A multitask multiple kernel learning formulation for discriminating early- and late-stage cancers.

MOTIVATION: Genomic information is increasingly being used in diagnosis, prognosis and treatment of cancer. The severity of the disease is usually measured by the tumor stage. Therefore, identifying pathways playing an important role in progression of the disease stage is of great interest. Given that there are similarities in the underlying mechanisms of different cancers, in addition to the considerable correlation in the genomic data, there is a need for machine learning methods that can take these aspects of genomic data into account. Furthermore, using machine learning for studying multiple cancer cohorts together with a collection of molecular pathways creates an opportunity for knowledge extraction. RESULTS: We studied the problem of discriminating early- and late-stage tumors of several cancers using genomic information while enforcing interpretability on the solutions. To this end, we developed a multitask multiple kernel learning (MTMKL) method with a co-clustering step based on a cutting-plane algorithm to identify the relationships between the input tasks and kernels. We tested our algorithm on 15 cancer cohorts and observed that, in most cases, MTMKL outperforms other algorithms (including random forests, support vector machine and single-task multiple kernel learning) in terms of predictive power. Using the aggregate results from multiple replications, we also derived similarity matrices between cancer cohorts, which are, in many cases, in agreement with available relationships reported in the relevant literature. AVAILABILITY AND IMPLEMENTATION: Our implementations of support vector machine and multiple kernel learning algorithms in R are available at https://github.com/arezourahimi/mtgsbc together with the scripts that replicate the reported experiments. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Association of the genetic polymorphisms in inhibiting and activating molecules of immune system with rheumatoid arthritis: A systematic review and meta-analysis.

Several studies have demonstrated that the genetic polymorphisms in the genes encoding immune regulatory molecules, namely cytotoxic T-lymphocyte-associated protein 4 (CTLA4) and CD28, play a fundamental role in susceptibility to rheumatoid arthritis (RA). Several disperse population studies have resulted in conflicting outcomes regarding the genetic polymorphisms in these genes and RA risk. This systematic review and meta-analysis study was performed to reach a conclusive understanding of the role of single-nucleotide polymorphisms (SNPs) of CTLA4-rs231775, CTLA4-rs5742909, and CD28-rs1980422 in susceptibility to RA. Databases (ISI Web of Science, MEDLINE/PubMed, and Scopus) were searched to find the case-control studies surveying the association of CTLA4 gene rs231775, CTLA4 gene rs5742909, and CD28 gene rs1980422 polymorphisms and RA susceptibility in different population until August 2020. Association comparison between the polymorphisms and RA proneness was assessed using pooled odds ratio (OR) and their corresponding 95% confidence interval. This study was conducted on 16 population studies, comprising 1078 RA patients and 1118 healthy controls for CTLA4-rs231775, 2193 RA patients and 2580 healthy controls for CTLA4-rs5742909, and 807 RA patients and 732 healthy controls for CD28-rs1980422. Analysis indicated that G-allele, GG and GA genotypes, and dominant model for rs231775, recessive model for rs5742909, and C-allele, CC and CT genotypes, and recessive model for rs1980422 were significantly associated with increased RA risk. This meta-analysis showed that genetic polymorphisms of both immune inhibitory and activating genes, including CTLA4-rs231775, CTLA4-rs5742909, and CD28-rs1980422 polymorphisms, may increase susceptibility to RA.

Discriminating early- and late-stage cancers using multiple kernel learning on gene sets.

Motivation: Identifying molecular mechanisms that drive cancers from early to late stages is highly important to develop new preventive and therapeutic strategies. Standard machine learning algorithms could be used to discriminate early- and late-stage cancers from each other using their genomic characterizations. Even though these algorithms would get satisfactory predictive performance, their knowledge extraction capability would be quite restricted due to highly correlated nature of genomic data. That is why we need algorithms that can also extract relevant information about these biological mechanisms using our prior knowledge about pathways/gene sets. Results: In this study, we addressed the problem of separating early- and late-stage cancers from each other using their gene expression profiles. We proposed to use a multiple kernel learning (MKL) formulation that makes use of pathways/gene sets (i) to obtain satisfactory/improved predictive performance and (ii) to identify biological mechanisms that might have an effect in cancer progression. We extensively compared our proposed MKL on gene sets algorithm against two standard machine learning algorithms, namely, random forests and support vector machines, on 20 diseases from the Cancer Genome Atlas cohorts for two different sets of experiments. Our method obtained statistically significantly better or comparable predictive performance on most of the datasets using significantly fewer gene expression features. We also showed that our algorithm was able to extract meaningful and disease-specific information that gives clues about the progression mechanism. Availability and implementation: Our implementations of support vector machine and multiple kernel learning algorithms in R are available at https://github.com/mehmetgonen/gsbc together with the scripts that replicate the reported experiments.

DOT: a flexible multi-objective optimization framework for transferring features across single-cell and spatial omics.

Single-cell transcriptomics and spatially-resolved imaging/sequencing technologies have revolutionized biomedical research. However, they suffer from lack of spatial information and a trade-off of resolution and gene coverage, respectively. We propose DOT, a multi-objective optimization framework for transferring cellular features across these data modalities, thus integrating their complementary information. DOT uses genes beyond those common to the data modalities, exploits the local spatial context, transfers spatial features beyond cell-type information, and infers absolute/relative abundance of cell populations at tissue locations. Thus, DOT bridges single-cell transcriptomics data with both high- and low-resolution spatially-resolved data. Moreover, DOT combines practical aspects related to cell composition, heterogeneity, technical effects, and integration of prior knowledge. Our fast implementation based on the Frank-Wolfe algorithm achieves state-of-the-art or improved performance in localizing cell features in high- and low-resolution spatial data and estimating the expression of unmeasured genes in low-coverage spatial data.

