voomDDA: discovery of diagnostic biomarkers and classification of RNA-seq data

Novel transcriptomic signatures associated with premature kidney allograft failure

BACKGROUND

The power to predict kidney allograft outcomes based on non-invasive assays is limited. Assessment of operational tolerance (OT) patients allows us to identify transcriptomic signatures of true non-responders for construction of predictive models.

METHODS

In this observational retrospective study, RNA sequencing of peripheral blood was used in a derivation cohort to identify a protective set of transcripts by comparing 15 OT patients (40% females), from the TOMOGRAM Study (NCT05124444), 14 chronic active antibody-mediated rejection (CABMR) and 23 stable graft function patients ≥15 years (STA). The selected differentially expressed transcripts between OT and CABMR were used in a validation cohort (n = 396) to predict 3-year kidney allograft loss at 3 time-points using RT-qPCR.

FINDINGS

Archetypal analysis and classifier performance of RNA sequencing data showed that OT is clearly distinguishable from CABMR, but similar to STA. Based on significant transcripts from the validation cohort in univariable analysis, 2 multivariable Cox models were created. A 3-transcript (ADGRG3, ATG2A, and GNLY) model from POD 7 predicted graft loss with C-statistics (C) 0.727 (95% CI, 0.638-0.820). Another 3-transcript (IGHM, CD5, GNLY) model from M3 predicted graft loss with C 0.786 (95% CI, 0.785-0.865). Combining 3-transcripts models with eGFR at POD 7 and M3 improved C-statistics to 0.860 (95% CI, 0.778-0.944) and 0.868 (95% CI, 0.790-0.944), respectively.

INTERPRETATION

Identification of transcripts distinguishing OT from CABMR allowed us to construct models predicting premature graft loss. Identified transcripts reflect mechanisms of injury/repair and alloimmune response when assessed at day 7 or with a loss of protective phenotype when assessed at month 3.

FUNDING

Supported by the Ministry of Health of the Czech Republic under grant NV19-06-00031.

Gene Expression Profiling: Identification of Novel Pathways and Potential Biomarkers in Severe Acute Pancreatitis

BACKGROUND

Determining the risk of developing severe acute pancreatitis (AP) on presentation to hospital is difficult but vital to enable early management decisions that reduce morbidity and mortality. The objective of this study was to determine global gene expression profiles of patients with different acute pancreatitis severity to identify genes and molecular mechanisms involved in the pathogenesis of severe AP.

STUDY DESIGN

AP patients (n = 87) were recruited within 24 hours of admission to the Emergency Department and were confirmed to exhibit at least 2 of the following features: (1) abdominal pain characteristic of AP, (2) serum amylase and/or lipase more than 3-fold the upper laboratory limit considered normal, and/or (3) radiographically demonstrated AP on CT scan. Severity was defined according to the Revised Atlanta classification. Thirty-two healthy volunteers were also recruited and peripheral venous blood was collected for performing RNA-Seq.

RESULTS

In severe AP, 422 genes (185 upregulated, 237 downregulated) were significantly differentially expressed when compared with moderately severe and mild cases. Pathway analysis revealed changes in specific innate and adaptive immune, sepsis-related, and surface modification pathways in severe AP. Data-driven approaches revealed distinct gene expression groups (endotypes), which were not entirely overlapping with the clinical Atlanta classification. Importantly, severe and moderately severe AP patients clustered away from healthy controls, whereas mild AP patients did not exhibit any clear separation, suggesting distinct underlying mechanisms that may influence severity of AP.

CONCLUSION

There were significant differences in gene expression affecting the severity of AP, revealing a central role of specific immunological pathways. Despite the existence of patient endotypes, a 4-gene transcriptomic signature (S100A8, S100A9, MMP25, and MT-ND4L) was determined that can predict severe AP with an accuracy of 64%.

Noncoding RNAs and Their Response Predictive Value in Azacitidine-treated Patients With Myelodysplastic Syndrome and Acute Myeloid Leukemia With Myelodysplasia-related Changes

BACKGROUND/AIM

Prediction of response to azacitidine (AZA) treatment is an important challenge in hematooncology. In addition to protein coding genes (PCGs), AZA efficiency is influenced by various noncoding RNAs (ncRNAs), including long ncRNAs (lncRNAs), circular RNAs (circRNAs), and transposable elements (TEs).

MATERIALS AND METHODS

RNA sequencing was performed in patients with myelodysplastic syndromes or acute myeloid leukemia before AZA treatment to assess contribution of ncRNAs to AZA mechanisms and propose novel disease prediction biomarkers.

