, and even therapeutic potentials. The purpose of glycosylation analysis and utilization of biology is to make a fundamental change in health care and medical practice, so as to lead medical research and practice into a new era of 3P medicine.

LTBP2 inhibits prostate cancer progression and metastasis via the PI3K/AKT signaling pathway

Biochemical recurrence (BCR) is a cause of concern in advanced prostate cancer (PCa). Thus, novel diagnostic biomarkers are required to improve clinical care. However, research on PCa immunotherapy is also scarce. Hence, the present study aimed to explore promising BCR-related diagnostic biomarkers, and their expression pattern, prognostic value, immune response effects, biological functions, and possible molecular mechanisms were evaluated. GEO datasets (GSE46602, GSE70768, and GSE116918) were downloaded and merged as the training cohort, and differential expression analysis was performed. Lasso regression and SVM-RFE algorithm, as well as PPI analysis and MCODE algorithm, were then applied to filter BCR-related biomarker genes. The CIBERSORT and estimation of stromal and immune cells in malignant tumor tissues using expression data (ESTIMATE) methods were used to calculate the fractions of tumor-infiltrating immune cells. GO/DO enrichment analyses were used to identify the biological functions. The expression of latent transforming growth factor β-binding protein 2 (LTBP2) was determined by RT-qPCR and western blotting. The role of LTBP2 in PCa was determined by CCK-8, Transwell, and the potential mechanism was investigated by KEGG and GSEA and confirmed by western blotting. In total, 44 BCR-related differentially expressed genes (DEGs) in the training cohort were screened. LTBP2 was found to be a diagnostic biomarker of BCR in PCa and was associated with CD4⁺ T-cell infiltration and response to anti-PD-1/PD-L1 immunotherapy. Subsequently, using the ESTIMATE algorithm, it was identified that LTBP2 was associated with the tumor microenvironment and could be a predictor of the clinical benefit of immune checkpoint blockade. Finally, the expression and biological function of LTBP2 were evaluated via cellular experiments. The results showed that LTBP2 was downregulated in PCa cells and inhibited PCa proliferation and metastasis via the PI3K/AKT signaling pathway in vitro. In conclusion, LTBP2 was a promising diagnostic biomarker of BCR of PCa and had an important role in CD4⁺ T-cell recruitment. Moreover, it was associated with immunotherapy in patients with PCa who developed BCR, and it inhibited PCa proliferation and metastasis via the PI3K/AKT signaling pathway in vitro.

Identification of hub genes and biological pathways in glioma via integrated bioinformatics analysis

OBJECTIVE

Glioma is the most common intracranial primary malignancy, but its pathogenesis remains unclear.

METHODS

We integrated four eligible glioma microarray datasets from the gene expression omnibus database using the robust rank aggregation method to identify a group of significantly differently expressed genes (DEGs) between glioma and normal samples. We used these DEGs to explore key genes closely associated with glioma survival through weighted gene co-expression network analysis. We then constructed validations of prognosis and survival analyses for the key genes via multiple databases. We also explored their potential biological functions using gene set enrichment analysis (GSEA) and gene set variation analysis (GSVA).

RESULTS

We selected DLGAP5, CDCA8, NCAPH, and CCNB2, as four genes that were abnormally up-regulated in glioma samples, for verification. They showed high levels of isocitrate dehydrogenase gene mutation and tumor grades, as well as good prognostic and diagnostic value for glioma. Their methylation levels were generally lower in glioma samples. GSEA and GSVA analyses suggested the genes were closely involved with glioma proliferation.

CONCLUSION

These findings provide new insights into the pathogenesis of glioma. The hub genes have the potential to be used as diagnostic and therapeutic markers.

Assessing the Potential Prognostic and Immunological Role of TK1 in Prostate Cancer

Background: It has been reported that thymidine kinase 1 (TK1) was up-regulated in multiple malignancies and participated in the regulation of tumor malignant behavior. However, its specific role in prostate cancer (PCa) remains unclear. Methods: TK1 expression in PCa patients and cell lines was identified via crossover analysis of the public datasets. A series of in vitro experiments and in vivo models was applied to investigate the function of TK1 in PCa. Functional enrichment analyses were further conducted to explore the underlying mechanism. Additionally, TISIDB was applied to explore the correlation between TK1 expression and tumor-infiltrating lymphocytes, immune subtypes, and immune regulatory factors. Results: TK1 expression was significantly up-regulated in PCa patients and cell lines. TK1 ablation inhibited tumor cell proliferation and migration potential, and in vivo experiments showed that TK1 inactivation can significantly restrain tumor growth. Functional enrichment analysis revealed TK1-related hub genes (AURKB, CCNB2, CDC20, CDCA5, CDK1, CENPA, CENPM, KIF2C, NDC80, NUF2, PLK1, SKA1, SPC25, ZWINT), and found that TK1 was closely involved in the regulation of cell cycle. Moreover, elevated mRNA expression of TK1 was related with higher Gleason score, higher clinical stage, higher pathological stage, higher lymph node stage, shorter overall survival, and DFS in PCa patients. Particularly, TK1 represented attenuated expression in C3 PCa and was related with infiltration of CD4+, CD8+ T cells, and dendritic cells as well as immunomodulator expression. Conclusion: Our study indicates that TK1 is a prognostic predictor correlated with poor outcomes of PCa patients, and for the first time represented that TK1 can promote the progression of PCa. Therefore, TK1 may be a potential diagnostic and prognostic biomarker, as well as a therapeutic target for PCa.

