Uncovering low-dimensional, miR-based signatures of acute myeloid and lymphoblastic leukemias with a machine-learning-driven network approach

miR-342-3p Inhibits Acute Myeloid Leukemia Progression by Targeting SOX12

Background

It is well known that microRNAs (miRNAs) interfere with the progression of various human malignancies. This article is aimed at exploring the regulating role of miR-342-3p in acute myeloid leukemia (AML) and its mechanism.

Methods

We used the Gene Expression Omnibus (GEO) database to determine miR-342-3p differential expression patterns in AML patients' plasma and cells as well as healthy individuals' plasma and T cells. Quantitative real-time PCR and Western blotting were performed for plasma and cell miR-342-3p and SRY-related high-mobility-group box (SOX12) expression quantification, and cell counting kit-8 assay and flow cytometry were used for the determination of AML cell growth, cycle, and apoptosis. A dual-luciferase reporter gene assay was further carried out to identify the targeted association between miR-342-3p and SOX12 mRNA 3′UTR after prediction by a bioinformatics website. Pearson's correlation analysis was performed to analyze the connection between miR-342-3p and SOX12 expressions. The LinkedOmics database was utilized to explore the downstream pathways in which SOX12 was enriched.

Results

Evidently downregulated plasma miR-342-3p and markedly elevated SOX12 were observed in AML patients versus healthy individuals. miR-342-3p mimics suppressed AML cell growth, enhanced apoptosis, and induced G0/G1 phase arrest; conversely, enhanced capacity of AML cells to proliferate, suppressed apoptosis, and accelerated cell cycle were observed after treatment with miR-342-3p inhibitors. SOX12 was confirmed as miR-342-3p's target gene. Overexpressing or knocking down SOX12 reversed miR-342-3p's impacts on AML cell growth, apoptosis, and cycle. Upregulated SOX12 was positively related to DNA replication and RNA polymerase signaling pathways.

Conclusion

miR-342-3p affects apoptosis of AML cells and their ability to proliferate via targeted regulation of SOX12.

Machine learning in haematological malignancies

Machine learning is a branch of computer science and statistics that generates predictive or descriptive models by learning from training data rather than by being rigidly programmed. It has attracted substantial attention for its many applications in medicine, both as a catalyst for research and as a means of improving clinical care across the cycle of diagnosis, prognosis, and treatment of disease. These applications include the management of haematological malignancy, in which machine learning has created inroads in pathology, radiology, genomics, and the analysis of electronic health record data. As computational power becomes cheaper and the tools for implementing machine learning become increasingly democratised, it is likely to become increasingly integrated into the research and practice landscape of haematology. As such, machine learning merits understanding and attention from researchers and clinicians alike. This narrative Review describes important concepts in machine learning for unfamiliar readers, details machine learning's current applications in haematological malignancy, and summarises important concepts for clinicians to be aware of when appraising research that uses machine learning.

eNetXplorer: an R package for the quantitative exploration of elastic net families for generalized linear models

Background

Regularized generalized linear models (GLMs) are popular regression methods in bioinformatics, particularly useful in scenarios with fewer observations than parameters/features or when many of the features are correlated. In both ridge and lasso regularization, feature shrinkage is controlled by a penalty parameter λ. The elastic net introduces a mixing parameter α to tune the shrinkage continuously from ridge to lasso. Selecting α objectively and determining which features contributed significantly to prediction after model fitting remain a practical challenge given the paucity of available software to evaluate performance and statistical significance.

Results

eNetXplorer builds on top of glmnet to address the above issues for linear (Gaussian), binomial (logistic), and multinomial GLMs. It provides new functionalities to empower practical applications by using a cross validation framework that assesses the predictive performance and statistical significance of a family of elastic net models (as α is varied) and of the corresponding features that contribute to prediction. The user can select which quality metrics to use to quantify the concordance between predicted and observed values, with defaults provided for each GLM. Statistical significance for each model (as defined by α) is determined based on comparison to a set of null models generated by random permutations of the response; the same permutation-based approach is used to evaluate the significance of individual features. In the analysis of large and complex biological datasets, such as transcriptomic and proteomic data, eNetXplorer provides summary statistics, output tables, and visualizations to help assess which subset(s) of features have predictive value for a set of response measurements, and to what extent those subset(s) of features can be expanded or reduced via regularization.

Conclusions

This package presents a framework and software for exploratory data analysis and visualization. By making regularized GLMs more accessible and interpretable, eNetXplorer guides the process to generate hypotheses based on features significantly associated with biological phenotypes of interest, e.g. to identify biomarkers for therapeutic responsiveness. eNetXplorer is also generally applicable to any research area that may benefit from predictive modeling and feature identification using regularized GLMs. The package is available under GPL-3 license at the CRAN repository, https://CRAN.R-project.org/package=eNetXplorer.

