ClickGene: an open cloud-based platform for big pan-cancer data genome-wide association study, visualization and exploration

Immunoglobulin-like transcript 2 blockade restores antitumor immune responses in glioblastoma

Glioblastoma stands as the most frequent primary brain tumor. Despite the multimodal therapy for glioblastoma patients, the survival rate is very low, highlighting the need for novel therapies that improve patient outcomes. Immune checkpoint blockade strategies are achieving promising results in a myriad of tumors and several studies have reported its efficacy in glioblastoma at a preclinical level. ILT2 is a novel immune checkpoint that exerts an inhibitory effect via the interaction with classical and non-classical HLA class-I molecules. Herein, we report that ILT2 blockade promotes antitumor responses against glioblastoma. In silico and immunohistochemical analyses revealed that the expression of ILT2 and its ligands HLA-A, -B, -C, and -E are highly expressed in patients with glioblastoma. Disruption of ILT2 with blocking monoclonal antibodies increased natural killer cell-mediated IFN-γ production and cytotoxicity against glioblastoma, partially reverting the immunosuppression linked to this malignancy. In addition, co-treatment with temozolomide strengthened the antitumor capacity of anti-ILT2-treated immune cells. Collectively, our results establish the basis for future studies regarding the clinical potential of ILT2 blockade alone or in combination regimens in glioblastoma.

Virtual reality for the observation of oncology models (VROOM): immersive analytics for oncology patient cohorts

The significant advancement of inexpensive and portable virtual reality (VR) and augmented reality devices has re-energised the research in the immersive analytics field. The immersive environment is different from a traditional 2D display used to analyse 3D data as it provides a unified environment that supports immersion in a 3D scene, gestural interaction, haptic feedback and spatial audio. Genomic data analysis has been used in oncology to understand better the relationship between genetic profile, cancer type, and treatment option. This paper proposes a novel immersive analytics tool for cancer patient cohorts in a virtual reality environment, virtual reality to observe oncology data models. We utilise immersive technologies to analyse the gene expression and clinical data of a cohort of cancer patients. Various machine learning algorithms and visualisation methods have also been deployed in VR to enhance the data interrogation process. This is supported with established 2D visual analytics and graphical methods in bioinformatics, such as scatter plots, descriptive statistical information, linear regression, box plot and heatmap into our visualisation. Our approach allows the clinician to interrogate the information that is familiar and meaningful to them while providing them immersive analytics capabilities to make new discoveries toward personalised medicine.

Serverless computing in omics data analysis and integration

A comprehensive analysis of omics data can require vast computational resources and access to varied data sources that must be integrated into complex, multi-step analysis pipelines. Execution of many such analyses can be accelerated by applying the cloud computing paradigm, which provides scalable resources for storing data of different types and parallelizing data analysis computations. Moreover, these resources can be reused for different multi-omics analysis scenarios. Traditionally, developers are required to manage a cloud platform’s underlying infrastructure, configuration, maintenance and capacity planning. The serverless computing paradigm simplifies these operations by automatically allocating and maintaining both servers and virtual machines, as required for analysis tasks. This paradigm offers highly parallel execution and high scalability without manual management of the underlying infrastructure, freeing developers to focus on operational logic. This paper reviews serverless solutions in bioinformatics and evaluates their usage in omics data analysis and integration. We start by reviewing the application of the cloud computing model to a multi-omics data analysis and exposing some shortcomings of the early approaches. We then introduce the serverless computing paradigm and show its applicability for performing an integrative analysis of multiple omics data sources in the context of the COVID-19 pandemic.

Identification of Vitamin D-related gene signature to predict colorectal cancer prognosis

Colorectal cancer (CRC) is one of the most common malignant carcinomas worldwide with poor prognosis, imposing an increasingly heavy burden on patients. Previous experiments and epidemiological studies have shown that vitamin D and vitamin D-related genes play a vital role in CRC. Therefore, we aimed to construct a vitamin D-related gene signature to predict prognosis in CRC. The CRC data from The Cancer Genome Atlas (TCGA) was performed as the training set. A total of 173 vitamin D-related genes in the TCGA CRC dataset were screened, and 17 genes associated with CRC prognosis were identified from them. Then, a vitamin D-related gene signature consisting of those 17 genes was established by univariate and multivariate Cox analyses. Moreover, four external datasets (GSE17536, GSE103479, GSE39582, and GSE17537) were used as testing set to validate the stability of this signature. The high-risk group presented a significantly poorer overall survival than low-risk group in both of training set and testing sets. Besides, the areas under the curve (AUCs) for signature on OS in training set at 1, 3, and 5 years were 0.710, 0.708, 0.710 respectively. The AUCs of the ROC curve in GSE17536 for 1, 3, and 5 years were 0.649, 0.654, and 0.694. These results indicated the vitamin D-related gene signature model could effectively predict the survival status of CRC patients. This vitamin D-related gene signature was also correlated with TNM stage in CRC clinical parameters, and the higher risk score from this model was companied with higher clinical stage. Furthermore, the high accuracy of this prognostic signature was validated and confirmed by nomogram model. In conclusion, we have proposed a novel vitamin D-related gene model to predict the prognosis of CRC, which will help provide new therapeutic targets and act as potential prognostic biomarkers for CRC.