Establishment of an Artificial Neural Network Model Using Immune-Infiltration Related Factors for Endometrial Receptivity Assessment

Background: A comprehensive clinical strategy for infertility involves treatment and, more importantly, post-treatment evaluation. As a component of assessment, endometrial receptivity does not have a validated tool. This study was anchored on immune factors, which are critical factors affecting embryonic implantation. We aimed at establishing novel approaches for assessing endometrial receptivity to guide clinical practice. Methods: Immune-infiltration levels in the GSE58144 dataset (n = 115) from GEO were analysed by digital deconvolution and validated by immunofluorescence (n = 23). Then, modules that were most associated with M1/M2 macrophages and their hub genes were selected by weighted gene co-expression network as well as univariate analyses and validated using the GSE5099 macrophage dataset and qPCR analysis (n = 19). Finally, the artificial neural network model was established from hub genes and its predictive efficacy validated using the GSE165004 dataset (n = 72). Results: Dysregulation of M1 to M2 macrophage ratio is an important factor contributing to defective endometrial receptivity. M1/M2 related gene modules were enriched in three biological processes in macrophages: antigen presentation, interleukin-1-mediated signalling pathway, and phagosome acidification. Their hub genes were significantly altered in patients and associated with ribosomal, lysosomal, and proteasomal pathways. The established model exhibited an excellent predictive value in both datasets, with an accuracy of 98.3% and an AUC of 0.975 (95% CI 0.945–1). Conclusions: M1/M2 polarization influences endometrial receptivity by regulating three gene modules, while the established ANN model can be used to effectively assess endometrial receptivity to inform pregnancy and individualized clinical management strategies.

Transcriptomics and network analysis highlight potential pathways in the pathogenesis of pterygium

Pterygium is a common ocular surface condition frequently associated with irritative symptoms. The precise identity of its critical triggers as well as the hierarchical relationship between all the elements involved in the pathogenesis of this disease are not yet elucidated. Meta-analysis of gene expression studies represents a novel strategy capable of identifying key pathogenic mediators and therapeutic targets in complex diseases. Samples from nine patients were collected during surgery after photo documentation and clinical characterization of pterygia. Gene expression experiments were performed using Human Clariom D Assay gene chip. Differential gene expression analysis between active and atrophic pterygia was performed using limma package after adjusting variables by age. In addition, a meta-analysis was performed including recent gene expression studies available at the Gene Expression Omnibus public repository. Two databases including samples from adults with pterygium and controls fulfilled our inclusion criteria. Meta-analysis was performed using the Rank Production algorithm of the RankProd package. Gene set analysis was performed using ClueGO and the transcription factor regulatory network prediction was performed using appropriate bioinformatics tools. Finally, miRNA-mRNA regulatory network was reconstructed using up-regulated genes identified in the gene set analysis from the meta-analysis and their interacting miRNAs from the Brazilian cohort expression data. The meta-analysis identified 154 up-regulated and 58 down-regulated genes. A gene set analysis with the top up-regulated genes evidenced an overrepresentation of pathways associated with remodeling of extracellular matrix. Other pathways represented in the network included formation of cornified envelopes and unsaturated fatty acid metabolic processes. The miRNA-mRNA target prediction network, also reconstructed based on the set of up-regulated genes presented in the gene ontology and biological pathways network, showed that 17 target genes were negatively correlated with their interacting miRNAs from the Brazilian cohort expression data. Once again, the main identified cluster involved extracellular matrix remodeling mechanisms, while the second cluster involved formation of cornified envelope, establishment of skin barrier and unsaturated fatty acid metabolic process. Differential expression comparing active pterygium with atrophic pterygium using data generated from the Brazilian cohort identified differentially expressed genes between the two forms of presentation of this condition. Our results reveal differentially expressed genes not only in pterygium, but also in active pterygium when compared to the atrophic ones. New insights in relation to pterygium's pathophysiology are suggested.

