Cellular Traits Research Articles

Harnessing Gene Editing Technology for Tumor Microenvironment Modulation: An Emerging Anticancer Strategy.

Cancer is a multifaceted disease influenced by both intrinsic cellular traits and extrinsic factors, with the tumor microenvironment (TME) being crucial for cancer progression. To satisfy their high proliferation and aggressiveness, cancer cells always plunder large amounts of nutrients and release various signals to their surroundings, forming a dynamic TME with special metabolic, immune, microbial and physical characteristics. Due to the neglect of interactions between tumor cells and the TME, traditional cancer therapies often struggle with challenges such as drug resistance, low efficacy, and recurrence. Importantly, the development of gene editing technologies, particularly the CRISPR-Cas system, offers promising new strategies for cancer treatment. Combined with nanomaterial strategies, CRISPR-Cas technology exhibits precision, affordability, and user-friendliness with reduced side effects, which holds great promise for profoundly altering the TME at the genetic level, potentially leading to lasting anticancer outcomes. This review will delve into how CRISPR-Cas can be leveraged to manipulate the TME, examining its potential as a transformative anticancer therapy.

Developmentally controlled subcellular remodeling and VND-initiated vacuole-executed PCD module shape xylem-like cells in peat moss

Peat moss (Sphagnum) is a non-vascular higher plant with unique xylem-like hyaline (H) cells that are accompanied by photosynthetic chlorophyllous cells. These cellular structures play crucial roles in water storage and carbon sequestration. However, it is largely unknown how peat moss develops the H cells. This study systematically explored the Sphagnum Developmental Cell Atlas and Lineage and classified leaf cell development into two lineages with six stages (S0-S5) based on changes in key cellular traits, including the formation of spiral secondary cell walls (S4) and the presence of water pores (S5). Cell lineage-specific subcellular remodeling was transcriptionally regulated during leaf development, and vacuole-mediated clearance of organelles and cell death led to mature dead H cells. Interestingly, expression of land plant conserved Vascular-related NAC Domain (VND) genes correlated with H cell formation. Overall, these results suggest that the origination of xylem-like H cells is related to VND, likely through the neofunctionalization of vacuole-mediated cell death to attempt xylem formation in peat moss, suggesting potential uncoupling of xylem and phloem cell origins. This study positions peat moss as a potential model organism for studying integrative evolutionary cell biology.

PP2A activation overcomes leptomeningeal dissemination in Group 3 medulloblastoma

Leptomeningeal dissemination (LMD) is the primary cause of treatment failure in children with Group 3 medulloblastoma (MB). Building on our previous work on protein phosphatase 2A (PP2A) activation in MB, here we present pre-clinical and molecular data on the effects of two novel classes of PP2A activators on disease processes of LMD in Group 3 MB. The PP2A activators employed in this study are ATUX-6156 and ATUX-6954 (diarylmethylcycloamine sulfonylureas), and ATUX-1215 and ATUX-5800 (diarylmethyl-4-aminotetrahydropyran-sulfonamides). Treatment with these compounds led to suppression of the endogenous PP2A inhibitor, cancerous inhibitor of PP2A (CIP2A), enhanced phosphatase activity (10-60%), and reduced MB viability, migration, and invasion, prerequisites for MB cells to access the cerebrospinal fluid, affecting the initiation stage of LMD. PP2A activator treatment of MB cells led to apoptosis mediated via caspase 9/PARP signaling due to decreased phosphorylation of Bad, impeding the dispersal stage of LMD. Cell proliferation and LMD-driving cellular traits and molecules pertinent to the third stage, colonization, were also affected. Treatment with ATUX-1215 or ATUX-5800 prevented LMD in an intraventricular murine model of MB, possibly mediated by disruption of the CCL2-CCR2 axis by altered NF-kB phosphorylation via disrupted AKT signaling. The present investigation offers proof-of-principle data for PP2A-based reactivation therapy for Group 3 MB and provides the first indications that PP2A reactivation may challenge the current paradigm in targeting the 3-stage process of MB LMD. Further investigations of PP2A activators are warranted as these compounds may prove beneficial as therapeutics for MB.

