Advancement in Deep Learning Methods for Diagnosis and Prognosis of Cervical Cancer.

Cervical cancer is the leading cause of death in women, mainly in developing countries, including India. Recent advancements in technologies could allow for more rapid, cost-effective, and sensitive screening and treatment measures for cervical cancer. To this end, deep learning-based methods have received importance for classifying cervical cancer patients into different risk groups. Furthermore, deep learning models are now available to study the progression and treatment of cancerous cervical conditions. Undoubtedly, deep learning methods can enhance our knowledge toward a better understanding of cervical cancer progression. However, it is essential to thoroughly validate the deep learning-based models before they can be implicated in everyday clinical practice. This work reviews recent development in deep learning approaches employed in cervical cancer diagnosis and prognosis. Further, we provide an overview of recent methods and databases leveraging these new approaches for cervical cancer risk prediction and patient outcomes. Finally, we conclude the state-of-the-art approaches for future research opportunities in this domain.

The Inhibitory Response to PI3K/AKT Pathway Inhibitors MK-2206 and Buparlisib Is Related to Genetic Differences in Pancreatic Ductal Adenocarcinoma Cell Lines.

The aberrant activation of the phosphoinositide 3-kinase (PI3K)/ protein kinase B (AKT) pathway is common in pancreatic ductal adenocarcinomas (PDAC). The application of inhibitors against PI3K and AKT has been considered as a therapeutic option. We investigated PDAC cell lines exposed to increasing concentrations of MK-2206 (an AKT1/2/3 inhibitor) and Buparlisib (a pan-PI3K inhibitor). Cell proliferation, metabolic activity, biomass, and apoptosis/necrosis were evaluated. Further, whole-exome sequencing (WES) and RNA sequencing (RNA-seq) were performed to analyze the recurrent aberrations and expression profiles of the inhibitor target genes and the genes frequently mutated in PDAC (Kirsten rat sarcoma virus (KRAS), Tumor protein p53 (TP53)). MK-2206 and Buparlisib demonstrated pronounced cytotoxic effects and limited cell-line-specific effects in cell death induction. WES revealed two sequence variants within the direct target genes (PIK3CA c.1143C > G in Colo357 and PIK3CD c.2480C > G in Capan-1), but a direct link to the Buparlisib response was not observed. RNA-seq demonstrated that the expression level of the inhibitor target genes did not affect the efficacy of the corresponding inhibitors. Moreover, increased resistance to MK-2206 was observed in the analyzed cell lines carrying a KRAS variant. Further, increased resistance to both inhibitors was observed in SU.86.86 carrying two TP53 missense variants. Additionally, the presence of the PIK3CA c.1143C > G in KRAS-variant-carrying cell lines was observed to correlate with increased sensitivity to Buparlisib. In conclusion, the present study reveals the distinct antitumor effects of PI3K/AKT pathway inhibitors against PDAC cell lines. Aberrations in specific target genes, as well as KRAS and TP53, individually or together, affect the efficacy of the two PI3K/AKT pathway inhibitors.

Inhibitory Response to CK II Inhibitor Silmitasertib and CDKs Inhibitor Dinaciclib Is Related to Genetic Differences in Pancreatic Ductal Adenocarcinoma Cell Lines.

Casein kinase II (CK2) and cyclin-dependent kinases (CDKs) frequently interact within multiple pathways in pancreatic ductal adenocarcinoma (PDAC). Application of CK2- and CDK-inhibitors have been considered as a therapeutic option, but are currently not part of routine chemotherapy regimens. We investigated ten PDAC cell lines exposed to increasing concentrations of silmitasertib and dinaciclib. Cell proliferation, metabolic activity, biomass, and apoptosis/necrosis were evaluated, and bioinformatic clustering was used to classify cell lines into sensitive groups based on their response to inhibitors. Furthermore, whole exome sequencing (WES) and RNA sequencing (RNA-Seq) was conducted to assess recurrent mutations and the expression profile of inhibitor targets and genes frequently mutated in PDAC, respectively. Dinaciclib and silmitasertib demonstrated pronounced and limited cell line specific effects in cell death induction, respectively. WES revealed no genomic variants causing changes in the primary structure of the corresponding inhibitor target proteins. RNA-Seq demonstrated that the expression of all inhibitor target genes was higher in the PDAC cell lines compared to non-neoplastic pancreatic tissue. The observed differences in PDAC cell line sensitivity to silmitasertib or dinaciclib did not depend on target gene expression or the identified gene variants. For the PDAC hotspot genes kirsten rat sarcoma virus (KRAS) and tumor protein p53 (TP53), three and eight variants were identified, respectively. In conclusion, both inhibitors demonstrated in vitro efficacy on the PDAC cell lines. However, aberrations and expression of inhibitor target genes did not appear to affect the efficacy of the corresponding inhibitors. In addition, specific aberrations in TP53 and KRAS affected the efficacy of both inhibitors.

Mutational hotspots of HSP47 and its potential role in cancer and bone-disorders.

Heat shock protein 47 kDa (HSP47) serves as a client-specific chaperone, essential for collagen biosynthesis and its folding and structural assembly. To date, there is no comprehensive study on mutational hotspots. Using five different human mutational databases, we deduced a comprehensive list of human HSP47 mutations with 24, 67, 50, 43 and 2 deleterious mutations from the 1000 genomes data, gnomAD, COSMICv86, cBioPortal, and CanVar, respectively. We identified thirteen top-ranked missense mutations of HSP47 with the stringent cut-off of CADD score (>25) and Grantham score (≥151) as Ser76Trp, Arg103Cys, Arg116Cys, Ser159Phe, Arg167Cys, Arg280Cys, Trp293Cys, Gly323Trp, Arg339Cys, Arg373Cys, Arg377Cys, Ser399Phe, and Arg405Cys with the arginine-cysteine changes as the predominant mutations. These findings will assist in the evaluation of roles of HSP47 in collagen misfolding and human diseases such as cancer and bone disorders.

