Improving prediction of blood cancer using leukemia microarray gene data and Chi2 features with weighted convolutional neural network.

Blood cancer has emerged as a growing concern over the past decade, necessitating early diagnosis for timely and effective treatment. The present diagnostic method, which involves a battery of tests and medical experts, is costly and time-consuming. For this reason, it is crucial to establish an automated diagnostic system for accurate predictions. A particular field of focus in medical research is the use of machine learning and leukemia microarray gene data for blood cancer diagnosis. Even with a great deal of research, more improvements are needed to reach the appropriate levels of accuracy and efficacy. This work presents a supervised machine-learning algorithm for blood cancer prediction. This work makes use of the 22,283-gene leukemia microarray gene data. Chi-squared (Chi2) feature selection methods and the synthetic minority oversampling technique (SMOTE)-Tomek resampling is used to overcome issues with imbalanced and high-dimensional datasets. To balance the dataset for each target class, SMOTE-Tomek creates synthetic data, and Chi2 chooses the most important features to train the learning models from 22,283 genes. A novel weighted convolutional neural network (CNN) model is proposed for classification, utilizing the support of three separate CNN models. To determine the importance of the proposed approach, extensive experiments are carried out on the datasets, including a performance comparison with the most advanced techniques. Weighted CNN demonstrates superior performance over other models when coupled with SMOTE-Tomek and Chi2 techniques, achieving a remarkable 99.9% accuracy. Results from k-fold cross-validation further affirm the supremacy of the proposed model.

Refining the relationship between gut microbiota and common hematologic malignancies: insights from a bidirectional Mendelian randomization study.

Background: The relationship between gut microbiota and hematologic malignancies has attracted considerable attention. As research progresses, it has become increasingly clear that the composition of gut microbiota may influence the onset and progression of hematologic malignancies. However, our understanding of this association remains limited. Methods: In our study, we classified gut microbiota into five groups based on information at the phylum, class, order, family, and genus levels. Subsequently, we obtained data related to common hematologic malignancies from the IEU Open GWAS project. We then employed a bidirectional Mendelian Randomization (MR) approach to determine whether there is a causal relationship between gut microbiota and hematologic malignancies. Additionally, we conducted bidirectional MR analyses to ascertain the directionality of this causal relationship. Results: Through forward and reverse MR analyses, we found the risk of lymphoid leukemia was significantly associated with the abundance of phylum Cyanobacteria, order Methanobacteriales, class Methanobacteria, family Peptococcaceae, family Methanobacteriaceae, and genera Lachnospiraceae UCG010, Methanobrevibacter, Eubacterium brachy group, and Butyrivibrio. The risk of myeloid leukemia was significantly associated with the abundance of phylum Actinobacteria, phylum Firmicutes, order Bifidobacteriales, order Clostridiales, class Actinobacteria, class Gammaproteobacteria, class Clostridia, family Bifidobacteriaceae, and genera Fusicatenibacter, Eubacterium hallii group, Blautia, Collinsella, Ruminococcus gauvreauii group, and Bifidobacterium. The risk of Hodgkin lymphoma was significantly associated with the abundance of family Clostridiales vadinBB60 group, genus Peptococcus, and genus Ruminococcaceae UCG010. The risk of malignant plasma cell tumor was significantly associated with the abundance of genera Romboutsia and Eubacterium rectale group. The risk of diffuse large B-cell lymphoma was significantly associated with the abundance of genera Erysipelatoclostridium and Eubacterium coprostanoligenes group. The risk of mature T/NK cell lymphomas was significantly associated with the abundance of phylum Verrucomicrobia, genus Ruminococcaceae UCG013, genus Lachnoclostridium, and genus Eubacterium rectale group. Lastly, the risk of myeloproliferative neoplasms was significantly associated with the abundance of genus Coprococcus 3 and Eubacterium hallii group. Conclusion: Our study provided new evidence for the causal relationship between gut microbiota and hematologic malignancies, offering novel insights and approaches for the prevention and treatment of these tumors.

Non­m6A RNA modifications in haematological malignancies.