Electronic supplementary material

The online version of this article (10.1186/s12859-019-2778-5) contains supplementary material, which is available to authorized users.

miR-708-5p: a microRNA with emerging roles in cancer

MicroRNAs (miRNAs) are small non-coding RNAs that negatively regulate gene expression post-transcriptionally. They are crucial for normal development and maintaining homeostasis. Researchers have discovered that dysregulated miRNA expression contributes to many pathological conditions, including cancer. miRNAs can augment or suppress tumorigenesis based on their expression and transcribed targetome in various cell types. In recent years, researchers have begun to identify miRNAs commonly dysregulated in cancer. One recently identified miRNA, miR-708-5p, has been shown to have profound roles in promoting or suppressing oncogenesis in a myriad of solid and hematological tumors. This review highlights the diverse, sometimes controversial findings reported for miR-708-5p in cancer, and the importance of further exploring this exciting miRNA.

Comprehensive Analysis of MILE Gene Expression Data Set Advances Discovery of Leukaemia Type and Subtype Biomarkers

Large collections of data in studies on cancer such as leukaemia provoke the necessity of applying tailored analysis algorithms to ensure supreme information extraction. In this work, a custom-fit pipeline is demonstrated for thorough investigation of the voluminous MILE gene expression data set. Three analyses are accomplished, each for gaining a deeper understanding of the processes underlying leukaemia types and subtypes. First, the main disease groups are tested for differential expression against the healthy control as in a standard case-control study. Here, the basic knowledge on molecular mechanisms is confirmed quantitatively and by literature references. Second, pairwise comparison testing is performed for juxtaposing the main leukaemia types among each other. In this case by means of the Dice coefficient similarity measure the general relations are pointed out. Moreover, lists of candidate main leukaemia group biomarkers are proposed. Finally, with this approach being successful, the third analysis provides insight into all of the studied subtypes, followed by the emergence of four leukaemia subtype biomarkers. In addition, the class enhanced DEG signature obtained on the basis of novel pipeline processing leads to significantly better classification power of multi-class data classifiers. The developed methodology consisting of batch effect adjustment, adaptive noise and feature filtration coupled with adequate statistical testing and biomarker definition proves to be an effective approach towards knowledge discovery in high-throughput molecular biology experiments.

Evaluation of the miRNA profiling and effectiveness of the propolis on B-cell acute lymphoblastic leukemia cell line

Acute lymphoblastic leukemia (ALL) is one of the most frequent causes of death from cancer. Since the discovery of chemotherapeutic agents, ALL has become a model for improvement of survival. In parallel to this, serious side effects were observed and new natural therapeutic options has been discussed. One of these substances is called propolis which is a resinous substance gathered by honeybees. In the molecular era, miRNAs have been shown to play crucial roles in the development of many clinical conditions. The aim of this study is to evaluate the effect of Aydın propolis on 81 human miRNA activity in CCRF-SB leukemia cell line. Apoptotic effects of propolis on cell lines were also evaluated and apoptosis were found to be induced 1.5 fold in B-cell leukemia cells. The expression of 63 miRNAs (46 miRNAs were downregulated, 19 miRNAs were upregulated) in propolis treated leukemia cells have changed significantly (p<0.05). In conclusion propolis has changed expression of miRNAs which have epigenetic effects on leukemic cells. It is thought that it can be a promising agent for ALL treatment for future studies.

Regulation of RAB5C is important for the growth inhibitory effects of MiR-509 in human precursor-B acute lymphoblastic leukemia

MicroRNAs (miRs) regulate essentially all cellular processes, but few miRs are known to inhibit growth of precursor-B acute lymphoblastic leukemias (B-ALLs). We identified miR-509 via a human genome-wide gain-of-function screen for miRs that inhibit growth of the NALM6 human B-ALL cell line. MiR-509-mediated inhibition of NALM6 growth was confirmed by 3 independent assays. Enforced miR-509 expression inhibited 2 of 2 additional B-ALL cell lines tested, but not 3 non-B-ALL leukemia cell lines. MiR-509-transduced NALM6 cells had reduced numbers of actively proliferating cells and increased numbers of cells undergoing apoptosis. Using miR target prediction algorithms and a filtering strategy, RAB5C was predicted as a potentially relevant target of miR-509. Enforced miR-509 expression in NALM6 cells reduced RAB5C mRNA and protein levels, and RAB5C was demonstrated to be a direct target of miR-509. Knockdown of RAB5C in NALM6 cells recapitulated the growth inhibitory effects of miR-509. Co-expression of the RAB5C open reading frame without its 3' untranslated region (3'UTR) blocked the growth-inhibitory effect mediated by miR-509. These findings establish RAB5C as a target of miR-509 and an important regulator of B-ALL cell growth with potential as a therapeutic target.