Transcriptomic Analysis of Breast Cancer Patients Sensitive and Resistant to Chemotherapy: Looking for Overall Survival and Drug Resistance Biomarkers

Worldwide breast cancer ranks first in mortality and incidence rates in women over 20 years old. Rather than one disease, breast cancer is a heterogeneous group of diseases that express distinct molecular profiles. Neoadjuvant chemotherapy is an important therapeutic strategy for breast cancer patients independently of their molecular subtype, with the drawback of resistance development. In addition, chemotherapy has adverse effects that combined with resistance could contribute to lower overall survival. Although great efforts have been made to find diagnostic and prognostic biomarkers for breast cancer and for response to targeted and immune therapy for this pathology, little has been explored regarding biomarkers of response to anthracyclines and taxanes based neoadjuvant chemotherapy. This work aimed to evaluate the molecular profile of patients who received neoadjuvant chemotherapy to identify differentially expressed genes (DEGs) that could be used as biomarkers of chemotherapy response and overall survival. Breast cancer patients who were candidates for neoadjuvant chemotherapy were enrolled in this study. After treatment and according to their pathological response, they were assigned as sensitive or resistant. To evaluate DEGs, Gene Ontology, Kyoto Encyclopedia Gene and Genome (KEGG), and protein–protein interactions, RNA-seq information from all patients was obtained by next-generation sequencing. A total of 1985 DEGs were found, and KEGG analysis indicated a great number of DEGs in metabolic pathways, pathways in cancer, cytokine–cytokine receptor interactions, and neuroactive ligand-receptor interactions. A selection of 73 DEGs was used further for an analysis of overall survival using the METABRIC study and the ductal carcinoma dataset of The Cancer Genome Atlas (TCGA) database. Nine DEGs correlated with overall survival, of which the subexpression of C1QTNF3, CTF1, OLFML3, PLA2R1, PODN, KRT15, HLA-A, and the overexpression of TUBB and TCP1 were found in resistant patients and related to patients with lower overall survival.

Kynurenine and Hemoglobin as Sex-Specific Variables in COVID-19 Patients: A Machine Learning and Genetic Algorithms Approach

Differences in clinical manifestations, immune response, metabolic alterations, and outcomes (including disease severity and mortality) between men and women with COVID-19 have been reported since the pandemic outbreak, making it necessary to implement sex-specific biomarkers for disease diagnosis and treatment. This study aimed to identify sex-associated differences in COVID-19 patients by means of a genetic algorithm (GALGO) and machine learning, employing support vector machine (SVM) and logistic regression (LR) for the data analysis. Both algorithms identified kynurenine and hemoglobin as the most important variables to distinguish between men and women with COVID-19. LR and SVM identified C10:1, cough, and lysoPC a 14:0 to discriminate between men with COVID-19 from men without, with LR being the best model. In the case of women with COVID-19 vs. women without, SVM had a higher performance, and both models identified a higher number of variables, including 10:2, lysoPC a C26:0, lysoPC a C28:0, alpha-ketoglutaric acid, lactic acid, cough, fever, anosmia, and dysgeusia. Our results demonstrate that differences in sexes have implications in the diagnosis and outcome of the disease. Further, genetic and machine learning algorithms are useful tools to predict sex-associated differences in COVID-19.

How can artificial intelligence be used for peptidomics?

INTRODUCTION

Peptidomics is an emerging field of omics sciences using advanced isolation, analysis, and computational techniques that enable qualitative and quantitative analyses of various peptides in biological samples. Peptides can act as useful biomarkers and as therapeutic molecules for diseases.

AREAS COVERED

The use of therapeutic peptides can be predicted quickly and efficiently using data-driven computational methods, particularly artificial intelligence (AI) approach. Various AI approaches are useful for peptide-based drug discovery, such as support vector machine, random forest, extremely randomized trees, and other more recently developed deep learning methods. AI methods are relatively new to the development of peptide-based therapies, but these techniques already become essential tools in protein science by dissecting novel therapeutic peptides and their functions (Figure 1).[Figure: see text].

EXPERT OPINION

Researchers have shown that AI models can facilitate the development of peptidomics and selective peptide therapies in the field of peptide science. Biopeptide prediction is important for the discovery and development of successful peptide-based drugs. Due to their ability to predict therapeutic roles based on sequence details, many AI-dependent prediction tools have been developed (Figure 1).

Leveraging Genetic Reports and Electronic Health Records for the Prediction of Primary Cancers: Algorithm Development and Validation Study

BACKGROUND

Precision oncology has the potential to leverage clinical and genomic data in advancing disease prevention, diagnosis, and treatment. A key research area focuses on the early detection of primary cancers and potential prediction of cancers of unknown primary in order to facilitate optimal treatment decisions.

OBJECTIVE

This study presents a methodology to harmonize phenotypic and genetic data features to classify primary cancer types and predict cancers of unknown primaries.

METHODS

We extracted genetic data elements from oncology genetic reports of 1011 patients with cancer and their corresponding phenotypical data from Mayo Clinic's electronic health records. We modeled both genetic and electronic health record data with HL7 Fast Healthcare Interoperability Resources. The semantic web Resource Description Framework was employed to generate the network-based data representation (ie, patient-phenotypic-genetic network). Based on the Resource Description Framework data graph, Node2vec graph-embedding algorithm was applied to generate features. Multiple machine learning and deep learning backbone models were compared for cancer prediction performance.

