Biology subjects

Nguyen, P.

Publications and source records attributed to Nguyen, P..

At least 19 recordsLinked to original sources

bioRxiv2026

Immune Aging is an Independent Risk Factor for Cardiovascular Disease

Cardiovascular disease remains the leading cause of mortality, yet current clinical predictors miss substantial disease-risk. While the immune system contributes to this residual risk, its complexity has hindered broadly applicable, clinically scalable metrics of immune-state. Here, we establish the prognostic relevance of IMM-AGE, a system-level metric of immune-aging, to cardiovascular disease. We learn reference-free, low-dimensional representations of IMM-AGE across cell, protein, and mRNA measurements, enabling high-fidelity quantification across modalities, blood fractions, and platforms, including standard hospital flow cytometers. Among UK-Biobank participants, 56.9% of IMM-AGE variation remained unexplained by routine clinical measures, and across diverse cohorts totaling ~48,000 individuals, elevated IMM-AGE was independently associated with future cardiovascular risk, intervention outcomes, and mortality. Moreover, incorporation of IMM-AGE into the PREVENT 10-year risk equation significantly improved risk stratification. These findings establish immune-aging as an independent biological dimension of cardiovascular disease-risk and support IMM-AGE as a practical tool for precision risk assessment.

immunology↗

bioRxiv2026

Fasting reverses PLN R14del-mediated cardiomyopathy through lysosomal reactivation

Genetic cardiomyopathies consist of a heterogeneous group of myocardial disorders caused by variants that disrupt key regulators of cardiac structure and function. Variants in PLN, encoding phospholamban (PLN), the main inhibitor of the sarco/endoplasmic reticulum Ca{superscript 2}-ATPase 2a (SERCA2a), have been linked to both dilated cardiomyopathy (DCM) and arrhythmogenic cardiomyopathy (ACM). Among these, the PLN Arg14del (R14del) variant is the most prevalent. PLN R14del cardiomyopathy is characterized by the accumulation of large perinuclear PLN aggregates in cardiomyocytes of end-stage heart failure tissue. However, the mechanisms driving PLN aggregate formation and their role in disease progression remain unresolved. Using a humanized plna R14del zebrafish model, left ventricular tissue from end-stage PLN R14del cardiomyopathy patients and pharmacological modeling in wild type (WT) cardiac slices, we demonstrate that previously described PLN aggregates represent accumulated sarcoplasmic reticulum (SR)-derived PLN-containing vesicles that form due to impaired SERCA2a activity and increased cytosolic Ca{superscript 2} levels. Furthermore, these SR-derived vesicles often localize adjacent to lysosomes. Interestingly, Ca2+ dysregulation in plna R14del hearts leads to reduced lysosomal function, resulting in SR-derived vesicle accumulation at the microtubule organizing center (MTOC). This perinuclear accumulation induces microtubule aster formation and subsequent cellular disorganization, including sarcomere misalignment and nuclear deformation. Strikingly, reactivation of lysosomal function through fasting reduces SR-derived vesicle accumulation, restores microtubule integrity, and rescues cellular organization in plna R14del zebrafish hearts. Together, these findings identify impaired lysosomal clearance of SR-derived vesicles and the resulting microtubule disorganization as key pathological mechanisms driving PLN R14del cardiomyopathy. Additionally, our results highlight lysosomal reactivation as a promising potential therapeutic strategy to halt or reverse PLN R14del cardiomyopathy progression. Main findingsO_LIPLN aggregates in PLN R14del cardiomyopathy represent SR-derived vesicles formed due to Ca{superscript 2} dysregulation. C_LIO_LIThese SR-derived vesicles often localize perinuclearly at the microtubule organizing center (MTOC), where they are positioned adjacent to lysosomes. C_LIO_LICa2+ dysregulation leads to lysosomal dysfunction which drives vesicle accumulation responsible for microtubule remodeling and pathological cellular rearrangements. C_LIO_LILysosomal reactivation restores vesicle clearance and rescues cardiomyocyte structure. C_LI

cell biology↗

bioRxiv2026

mRNAbow: A versatile gene expression system for multiplexed fluorescent imaging using optimized in vitro transcribed mRNA