RESULTS

Our analyses showed that lncRNAs had the strongest predictive potential. The combined set of the best predictors included 14 lncRNAs, and only four PCGs, one circRNA, and no TEs. Epigenetic regulation and recombinational repair were suggested as crucial for AZA response, and network modeling defined three deregulated lncRNAs (CTC-482H14.5, RP11-419K12.2, and RP11-736I24.4) associated with these processes.

CONCLUSION

The expression of various ncRNAs can influence the effect of AZA and new ncRNA-based predictive biomarkers can be defined.

Genes and regulatory mechanisms associated with experimentally-induced bovine respiratory disease identified using supervised machine learning methodology

Bovine respiratory disease (BRD) is a multifactorial disease involving complex host immune interactions shaped by pathogenic agents and environmental factors. Advancements in RNA sequencing and associated analytical methods are improving our understanding of host response related to BRD pathophysiology. Supervised machine learning (ML) approaches present one such method for analyzing new and previously published transcriptome data to identify novel disease-associated genes and mechanisms. Our objective was to apply ML models to lung and immunological tissue datasets acquired from previous clinical BRD experiments to identify genes that classify disease with high accuracy. Raw mRNA sequencing reads from 151 bovine datasets (n = 123 BRD, n = 28 control) were downloaded from NCBI-GEO. Quality filtered reads were assembled in a HISAT2/Stringtie2 pipeline. Raw gene counts for ML analysis were normalized, transformed, and analyzed with MLSeq, utilizing six ML models. Cross-validation parameters (fivefold, repeated 10 times) were applied to 70% of the compiled datasets for ML model training and parameter tuning; optimized ML models were tested with the remaining 30%. Downstream analysis of significant genes identified by the top ML models, based on classification accuracy for each etiological association, was performed within WebGestalt and Reactome (FDR ≤ 0.05). Nearest shrunken centroid and Poisson linear discriminant analysis with power transformation models identified 154 and 195 significant genes for IBR and BRSV, respectively; from these genes, the two ML models discriminated IBR and BRSV with 100% accuracy compared to sham controls. Significant genes classified by the top ML models in IBR (154) and BRSV (195), but not BVDV (74), were related to type I interferon production and IL-8 secretion, specifically in lymphoid tissue and not homogenized lung tissue. Genes identified in Mannheimia haemolytica infections (97) were involved in activating classical and alternative pathways of complement. Novel findings, including expression of genes related to reduced mitochondrial oxygenation and ATP synthesis in consolidated lung tissue, were discovered. Genes identified in each analysis represent distinct genomic events relevant to understanding and predicting clinical BRD. Our analysis demonstrates the utility of ML with published datasets for discovering functional information to support the prediction and understanding of clinical BRD.

Cellular, molecular, and therapeutic characterization of pilocarpine-induced temporal lobe epilepsy

Animal models have expanded our understanding of temporal lobe epilepsy (TLE). However, translating these to cell-specific druggable hypotheses is not explored. Herein, we conducted an integrative insilico-analysis of an available transcriptomics dataset obtained from animals with pilocarpine-induced-TLE. A set of 119 genes with subtle-to-moderate impact predicted most forms of epilepsy with ~ 97% accuracy and characteristically mapped to upregulated homeostatic and downregulated synaptic pathways. The deconvolution of cellular proportions revealed opposing changes in diverse cell types. The proportion of nonneuronal cells increased whereas that of interneurons, except for those expressing vasoactive intestinal peptide (Vip), decreased, and pyramidal neurons of the cornu-ammonis (CA) subfields showed the highest variation in proportion. A probabilistic Bayesian-network demonstrated an aberrant and oscillating physiological interaction between nonneuronal cells involved in the blood–brain-barrier and Vip interneurons in driving seizures, and their role was evaluated insilico using transcriptomic changes induced by valproic-acid, which showed opposing effects in the two cell-types. Additionally, we revealed novel epileptic and antiepileptic mechanisms and predicted drugs using causal inference, outperforming the present drug repurposing approaches. These well-powered findings not only expand the understanding of TLE and seizure oscillation, but also provide predictive biomarkers of epilepsy, cellular and causal micro-circuitry changes associated with it, and a drug-discovery method focusing on these events.