RESULTS

With 6 machine learning tasks designed in the experiment, we demonstrated the proposed method achieved favorable results in classifying primary cancer types (area under the receiver operating characteristic curve [AUROC] 96.56% for all 9 cancer predictions on average based on the cross-validation) and predicting unknown primaries (AUROC 80.77% for all 8 cancer predictions on average for real-patient validation). To demonstrate the interpretability, 17 phenotypic and genetic features that contributed the most to the prediction of each cancer were identified and validated based on a literature review.

CONCLUSIONS

Accurate prediction of cancer types can be achieved with existing electronic health record data with satisfactory precision. The integration of genetic reports improves prediction, illustrating the translational values of incorporating genetic tests early at the diagnosis stage for patients with cancer.

Clinical applications of artificial intelligence and machine learning in cancer diagnosis: looking into the future

Artificial intelligence (AI) is the use of mathematical algorithms to mimic human cognitive abilities and to address difficult healthcare challenges including complex biological abnormalities like cancer. The exponential growth of AI in the last decade is evidenced to be the potential platform for optimal decision-making by super-intelligence, where the human mind is limited to process huge data in a narrow time range. Cancer is a complex and multifaced disorder with thousands of genetic and epigenetic variations. AI-based algorithms hold great promise to pave the way to identify these genetic mutations and aberrant protein interactions at a very early stage. Modern biomedical research is also focused to bring AI technology to the clinics safely and ethically. AI-based assistance to pathologists and physicians could be the great leap forward towards prediction for disease risk, diagnosis, prognosis, and treatments. Clinical applications of AI and Machine Learning (ML) in cancer diagnosis and treatment are the future of medical guidance towards faster mapping of a new treatment for every individual. By using AI base system approach, researchers can collaborate in real-time and share knowledge digitally to potentially heal millions. In this review, we focused to present game-changing technology of the future in clinics, by connecting biology with Artificial Intelligence and explain how AI-based assistance help oncologist for precise treatment.

Novel prognostic prediction model constructed through machine learning on the basis of methylation-driven genes in kidney renal clear cell carcinoma

Kidney renal clear cell carcinoma (KIRC) is a common tumor with poor prognosis and is closely related to many aberrant gene expressions. DNA methylation is an important epigenetic modification mechanism and a novel research target. Thus, exploring the relationship between methylation-driven genes and KIRC prognosis is important. The methylation profile, methylation-driven genes, and methylation characteristics in KIRC was revealed through the integration of KIRC methylation, RNA-seq, and clinical information data from The Cancer Genome Atlas. The Lasso regression was used to establish a prognosis model on the basis of methylation-driven genes. Then, a trans-omics prognostic nomogram was constructed and evaluated by combining clinical information and methylated prognosis model. A total of 242 methylation-driven genes were identified. The Gene Ontology terms of these methylation-driven genes mainly clustered in the activation, adhesion, and proliferation of immune cells. The methylation prognosis prediction model that was established using the Lasso regression included four genes in the methylation data, namely, FOXI2, USP44, EVI2A, and TRIP13. The areas under the receiver operating characteristic curve of 1-, 3-, and 5-year survival rates were 0.810, 0.824, and 0.799, respectively, in the training group and 0.794, 0.752, and 0.731, respectively, in the testing group. An easy trans-omics nomogram was successfully established. The C-indices of the nomogram in the training and the testing groups were 0.8015 and 0.8389, respectively. The present study revealed the overall perspective of methylation-driven genes in KIRC and can help in the evaluation of the prognosis of KIRC patients and provide new clues for further study.

A practical method to screen and identify functioning biomarkers in nasopharyngeal carcinoma

Nasopharyngeal carcinoma (NPC) is a rare malignancy, with the unique geographical and ethnically characteristics of distribution. Gene chip and bioinformatics have been employed to reveal regulatory mechanisms in current functional genomics. However, a practical solution addressing the unresolved aspects of microarray data processing and analysis have been long pursuit. This study developed a new method to improve the accuracy of identifying key biomarkers, namely Unit Gamma Measurement (UGM), accounting for multiple hypotheses test statistics distribution, which could reduce the dependency problem. Three mRNA expression profile of NPC were selected to feed UGM. Differentially expressed genes (DEGs) were identified with UGM and hub genes were derived from them to explore their association with NPC using functional enrichment and pathway analysis. 47 potential DEGs were identified by UGM from the 3 selected datasets, and affluent in cysteine-type endopeptidase inhibitor activity, cilium movement, extracellular exosome etc. also participate in ECM-receptor interaction, chemical carcinogenesis, TNF signaling pathway, small cell lung cancer and mismatch repair pathway. Down-regulation of CAPS and WFDC2 can prolongation of the overall survival periods in the patients. ARMC4, SERPINB3, MUC4 etc. have a close relationship with NPC. The UGM is a practical method to identify NPC-associated genes and biomarkers.

