Constructing cancer patient-specific and group-specific gene networks with multi-omics data

Transfer Learning for Classification of Alzheimer's Disease Based on Genome Wide Data

Alzheimer's disease (AD) is a type of brain disorder that is regarded as a degenerative disease because the corresponding symptoms aggravate with the time progression. Single nucleotide polymorphisms (SNPs) have been identified as relevant biomarkers for this condition. This study aims to identify SNPs biomarkers associated with the AD in order to perform a reliable classification of AD. In contrast to existing related works, we utilize deep transfer learning with varying experimental analysis for reliable classification of AD. For this purpose, the convolutional neural networks (CNN) are firstly trained over the genome-wide association studies (GWAS) dataset requested from the AD neuroimaging initiative. We then employ the deep transfer learning for further training of our CNN (as base model) over a different AD GWAS dataset, to extract the final set of features. The extracted features are then fed into Support Vector Machine for classification of AD. Detailed experiments are performed using multiple datasets and varying experimental configurations. The statistical outcomes indicate an accuracy of 89% which is a significant improvement when benchmarked with existing related works.

Constructing a Cancer Patient-Specific Network Based on Second-Order Partial Correlations of Gene Expression and DNA Methylation

Typically patient-specific gene networks are constructed with gene expression data only. Such networks cannot distinguish direct gene interactions from indirect interactions via others such as the effect of epigenetic events to gene activity. There is an increasing evidence of inter-individual variations not only in gene expression but also in epigenetic events such as DNA methylation. In this paper we propose a new method for constructing a cancer patient-specific gene correlation network using both gene expression and DNA methylation data. We derive a patient-specific network from differential second-order partial correlations of gene expression and DNA methylation between normal samples and the patient sample. The network represents direct interactions between genes by controlling the effect of DNA methylation. Using this method, we constructed 4,000 patient-specific networks for 10 types of cancer. The networks are highly effective in classifying different types of cancer and in deriving potential prognostic gene pairs. In particular, potential prognostic gene pairs derived from the networks were powerful in predicting the survival time of cancer patients. This approach will help identify patient-specific gene correlations and predict prognosis of cancer patients.

RMSCNN: A Random Multi-Scale Convolutional Neural Network for Marine Microbial Bacteriocins Identification

The abuse of traditional antibiotics has led to an increase in the resistance of bacteria and viruses. Similar to the function of antibacterial peptides, bacteriocins are more common as a kind of peptides produced by bacteria that have bactericidal or bacterial effects. More importantly, the marine environment is one of the most abundant resources for extracting marine microbial bacteriocins (MMBs). Identifying bacteriocins from marine microorganisms is a common goal for the development of new drugs. Effective use of MMBs will greatly alleviate the current antibiotic abuse problem. In this work, deep learning is used to identify meaningful MMBs. We propose a random multi-scale convolutional neural network method. In the scale setting, we set a random model to update the scale value randomly. The scale selection method can reduce the contingency caused by artificial setting under certain conditions, thereby making the method more extensive. The results show that the classification performance of the proposed method is better than the state-of-the-art classification methods. In addition, some potential MMBs are predicted, and some different sequence analyses are performed on these candidates. It is worth mentioning that after sequence analysis, the HNH endonucleases of different marine bacteria are considered as potential bacteriocins.

DLoopCaller: A deep learning approach for predicting genome-wide chromatin loops by integrating accessible chromatin landscapes

In recent years, major advances have been made in various chromosome conformation capture technologies to further satisfy the needs of researchers for high-quality, high-resolution contact interactions. Discriminating the loops from genome-wide contact interactions is crucial for dissecting three-dimensional(3D) genome structure and function. Here, we present a deep learning method to predict genome-wide chromatin loops, called DLoopCaller, by combining accessible chromatin landscapes and raw Hi-C contact maps. Some available orthogonal data ChIA-PET/HiChIP and Capture Hi-C were used to generate positive samples with a wider contact matrix which provides the possibility to find more potential genome-wide chromatin loops. The experimental results demonstrate that DLoopCaller effectively improves the accuracy of predicting genome-wide chromatin loops compared to the state-of-the-art method Peakachu. Moreover, compared to two of most popular loop callers, such as HiCCUPS and Fit-Hi-C, DLoopCaller identifies some unique interactions. We conclude that a combination of chromatin landscapes on the one-dimensional genome contributes to understanding the 3D genome organization, and the identified chromatin loops reveal cell-type specificity and transcription factor motif co-enrichment across different cell lines and species.

Interplay between the Cannabinoid System and microRNAs in Cancer

Cancer patients often use cannabinoids for alleviating symptoms induced by cancer pathogenesis and cancer treatment. This use of cannabinoids can have unexpected effects in cancer patients depending on the cancer type, resulting in either beneficial (e.g., anticancer) or adverse (e.g., oncogenic) effects. While cannabinoids can enhance the growth and progression of some cancers, they can also suppress the growth and progression of other cancers. However, the underlying mechanisms of such differential effects are poorly understood. miRNAs have been shown to be involved in driving the hallmarks of cancer, affecting cancer growth and progression as well as cancer therapy response. Although the understanding of the effects of cannabinoids and miRNAs as they relate to cancer continues to improve, the interplay between cannabinoid system and miRNAs in cancer pathogenesis and cancer treatment response is poorly understood. Investigation of such interactions between the cannabinoid system and miRNAs could provide novel insights into the underlying mechanisms of the differential effects of cannabinoids in cancer and can help predict and improve the prognosis of cancer patients.

