Machine Learning Applicability for Classification of PAD/VCD Chemotherapy Response Using 53 Multiple Myeloma RNA Sequencing Profiles

Uniformly shaped harmonization combines human transcriptomic data from different platforms while retaining their biological properties and differential gene expression patterns

Introduction: Co-normalization of RNA profiles obtained using different experimental platforms and protocols opens avenue for comprehensive comparison of relevant features like differentially expressed genes associated with disease. Currently, most of bioinformatic tools enable normalization in a flexible format that depends on the individual datasets under analysis. Thus, the output data of such normalizations will be poorly compatible with each other. Recently we proposed a new approach to gene expression data normalization termed Shambhala which returns harmonized data in a uniform shape, where every expression profile is transformed into a pre-defined universal format. We previously showed that following shambhalization of human RNA profiles, overall tissue-specific clustering features are strongly retained while platform-specific clustering is dramatically reduced. Methods: Here, we tested Shambhala performance in retention of fold-change gene expression features and other functional characteristics of gene clusters such as pathway activation levels and predicted cancer drug activity scores. Results: Using 6,793 cancer and 11,135 normal tissue gene expression profiles from the literature and experimental datasets, we applied twelve performance criteria for different versions of Shambhala and other methods of transcriptomic harmonization with flexible output data format. Such criteria dealt with the biological type classifiers, hierarchical clustering, correlation/regression properties, stability of drug efficiency scores, and data quality for using machine learning classifiers. Discussion: Shambhala-2 harmonizer demonstrated the best results with the close to 1 correlation and linear regression coefficients for the comparison of training vs validation datasets and more than two times lesser instability for calculation of drug efficiency scores compared to other methods.

Computational approaches in rheumatic diseases - Deciphering complex spatio-temporal cell interactions

Inflammatory arthritis, including rheumatoid (RA), and psoriatic (PsA) arthritis, are clinically and immunologically heterogeneous diseases with no identified cure. Chronic inflammation of the synovial tissue ushers loss of function of the joint that severely impacts the patient's quality of life, eventually leading to disability and life-threatening comorbidities. The pathogenesis of synovial inflammation is the consequence of compounded immune and stromal cell interactions influenced by genetic and environmental factors. Deciphering the complexity of the synovial cellular landscape has accelerated primarily due to the utilisation of bulk and single cell RNA sequencing. Particularly the capacity to generate cell-cell interaction networks could reveal evidence of previously unappreciated processes leading to disease. However, there is currently a lack of universal nomenclature as a result of varied experimental and technological approaches that discombobulates the study of synovial inflammation. While spatial transcriptomic analysis that combines anatomical information with transcriptomic data of synovial tissue biopsies promises to provide more insights into disease pathogenesis, in vitro functional assays with single-cell resolution will be required to validate current bioinformatic applications. In order to provide a comprehensive approach and translate experimental data to clinical practice, a combination of clinical and molecular data with machine learning has the potential to enhance patient stratification and identify individuals at risk of arthritis that would benefit from early therapeutic intervention. This review aims to provide a comprehensive understanding of the effect of computational approaches in deciphering synovial inflammation pathogenesis and discuss the impact that further experimental and novel computational tools may have on therapeutic target identification and drug development.

Mechanistic insights into dietary (poly)phenols and vascular dysfunction-related diseases using multi-omics and integrative approaches: Machine learning as a next challenge in nutrition research