A machine learning-based gene signature of response to the novel alkylating agent LP-184 distinguishes its potential tumor indications

BACKGROUND

Non-targeted cytotoxics with anticancer activity are often developed through preclinical stages using response criteria observed in cell lines and xenografts. A panel of the NCI-60 cell lines is frequently the first line to define tumor types that are optimally responsive. Open data on the gene expression of the NCI-60 cell lines, provides a unique opportunity to add another dimension to the preclinical development of such drugs by interrogating correlations with gene expression patterns. Machine learning can be used to reduce the complexity of whole genome gene expression patterns to derive manageable signatures of response. Application of machine learning in early phases of preclinical development is likely to allow a better positioning and ultimate clinical success of molecules. LP-184 is a highly potent novel alkylating agent where the preclinical development is being guided by a dedicated machine learning-derived response signature. We show the feasibility and the accuracy of such a signature of response by accurately predicting the response to LP-184 validated using wet lab derived IC50s on a panel of cell lines.

RESULTS

We applied our proprietary RADR® platform to an NCI-60 discovery dataset encompassing LP-184 IC50s and publicly available gene expression data. We used multiple feature selection layers followed by the XGBoost regression model and reduced the complexity of 20,000 gene expression values to generate a 16-gene signature leading to the identification of a set of predictive candidate biomarkers which form an LP-184 response gene signature. We further validated this signature and predicted response to an additional panel of cell lines. Considering fold change differences and correlation between actual and predicted LP-184 IC50 values as validation performance measures, we obtained 86% accuracy at four-fold cut-off, and a strong (r = 0.70) and significant (p value 1.36e-06) correlation between actual and predicted LP-184 sensitivity. In agreement with the perceived mechanism of action of LP-184, PTGR1 emerged as the top weighted gene.

CONCLUSION

Integration of a machine learning-derived signature of response with in vitro assessment of LP-184 efficacy facilitated the derivation of manageable yet robust biomarkers which can be used to predict drug sensitivity with high accuracy and clinical value.

Artificial Intelligence and Machine Learning in Prostate Cancer Patient Management-Current Trends and Future Perspectives

Artificial intelligence (AI) is the field of computer science that aims to build smart devices performing tasks that currently require human intelligence. Through machine learning (ML), the deep learning (DL) model is teaching computers to learn by example, something that human beings are doing naturally. AI is revolutionizing healthcare. Digital pathology is becoming highly assisted by AI to help researchers in analyzing larger data sets and providing faster and more accurate diagnoses of prostate cancer lesions. When applied to diagnostic imaging, AI has shown excellent accuracy in the detection of prostate lesions as well as in the prediction of patient outcomes in terms of survival and treatment response. The enormous quantity of data coming from the prostate tumor genome requires fast, reliable and accurate computing power provided by machine learning algorithms. Radiotherapy is an essential part of the treatment of prostate cancer and it is often difficult to predict its toxicity for the patients. Artificial intelligence could have a future potential role in predicting how a patient will react to the therapy side effects. These technologies could provide doctors with better insights on how to plan radiotherapy treatment. The extension of the capabilities of surgical robots for more autonomous tasks will allow them to use information from the surgical field, recognize issues and implement the proper actions without the need for human intervention.

Integrated meta-analysis and machine learning approach identifies acyl-CoA thioesterase with other novel genes responsible for biofilm development in Staphylococcus aureus

Biofilm forming Staphylococcus aureus is a major threat to the health-care industry. It is important to understand the differences between planktonic and biofilm growth forms in the pathogen since conventional treatments targeting the planktonic forms are not effective against biofilms. The current study conducts a meta-analysis of three public transcriptomic profiles to examine the differences in gene expression between the planktonic and biofilm states of S. aureus using random-effects modeling. Mean effect sizes were calculated for 2847 genes among which 726 differentially expressed genes were taken for further analysis. Major genes that are discriminatory between the two conditions were mined using supervised learning techniques and validated by high-accuracy classifiers. Ten different feature selection algorithms were applied and used to rank the most important genes in S. aureus biofilms. Finally, an optimal set of 36 genes are presented as candidate genes in biofilm formation or development while throwing light on the novel roles of an acyl-CoA thioesterase enzyme and 10 hypothetical proteins in biofilms. The relevance of the identified gene set was further validated by building five different classification models using SVM, RF, kNN, NB and DT algorithms that were compared with models built from other relevant gene sets and by reviewing the functional role of 25 previously known genes in biofilm development. The study combines meta-analysis of differential expression with supervised machine learning strategies and feature selection for the first time to identify and validate a discriminatory set of genes important in biofilms of S. aureus. The functional roles of the identified genes predicted to be important in biofilms are further scrutinized and can be considered as a signature target list to develop anti-biofilm therapeutics in S. aureus.