Joint Modeling of RNAseq and Radiomics Data for Glioma Molecular Characterization and Prediction

RNA sequencing (RNAseq) is a recent technology that profiles gene expression by measuring the relative frequency of the RNAseq reads. RNAseq read counts data is increasingly used in oncologic care and while radiology features (radiomics) have also been gaining utility in radiology practice such as disease diagnosis, monitoring, and treatment planning. However, contemporary literature lacks appropriate RNA-radiomics (henceforth, radiogenomics ) joint modeling where RNAseq distribution is adaptive and also preserves the nature of RNAseq read counts data for glioma grading and prediction. The Negative Binomial (NB) distribution may be useful to model RNAseq read counts data that addresses potential shortcomings. In this study, we propose a novel radiogenomics-NB model for glioma grading and prediction. Our radiogenomics-NB model is developed based on differentially expressed RNAseq and selected radiomics/volumetric features which characterize tumor volume and sub-regions. The NB distribution is fitted to RNAseq counts data, and a log-linear regression model is assumed to link between the estimated NB mean and radiomics. Three radiogenomics-NB molecular mutation models (e.g., IDH mutation, 1p/19q codeletion, and ATRX mutation) are investigated. Additionally, we explore gender-specific effects on the radiogenomics-NB models. Finally, we compare the performance of the proposed three mutation prediction radiogenomics-NB models with different well-known methods in the literature: Negative Binomial Linear Discriminant Analysis (NBLDA), differentially expressed RNAseq with Random Forest (RF-genomics), radiomics and differentially expressed RNAseq with Random Forest (RF-radiogenomics), and Voom-based count transformation combined with the nearest shrinkage classifier (VoomNSC). Our analysis shows that the proposed radiogenomics-NB model significantly outperforms (ANOVA test, p < 0.05) for prediction of IDH and ATRX mutations and offers similar performance for prediction of 1p/19q codeletion, when compared to the competing models in the literature, respectively.

qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data

Classification on the basis of gene expression data derived from RNA-seq promises to become an important part of modern medicine. We propose a new classification method based on a model where the data is marginally negative binomial but dependent, thereby incorporating the dependence known to be present between measurements from different genes. The method, called qtQDA, works by first performing a quantile transformation (qt) then applying Gaussian quadratic discriminant analysis (QDA) using regularized covariance matrix estimates. We show that qtQDA has excellent performance when applied to real data sets and has advantages over some existing approaches. An R package implementing the method is also available on https://github.com/goknurginer/qtQDA.

MLSeq: Machine learning interface for RNA-sequencing data

BACKGROUND AND OBJECTIVE

In the last decade, RNA-sequencing technology has become method-of-choice and prefered to microarray technology for gene expression based classification and differential expression analysis since it produces less noisy data. Although there are many algorithms proposed for microarray data, the number of available algorithms and programs are limited for classification of RNA-sequencing data. For this reason, we developed MLSeq, to bring not only frequently used classification algorithms but also novel approaches together and make them available to be used for classification of RNA sequencing data. This package is developed using R language environment and distributed through BIOCONDUCTOR network.

METHODS

Classification of RNA-sequencing data is not straightforward since raw data should be preprocessed before downstream analysis. With MLSeq package, researchers can easily preprocess (normalization, filtering, transformation etc.) and classify raw RNA-sequencing data using two strategies: (i) to perform algorithms which are directly proposed for RNA-sequencing data structure or (ii) to transform RNA-sequencing data in order to bring it distributionally closer to microarray data structure, and perform algorithms which are developed for microarray data. Moreover, we proposed novel algorithms such as voom (an acronym for variance modelling at observational level) based nearest shrunken centroids (voomNSC), diagonal linear discriminant analysis (voomDLDA), etc. through MLSeq.

MATERIALS

Three real RNA-sequencing datasets (i.e cervical cancer, lung cancer and aging datasets) were used to evalute model performances. Poisson linear discriminant analysis (PLDA) and negative binomial linear discriminant analysis (NBLDA) were selected as algorithms based on dicrete distributions, and voomNSC, nearest shrunken centroids (NSC) and support vector machines (SVM) were selected as algorithms based on continuous distributions for model comparisons. Each algorithm is compared using classification accuracies and sparsities on an independent test set.

RESULTS

The algorithms which are based on discrete distributions performed better in cervical cancer and aging data with accuracies above 0.92. In lung cancer data, the most of algorithms performed similar with accuracies of 0.88 except that SVM achieved 0.94 of accuracy. Our voomNSC algorithm was the most sparse algorithm, and able to select 2.2% and 6.6% of all features for cervical cancer and lung cancer datasets respectively. However, in aging data, sparse classifiers were not able to select an optimal subset of all features.

CONCLUSION

MLSeq is comprehensive and easy-to-use interface for classification of gene expression data. It allows researchers perform both preprocessing and classification tasks through single platform. With this property, MLSeq can be considered as a pipeline for the classification of RNA-sequencing data.