Applied machine learning in cancer research: A systematic review for patient diagnosis, classification and prognosis

Artificial Intelligence (AI) has recently altered the landscape of cancer research and medical oncology using traditional Machine Learning (ML) algorithms and cutting-edge Deep Learning (DL) architectures. In this review article we focus on the ML aspect of AI applications in cancer research and present the most indicative studies with respect to the ML algorithms and data used. The PubMed and dblp databases were considered to obtain the most relevant research works of the last five years. Based on a comparison of the proposed studies and their research clinical outcomes concerning the medical ML application in cancer research, three main clinical scenarios were identified. We give an overview of the well-known DL and Reinforcement Learning (RL) methodologies, as well as their application in clinical practice, and we briefly discuss Systems Biology in cancer research. We also provide a thorough examination of the clinical scenarios with respect to disease diagnosis, patient classification and cancer prognosis and survival. The most relevant studies identified in the preceding year are presented along with their primary findings. Furthermore, we examine the effective implementation and the main points that need to be addressed in the direction of robustness, explainability and transparency of predictive models. Finally, we summarize the most recent advances in the field of AI/ML applications in cancer research and medical oncology, as well as some of the challenges and open issues that need to be addressed before data-driven models can be implemented in healthcare systems to assist physicians in their daily practice.

Identification of Immune Function-Related Subtypes in Cutaneous Melanoma

Tumour immunotherapy combined with molecular typing is a new therapy to help select patients. However, molecular typing algorithms related to tumour immune function have not been thoroughly explored. We herein proposed a single sample immune signature network (SING) method to identify new immune function-related subtypes of cutaneous melanoma of the skin. A sample-specific network and tumour microenvironment were constructed based on the immune annotation of cutaneous melanoma samples. Then, the differences and heterogeneity of immune function among different subtypes were analysed and verified. A total of 327 cases of cutaneous melanoma were divided into normal and immune classes; the immune class had more immune enrichment characteristics. After further subdividing the 327 cases into three immune-related subtypes, the degree of immune enrichment in the "high immune subtype" was greater than that in other subtypes. Similar results were validated in both tumour samples and cell lines. Sample-specific networks and the tumour microenvironment based on immune annotation contribute to the mining of cutaneous melanoma immune function-related subtypes. Mutations in B2M and PTEN are considered potential therapeutic targets that can improve the immune response. Patients with a high immune subtype can generally obtain a better immune prognosis effect, and the prognosis may be improved when combined with TGF-β inhibitors.

NETest is superior to chromogranin A in neuroendocrine neoplasia: a prospective ENETS CoE analysis

INTRODUCTION

The absence of a reliable, universal biomarker is a significant limitation in neuroendocrine neoplasia (NEN) management. We prospectively evaluated two CgA assays, (NEOLISA, EuroDiagnostica) and (CgA ELISA, Demeditec Diagnostics (DD)) and compared the results to the NETest.

METHODS

NEN cohort (n = 258): pancreatic, n = 67; small intestine, n = 40; appendiceal, n = 10; rectal, n = 45; duodenal, n = 9; gastric, n = 44; lung, n = 43. Image-positive disease (IPD) (n = 123), image & histology- negative (IND) (n = 106), and image-negative and histology positive (n = 29). CgA metrics: NEOLISA, ULN: 108 ng/mL, DD: ULN: 99 ng/mL. Data mean ± s.e.m. NETest: qRT-PCR - multianalyte analyses, ULN: 20. All samples de-identified and assessed blinded. Statistics: Mann-Whitney U-test, Pearson correlation and McNemar-test.

RESULTS

CgA positive in 53/258 (NEOLISA), 32 (DD) and NETest-positive in 157/258. In image- positive disease (IPD, n = 123), NEOLISA-positive: 33% and DD: 19%. NETest-positive: 122/123 (99%; McNemar's Chi2= 79-97, P < 0.0001). NEOLISA was more accurate than DD (P = 0.0003). In image- negative disease (IND), CgA was NEOLISA-positive (11%), DD (8%), P = NS, and NETest (33%). CgA assays could not distinguish progressive (PD) from stable disease (SD) or localized from metastatic disease (MD). NETest was significantly higher in PD (47 ± 5) than SD (29 ± 1, P = 0.0009). NETest levels in MD (35 ± 2) were elevated vs localized disease (24 ± 1.3, P = 0.008).

CONCLUSIONS

NETest, a multigenomic mRNA biomarker, was ~99% accurate in the identification of NEN disease. The CgA assays detected NEN disease in 19-33%. Multigenomic blood analysis using NETest is more accurate than CgA and should be considered the biomarker standard of care.