Dysregulated RNA modifications, stemming from the aberrant expression and/or malfunction of RNA modification regulators operating through various pathways, play pivotal roles in driving the progression of haematological malignancies. Among RNA modifications, N6-methyladenosine (m6A) RNA modification, the most abundant internal mRNA modification, stands out as the most extensively studied modification. This prominence underscores the crucial role of the layer of epitranscriptomic regulation in controlling haematopoietic cell fate and therefore the development of haematological malignancies. Additionally, other RNA modifications (non-m6A RNA modifications) have gained increasing attention for their essential roles in haematological malignancies. Although the roles of the m6A modification machinery in haematopoietic malignancies have been well reviewed thus far, such reviews are lacking for non-m6A RNA modifications. In this review, we mainly focus on the roles and implications of non-m6A RNA modifications, including N4-acetylcytidine, pseudouridylation, 5-methylcytosine, adenosine to inosine editing, 2'-O-methylation, N1-methyladenosine and N7-methylguanosine in haematopoietic malignancies. We summarise the regulatory enzymes and cellular functions of non-m6A RNA modifications, followed by the discussions of the recent studies on the biological roles and underlying mechanisms of non-m6A RNA modifications in haematological malignancies. We also highlight the potential of therapeutically targeting dysregulated non-m6A modifiers in blood cancer.

Cell Culture and Slide Preparation for Cytogenetic Studies of Hematological Neoplasms.

Hematological neoplasms are heterogeneous diseases with various subtypes, each with its unique genomic features. Cell culture and slide preparation are essential steps to enrich and collect sufficient neoplastic cells for cytogenetic studies of the neoplasms. This chapter describes methods that are commonly used for culturing hematological neoplastic cells and preparing cytogenetic slides for clinical diagnosis and research of the neoplasms.

Prospects and Potential for Chimerism Analysis after Allogeneic Hematopoietic Stem Cell Transplantation.

Chimerism analysis after allogeneic hematopoietic stem cell transplantation serves to confirm engraftment, indicate relapse of hematologic malignancy, and attribute graft failure to either immune rejection or poor graft function. Short tandem repeat PCR (STR-PCR) is the prevailing method, followed by quantitative real-time PCR (qPCR), with detection limits of 1-5% and 0.1%, respectively. Chimerism assays using digital PCR or next-generation sequencing, both of which are more sensitive than STR-PCR, are increasingly used. Stable mixed chimerism is usually not associated with poor outcomes in non-malignant diseases, but recipient chimerism may foretell relapse of hematologic malignancies, so higher detection sensitivity may be beneficial in such cases. Thus, the need for and the type of intervention, e.g., immunosuppression regimen, donor lymphocyte infusion, and/or salvage second transplantation, should be guided by donor chimerism in the context of the feature and/or residual malignant cells of the disease to be treated.

Leukemic Stem Cells and Hematological Malignancies.

The association between leukemic stem cells (LSCs) and leukemia development has been widely established in the context of genetic alterations, epigenetic pathways, and signaling pathway regulation. Hematopoietic stem cells are at the top of the bone marrow hierarchy and can self-renew and progressively generate blood and immune cells. The microenvironment, niche cells, and complex signaling pathways that regulate them acquire genetic mutations and epigenetic alterations due to aging, a chronic inflammatory environment, stress, and cancer, resulting in hematopoietic stem cell dysregulation and the production of abnormal blood and immune cells, leading to hematological malignancies and blood cancer. Cells that acquire these mutations grow at a faster rate than other cells and induce clone expansion. Excessive growth leads to the development of blood cancers. Standard therapy targets blast cells, which proliferate rapidly; however, LSCs that can induce disease recurrence remain after treatment, leading to recurrence and poor prognosis. To overcome these limitations, researchers have focused on the characteristics and signaling systems of LSCs and therapies that target them to block LSCs. This review aims to provide a comprehensive understanding of the types of hematopoietic malignancies, the characteristics of leukemic stem cells that cause them, the mechanisms by which these cells acquire chemotherapy resistance, and the therapies targeting these mechanisms.

A mitochondrial surveillance mechanism activated by SRSF2 mutations in hematologic malignancies.