Overview of Genomic Tools for Circular Visualization in the Next-generation Genomic Sequencing Era.

After human genome sequencing and rapid changes in genome sequencing methods, we have entered into the era of rapidly accumulating genome-sequencing data. This has derived the development of several types of methods for representing results of genome sequencing data. Circular genome visual-ization tools are also critical in this area as they provide rapid interpretation and simple visualization of overall data. In the last 15 years, we have seen rapid changes in circular visualization tools after the de-velopment of the circos tool with 1-2 tools published per year. Herein we have summarized and revisited all these tools until the third quarter of 2018.

Applications of Machine Learning in miRNA Discovery and Target Prediction.

MicroRNA (miRNA) is a small non-coding molecule that is involved in gene regulation and RNA silencing by complementary on their targets. Experimental methods for target prediction can be time-consuming and expensive. Thus, the application of the computational approach is implicated to enlighten these complications with experimental studies. However, there is still a need for an optimized approach in miRNA biology. Therefore, machine learning (ML) would initiate a new era of research in miRNA biology towards potential diseases biomarker. In this article, we described the application of ML approaches in miRNA discovery and target prediction with functions and future prospective. The implementation of a new era of computational methodologies in this direction would initiate further advanced levels of discoveries in miRNA.

Computational Methods for Predicting Mature microRNAs.

Tiny single-stranded noncoding RNAs with size 19-27 nucleotides serve as microRNAs (miRNAs), which have emerged as key gene regulators in the last two decades. miRNAs serve as one of the hallmarks in regulatory pathways with critical roles in human diseases. Ever since the discovery of miRNAs, researchers have focused on how mature miRNAs are produced from precursor mRNAs. Experimental methods are faced with notorious challenges in terms of experimental design, since it is time consuming and not cost-effective. Hence, different computational methods have been employed for the identification of miRNA sequences where most of them labeled as miRNA predictors are in fact pre-miRNA predictors and provide no information about the putative miRNA location within the pre-miRNA. This chapter provides an update and the current state of the art in this area covering various methods and 15 software suites used for prediction of mature miRNA.

Fibroblast Growth Factor 21 as a Potential Biomarker for Improved Locomotion and Olfaction Detection Ability after Weight Reduction in Obese Mice.

Obesity is one of the most challenging diseases of the 21st century and is accompanied by behavioural disorders. Exercise, dietary adjustments, or time-restricted feeding are the only successful long-term treatments to date. Fibroblast growth factor 21 (FGF21) plays a key role in dietary regulation, but FGF21 resistance is prevalent in obesity. The aim of this study was to investigate in obese mice whether weight reduction leads to improved behaviour and whether these behavioural changes are associated with decreased plasma FGF21 levels. After establishing a model for diet-induced obesity, mice were subjected to three different interventions for weight reduction, namely dietary change, treadmill exercise, or time-restricted feeding. In this study, we demonstrated that only the combination of dietary change and treadmill exercise affected all parameters leading to a reduction in weight, fat, and FGF21, as well as less anxious behaviour, higher overall activity, and improved olfactory detection abilities. To investigate the interrelationship between FGF21 and behavioural parameters, feature selection algorithms were applied designating FGF21 and body weight as one of five highly weighted features. In conclusion, we concluded from the complementary methods that FGF21 can be considered as a potential biomarker for improved behaviour in obese mice after weight reduction.

Super-rapid race for saving lives by developing COVID-19 vaccines.

The pandemic of coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has affected millions of people and claimed thousands of lives. Starting in China, it is arguably the most precipitous global health calamity of modern times. The entire world has rocked back to fight against the disease and the COVID-19 vaccine is the prime weapon. Even though the conventional vaccine development pipeline usually takes more than a decade, the escalating daily death rates due to COVID-19 infections have resulted in the development of fast-track strategies to bring in the vaccine under a year's time. Governments, companies, and universities have networked to pool resources and have come up with a number of vaccine candidates. Also, international consortia have emerged to address the distribution of successful candidates. Herein, we summarize these unprecedented developments in vaccine science and discuss the types of COVID-19 vaccines, their developmental strategies, and their roles as well as their limitations.

miRWalk: An online resource for prediction of microRNA binding sites.

miRWalk is an open-source platform providing an intuitive interface that generates predicted and validated miRNA-binding sites of known genes of human, mouse, rat, dog and cow. The core of miRWalk is the miRNA target site prediction with the random-forest-based approach software TarPmiR searching the complete transcript sequence including the 5'-UTR, CDS and 3'-UTR. Moreover, it integrates results other databases with predicted and validated miRNA-target interactions. The focus is set on a modular design and extensibility as well as a fast update cycle. The database is available using Python, MySQL and HTML/Javascript Database URL: http://mirwalk.umm.uni-heidelberg.de.

Obtaining miRNA-Target Interaction Information from miRWalk2.0.

miRWalk2.0 (http://zmf.umm.uni-heidelberg.de/mirwalk2) is a freely accessible, regularly updated comprehensive archive supplying the largest available collection of predicted and experimentally verified miRNA-target interactions, with various novel and unique features to assist the scientific community. Approximately 949 million interactions between 11,748 miRNAs, 308,700 genes, and 68,460 lncRNAs are documented in miRWalk2.0 with 5,146,217 different kinds of identifiers to offer a one-stop site to collect an abundance of information. This article describes a schematic workflow on how to obtain miRNA-target interactions from miRWalk2.0. © 2016 by John Wiley & Sons, Inc.