Single-cell phenotypic profiling and backtracing exposes and predicts clinically relevant subpopulations in isogenic Staphylococcus aureus communities

Isogenic bacterial cell populations are phenotypically heterogenous and may include subpopulations of antibiotic tolerant or heteroresistant cells. The reversibility of these phenotypes and lack of biomarkers to differentiate functionally different, but morphologically identical cells is a challenge for research and clinical detection. To overcome this, we present ´Cellular Phenotypic Profiling and backTracing (CPPT)´, a fluorescence-activated cell sorting platform that uses fluorescent probes to visualize and quantify cellular traits and connects this phenotypic profile with a cell´s experimentally determined fate in single cell-derived growth and antibiotic susceptibility analysis. By applying CPPT on Staphylococcus aureus we phenotypically characterized dormant cells, exposed bimodal growth patterns in colony-derived cells and revealed different culturability of single cells on solid compared to liquid media. We demonstrate that a fluorescent vancomycin conjugate marks cellular subpopulations of vancomycin-intermediate S. aureus with increased likelihood to survive antibiotic exposure, showcasing the value of CPPT for discovery of clinically relevant biomarkers.

Variations in the germinal center response revealed by genetically diverse mouse strains.

The humoral response is complex and involves multiple cellular populations and signaling pathways. Bacterial and viral infections, as well as immunization regimens, can trigger this type of response, promoting the formation of microanatomical cellular structures called germinal centers (GCs). GCs formed in secondary lymphoid organs support the differentiation of high-affinity plasma cells and memory B cells. There is growing evidence that the quality of the humoral response is influenced by genetic variants. Using 12 genetically divergent mouse strains, we assessed the impact of genetics on GC cellular traits. At steady state, in the spleen, lymph nodes and Peyer's patches, we quantified GC B cells, plasma cells and follicular helper Tcells. These traits were also quantified in the spleen of mice following immunization with a foreign antigen, namely, sheep red blood cells, in addition to the number and size of GCs. We observed both strain- and organ-specific variations in cell type abundance, as well as for GC number and size. Moreover, we find that some of these traits are highly heritable. Importantly, the results of this study inform on the impact of genetic diversity in shaping the GC response and identify the traits that are the most impacted by genetic background.

Positional differences in the micro- and ultra-structural variations of ray parenchyma cells during the transformation from sapwood to heartwood.

Ray parenchyma cells are involved in the initiation of heartwood formation. The position within a ray influences the timing of ray parenchyma cell differentiation and function; however, there is little information concerning the positional influence on the cellular changes of ray parenchyma cells from sapwood and heartwood. In this study, radial variations in morphology, size, and ultrastructure of ray parenchyma cells were studied by combined transmission electron microscopy and optical microscopy. Results showed that cellular traits of ray parenchyma cells in Populus tomentosa were all affected by both radial position in the secondary xylem and position within a ray. Specifically, radial variations in cellular traits were more evident in isolation cells, which were not adjacent to vessel elements. Both cell length and cell width/length ratio of isolation cells were bigger than contact cells, which contacted adjacent vessel elements via pits. Moreover, the secondary wall thickening and lignification of contact cells developed in the current-year xylem, much earlier than isolation cells. Secondary walls in contact cells were in a polylamellate structure with a protective layer on the inner side. No alteration in the ultrastructure of contact cells occurred in the sapwood-heartwood transition zone, except that most contact cells died. By contrast, in the transition zone, isolation cells still lived. A thin secondary wall began to deposit on the thick primary wall of isolation cells, with two isotropic layers on the inner side of the primary wall and secondary wall respectively being characteristic. Meanwhile, starch grains in isolation cells were depleted, and dark polyphenolic droplets lost their spherical shape and flowed together. Furthermore, the intercellular spaces of isolation cells became densified in the transition zone. Overall, cellular changes suggested that the positional information of ray parenchyma cells appeared to be an important factor in the transformation from sapwood to heartwood. Unlike contact cells, isolation cells were more elongated, specialized in radial transport, had a delayed formation of secondary walls, and were involved in the synthesis of heartwood substances. Our result promotes the elucidation of the involvement of xylem rays in heartwood formation.

Cellular and molecular basis of proximal small intestine disorders.

The proximal part of the small intestine, including duodenum and jejunum, is not only dedicated to nutrient digestion and absorption but is also a highly regulated immune site exposed to environmental factors. Host-protective responses against pathogens and tolerance to food antigens are essential functions in the small intestine. The cellular ecology and molecular pathways to maintain those functions are complex. Maladaptation is highlighted by common immune-mediated diseases such as coeliac disease, environmental enteric dysfunction or duodenal Crohn's disease. An expanding spectrum of more than 100 rare monogenic disorders inform on causative molecular mechanisms of nutrient absorption, epithelial homeostasis and barrier function, as well as inflammatory immune responses and immune regulation. Here, after summarizing the architectural and cellular traits that underlie the functions of the proximal intestine, we discuss how the integration of tissue immunopathology and molecular mechanisms can contributetowardsour understanding of disease and guide diagnosis. We propose an integrated mechanism-based taxonomy and discuss the latest experimental approaches to gain new mechanistic insight into these disorders with large disease burden worldwide as well as implications for therapeutic interventions.