Messenger RNA (mRNA) transfection enables rapid, transient protein expression without nuclear entry, providing a powerful alternative to DNA or viral delivery in post-mitotic and otherwise difficult-to-transfect cells. Although in vitro transcribed (IVT) mRNAs have revolutionized therapeutic applications, their adoption in experimental biology remains limited by challenges in synthesis, variability across cell types, and concerns about cytotoxicity. Here, we define design principles that maximize IVT mRNA performance across diverse cellular and organismal systems. Through systematic comparison of capping strategies and base modifications, including N1-methyl-pseudouridine, 5-methylcytidine, and 5-methoxyuridine, we identify modifications that enhance translation while minimizing activation of cellular stress responses. Optimized transcripts drive robust protein expression within four hours, persist for up to one week, and support multiplexed expression of structurally and functionally distinct proteins in mammalian cells, including cancer cell lines, iPSC-derived systems, primary cells, and organoids, as well as in vivo in zebrafish embryos and in less genetically tractable models such as Danionella cerebrum and sea urchin embryos. To further expand accessibility for community use, we developed mRNAbow, a platform for generating low-toxicity mRNAs encoding organelle-targeted fluorescent proteins and biosensors for multiplex imaging, with corresponding plasmids made publicly available. Together, these advances establish a generalizable framework for IVT mRNA design and expand experimental access to synthetic mRNA technologies for dissecting cellular architecture and dynamics.

cell biology↗

bioRxiv2025

Insights from the lack of an enigmatic trait: monomorphic sperm in evergreen bagworm moths and the evolution of sperm dimorphism

Reproductive traits contain some of the most bizarre and unintuitive innovations seen across the tree of life. Chief among these is the sperm dimorphism of butterflies and moths (Lepidoptera). Males make two types of sperm: traditional fertilizing sperm (eupyrene) and a second, non-fertilizing type (apyrene) that lacks a nucleus entirely. Despite decades of study, the function and evolution of this second sperm type has remained unclear. Here we explore the sperm biology of the evergreen bagworm moth, Thyridopteryx ephemeraeformis (Lepidoptera: Tineoidea: Psychidae), and find no evidence for non-fertilizing sperm in this species. We generate genomic, transcriptomic, and proteomic resources to characterize the apparently monomorphic sperm of this species and compare it to that of other Lepidoptera. The fertilizing sperm of the evergreen bagworm shows key differences from other studied species, especially a lack of proteolytic enzymes used to break down sperm bundles in other species. Combining this and other evidence, we offer new hypotheses for the evolution and function of this enigmatic reproductive trait. Notably, early diverging moths appear to produce far less non-fertilizing sperm in general than later diverging Lepidoptera. We infer that non-fertilizing sperm are not necessary in these taxa, perhaps because less robust packaging of fertilizing sperm enables greater mobility than in later diverging moths.

evolutionary biology↗

bioRxiv2025

SigRescueR: A Pan-System Framework for Noise Correction and Mutational Signature Identification Across Sequencing Platforms

Mutational signatures serve as molecular fingerprints of the biological processes and exposures that shape cancer genomes. However, accurate signal recovery remains challenging due to pervasive background variants, sequencing artifacts, technical noise, and platform-specific biases that obscure true mutagenic patterns, hampering biomarker discovery and mechanistic interpretation. Here we introduce SigRescueR, a rigorous, pan-system, computational framework designed for noise correction and mutational signature identification. SigRescueR applies statistically robust baseline correction to effectively disentangle true mutational signals from confounding noise and artifacts. When applied to extensive datasets spanning experimental models and human cancers, SigRescueR reliably identified canonical mutational signatures associated with environmental mutagens such as colibactin, benzo[a]pyrene, and UV radiation, and chemotherapeutic agents, namely 5-fluorouracil and cisplatin. SigRescueR effectively operated across diverse mutation classes, including single base substitutions, insertions and deletions, and doublet base substitutions, while also integrating strand bias and duplex sequencing data for toxicology applications. SigRescueR offers a unified, high-precision platform that seamlessly integrates cancer genomics, molecular toxicology, and mechanistic studies. It enables precise mapping of mutagenic processes and identification of robust genomic biomarkers of environmental and therapeutic exposures, providing a transformative framework for translational cancer research. Availability and implementationSigRescueR is implemented in R and provided as open-source software on GitHub at https://github.com/ZhivaguiLab/SigRescueR/