BACTERIOPHAGE M13 MODULATES THE SEPSIS-RELATED INFLAMMATORY RESPONSES AND ORGAN DAMAGE IN A CLP MODEL.

ABSTRACT: Background: Sepsis is a life-threatening disorder that leads to the induction of inflammatory responses and organ failure. Phage therapy is a new approach to controlling infections resistant to common treatments, including sepsis. Several studies have shown the effect of lytic bacteriophages on infection control by reducing the bacterial load. The present study deals with lysogenic bacteriophage M13 on the inflammatory responses caused by cecal ligation and puncture (CLP)-induced sepsis in a mouse model. Methods Bacteriophage M13 harvested from ER2738, titrated, and confirmed by transmission electron microscopy analysis. In vitro toxicity and immunomodulatory effect of bacteriophage M13 were assessed on splenocytes by measurement of cell viability and the production level of cytokines, nitric oxide, and reactive oxygen species. For in vivo experiments, 8-weeks-old male C57BL/6 mice were randomly divided into the following three groups: CLP + NS (treated with normal saline), CLP + M13 (treated with an intraperitoneal injection of 10 9 PFU/mL of bacteriophage M13), and sham + NS (induced surgery but without ligation and puncture, treated with NS). The mice were killed at different time points after surgery (6, 24, 48, and 72, n = 10 for each time point of each group). The kidney, liver, and lungs were harvested for histopathological analysis, and blood was obtained for cytokine and liver enzyme assay. The spleen was used to assess the bacterial load using colony-forming unit assay. The rectal temperature and survival were evaluated during the study. Results According to the in vitro results, 10 9 PFU/mL of bacteriophage M13 was not toxic and did not affect the level of cytokine, nitric oxide, and reactive oxygen species production by splenocytes, but it reduced the inflammatory response of splenocytes in responses to LPS. In vivo studies indicated that the amount of proinflammatory cytokines, liver enzymes, bacterial load, and organ failure were decreased in the CLP + M13 group compared with CLP + NS, whereas the survival rate was increased. Conclusions These experiments demonstrated that bacteriophage M13 could lessen the consequences related to sepsis in CLP mice and can be considered a therapeutic approach in sepsis.

Dual blockage of both PD-L1 and CD47 enhances the therapeutic effect of oxaliplatin and FOLFOX in CT-26 mice tumor model.

Colorectal cancer is a poorly immunogenic. Such property can be reverted by using ICD. However, ICD inducers can also induce the expression of inhibitory checkpoint receptors CD47 and PD-L1 on tumor cells, making CRC tumors resistant to mainly CD8 T cell killing and macrophage-mediated phagocytosis. In this study, we examined the therapeutic effect of Oxaliplatin and FOLFOX regimen in combination with blocking antibodies against CD47 and PD-L1. FOLFOX and Oxaliplatin treatment lead to an increase in CD47 and PD-L1 expression on CT-26 cells invitro and invivo. Combining blocking antibodies against CD47 and PD-L1 with FOLFOX leads to a significant increase in survival and a decrease in tumor size. This triple combining regimen also leads to a significant decrease in Treg and MDSC and a significant increase in CD8 + INF-γ + lymphocytes and M1/M2 macrophage ratio in the tumor microenvironment. Our study showed triple combining therapy with FOLFOX, CD47 and PD-L1 is an effective treatment regimen in CT-26 mice tumor model and may consider as a potential to translate to the clinic.

Efficient Multitask Multiple Kernel Learning With Application to Cancer Research.

Multitask multiple kernel learning (MKL) algorithms combine the capabilities of incorporating different data sources into the prediction model and using the data from one task to improve the accuracy on others. However, these methods do not necessarily produce interpretable results. Restricting the solutions to the set of interpretable solutions increases the computational burden of the learning problem significantly, leading to computationally prohibitive run times for some important biomedical applications. That is why we propose a multitask MKL formulation with a clustering of tasks and develop a highly time-efficient solution approach for it. Our solution method is based on the Benders decomposition and treating the clustering problem as finding a given number of tree structures in a graph; hence, it is called the forest formulation. We use our method to discriminate early-stage and late-stage cancers using genomic data and gene sets and compare our algorithm against two other algorithms. The two other algorithms are based on different approaches for linearization of the problem while all algorithms make use of the cutting-plane method. Our results indicate that as the number of tasks and/or the number of desired clusters increase, the forest formulation becomes increasingly favorable in terms of computational performance.

Immune cells-derived exosomes function as a double-edged sword: role in disease progression and their therapeutic applications.

Exosomes, ranging in size from 30 to 150 nm as identified initially via electron microscopy in 1946, are one of the extracellular vesicles (EVs) produced by many cells and have been the subject of many studies; initially, they were considered as cell wastes with the belief that cells produced exosomes to maintain homeostasis. Nowadays, it has been found that EVs secreted by different cells play a vital role in cellular communication and are usually secreted in both physiological and pathological conditions. Due to the presence of different markers and ligands on the surface of exosomes, they have paracrine, endocrine and autocrine effects in some cases. Immune cells, like other cells, can secrete exosomes that interact with surrounding cells via these vesicles. Immune system cells-derived exosomes (IEXs) induce different responses, such as increasing and decreasing the transcription of various genes and regulating cytokine production. This review deliberate the function of innate and acquired immune cells derived exosomes, their role in the pathogenesis of immune diseases, and their therapeutic appliances.