Non-linear transcriptional responses to gradual modulation of transcription factor dosage.

Genomic loci associated with common traits and diseases are typically non-coding and likely impact gene expression, sometimes coinciding with rare loss-of-function variants in the target gene. However, our understanding of how gradual changes in gene dosage affect molecular, cellular, and organismal traits is currently limited. To address this gap, we induced gradual changes in gene expression of four genes using CRISPR activation and inactivation. Downstream transcriptional consequences of dosage modulation of three master trans-regulators associated with blood cell traits (GFI1B, NFE2, and MYB) were examined using targeted single-cell multimodal sequencing. We showed that guide tiling around the TSS is the most effective way to modulate cis gene expression across a wide range of fold-changes, with further effects from chromatin accessibility and histone marks that differ between the inhibition and activation systems. Our single-cell data allowed us to precisely detect subtle to large gene expression changes in dozens of trans genes, revealing that many responses to dosage changes of these three TFs are non-linear, including non-monotonic behaviours, even when constraining the fold-changes of the master regulators to a copy number gain or loss. We found that the dosage properties are linked to gene constraint and that some of these non-linear responses are enriched for disease and GWAS genes. Overall, our study provides a straightforward and scalable method to precisely modulate gene expression and gain insights into its downstream consequences at high resolution.

TDP-43 dysfunction leads to bioenergetic failure and lipid metabolic rewiring in human cells

The dysfunction of TAR DNA-binding protein 43 (TDP-43) is implicated in various neurodegenerative diseases, though the specific contributions of its toxic gain-of-function versus loss-of-function effects remain unclear. This study investigates the impact of TARDBP loss on cellular metabolism and viability using human-induced pluripotent stem cell-derived motor neurons and HeLa cells. TARDBP silencing led to reduced metabolic activity and cell growth, accompanied by neurite degeneration and decreased oxygen consumption rates in both cell types. Notably, TARDBP depletion induced a metabolic shift, impairing ATP production, increasing metabolic inflexibility, and elevating free radical production, indicating a critical role for TDP-43 in maintaining cellular bioenergetics. Furthermore, TARDBP loss triggered non-apoptotic cell death, increased ACSL4 expression, and reprogrammed lipid metabolism towards lipid droplet accumulation, while paradoxically enhancing resilience to ferroptosis inducers. Overall, our findings highlight those essential cellular traits such as ATP production, metabolic activity, oxygen consumption, and cell survival are highly dependent on TARDBP function.

Disentangling cell-intrinsic and extrinsic factors underlying evolution.

A key goal of developmental biology is to determine the extent to which cells and organs develop autonomously, as opposed to requiring interactions with other cells or environmental factors. Chimeras have played a foundational role in this by enabling qualitative classification of cell-intrinsically vs. extrinsically driven processes. Here, we extend this framework to precisely decompose evolutionary divergence in any quantitative trait into cell-intrinsic, extrinsic, and intrinsic-extrinsic interaction components. Applying this framework to thousands of gene expression levels in reciprocal rat-mouse chimeras, we found that the majority of their divergence is attributable to cell-intrinsic factors, though extrinsic factors also play an integral role. For example, a rat-like extracellular environment extrinsically up-regulates the expression of a key transcriptional regulator of the endoplasmic reticulum (ER) stress response in some but not all cell types, which in turn strongly predicts extrinsic up-regulation of its target genes and of the ER stress response pathway as a whole. This effect is also seen at the protein level, suggesting propagation through multiple regulatory levels. Applying our framework to a cellular trait, neuronal differentiation, revealed a complex interaction of intrinsic and extrinsic factors. Finally, we show that imprinted genes are dramatically mis-expressed in species-mismatched environments, suggesting that mismatch between rapidly evolving intrinsic and extrinsic mechanisms controlling gene imprinting may contribute to barriers to interspecies chimerism. Overall, our conceptual framework opens new avenues to investigate the mechanistic basis of developmental processes and evolutionary divergence across myriad quantitative traits in any multicellular organism.