Splicing factor mutations are common in myelodysplastic syndrome (MDS) and acute myeloid leukemia (AML), but how they alter cellular functions is unclear. We show that the pathogenic SRSF2P95H/+ mutation disrupts the splicing of mitochondrial mRNAs, impairs mitochondrial complex I function, and robustly increases mitophagy. We also identified a mitochondrial surveillance mechanism by which mitochondrial dysfunction modifies splicing of the mitophagy activator PINK1 to remove a poison intron, increasing the stability and abundance of PINK1 mRNA and protein. SRSF2P95H-induced mitochondrial dysfunction increased PINK1 expression through this mechanism, which is essential for survival of SRSF2P95H/+ cells. Inhibition of splicing with a glycogen synthase kinase 3 inhibitor promoted retention of the poison intron, impairing mitophagy and activating apoptosis in SRSF2P95H/+ cells. These data reveal a homeostatic mechanism for sensing mitochondrial stress through PINK1 splicing and identify increased mitophagy as a disease marker and a therapeutic vulnerability in SRSF2P95H mutant MDS and AML.

MEG3 in hematologic malignancies: from the role of disease biomarker to therapeutic target.

Maternally expressed gene 3 ( MEG3 ) is a noncoding RNA that is known as a tumor suppressor in solid cancers. Recently, a line of studies has emphasized its potential role in hematological malignancies in terms of tumorigenesis, metastasis, and drug resistance. Similar to solid cancers, MEG3 can regulate various cancer hallmarks via sponging miRNA, transcriptional, or posttranslational regulation mechanisms, but may regulate different key elements. In contrast with solid cancers, in some subtypes of leukemia, MEG3 has been found to be upregulated and oncogenic. In this review, we systematically describe the role and underlying mechanisms of MEG3 in multiple types of hematological malignancies. Particularly, we highlight the role of MEG3 in drug resistance and as a novel therapeutic target.

Analysis of 3760 hematologic malignancies reveals rare transcriptomic aberrations of driver genes.

BACKGROUND: Rare oncogenic driver events, particularly affecting the expression or splicing of driver genes, are suspected to substantially contribute to the large heterogeneity of hematologic malignancies. However, their identification remains challenging. METHODS: To address this issue, we generated the largest dataset to date of matched whole genome sequencing and total RNA sequencing of hematologic malignancies from 3760 patients spanning 24 disease entities. Taking advantage of our dataset size, we focused on discovering rare regulatory aberrations. Therefore, we called expression and splicing outliers using an extension of the workflow DROP (Detection of RNA Outliers Pipeline) and AbSplice, a variant effect predictor that identifies genetic variants causing aberrant splicing. We next trained a machine learning model integrating these results to prioritize new candidate disease-specific driver genes. RESULTS: We found a median of seven expression outlier genes, two splicing outlier genes, and two rare splice-affecting variants per sample. Each category showed significant enrichment for already well-characterized driver genes, with odds ratios exceeding three among genes called in more than five samples. On held-out data, our integrative modeling significantly outperformed modeling based solely on genomic data and revealed promising novel candidate driver genes. Remarkably, we found a truncated form of the low density lipoprotein receptor LRP1B transcript to be aberrantly overexpressed in about half of hairy cell leukemia variant (HCL-V) samples and, to a lesser extent, in closely related B-cell neoplasms. This observation, which was confirmed in an independent cohort, suggests LRP1B as a novel marker for a HCL-V subclass and a yet unreported functional role of LRP1B within these rare entities. CONCLUSIONS: Altogether, our census of expression and splicing outliers for 24 hematologic malignancy entities and the companion computational workflow constitute unique resources to deepen our understanding of rare oncogenic events in hematologic cancers.

Multiple roles for AU-rich RNA binding proteins in the development of haematologic malignancies and their resistance to chemotherapy.

Post-transcriptional regulation by RNA binding proteins can determine gene expression levels and drive changes in cancer cell proteomes. Identifying mechanisms of protein-RNA binding, including preferred sequence motifs bound in vivo, provides insights into protein-RNA networks and how they impact mRNA structure, function, and stability. In this review, we will focus on proteins that bind to AU-rich elements (AREs) in nascent or mature mRNA where they play roles in response to stresses encountered by cancer cells. ARE-binding proteins (ARE-BPs) specifically impact alternative splicing, stability, decay and translation, and formation of RNA-rich biomolecular condensates like cytoplasmic stress granules (SGs). For example, recent findings highlight the role of ARE-BPs - like TIAR and HUR - in chemotherapy resistance and in translational regulation of mRNAs encoding pro-inflammatory cytokines. We will discuss emerging evidence that different modes of ARE-BP activity impact leukaemia and lymphoma development, progression, adaptation to microenvironment and chemotherapy resistance.