Dietary (poly)phenols have been extensively studied for their vasculoprotective effects and consequently their role in preventing or delaying onsets of cardiovascular and metabolic diseases. Even though early studies have ascribed the vasculoprotective properties of (poly)phenols primarily on their putative free radical scavenging properties, recent data indicate that in biological systems, (poly)phenols act primarily through genomic and epigenomic mechanisms. The molecular mechanisms underlying their health properties are still not well identified, mainly due to the use of physiologically non-relevant conditions (native molecules or extracts at high concentrations, rather than circulating metabolites), but also due to the use of targeted genomic approaches aiming to evaluate the effect only on few specific genes, thus preventing to decipher detailed molecular mechanisms involved. The use of state-of-the-art untargeted analytical methods represents a significant breakthrough in nutrigenomics, as these methods enable detailed insights into the effects at each specific omics level. Moreover, the implementation of multi-omics approaches allows integration of different levels of regulation of cellular functions, to obtain a comprehensive picture of the molecular mechanisms of action of (poly)phenols. In combination with bioinformatics and the methods of machine learning, multi-omics has potential to make a huge contribution to the nutrition science. The aim of this review is to provide an overview of the use of the omics, multi-omics, and integrative approaches in studying the vasculoprotective properties of dietary (poly)phenols and address the potentials for use of the machine learning in nutrigenomics.

Clinically relevant fusion oncogenes: detection and practical implications

Mechanistically, chimeric genes result from DNA rearrangements and include parts of preexisting normal genes combined at the genomic junction site. Some rearranged genes encode pathological proteins with altered molecular functions. Those which can aberrantly promote carcinogenesis are called fusion oncogenes. Their formation is not a rare event in human cancers, and many of them were documented in numerous study reports and in specific databases. They may have various molecular peculiarities like increased stability of an oncogenic part, self-activation of tyrosine kinase receptor moiety, and altered transcriptional regulation activities. Currently, tens of low molecular mass inhibitors are approved in cancers as the drugs targeting receptor tyrosine kinase (RTK) oncogenic fusion proteins, that is, including ALK, ABL, EGFR, FGFR1-3, NTRK1-3, MET, RET, ROS1 moieties. Therein, the presence of the respective RTK fusion in the cancer genome is the diagnostic biomarker for drug prescription. However, identification of such fusion oncogenes is challenging as the breakpoint may arise in multiple sites within the gene, and the exact fusion partner is generally unknown. There is no gold standard method for RTK fusion detection, and many alternative experimental techniques are employed nowadays to solve this issue. Among them, RNA-seq-based methods offer an advantage of unbiased high-throughput analysis of only transcribed RTK fusion genes, and of simultaneous finding both fusion partners in a single RNA-seq read. Here we focus on current knowledge of biology and clinical aspects of RTK fusion genes, related databases, and laboratory detection methods.

Expression levels of NONO, a nuclear protein primarily involved in paraspeckles function, are associated with several deregulated molecular pathways and poor clinical outcome in multiple myeloma

PURPOSE

The NONO protein belongs to the multifunctional family of proteins that can bind DNA, RNA and proteins. It is located in the nucleus of most mammalian cells and can affect almost every step of gene regulation. Dysregulation of NONO has been found in many types of cancer; however, data regarding its expression and relevance in Multiple Myeloma (MM) are virtually absent.

METHODS

We took advantage of a large cohort of MM patients enrolled in the Multiple Myeloma Research Foundation CoMMpass study to elucidate better the clinical and biological relevance of NONO expression in the context of the MM genomic landscape and transcriptome.

RESULTS

NONO is overexpressed in pathological samples compared to normal controls. In addition, higher NONO expression levels are significant independent prognostic markers of worse clinical outcome in MM. Our results indicate that NONO deregulation may play a pathogenetic role in MM by affecting cell cycle, DNA repair mechanisms, and influencing translation by regulating ribosome biogenesis and assembly. Furthermore, our data suggest NONO involvement in the metabolic reprogramming of glucose metabolism from respiration to aerobic glycolysis, a phenomenon known as the 'Warburg Effect' that supports rapid cancer cell growth, survival, and invasion.

CONCLUSION

These findings strongly support the need of future investigations for the understanding of the mechanisms of deregulation and the biological role and activity of NONO in MM.