CRISPR/Cas9 protocols for disrupting gene function in the non-vertebrate chordate Ciona.

The evolutionary origins of chordates and their diversification into the three major subphyla of tunicates, vertebrates, and cephalochordates pose myriad questions about the genetic and developmental mechanisms underlying this radiation. Studies in non-vertebrate chordates have refined our model of what the ancestral chordate may have looked like, and have revealed the pre-vertebrate origins of key cellular and developmental traits. Work in the major tunicate laboratory model Ciona has benefitted greatly from the emergence of CRISPR/Cas9 techniques for targeted gene disruption. Here we review some of the important findings made possible by CRISPR in Ciona, and present our latest protocols and recommended practices for plasmid-based, tissue-specific CRISPR/Cas9-mediated mutagenesis.

Senescence and senolysis in cancer: The latest findings.

Aging is a life phenomenon that occurs in most living organisms and is a major risk factor for many diseases, including cancer. Cellular senescence is a cellular trait induced by various genomic and epigenetic stresses. Senescent cells are characterized by irreversible cell growth arrest and excessive secretion of inflammatory cytokines (senescence-associated secretory phenotypes, SASP). Chronic tissue microinflammation induced by SASP contributes to the pathogenesis of a variety of age-related diseases, including cancer. Senolysis is a promising new strategy to selectively eliminate senescent cells in order to suppress chronic inflammation, suggesting its potential use as an anticancer therapy. This review summarizes recent findings on the molecular basis of senescence in cancer cells and senolysis.

Single-cell signatures identify microenvironment factors in tumors associated with patient outcomes

The cellular components of tumors and their microenvironment play pivotal roles in tumor progression, patient survival, and the response to cancer treatments. Unveiling a comprehensive cellular profile within bulk tumors via single-cell RNA sequencing (scRNA-seq) data is crucial, as it unveils intrinsic tumor cellular traits that elude identification through conventional cancer subtyping methods. Our contribution, scBeacon, is a tool that derives cell-type signatures by integrating and clustering multiple scRNA-seq datasets to extract signatures for deconvolving unrelated tumor datasets on bulk samples. Through the employment of scBeacon on the The Cancer Genome Atlas (TCGA) cohort, we find cellular and molecular attributes within specific tumor categories, many with patient outcome relevance. We developed a tumor cell-type map to visually depict the relationships among TCGA samples based on the cell-type inferences.

Shark genome size evolution and its relationship with cellular, life-history, ecological, and diversity traits.

Among vertebrates, sharks exhibit both large and heterogeneous genome sizes ranging from 2.86 to 17.05pg. Aiming for a better understanding of the patterns and causalities of shark genome size evolution, we applied phylogenetic comparative methods to published genome-size estimates for 71 species representing the main phylogenetic lineages, life-histories and ecological traits. The sixfold range of genome size variation was strongly traceable throughout the phylogeny, with a major expansion preceding shark diversification during the late Paleozoic and an ancestral state (6.33pg) close to the present-day average (6.72pg). Subsequent deviations from this average occurred at higher rates in squalomorph than in galeomorph sharks and were unconnected to evolutionary changes in the karyotype architecture, which were dominated by descending disploidy events. Genome size was positively correlated with cell and nucleus sizes and negatively with metabolic rate. The metabolic constraints on increasing genome size also manifested at higher phenotypic scales, with large genomes associated with slow lifestyles and purely marine waters. Moreover, large genome sizes were also linked to non-placental reproductive modes, which may entail metabolically less demanding embryological developments. Contrary to ray-finned fishes, large genome size was associated neither with the taxonomic diversity of affected clades nor with low genetic diversity.

Early dynamic changes to monocytes following major surgery are associated with subsequent infections.