genomics↗

bioRxiv2025

Carbohydrate adaptation drives liver-brain axis maturation

Mammalian postnatal life requires adaptation to a carbohydrate-rich diet, yet how metabolic programs are coordinated within and across organs is unclear. Using time-resolved transcriptomic and metabolomic analyses from the neonatal period through adulthood, we show that mouse liver rapidly acquires oxidative and detoxification capacity after weaning. This transition enables the brain to establish energy-sufficient, low-toxicity metabolic environment for neuronal development. This maturation process is marked by progressive activation of the hepatic electron transport chain (ETC), with the mitochondrial RNA endoribonuclease LACTB2 acting as a key regulator. LACTB2 prevents the accumulation of mitochondrial RNAs and sustains expression of mtDNA-encoded ETC subunits, thereby preserving mitochondrial competence for oxidative metabolism. LACTB2 is postnatally induced in hepatocytes, and its loss causes defective glucose utilization, systemic metabolic toxicity, and impaired brain metabolism and myelination, leading to prepubertal lethality, particularly in males. Restoring ETC function through liver-targeted expression of yeast NADH dehydrogenase NDI1, inhibiting the integrated stress response or ammonia scavenging improved survival. Our findings identify LACTB2-dependent hepatic mitochondrial maturation as a central mechanism that aligns carbohydrate adaptation with the liver-brain metabolic coordination to support early-life development.

developmental biology↗

bioRxiv2025

BudFinder: A Masked Auto-Encoder Vision Transformer Framework for Yeast Budding Detection

Yeast replicative lifespan is a crucial part of aging research, yet its quantification remains labor-intensive and time-consuming, particularly when using time-lapse imaging and microfluidics. Manual counting methods for cell division events are prone to bias and inefficiency, while existing automated approaches often require extensive annotated datasets. These limitations hinder the adaptability of such tools across different microfluidic setups. To address these challenges, we propose a versatile image analysis approach that accurately detects yeast cell division events. To reduce the burden of requiring a large cell division annotated dataset, we pretrained a Masked Auto-Encoder on large-scale segmented yeast cell images. This substantially reduced the annotated data needed to train the transformer model for detecting cellular division events. Additionally, the model is trained directly on budding event detection, circumventing reliance on arbitrary heuristics, such as changes in cell area. By leveraging self-supervised pretraining, we reduced the training data requirement to fewer than 50 mother cells ([~]1,000 divisions), representing a >5-fold reduction compared to prior methods while maintaining comparable accuracy. Author SummaryOur work addresses a longstanding challenge in in live-cell time-lapse microscopy analysis, namely, automating cellular division tracking while minimizing the amount of training data required. Traditionally, scientists identify each division event by manually inspecting thousands of time-lapse images, a process that is both tedious and prone to bias. While automated tools exist, they often require large amounts of annotated data to work effectively, limiting their use across different experimental setups. To overcome these barriers, we developed BudFinder, which can recognize and track cell divisions with far less training data. Using yeast replicative aging data as an example, we first trained a model to understand what a yeast cell "looks like", using tens of thousands of segmented yeast cell images entrapped in our custom-built microfluidic device. Then, we taught it to detect budding events directly from time-lapse movies. This approach reduces the need for manual labeling by more than five-fold compared to previous structures in place, while maintaining accuracy comparable to existing methods. By making high-throughput analysis of cellular division more accessible, our work paves the way for faster and more scalable quantification of cellular dynamics.

systems biology↗

bioRxiv2025

Multilayer control of KaiR1D-autoreceptor function by the auxiliary protein Neto

Kainate-type glutamate receptors and their dedicated auxiliary protein Neto function at both pre- and postsynaptic sites to regulate the activity of synaptic networks. However, attributing specific synaptic functions to Neto and/or kainate receptors is challenging. Here we focus on Drosophila KaiR1D receptors, which modulate synaptic transmission at neuromuscular junction, and elucidate the role of Neto in the regulation of autoreceptor activities and neurotransmitter release. We show that Neto- limits the presynaptic accumulation and function of KaiR1D autoreceptors in vivo. Using outside-out patch recordings, we demonstrate that Neto- modulates the KaiR1D gating properties, slowing desensitization and attenuating the block by intracellular polyamines and extracellular toxins. Neto- also promotes the axonal distribution of KaiR1D, but this function is not critical for the KaiR1D-dependent regulation of synaptic transmission. Instead, Neto- increases the charge transfer and likely the KaiR1D-mediated influx of Ca2+ in the presynaptic compartment leading to increased neurotransmitter release. Our data demonstrate that Neto- provides multiple layers of modulation to KaiR1D autoreceptors to ensure proper neurotransmitter release. These findings broaden our view on how auxiliary subunits shape channel gating and subcellular distribution, suggesting that coordinated regulation of receptor function and localization represents an ancestral strategy to safeguard synaptic stability.