Experimentally Deduced Criteria for Detection of Clinically Relevant Fusion 3′ Oncogenes from FFPE Bulk RNA Sequencing Data

Drugs targeting receptor tyrosine kinase (RTK) oncogenic fusion proteins demonstrate impressive anti-cancer activities. The fusion presence in the cancer is the respective drug prescription biomarker, but their identification is challenging as both the breakpoint and the exact fusion partners are unknown. RNAseq offers the advantage of finding both fusion parts by screening sequencing reads. Paraffin (FFPE) tissue blocks are the most common way of storing cancer biomaterials in biobanks. However, finding RTK fusions in FFPE samples is challenging as RNA fragments are short and their artifact ligation may appear in sequencing libraries. Here, we annotated RNAseq reads of 764 experimental FFPE solid cancer samples, 96 leukemia samples, and 2 cell lines, and identified 36 putative clinically relevant RTK fusions with junctions corresponding to exon borders of the fusion partners. Where possible, putative fusions were validated by RT-PCR (confirmed for 10/25 fusions tested). For the confirmed 3′RTK fusions, we observed the following distinguishing features. Both moieties were in-frame, and the tyrosine kinase domain was preserved. RTK exon coverage by RNAseq reads upstream of the junction site were lower than downstream. Finally, most of the true fusions were present by more than one RNAseq read. This provides the basis for automatic annotation of 3′RTK fusions using FFPE RNAseq profiles.

Shambhala-2: A Protocol for Uniformly Shaped Harmonization of Gene Expression Profiles of Various Formats

Uniformly shaped harmonization of gene expression profiles is central for the simultaneous comparison of multiple gene expression datasets. It is expected to operate with the gene expression data obtained using various experimental methods and equipment, and to return harmonized profiles in a uniform shape. Such uniformly shaped expression profiles from different initial datasets can be further compared directly. However, current harmonization techniques have strong limitations that prevent their broad use for bioinformatic applications. They can either operate with only up to two datasets/platforms or return data in a dynamic format that will be different for every comparison under analysis. This also does not allow for adding new data to the previously harmonized dataset(s), which complicates the analysis and increases calculation costs. We propose here a new method termed Shambhala-2 that can transform multi-platform expression data into a universal format that is identical for all harmonizations made using this technique. Shambhala-2 is based on sample-by-sample cubic conversion of the initial expression dataset into a preselected shape of the reference definitive dataset. Using 8390 samples of 12 healthy human tissue types and 4086 samples of colorectal, kidney, and lung cancer tissues, we verified Shambhala-2's capacity in restoring tissue-specific expression patterns for seven microarray and three RNA sequencing platforms. Shambhala-2 performed well for all tested combinations of RNAseq and microarray profiles, and retained gene-expression ranks, as evidenced by high correlations between different single- or aggregated gene expression metrics in pre- and post-Shambhalized samples, including preserving cancer-specific gene expression and pathway activation features. © 2022 Wiley Periodicals LLC. Basic Protocol: Shambhala-2 harmonizer Alternate Protocol 1: Linear Shambhala/Shambhala-1 Alternate Protocol 2: Alternative (flexible-format and uniformly shaped) normalization methods Support Protocol 1: Watermelon multisection (WM) Support Protocol 2: Calculation of cancer-to-normal log-fold-change (LFC) and pathway activation level (PAL).