TNF-α promoter hypomethylation is frequent in oncopediatric patients who recovered from mucositis.

The aim of this study was to investigate the DNA methylation profile in genes encoding catalase (CAT) and superoxide dismutase (SOD3) enzymes, which are involved in oxidative stress mechanisms, and in genes encoding pro-inflammatory cytokines interleukin-6 (IL6) and tumor necrosis factor-alpha (TNF-α) in the oral mucosa of oncopediatric patients treated with methotrexate (MTX®). This was a cross-sectional observational study and the population comprised healthy dental patients (n = 21) and those with hematological malignancies (n = 64) aged between 5 and 19 years. Oral conditions were evaluated using the Oral Assessment Guide and participants were divided into 4 groups: 1- healthy individuals; 2- oncopediatric patients without mucositis; 3- oncopediatric patients with mucositis; 4- oncopediatric patients who had recovered from mucositis. Methylation of DNA from oral mucosal cells was evaluated using the Methylation-Specific PCR technique (MSP). For CAT, the partially methylated profile was the most frequent and for SOD3 and IL6, the hypermethylated profile was the most frequent, with no differences between groups. For TNF-α, the hypomethylated profile was more frequent in the group of patients who had recovered from mucositis. It was concluded that the methylation profiles of CAT, SOD3, and IL6 are common profiles for oral cells of children and adolescents and have no association with oral mucositis or exposure to chemotherapy with MTX®. Hypomethylation of TNF-α is associated with oral mucosal recovery in oncopediatric patients who developed oral mucositis during chemotherapy.

Comparative analysis of dynamic transcriptomes reveals specific COVID-19 features and pathogenesis of immunocompromised populations.

A dysfunction of human host genes and proteins in coronavirus infectious disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a key factor impacting clinical symptoms and outcomes. Yet, a detailed understanding of human host immune responses is still incomplete. Here, we applied RNA sequencing to 94 samples of COVID-19 patients with and without hematological tumors as well as COVID-19 uninfected non-tumor individuals to obtain a comprehensive transcriptome landscape of both hematological tumor patients and non-tumor individuals. In our analysis, we further accounted for the human-SARS-CoV-2 protein interactome, human protein interactome, and human protein complex subnetworks to understand the mechanisms of SARS-CoV-2 infection and host immune responses. Our data sets enabled us to identify important SARS-CoV-2 (non-)targeted differentially expressed genes and complexes post-SARS-CoV-2 infection in both hematological tumor and non-tumor individuals. We found several unique differentially expressed genes, complexes, and functions/pathways such as blood coagulation (APOE, SERPINE1, SERPINE2, and TFPI), lipoprotein particle remodeling (APOC2, APOE, and CETP), and pro-B cell differentiation (IGHM, VPREB1, and IGLL1) during COVID-19 infection in patients with hematological tumors. In particular, APOE, a gene that is associated with both blood coagulation and lipoprotein particle remodeling, is not only upregulated in hematological tumor patients post-SARS-CoV-2 infection but also significantly expressed in acute dead patients with hematological tumors, providing clues for the design of future therapeutic strategies specifically targeting COVID-19 in patients with hematological tumors. Our data provide a rich resource for understanding the specific pathogenesis of COVID-19 in immunocompromised patients, such as those with hematological malignancies, and developing effective therapeutics for COVID-19. IMPORTANCE: A majority of previous studies focused on the characterization of coronavirus infectious disease 2019 (COVID-19) disease severity in people with normal immunity, while the characterization of COVID-19 in immunocompromised populations is still limited. Our study profiles changes in the transcriptome landscape post-severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection in hematological tumor patients and non-tumor individuals. Furthermore, our integrative and comparative systems biology analysis of the interactome, complexome, and transcriptome provides new insights into the tumor-specific pathogenesis of COVID-19. Our findings confirm that SARS-CoV-2 potentially tends to target more non-functional host proteins to indirectly affect host immune responses in hematological tumor patients. The identified unique genes, complexes, functions/pathways, and expression patterns post-SARS-CoV-2 infection in patients with hematological tumors increase our understanding of how SARS-CoV-2 manipulates the host molecular mechanism. Our observed differential genes/complexes and clinical indicators of normal/long infection and deceased COVID-19 patients provide clues for understanding the mechanism of COVID-19 progression in hematological tumors. Finally, our study provides an important data resource that supports the increasing value of the application of publicly accessible data sets to public health.

