Study of gene expressions' correlation structures in subgroups of Chronic Lymphocytic Leukemia Patients

Hematologic cancer diagnosis and classification using machine and deep learning: State-of-the-art techniques and emerging research directives

Hematology is the study of diagnosis and treatment options for blood diseases, including cancer. Cancer is considered one of the deadliest diseases across all age categories. Diagnosing such a deadly disease at the initial stage is essential to cure the disease. Hematologists and pathologists rely on microscopic evaluation of blood or bone marrow smear images to diagnose blood-related ailments. The abundance of overlapping cells, cells of varying densities among platelets, non-illumination levels, and the amount of red and white blood cells make it more difficult to diagnose illness using blood cell images. Pathologists are required to put more effort into the traditional, time-consuming system. Nowadays, it becomes possible with machine learning and deep learning techniques, to automate the diagnostic processes, categorize microscopic blood cells, and improve the accuracy of the procedure and its speed as the models developed using these methods may guide an assisting tool. In this article, we have acquired, analyzed, scrutinized, and finally selected around 57 research papers from various machine learning and deep learning methodologies that have been employed in the diagnosis of leukemia and its classification over the past 20 years, which have been published between the years 2003 and 2023 by PubMed, IEEE, Science Direct, Google Scholar and other pertinent sources. Our primary emphasis is on evaluating the advantages and limitations of analogous research endeavors to provide a concise and valuable research directive that can be of significant utility to fellow researchers in the field.

HELQ and EGR3 expression correlate with IGHV mutation status and prognosis in chronic lymphocytic leukemia

Background

IGHV mutation status is a crucial prognostic biomarker for CLL. In the present study, we investigated the transcriptomic signatures associating with IGHV mutation status and CLL prognosis.

Methods

The co-expression modules and hub genes correlating with IGHV status, were identified using the GSE28654, by ‘WGCNA’ package and R software (version 4.0.2). The over-representation analysis was performed to reveal enriched cell pathways for genes of correlating modules. Then 9 external cohorts were used to validate the correlation of hub genes expression with IGHV status or clinical features (treatment response, transformation to Richter syndrome, etc.). Moreover, to elucidate the significance of hub genes on disease course and prognosis of CLL patients, the Kaplan–Meier analysis for the OS and TTFT of were performed between subgroups dichotomized by the median expression value of individual hub genes.

Results

2 co-expression modules and 9 hub genes ((FCRL1/FCRL2/HELQ/EGR3LPL/LDOC1/ZNF667/SOWAHC/SEPTIN10) correlating with IGHV status were identified by WGCNA, and validated by external datasets. The modules were found to be enriched in NF-kappaB, HIF-1 and other important pathways, involving cell proliferation and apoptosis. The expression of hub genes was revealed to be significantly different, not only between CLL and normal B cell, but also between various types of lymphoid neoplasms. HELQ expression was found to be related with response of immunochemotherapy treatment significantly (p = 0.0413), while HELQ and ZNF667 were expressed differently between stable CLL and Richter syndrome patients (p < 0.0001 and p = 0.0278, respectively). By survival analysis of subgroups, EGR3 expression was indicated to be significantly associated with TTFT by 2 independent cohorts (GSE39671, p = 0.0311; GSE22762, p = 0.0135). While the expression of HELQ and EGR3 was found to be associated with OS (p = 0.0291 and 0.0114 respectively).The Kras, Hedgehog and IL6-JAK-STAT3 pathways were found to be associating with the expression of hub genes, resulting from GSEA.

Conclusions

The expression of HELQ and EGR3 were correlated with IGHV mutation status in CLL patients. Additionally, the expression of HELQ/EGR3 were prognostic markers for CLL associating with targetable cell signaling pathways.