FABP5 as a novel molecular target in prostate cancer

Emerging evidence suggests that dysregulated lipid signaling is a key factor in prostate cancer (PC), through fatty acid activation of the nuclear receptors peroxisome proliferator-activated receptors (PPARs), leading to the upregulation of protumoral genes. Fatty acid-binding proteins (FABPs) are intracellular lipid-binding proteins that transport fatty acid to PPARs, facilitating their activation. FABP5 is overexpressed in PC, and correlates with poor patient prognosis and survival. Genetic knockdown or silencing of FABP5 decreases the proliferation and invasiveness of PC cells in vitro, and reduces tumor growth and metastasis in vivo. Pharmacological FABP5-specific inhibitors also reduce tumor growth and metastases, and produce synergistic effects with taxanes. In this review, we present current data supporting FABP5 as a novel molecular target for PC.

The Application of Artificial Intelligence in Prostate Cancer Management—What Improvements Can Be Expected? A Systematic Review

Artificial Intelligence (AI) is progressively remodeling our daily life. A large amount of information from “big data” now enables machines to perform predictions and improve our healthcare system. AI has the potential to reshape prostate cancer (PCa) management thanks to growing applications in the field. The purpose of this review is to provide a global overview of AI in PCa for urologists, pathologists, radiotherapists, and oncologists to consider future changes in their daily practice. A systematic review was performed, based on PubMed MEDLINE, Google Scholar, and DBLP databases for original studies published in English from January 2009 to January 2019 relevant to PCa, AI, Machine Learning, Artificial Neural Networks, Convolutional Neural Networks, and Natural-Language Processing. Only articles with full text accessible were considered. A total of 1008 articles were reviewed, and 48 articles were included. AI has potential applications in all fields of PCa management: analysis of genetic predispositions, diagnosis in imaging, and pathology to detect PCa or to differentiate between significant and non-significant PCa. AI also applies to PCa treatment, whether surgical intervention or radiotherapy, skills training, or assessment, to improve treatment modalities and outcome prediction. AI in PCa management has the potential to provide a useful role by predicting PCa more accurately, using a multiomic approach and risk-stratifying patients to provide personalized medicine.

Identification of Potential Therapeutic Targets and Immune Cell Infiltration Characteristics in Osteosarcoma Using Bioinformatics Strategy

Osteosarcoma is one of the most aggressive malignant bone tumors worldwide. Although great advancements have been made in its treatment owing to the advent of neoadjuvant chemotherapy, the problem of lung metastasis is a major obstacle in the improvement of survival outcomes. Thus, the aim of the present study is to screen novel and key biomarkers, which may act as potential prognostic markers and therapeutic targets in osteosarcoma. We utilized the robust rank aggregation (RRA) method to integrate three osteosarcoma microarray datasets downloaded from the Gene Expression Omnibus (GEO) database, and we identified the robust differentially expressed genes (DEGs) between primary and metastatic osteosarcoma tissues. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed to explore the functions of robust DEGs. The results of enrichment analysis showed that the robust DEGs were closely associated with osteosarcoma development and progression. Immune cell infiltration analysis was also conducted by CIBERSORT algorithm, and we found that macrophages are the most principal infiltrating immune cells in osteosarcoma, especially macrophages M0 and M2. Then, the protein–protein interaction network and key modules were constructed by Cytoscape, and 10 hub genes were selected by plugin cytoHubba from the whole network. The survival analysis of hub genes was also carried out based on the Therapeutically Applicable Research to Generate Effective Treatments (TARGET) database. The integrated bioinformatics analysis was utilized to provide new insight into osteosarcoma development and metastasis and identified EGR1, CXCL10, MYC, and CXCR4 as potential biomarkers for prognosis of osteosarcoma.

Identification of common and divergent gene expression signatures in patients with venous and arterial thrombosis using data from public repositories

STRENGTHS AND LIMITATIONS OF THIS STUDY

Our results represent the first comparison of venous and arterial thrombosis at the transcriptomic level.Our main result was the demonstration that immunothrombosis pathways are important to the pathophysiology of these conditions, also at the transcriptomic level.A specific signature for venous and arterial thrombosis was described, and validated in independent cohorts.The limited number of public repositories with gene expression data from patients with venous thromboembolism limits the representation of these patients in our analyses.In order to gather a meaningful number of studies with gene expression data we had to include patients in different time-points since the index thrombotic event, which might have increased the heterogeneity of our population.

Identification of castration-resistant prostate cancer-related hub genes using weighted gene co-expression network analysis

Prostate cancer is the most common malignancy in urinary system and brings heavy burdens in men. We downloaded gene expression profile of mRNA and related clinical data of GSE70768 data set from public database. Weighted gene co‐expression network analysis (WGCNA) was used to identify the relationships between gene modules and clinical features, as well as the candidate genes. Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) analyses were developed to investigate the potential functions of related hub genes. Importantly, basic experiments were performed to verify the relationship between hub genes and the phenotype previously identified. Lastly, copy number variation (CNV) analysis was conducted to explore the genetical alteration. WGCNA identified that black module was the most relevant module which was tightly related to castration‐resistant prostate cancer (CRPC) phenotype. KEGG and GO analysis results revealed genes in black module were mainly related to RNA splicing. Additionally, 9 genes were chosen as hub genes and heterogeneous nuclear ribonucleoprotein A2/B1 (HNRNPA2B1), golgin A8 family member B (GOLGA8B) and mitogen‐activated protein kinase 8 interacting protein 3 (MAPK8IP3) were identified to be associated with PCa progression and prognosis. Moreover, all above three genes were highly expressed in CRPC‐like cells and their suppression led to hindered cell proliferation in vitro. Finally, CNV analysis found that amplification was the main type of alteration of the 3 hub genes. Our study found that HNRNPA2B1, GOLGA8B and MAPK8IP3 were identified to be tightly associated with tumour progression and prognosis, and further researches are needed before clinical application.