An artificial intelligence-assisted clinical framework to facilitate diagnostics and translational discovery in hematologic neoplasia.

BACKGROUND: The increasing volume and intricacy of sequencing data, along with other clinical and diagnostic data, like drug responses and measurable residual disease, creates challenges for efficient clinical comprehension and interpretation. Using paediatric B-cell precursor acute lymphoblastic leukaemia (BCP-ALL) as a use case, we present an artificial intelligence (AI)-assisted clinical framework clinALL that integrates genomic and clinical data into a user-friendly interface to support routine diagnostics and reveal translational insights for hematologic neoplasia. METHODS: We performed targeted RNA sequencing in 1365 cases with haematological neoplasms, primarily paediatric B-cell precursor acute lymphoblastic leukaemia (BCP-ALL) from the AIEOP-BFM ALL study. We carried out fluorescence in situ hybridization (FISH), karyotyping and arrayCGH as part of the routine diagnostics. The analysis results of these assays as well as additional clinical information were integrated into an interactive web interface using Bokeh, where the main graph is based on Uniform Manifold Approximation and Projection (UMAP) analysis of the gene expression data. At the backend of the clinALL, we built both shallow machine learning models and a deep neural network using Scikit-learn and PyTorch respectively. FINDINGS: By applying clinALL, 78% of undetermined patients under the current diagnostic protocol were stratified, and ambiguous cases were investigated. Translational insights were discovered, including IKZF1plus status dependent subpopulations of BCR::ABL1 positive patients, and a subpopulation within ETV6::RUNX1 positive patients that has a high relapse frequency. Our best machine learning models, LDA and PASNET-like neural network models, achieve F1 scores above 97% in predicting patients' subgroups. INTERPRETATION: An AI-assisted clinical framework that integrates both genomic and clinical data can take full advantage of the available data, improve point-of-care decision-making and reveal clinically relevant insights promptly. Such a lightweight and easily transferable framework works for both whole transcriptome data as well as the cost-effective targeted RNA-seq, enabling efficient and equitable delivery of personalized medicine in small clinics in developing countries. FUNDING: German Ministry of Education and Research (BMBF), German Research Foundation (DFG) and Foundation for Polish Science.

Biological relevance of alternative splicing in hematologic malignancies.

Alternative splicing (AS) is a strictly regulated process that generates multiple mRNA variants from a single gene, thus contributing to proteome diversity. Transcriptome-wide sequencing studies revealed networks of functionally coordinated splicing events, which produce isoforms with distinct or even opposing functions. To date, several mechanisms of AS are deregulated in leukemic cells, mainly due to mutations in splicing and/or epigenetic regulators and altered expression of splicing factors (SFs). In this review, we discuss aberrant splicing events induced by mutations affecting SFs (SF3B1, U2AF1, SRSR2, and ZRSR2), spliceosome components (PRPF8, LUC7L2, DDX41, and HNRNPH1), and epigenetic modulators (IDH1 and IDH2). Finally, we provide an extensive overview of the biological relevance of aberrant isoforms of genes involved in the regulation of apoptosis (e. g. BCL-X, MCL-1, FAS, and c-FLIP), activation of key cellular signaling pathways (CASP8, MAP3K7, and NOTCH2), and cell metabolism (PKM).

Germline Predisposition in Hematologic Malignancies: Testing, Management, and Implications.