Machine Learning: A New Prospect in Multi-Omics Data Analysis of Cancer

Cancer is defined as a large group of diseases that is associated with abnormal cell growth, uncontrollable cell division, and may tend to impinge on other tissues of the body by different mechanisms through metastasis. What makes cancer so important is that the cancer incidence rate is growing worldwide which can have major health, economic, and even social impacts on both patients and the governments. Thereby, the early cancer prognosis, diagnosis, and treatment can play a crucial role at the front line of combating cancer. The onset and progression of cancer can occur under the influence of complicated mechanisms and some alterations in the level of genome, proteome, transcriptome, metabolome etc. Consequently, the advent of omics science and its broad research branches (such as genomics, proteomics, transcriptomics, metabolomics, and so forth) as revolutionary biological approaches have opened new doors to the comprehensive perception of the cancer landscape. Due to the complexities of the formation and development of cancer, the study of mechanisms underlying cancer has gone beyond just one field of the omics arena. Therefore, making a connection between the resultant data from different branches of omics science and examining them in a multi-omics field can pave the way for facilitating the discovery of novel prognostic, diagnostic, and therapeutic approaches. As the volume and complexity of data from the omics studies in cancer are increasing dramatically, the use of leading-edge technologies such as machine learning can have a promising role in the assessments of cancer research resultant data. Machine learning is categorized as a subset of artificial intelligence which aims to data parsing, classification, and data pattern identification by applying statistical methods and algorithms. This acquired knowledge subsequently allows computers to learn and improve accurate predictions through experiences from data processing. In this context, the application of machine learning, as a novel computational technology offers new opportunities for achieving in-depth knowledge of cancer by analysis of resultant data from multi-omics studies. Therefore, it can be concluded that the use of artificial intelligence technologies such as machine learning can have revolutionary roles in the fight against cancer.

Machine Learning and Deep Learning Applications in Multiple Myeloma Diagnosis, Prognosis, and Treatment Selection

Simple Summary

Multiple myeloma is a malignant neoplasm of plasma cells with complex pathogenesis. With major progresses in multiple myeloma research, it is essential that we reconsider our methods for diagnosing and monitoring multiple myeloma disease. This fact needs the integration of serology, histology, radiology, and genetic data; therefore, multiple myeloma study has generated massive quantities of granular high-dimensional data exceeding human understanding. With improved computational techniques, artificial intelligence tools for data processing and analysis are becoming more and more relevant. Artificial intelligence represents a wide set of algorithms for which machine learning and deep learning are presently among the most impactful. This review focuses on artificial intelligence applications in multiple myeloma research, first illustrating machine learning and deep learning procedures and workflow, followed by how these algorithms are used for multiple myeloma diagnosis, prognosis, bone lesions identification, and evaluation of response to the treatment.

Abstract

Artificial intelligence has recently modified the panorama of oncology investigation thanks to the use of machine learning algorithms and deep learning strategies. Machine learning is a branch of artificial intelligence that involves algorithms that analyse information, learn from that information, and then employ their discoveries to make abreast choice, while deep learning is a field of machine learning basically represented by algorithms inspired by the organization and function of the brain, named artificial neural networks. In this review, we examine the possibility of the artificial intelligence applications in multiple myeloma evaluation, and we report the most significant experimentations with respect to the machine and deep learning procedures in the relevant field. Multiple myeloma is one of the most common haematological malignancies in the world, and among them, it is one of the most difficult ones to cure due to the high occurrence of relapse and chemoresistance. Machine learning- and deep learning-based studies are expected to be among the future strategies to challenge this negative-prognosis tumour via the detection of new markers for their prompt discovery and therapy selection and by a better evaluation of its relapse and survival.

Ablation of VLA4 in multiple myeloma cells redirects tumor spread and prolongs survival

Multiple myeloma (MM) is a cancer of bone marrow (BM) plasma cells, which is increasingly treatable but still incurable. In 90% of MM patients, severe osteolysis results from pathological interactions between MM cells and the bone microenvironment. Delineating specific molecules and pathways for their role in cancer supportive interactions in the BM is vital for developing new therapies. Very Late Antigen 4 (VLA4, integrin α₄β₁) is a key player in cell–cell adhesion and signaling between MM and BM cells. We evaluated a VLA4 selective near infrared fluorescent probe, LLP2A-Cy5, for in vitro and in vivo optical imaging of VLA4. Furthermore, two VLA4-null murine 5TGM1 MM cell (KO) clones were generated by CRISPR/Cas9 knockout of the Itga4 (α₄) subunit, which induced significant alterations in the transcriptome. In contrast to the VLA4⁺ 5TGM1 parental cells, C57Bl/KaLwRij immunocompetent syngeneic mice inoculated with the VLA4-null clones showed prolonged survival, reduced medullary disease, and increased extramedullary disease burden. The KO tumor foci showed significantly reduced uptake of LLP2A-Cy5, confirming in vivo specificity of this imaging agent. This work provides new insights into the pathogenic role of VLA4 in MM, and evaluates an optical tool to measure its expression in preclinical models.