Post-operative infections are a common cause of morbidity following major surgery. Little is understood about how major surgery perturbs immune function leading to heightened risk of subsequent infection. Through analysis of paired blood samples obtained immediately before and 24 h following surgery, we evaluated changes in circulating immune cell phenotype and function across the first 24 h, to identify early immune changes associated with subsequent infection. We conducted a prospective observational study of adult patients undergoing major elective gastrointestinal, gynecological, or maxillofacial surgery requiring planned admission to the post-anesthetic care unit. Patients were followed up to hospital discharge or death. Outcome data collected included mortality, length of stay, unplanned intensive care unit admission, and post-operative infections (using the standardized endpoints in perioperative medicine-core outcome measures for perioperative and anesthetic care criteria). Peripheral blood mononuclear cells were isolated prior to and 24 h following surgery from which cellular immune traits including activation and functional status were assessed by multi-parameter flow cytometry and serum immune analytes compared by enzyme-linked immunosorbent assay (ELISA). Forty-eight patients were recruited, 26 (54%) of whom developed a post-operative infection. We observed reduced baseline pre- and post-operative monocyte CXCR4 and CD80 expression (chemokine receptors and co-stimulation markers, respectively) in patients who subsequently developed an infection as well as a profound and selective post-operative increase in CD4+ lymphocyte IL-7 receptor expression in the infection group only. Higher post-operative monocyte count was significantly associated with the development of post-operative infection (false discovery rate < 1%; adjusted p-value = 0.001) with an area under the receiver operating characteristic curve of 0.84 (p < 0.0001). Lower monocyte chemotaxis markers, higher post-operative circulating monocyte counts, and reduced co-stimulatory signals are associated with subsequent post-operative infections. Identifying the underlying mechanisms and therapeutics to reverse defects in immune cell function requires further exploration.

Nature as blueprint: Global phenotype engineering of CHO production cells based on a multi-omics comparison with plasma cells

Especially for the production of artificial, difficult to express molecules a further development of the CHO production cell line is required to keep pace with the continuously increasing demands. However, the identification of novel targets for cell line engineering to improve CHO cells is a time and cost intensive process. Since plasma cells are evolutionary optimized for a high antibody expression in mammals, we performed a comprehensive multi-omics comparison between CHO and plasma cells to exploit optimized cellular production traits. Comparing the transcriptome, proteome, miRNome, surfaceome and secretome of both cell lines identified key differences including 392 potential overexpression targets for CHO cell engineering categorized in 15 functional classes like transcription factors, protein processing or secretory pathway. In addition, 3 protein classes including 209 potential knock-down/out targets for CHO engineering were determined likely to affect aggregation or proteolysis. For production phenotype engineering, several of these novel targets were successfully applied to transient and transposase mediated overexpression or knock-down strategies to efficiently improve productivity of CHO cells. Thus, substantial improvement of CHO productivity was achieved by taking nature as a blueprint for cell line engineering.

The soil microbiome modulates the sorghum root metabolome and cellular traits with a concomitant reduction of Striga infection

Sorghum bicolor is among the most important cereals globally and a staple crop for smallholder farmers in sub-Saharan Africa. Approximately 20% of sorghum yield is lost annually in Africa due to infestation with the root parasitic weed Striga hermonthica. Existing Striga management strategies are not singularly effective and integrated approaches are needed. Here, we demonstrate the functional potential of the soil microbiome to suppress Striga infection in sorghum. We associate this suppression with microbiome-mediated induction of root endodermal suberization and aerenchyma formation and with depletion of haustorium-inducing factors, compounds required for the initial stages of Striga infection. We further identify specific bacterial taxa that trigger the observed Striga-suppressive traits. Collectively, our study describes the importance of the soil microbiome in the early stages of root infection by Striga and pinpoints mechanisms of Striga suppression. These findings open avenues to broaden the effectiveness of integrated Striga management practices.

Abstract 3534: GeneLLM: Unveiling gene functions through literature-driven transformer embeddings

Abstract INTRODUCTION: Our understanding of gene properties has advanced through representation learning such as Alpha fold. Representation learning involves encoding the relationships between genes by embedding them into a numerical space. These embeddings, which capture complex genetic interactions and characteristics, can then be leveraged by machine learning models to predict various gene properties. Current embeddings derive from transcriptome or sequence data. Over the past 150 years, numerous experimental assays have uncovered gene functions and interactions- comprehensive knowledge documented in the literature but not always evident in transcriptome or sequence data. It has been posited that leveraging this knowledge to create gene embeddings; however, could result in machine learning models biased towards well-studied genes. METHODS AND RESULTS: We tested this hypothesis by developing a novel knowledge-embedding framework, GeneLLM. During training, GeneLLM learns to comprehend summaries of every gene- a compressed form of published knowledge- using Large Language Models (LLMs), fine-tuned for downstream tasks mapping cellular properties and biochemical processes. Despite the expected bias towards well-known genes, GeneLLM surprisingly showed high predictive power for an array of gene properties. Compared to baseline models, GeneLLM boosted an increase in performance of 20.3% correlation in gene conservation across species, 8.6% and 57.2% prediction accuracy in subcellular localization and gene ontology respectively. GeneLLM also showed competitive results on solubility prediction with 0.91 accuracy and a correlation of 0.71 for tissue-specific expression levels for 1001 cell lines. We also showed that the bias toward well-known genes could be mitigated by combining GeneLLM representation with transcriptome or sequence-based embedding. The combined embeddings exhibited superior performance to their individual components which suggests that GeneLLM extracts views complementary to existing embedding methods. CONCLUSION: The GeneLLM framework demonstrates the ability of LLMs to extract information from the rich knowledge available about the nexus of genes and their cellular traits. It also illustrates how bias in knowledge representation is complementary to other transcriptome and sequence-based information. This ability of GeneLLM to advance our understanding of genes, their roles in cellular processes, and their impact on oncogenesis, as well as in response and resistance mechanisms, highlights its potential in cancer research. Citation Format: Ala Jararweh, Kushal Virupakshappa, Oladimeji S. Macaulay, Aaron Segura, Olufunmilola M. Oyebamiji, Yue Hu, Avinash D. Sahu. GeneLLM: Unveiling gene functions through literature-driven transformer embeddings [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3534.