The study of multiple diagnosis models of human prostate cancer based on Taylor database by artificial neural networks

BACKGROUND

Prostate cancer (PCa) is the most common malignancy seen in men and the second leading cause of cancer-related death in males. The incidence and mortality associated with PCa has been rapidly increasing in China recently.

METHODS

Multiple diagnostic models of human PCa were developed based on Taylor database by combining the artificial neural networks (ANNs) to enhance the ability of PCa diagnosis. Genetic algorithm (GA) is used to select feature genes as numerical encoded parameters that reflect cancer, metastatic, or normal samples. Back propagation (BP) neural network and learning vector quantization (LVQ) neural network were used to build different Cancer/Normal, Primary/Metastatic, and Gleason Grade diagnostic models.

RESULTS

The performance of these modeling approaches was evaluated by predictive accuracy (ACC) and area under the receiver operating characteristic curve (AUC). By observing the statistically significant parameters of the three training sets, our Cancer/Normal, Primary/Metastatic, and Gleason Grade models' with ACC and AUC can be drawn (97.33%, 0.9832), (99.17%, 0.9952), and (90.48%, 0.8742), respectively.

CONCLUSION

These results indicated that our diagnostic models of human PCa based on Taylor database combining the feature gene expression profiling data and artificial intelligence algorithms might act as a powerful tool for diagnosing PCa. Gleason Grade diagnostic models were used as novel prognostic diagnosis models for biochemical recurrence-free survival and overall survival, which might be helpful in the prognostic diagnosis of PCa in patients.

Identification of hub genes in hepatocellular carcinoma using integrated bioinformatic analysis

The molecular mechanisms underlying hepatocellular carcinoma (HCC) progression remain largely undefined. Here, we identified 176 commonly upregulated genes in HCC tissues based on three Gene Expression Omnibus datasets and The Cancer Genome Atlas (TCGA) cohort. We integrated survival and methylation analyses to further obtain 12 upregulated genes for validation. These genes were overexpressed in HCC tissues at the transcription and protein levels, and increased mRNA levels were related to higher tumor grades and cancer stages. The expression of all markers was negatively associated with overall and disease-free survival in HCC patients. Most of these hub genes can promote HCC proliferation and/or metastasis. These 12 hub genes were also overexpressed and had strong prognostic value in many other cancer types. Methylation and gene copy number analyses indicated that the upregulation of these hub genes was probably due to hypomethylation or increased gene copy numbers. Further, the methylation levels of three genes, KPNA2, MCM3, and LRRC1, were associated with HCC clinical features. Moreover, the levels of most hub genes were related to immune cell infiltration in HCC microenvironments. Finally, we identified three upregulated genes (KPNA2, TARBP1, and RNASEH2A) that could comprehensively and accurately provide diagnostic and prognostic value for HCC patients.

Predicting the effect of 5-fluorouracil-based adjuvant chemotherapy on colorectal cancer recurrence: A model using gene expression profiles

It is critical to identify patients with stage II and III colorectal cancer (CRC) who will benefit from adjuvant chemotherapy (ACT) after curative surgery, while the only use of clinical factors is insufficient to predict this beneficial effect. In this study, we performed genetic algorithm (GA) to select ACT candidate genes, and built a predictive model of support vector machine (SVM) using gene expression profiles from the Gene Expression Omnibus database. The model contained four ACT candidate genes (EDEM1, MVD, SEMA5B, and WWP2) and TNM stage (stage II or III). After using Subpopulation Treatment Effect Pattern Plot to determine the optimal cutoff value of predictive scores, the validated patients from The Cancer Genome Atlas database can be divided into the predictive ACT-benefit/-futile groups. Patients in the predictive ACT-benefit group with 5-fluorouracil (5-Fu)-based ACT had significantly longer relapse-free survival (RFS) compared to those without ACT (P = .015); However, the difference in RFS in the predictive ACT-futile group was insignificant (P = .596). The multivariable analysis found that the predictive groups were significantly associated with the effect of ACT (P_interaction  = .011). Consequently, we developed a predictive model based on the SVM and GA algorithm which was further validated to define patients who benefit from ACT on recurrence.