EGFR Pathway-Based Gene Signatures of Druggable Gene Mutations in Melanoma, Breast, Lung, and Thyroid Cancers

EGFR, BRAF, PIK3CA, and KRAS genes play major roles in EGFR pathway, and accommodate activating mutations that predict response to many targeted therapeutics. However, connections between these mutations and EGFR pathway expression patterns remain unexplored. Here, we investigated transcriptomic associations with these activating mutations in three ways. First, we compared expressions of these genes in the mutant and wild type tumors, respectively, using RNA sequencing profiles from The Cancer Genome Atlas project database (n = 3660). Second, mutations were associated with the activation level of EGFR pathway. Third, they were associated with the gene signatures of differentially expressed genes from these pathways between the mutant and wild type tumors. We found that the upregulated EGFR pathway was linked with mutations in the BRAF (thyroid cancer, melanoma) and PIK3CA (breast cancer) genes. Gene signatures were associated with BRAF (thyroid cancer, melanoma), EGFR (squamous cell lung cancer), KRAS (colorectal cancer), and PIK3CA (breast cancer) mutations. However, only for the BRAF gene signature in the thyroid cancer we observed strong biomarker diagnostic capacity with AUC > 0.7 (0.809). Next, we validated this signature on the independent literature-based dataset (n = 127, fresh-frozen tissue samples, AUC 0.912), and on the experimental dataset (n = 42, formalin fixed, paraffin embedded tissue samples, AUC 0.822). Our results suggest that the RNA sequencing profiles can be used for robust identification of the replacement of Valine at position 600 with Glutamic acid in the BRAF gene in the papillary subtype of thyroid cancer, and evidence that the specific gene expression levels could provide information about the driver carcinogenic mutations.

RNA Sequencing Data for FFPE Tumor Blocks Can Be Used for Robust Estimation of Tumor Mutation Burden in Individual Biosamples

Tumor mutation burden (TMB) is a well-known efficacy predictor for checkpoint inhibitor immunotherapies. Currently, TMB assessment relies on DNA sequencing data. Gene expression profiling by RNA sequencing (RNAseq) is another type of analysis that can inform clinical decision-making and including TMB estimation may strongly benefit this approach, especially for the formalin-fixed, paraffin-embedded (FFPE) tissue samples. Here, we for the first time compared TMB levels deduced from whole exome sequencing (WES) and RNAseq profiles of the same FFPE biosamples in single-sample mode. We took TCGA project data with mean sequencing depth 23 million gene-mapped reads (MGMRs) and found 0.46 (Pearson)–0.59 (Spearman) correlation with standard mutation calling pipelines. This was converted into low (<10) and high (>10) TMB per megabase classifier with area under the curve (AUC) 0.757, and application of machine learning increased AUC till 0.854. We then compared 73 experimental pairs of WES and RNAseq profiles with lower (mean 11 MGMRs) and higher (mean 68 MGMRs) RNA sequencing depths. For higher depth, we observed ~1 AUC for the high/low TMB classifier and 0.85 (Pearson)–0.95 (Spearman) correlation with standard mutation calling pipelines. For the lower depth, the AUC was below the high-quality threshold of 0.7. Thus, we conclude that using RNA sequencing of tumor materials from FFPE blocks with enough coverage can afford for high-quality discrimination of tumors with high and low TMB levels in a single-sample mode.