neuroscience↗

bioRxiv2025

The Pdgfd-Pdgfrb axis orchestrates tumor-nerve crosstalk in pancreatic cancer

Nerves are an integral component of the tumor microenvironment, contributing to cancer progression, metastasis, morbidity, and mortality. In pancreatic ductal adenocarcinoma (PDAC), worse clinical outcomes are associated with perineural invasion (PNI), a process by which cancer cells surround and invade nerves. Here, we employed whole-transcriptome and single-cell spatial transcriptomics to identify candidate tumor-nerve interactions that promote PNI. We discovered that Pdgfd signaling promotes key features of nerve invasion. Mechanistically, Pdgfd stimulated cancer cell invasiveness, neurite outgrowth, and direct physical engagement with glia. Pharmacological blockade of this axis reduced each of these processes in vitro as well as PNI in vivo. Thus, Pdgfd-Pdgfrb signaling mediates PNI by coordinating multifaceted cancer-neuron-glia interactions and represents a promising therapeutic strategy aimed at disrupting harmful cancer-nerve crosstalk.

cancer biology↗

bioRxiv2025

On the Utility of Virtual Staining for Downstream Applications as it relates to Task Network Capacity

Virtual staining, or in-silico-labeling, has been proposed to computationally generate synthetic fluorescence images from label-free images by use of deep learning-based image-to-image translation networks. In most reported studies, virtually stained images have been assessed only using traditional image quality measures such as structural similarity or signal-to-noise ratio. However, in biomedical imaging, images are typically acquired to facilitate an image-based inference, which we refer to as a downstream biological or clinical task. This study systematically investigates the utility of virtual staining for facilitating clinically relevant downstream tasks (like segmentation or classification) with consideration of the capacity of the deep neural networks employed to perform the tasks. Comprehensive empirical evaluations were conducted using biological datasets, assessing task performance by use of label-free, virtually stained, and ground truth fluorescence images. The results demonstrated that the utility of virtual staining is largely dependent on the ability of the segmentation or classification task network to extract meaningful task-relevant information, which is related to the concept of network capacity. Examples are provided in which virtual staining does not improve, or even degrades, segmentation or classification performance when the capacity of the associated task network is sufficiently large. The results demonstrate that task network capacity should be considered when deciding whether to perform virtual staining.

bioinformatics↗

bioRxiv2025

Targeting Regnase-1 unleashes CAR T cell antitumor activity for osteosarcoma and creates a proinflammatory tumor microenvironment

Negative regulators of T cell function represent promising targets to enhance the intrinsic antitumor activity of CAR T cells against solid tumors. However, the endogenous immune ecosystem in solid tumors often represents an immunosuppressive therapeutic barrier to CAR T cell therapy, and it is currently unknown whether deletion of negative regulators in CAR T cells reshapes the endogenous immune landscape. To address this knowledge gap, we developed CAR T cells targeting B7-H3 in immune-competent osteosarcoma models and evaluated the intrinsic and extrinsic effects of deleting a potent negative regulator called Regnase-1 (Reg-1). Deletion of Reg-1 not only improved the effector function of B7-H3-CAR T cells but also endowed them with the ability to create a proinflammatory landscape characterized by an influx of IFN{gamma}-producing endogenous T cells and NK cells and a reduction of inhibitory myeloid cells, including M2 macrophages. Thus, deleting negative regulators in CAR T cells enforces a non-cell-autonomous state by creating a proinflammatory tumor microenvironment.

immunology↗

bioRxiv2025

Discovery of a tRNA-regulatory transcription factor that suppresses breast cancer metastasis