Although numerous barriers for clinical germline cancer predisposition testing exist, the increasing recognition of deleterious germline DNA variants contributing to myeloid malignancy risk is yielding steady improvements in referrals for testing and testing availability. Many germline predisposition alleles are common in populations, and the increasing number of recognized disorders makes inherited myeloid malignancy risk an entity worthy of consideration for all patients regardless of age at diagnosis. Germline testing is facilitated by obtaining DNA from cultured skin fibroblasts or hair bulbs, and cascade testing is easily performed via buccal swab, saliva, or blood. Increasingly as diagnostic criteria and clinical management guidelines include germline myeloid malignancy predisposition, insurance companies recognize the value of testing and provide coverage. Once an individual is recognized to have a deleterious germline variant that confers risk for myeloid malignancies, a personalized cancer surveillance plan can be developed that incorporates screening for other cancer risk outside of the hematopoietic system and/or other organ pathology. The future may also include monitoring the development of clonal hematopoiesis, which is common for many of these cancer risk disorders and/or inclusion of strategies to delay or prevent progression to overt myeloid malignancy. As research continues to identify new myeloid predisposition disorders, we may soon recommend testing for these conditions for all patients diagnosed with a myeloid predisposition condition.

Clonal hematopoiesis and inflammation in the vasculature: CHIVE, a prospective, longitudinal clonal hematopoiesis cohort and biorepository.

ABSTRACT: Clonal hematopoiesis (CH) is an age-associated phenomenon leading to an increased risk of both hematologic malignancy and nonmalignant organ dysfunction. Increasingly available genetic testing has made the incidental discovery of CH clinically common yet evidence-based guidelines and effective management strategies to prevent adverse CH health outcomes are lacking. To address this gap, the prospective CHIVE (clonal hematopoiesis and inflammation in the vasculature) registry and biorepository was created to identify and monitor individuals at risk, support multidisciplinary CH clinics, and refine taxonomy and standards of practice for CH risk mitigation. Data from the first 181 patients enrolled in this prospective registry recapitulate the molecular epidemiology of CH from biobank-scale retrospective studies, with DNMT3A, TET2, ASXL1, and TP53 as the most commonly mutated genes. Blood counts across all hematopoietic lineages trended lower in patients with CH. In addition, patients with CH had higher rates of end organ dysfunction, in particular chronic kidney disease. Among patients with CH, variant allele frequency was independently associated with the presence of cytopenias and progression to hematologic malignancy, whereas other common high-risk CH clone features were not clear. Notably, accumulation of multiple distinct high-risk clone features was also associated with cytopenias and hematologic malignancy progression, supporting a recently published CH risk score. Surprisingly, ∼30% of patients enrolled in CHIVE from CH clinics were adjudicated as not having clonal hematopoiesis of indeterminate potential, highlighting the need for molecular standards and purpose-built assays in this field. Maintenance of this well-annotated cohort and continued expansion of CHIVE to multiple institutions are underway and will be critical to understanding how to thoughtfully care for this patient population.

Non-invasive prenatal test identifies circulating cell-free DNA chromosomal abnormalities derived from clonal hematopoiesis in aggressive hematological malignancies.

Liquid biopsy is a minimally invasive diagnostic tool for identification of tumor-related mutations in circulating cell-free DNA (cfDNA). The aim of this study was to investigate feasibility, sensitivity, and specificity of non-invasive prenatal test (NIPT) for identification of chromosomal abnormalities in cfDNA from a total of 77 consecutive patients with non-Hodgkin B-cell lymphomas, Hodgkin lymphoma (HL), or plasma cell dyscrasia. In this case series, half of patients had at least one alteration, more frequently in chromosome 6 (23.1%), chromosome 9 (20.5%), and chromosomes 3 and 18 (16.7%), with losses of chromosome 6 and gains of chromosome 7 negatively impacting on overall survival (OS), with a 5-year OS of 26.9% and a median OS of 14.6 months, respectively (P = 0.0009 and P = 0.0004). Moreover, B-cell lymphomas had the highest NIPT positivity, especially those with aggressive lymphomas, while patients with plasma cell dyscrasia with extramedullary disease had a higher NIPT positivity compared to conventional cytogenetics analysis and a worse outcome. Therefore, we proposed a NIPT-based liquid biopsy a complementary minimally invasive tool for chromosomal abnormality detection in hematological malignancies. However, prospective studies on larger cohorts are needed to validate clinical utility of NIPT-based liquid biopsy in routinely clinical practice.