FABP5 coordinates lipid signaling that promotes prostate cancer metastasis

Prostate cancer (PCa) is defined by dysregulated lipid signaling and is characterized by upregulation of lipid metabolism-related genes including fatty acid binding protein 5 (FABP5), fatty acid synthase (FASN), and monoacylglycerol lipase (MAGL). FASN and MAGL are enzymes that generate cellular fatty acid pools while FABP5 is an intracellular chaperone that delivers fatty acids to nuclear receptors to enhance PCa metastasis. Since FABP5, FASN, and MAGL have been independently implicated in PCa progression, we hypothesized that FABP5 represents a central mechanism linking cytosolic lipid metabolism to pro-metastatic nuclear receptor signaling. Here, we show that the abilities of FASN and MAGL to promote nuclear receptor activation and PCa metastasis are critically dependent upon co-expression of FABP5 in vitro and in vivo. Our findings position FABP5 as a key driver of lipid-mediated metastasis and suggest that disruption of lipid signaling via FABP5 inhibition may constitute a new avenue to treat metastatic PCa.

Establishment and application of an artificial intelligence diagnosis system for pancreatic cancer with a faster region-based convolutional neural network

BACKGROUND

Early diagnosis and accurate staging are important to improve the cure rate and prognosis for pancreatic cancer. This study was performed to develop an automatic and accurate imaging processing technique system, allowing this system to read computed tomography (CT) images correctly and make diagnosis of pancreatic cancer faster.

METHODS

The establishment of the artificial intelligence (AI) system for pancreatic cancer diagnosis based on sequential contrast-enhanced CT images were composed of two processes: training and verification. During training process, our study used all 4385 CT images from 238 pancreatic cancer patients in the database as the training data set. Additionally, we used VGG16, which was pre-trained in ImageNet and contained 13 convolutional layers and three fully connected layers, to initialize the feature extraction network. In the verification experiment, we used sequential clinical CT images from 238 pancreatic cancer patients as our experimental data and input these data into the faster region-based convolution network (Faster R-CNN) model that had completed training. Totally, 1699 images from 100 pancreatic cancer patients were included for clinical verification.

RESULTS

A total of 338 patients with pancreatic cancer were included in the study. The clinical characteristics (sex, age, tumor location, differentiation grade, and tumor-node-metastasis stage) between the two training and verification groups were insignificant. The mean average precision was 0.7664, indicating a good training effect of the Faster R-CNN. Sequential contrast-enhanced CT images of 100 pancreatic cancer patients were used for clinical verification. The area under the receiver operating characteristic curve calculated according to the trapezoidal rule was 0.9632. It took approximately 0.2 s for the Faster R-CNN AI to automatically process one CT image, which is much faster than the time required for diagnosis by an imaging specialist.

CONCLUSIONS

Faster R-CNN AI is an effective and objective method with high accuracy for the diagnosis of pancreatic cancer.

TRIAL REGISTRATION

ChiCTR1800017542; http://www.chictr.org.cn.

Identification of hub genes in prostate cancer using robust rank aggregation and weighted gene co-expression network analysis

The pathogenic mechanisms of prostate cancer (PCa) remain to be defined. In this study, we utilized the Robust Rank Aggregation (RRA) method to integrate 10 eligible PCa microarray datasets from the GEO and identified a set of significant differentially expressed genes (DEGs) between tumor samples and normal, matched specimens. To explore potential associations between gene sets and PCa clinical features and to identify hub genes, we utilized WGCNA to construct gene co-expression networks incorporating the DEGs screened with the use of RRA. From the key module, we selected LMNB1, TK1, ZWINT, and RACGAP1 for validation. We found that these genes were up-regulated in PCa samples, and higher expression levels were associated with higher Gleason scores and tumor grades. Moreover, ROC and K-M plots indicated these genes had good diagnostic and prognostic value for PCa. On the other hand, methylation analyses suggested that the abnormal up-regulation of these four genes likely resulted from hypomethylation, while GSEA and GSVA for single hub gene revealed they all had a close association with proliferation of PCa cells. These findings provide new insight into PCa pathogenesis, and identify LMNB1, TK1, RACGAP1 and ZWINT as candidate biomarkers for diagnosis and prognosis of PCa.

A survey of neural network-based cancer prediction models from microarray data

Neural networks are powerful tools used widely for building cancer prediction models from microarray data. We review the most recently proposed models to highlight the roles of neural networks in predicting cancer from gene expression data. We identified articles published between 2013-2018 in scientific databases using keywords such as cancer classification, cancer analysis, cancer prediction, cancer clustering and microarray data. Analyzing the studies reveals that neural network methods have been either used for filtering (data engineering) the gene expressions in a prior step to prediction; predicting the existence of cancer, cancer type or the survivability risk; or for clustering unlabeled samples. This paper also discusses some practical issues that can be considered when building a neural network-based cancer prediction model. Results indicate that the functionality of the neural network determines its general architecture. However, the decision on the number of hidden layers, neurons, hypermeters and learning algorithm is made using trail-and-error techniques.