Transfer RNAs (tRNAs), once viewed as static adaptors in translation, are now recognized as dynamic regulators of gene expression. While recent studies have illuminated roles for tRNA stability, the upstream mechanisms governing tRNA transcription remain poorly understood. To address this gap, we generated the EXpression atlas of tRNA (EXTRNA), a high-resolution tRNA expression dataset spanning 24 cell lines across 9 human tissues. EXTRNA revealed both tissue-type-specific expression programs ("tRNAomes") and unexpected intra-tissue heterogeneity across breast cancer samples. Integrating EXTRNA with computational network analysis and data from other publicly available datasets, we identified Zinc Finger ZZ-Type And EF-Hand Domain Containing 1 (ZZEF1) as the first sequence-specific transcription factor of a particular tRNA. ZZEF1 promoted tRNA-LysUUU transcription by partnering with the ATP-dependent chromatin remodeler Chromodomain Helicase DNA Binding Protein 6 (CHD6), enhancing chromatin accessibility at tRNA-Lys-TTT-3 loci. ZZEF1 deficiency reduced tRNA-LysUUU abundance, decreased the translational efficiency of AAR codon-enriched mRNAs--including the tumor suppressor Serine/Threonine Kinase 3 (STK3)--and promoted metastatic progression in breast cancer in vivo. Together, our findings establish a previously unrecognized mechanism for RNA polymerase III-mediated tRNA transcription and define a regulatory circuit linking chromatin remodeling, codon-specific translation, and tumor suppression. More broadly, this work introduces a framework for dissecting the regulatory logic of the tRNAome and highlights tRNA expression control as a promising avenue for therapeutic intervention.

genomics↗

bioRxiv2025

Evolved microbial diversity enables combinatoric biosensing in complex environments

Whole-cell biosensors (WCBs) offer rapid, cost-effective monitoring of environmental contamination and human disease. Current WCB efforts to optimize detection of single target analytes under laboratory conditions have achieved vastly improved performance, setting the stage for WCB deployment in complex environments. We propose a framework that leverages the cross-specificity of single-target WCBs to quantify multiple targets using supervised machine learning. Specifically, we engineer six sensors for heavy metal contaminants in laboratory E. coli. We then evolve the strain to generate five chassis with improved growth in seawater conditions. We transform the chassis with the sensors, creating a set of 30 variants. The variant dynamic responses are characterized with microfluidics, revealing significant diversity. Leveraging this diversity, we construct a consortium to combinatorically quantify multiple analytes with machine learning, outperforming single-target biosensors in over 90% of our test samples. These results form a generalizable framework that facilitates WCB translation toward settings beyond the laboratory.

bioengineering↗

bioRxiv2025

A multi-modal whole-slide image processing pipeline for quantitative mapping of tissue architecture, histopathology, and tissue microenvironment

Multi-modal, multiscale imaging is crucial for quantitative high-content spatial profiling. We present an integrated image processing pipeline for comprehensive tissue analysis that combines quantitative phase microscopy for tissue architecture mapping, hyper-plex fluorescence imaging for immune microenvironment profiling, and whole-slide histopathology. This approach enables detailed morphological mapping of tissue architecture and cell morphology, while simultaneously linking them to the functional states of individual cells across the entire slide. By analyzing tissue biopsies from patients with ulcerative colitis, we demonstrate the potential of this pipeline for quantitative spatial analysis of molecular markers related to mucosal healing. Open-source and compatible with conventional microscopy systems, this pipeline provides a powerful tool for research and clinical applications through its comprehensive integration of quantitative, high-content, and histological imaging modalities.

bioinformatics↗

bioRxiv2025

SAMHD1 Knockout iPSC model enables high lenti-viral transduction in myeloid cell types

Recent advances in functional genomics tools have ushered in a new era of genetic editing to identify molecular pathways relevant to developmental and disease biology. However, limited model systems are available that adequately mimic cell states and phenotypes associated with human disease pathways. Here, we quantitatively analyzed the founder population bottleneck effect and demonstrated how the population changes from induced pluripotent stem cells (iPSCs) to hematopoietic stem cells and to the final induced macrophage population. We then engineered SAMHD1 knockout (KO) iPSC and characterized the iPSC line with RNA Seq, and induced macrophages from two distinct protocols with functional analysis. We then generated SAMHD1 KO CRISPR-dCAS9 KRAB iPSC through lenti-viral transduction aiming to increase the efficiency of lentiviral mediated gene transfer. We demonstrated increased lenti-viral transduction efficiency in induced macrophage, as well as microglia induced with two distinct protocols. This model allows for efficient gene knock down, as well as large-scale functional genomics screens in mature iPSC-derived macrophages or microglia with applications in innate immunity and chronic inflammatory disease biology. These experiments highlight the broad applicability of this platform for disease-relevant target identification and may improve our ability to run large-scale screens in iPSC-derived myeloid model systems.

cell biology↗

bioRxiv2024

Selective Targeting of a Defined Subpopulation of Corticospinal Neurons using a Novel Klhl14-Cre Mouse Line Enables Molecular and Anatomical Investigations through Development into Maturity