Protocol for Epistasis Detection with Machine Learning Using GenEpi Package

To develop medical treatments and prevention, the association between disease and genetic variants needs to be identified. The main goal of genome-wide association study (GWAS) is to discover the underlying reason for vulnerability to disease and utilize this knowledge for the development of prevention and treatment against these diseases. Given the methods available to address the scientific problems involved in the search for epistasis, there is not any standard for detecting epistasis, and this remains a problem due to limited statistical power. The GenEpi package is a Python package that uses a two-level workflow machine learning model to detect within-gene and cross-gene epistasis. This protocol chapter shows the usage of GenEpi with example data. The package uses a three-step procedure to reduce dimensionality, select the within-gene epistasis, and select the cross-gene epistasis. The package also provides a medium to build prediction models with the combination of genetic features and environmental influences.

Perspectives of using Cloud computing in integrative analysis of multi-omics data

Integrative analysis of multi-omics data is usually computationally demanding. It frequently requires building complex, multi-step analysis pipelines, applying dedicated techniques for data processing and combining several data sources. These efforts lead to a better understanding of life processes, current health state or the effects of therapeutic activities. However, many omics data analysis solutions focus only on a selected problem, disease, types of data or organisms. Moreover, they are implemented for general-purpose scientific computational platforms that most often do not easily scale the calculations natively. These features are not conducive to advances in understanding genotype-phenotypic relationships. Fortunately, with new technological paradigms, including Cloud computing, virtualization and containerization, these functionalities could be orchestrated for easy scaling and building independent analysis pipelines for omics data. Therefore, solutions can be re-used for purposes that they were not primarily designed. This paper shows perspectives of using Cloud computing advances and containerization approach for such a purpose. We first review how the Cloud computing model is utilized in multi-omics data analysis and show weak points of the adopted solutions. Then, we introduce containerization concepts, which allow both scaling and linking of functional services designed for various purposes. Finally, on the Bioconductor software package example, we disclose a verified concept model of a universal solution that exhibits the potentials for performing integrative analysis of multiple omics data sources.

Research on Early Warning Mechanism and Model of Liver Cancer Rehabilitation Based on CS-SVM

Since the 20^th century, cancer has become one of the main diseases threatening human health. Liver cancer is a malignant tumor with extremely high clinical morbidity and fatality rate and easy recurrence after surgery. Research on the postoperative recurrence time and recurrence location of patients with liver cancer has a crucial influence on the postoperative intervention of patients. Evaluation of the clinical manifestations of patients after liver cancer surgery is conducted according to medical knowledge or national standards to determine the main factors affecting liver cancer rehabilitation. In order to better study the mechanism of liver cancer recurrence, this paper uses CS-SVM to predict the recurrence time of liver cancer patients, so as to timely intervene the patients. There are five evaluation indicators which are basic indicators, immune indicators, microenvironment indicators, psychological indicators, and nutritional indicators, respectively. This paper collects the clinical evaluation data of postoperative follow-up visits for patients with liver cancer in a hospital, improves the parameter selection process of the support vector machine by using the search ability of the cuckoo algorithm, and establishes an algorithm-optimized prediction model of support vector machine for the prognosis of liver cancer to predict the location and approximate time of recurrence. According to the clinical evaluation data of patients with liver cancer after surgery, logistics regression, BP neural network, and other related methods are used to predict the prognosis of liver cancer patients after surgery. The prediction effects of several methods are compared, and the superiority of the model is discussed. At the end of this article, we conducted an empirical analysis on the clinical evaluation data of patients with liver cancer after surgery. For the collected samples of 776 liver cancer recurrences after surgery, the established liver cancer prognosis outcome prediction model was used to predict the recurrence time and recurrence location, respectively. The mean square error of recurrence time prediction is 9.2101, which is much smaller than the prediction mean square error of BP neural network of 177.9451; the prediction accuracy of recurrence location is 95.7%, which is much higher than the 63.14% of logistic regression. The empirical analysis results show that the improved support vector machine model based on cuckoo established in this paper can effectively predict the time and location of cancer recurrence.

Gut microbiome, big data and machine learning to promote precision medicine for cancer

The gut microbiome has been implicated in cancer in several ways, as specific microbial signatures are known to promote cancer development and influence safety, tolerability and efficacy of therapies. The 'omics' technologies used for microbiome analysis continuously evolve and, although much of the research is still at an early stage, large-scale datasets of ever increasing size and complexity are being produced. However, there are varying levels of difficulty in realizing the full potential of these new tools, which limit our ability to critically analyse much of the available data. In this Perspective, we provide a brief overview on the role of gut microbiome in cancer and focus on the need, role and limitations of a machine learning-driven approach to analyse large amounts of complex health-care information in the era of big data. We also discuss the potential application of microbiome-based big data aimed at promoting precision medicine in cancer.