Effects of ammonia on the cellular, physiological, biochemical and genetic traits of Indian major carp (Labeo rohita) fry in artisanal Bangladeshi aquaculture

AbstractThe major carp Rohu (Labeo rohita) is a prime freshwater aquaculture species across the Indian subcontinent that faces various production‐related issues associated with water quality parameters. The present study examined the effects of three different doses of NH3 (T1 = 1 mg/L, T2 = 2 mg/L and T3 = 3 mg/L) on cellular (gill ultrastructure), physiological (growth and oxygen consumption rate), biochemical (blood cell counts, blood cortisol and glucose levels) and genetic (expression of five genes involved in growth, immunity and metabolism) traits of Rohu. The experimental ammonia dose significantly affected the tested biological parameters (p &lt; 0.05), causing moderate‐to‐severe gill tissue damage. In general, compared with those in the control group, 16%–25% slower growth, 12%–30% lower survival and 15%–56% higher O2 consumption were observed for the treatment groups. Blood glucose and cortisol levels increased with increasing ammonia levels, but blood cell counts decreased. The five selected candidate genes showed a differential expression pattern in response to the ammonia dose, with higher expression in the control group and lower expression in the treatment groups. The results indicate that different concentrations of ammonia impose stress on different orders of magnitude in the experimental fishes. Therefore, it can be inferred that the presence of ammonia in aquatic/farming environments can adversely affect production performance; the severity of damage during production depends on the concentration of ammonia. Therefore, maintaining no or minimum ammonia levels in farming environments is urgently needed for sustainable aquaculture production of Rohu.

Comparing Deep Learning Performance for Chronic Lymphocytic Leukaemia Cell Segmentation in Brightfield Microscopy Images.

This article focuses on the detection of cells in low-contrast brightfield microscopy images; in our case, it is chronic lymphocytic leukaemia cells. The automatic detection of cells from brightfield time-lapse microscopic images brings new opportunities in cell morphology and migration studies; to achieve the desired results, it is advisable to use state-of-the-art image segmentation methods that not only detect the cell but also detect its boundaries with the highest possible accuracy, thus defining its shape and dimensions. We compared eight state-of-the-art neural network architectures with different backbone encoders for image data segmentation, namely U-net, U-net++, the Pyramid Attention Network, the Multi-Attention Network, LinkNet, the Feature Pyramid Network, DeepLabV3, and DeepLabV3+. The training process involved training each of these networks for 1000 epochs using the PyTorch and PyTorch Lightning libraries. For instance segmentation, the watershed algorithm and three-class image semantic segmentation were used. We also used StarDist, a deep learning-based tool for object detection with star-convex shapes. The optimal combination for semantic segmentation was the U-net++ architecture with a ResNeSt-269 background with a data set intersection over a union score of 0.8902. For the cell characteristics examined (area, circularity, solidity, perimeter, radius, and shape index), the difference in mean value using different chronic lymphocytic leukaemia cell segmentation approaches appeared to be statistically significant (Mann-Whitney U test, P < .0001). We found that overall, the algorithms demonstrate equal agreement with ground truth, but with the comparison, it can be seen that the different approaches prefer different morphological features of the cells. Consequently, choosing the most suitable method for instance-based cell segmentation depends on the particular application, namely, the specific cellular traits being investigated.