The corticospinal tract (CST) facilitates skilled, precise movements, which necessitates that subcerebral projection neurons (SCPN) establish segmentally specific connectivity with brainstem and spinal circuits. Developmental molecular delineation enables prospective identification of corticospinal neurons (CSN) projecting to thoraco-lumbar spinal segments; however, it remains unclear whether other SCPN subpopulations in developing sensorimotor cortex can be prospectively identified in this manner. Such molecular tools could enable investigations of SCPN circuitry with precision and specificity. During development, Kelch-like 14 (Klhl14) is specifically expressed by a specific SCPN subpopulation, CSNBC-lat, that reside in lateral sensorimotor cortex with axonal projections exclusively to bulbar-cervical targets. In this study, we generated Klhl14-T2A-Cre knock-in mice to investigate SCPN that are Klhl14+ during development into maturity. Using conditional anterograde and retrograde labeling, we find that Klhl14-Cre is specifically expressed by CSNBC-lat only at specific developmental time points. We establish conditional viral labeling in Klhl14-T2A-Cre mice as a new approach to reliably investigate CSNBC-lat axon targeting and confirm that this identifies known molecular regulators of CSN axon targeting. Therefore, Klhl14-T2A-Cre mice can be used as a novel tool for identifying molecular regulators of CST axon guidance in a relatively high-throughput manner in vivo. Finally, we demonstrate that intersectional viral labeling enables precise targeting of only Klhl14-Cre+ CSNBC-lat in the adult central nervous system. Together, our results establish that developmental molecular delineation of SCPN subpopulations can be used to selectively and specifically investigate their development, as well as anatomical and functional organization into maturity. Significance StatementThe cortex connects to brainstem and spinal targets through subcerebral projection neurons (SCPN), which exhibit molecular diversity during development based on their neocortical location and axonal targets. We generated a novel Klhl14-Cre mouse line to utilize this developmental delineation and drive Cre expression in a specific SCPN subpopulation. This developmental specificity enabled investigation of 1) areal locations of Klhl14+ SCPN in mature cortex, 2) their axonal collateralization at maturity, and 3) which genes can control their axon targeting. Using intersectional tools, we can also selectively label these neurons in the adult CNS. Therefore, developmental molecular delineation of SCPN not only provides prospective identification but also enables molecular analysis during development, as well as anatomical and functional investigations in adulthood.

neuroscience↗

bioRxiv2024

Automated cell tracking using 3D nnUnet and Light Sheet Microscopy to quantify regional deformation in zebrafish

Light Sheet Microscopy (LSM) in conjunction with embryonic zebrafish, is rapidly advancing three-dimensional, in vivo characterization of myocardial contractility. Preclinical cardiac deformation imaging is predominantly restricted to a low-order dimensionality image space (2i) or suffers from poor reproducibility. In this regard, LSM has enabled high throughput, non-invasive 4i (3d+time) characterization of dynamic organogenesis within the transparent zebrafish model. More importantly, LSM offers cellular resolution across large imaging Field-of-Views at millisecond camera frame rates, enabling single cell localization for global cardiac deformation analysis. However, manual labeling of cells within multilayered tissue is a time-consuming task and requires substantial expertise. In this study, we applied the 3i nnU-Net with Linear Assignment Problem (LAP) framework for automated segmentation and tracking of myocardial cells. Using binarized labels from the neural network, we quantified myocardial deformation of the zebrafish ventricle across 4-6 days post fertilization (dpf). Our study offers tremendous promise for developing highly scalable and disease-specific biomechanical quantification of myocardial microstructures.

bioengineering↗

bioRxiv2024

lucie: An Improved Python Package for Loading Datasets from the UCI Machine Learning Repository

The University of California-Irvine (UCI) Machine Learning (ML) Repository (UCIMLR) is consistently cited as one of the most popular dataset repositories, hosting hundreds of high-impact datasets. However, a significant portion, including 28.4% of the top 250, cannot be imported via the ucimlrepo package that is provided and recommended by the UCIMLR website. Instead, they are hosted as .zip files, containing nonstandard formats that are difficult to import without additional ad hoc processing. To address this issue, here we present lucie--load University California Irvine examples--a utility that automatically determines the data format and imports many of these previously non-importable datasets, while preserving as much of a tabular data structure as possible. lucie was designed using the top 100 most popular datasets and benchmarked on the next 130, where it resulted in a success rate of 95.4% vs. 73.1% for ucimlrepo. lucie is available as a Python package on PyPI with 98% code coverage.

bioinformatics↗