Data Brief. 2024 Dec 10;58:111216. doi: 10.1016/j.dib.2024.111216. eCollection 2025 Feb.

ABSTRACT

Epipremnum aureum, sometimes known as the Money Plant, is a popular houseplant known for its hearts-shaped leaves and durability. Commonly referred to as Golden Pothos or Devil's Ivy, it is also appreciated for its ornamental value and air cleaning ability. They say that these plants are attractive to many people owing to their tolerance to several conditions and easy care, therefore, it is no surprise that they are found in many households and workplaces. Money Plants are hardy, but like any other plant they can also be infected by various diseases, which may render them less attractive, or even unattractive. This work encompasses bacterial wilt, manganese poisoning aspects and together with a healthy leaves aspect presents all prevalent masses and offer a comprehensive image of diseases. A dataset of 224 × 224 pixel images is utilized to accomplish this work with the intention to further enhance support in Ornamental Horticulture practices and diagnose more accurately. This work not only contributes ideas and approaches in understanding the field of plants pathology but also stresses on the fact how image processing can be beneficial in looking after plants. The dataset serves as a solid foundation for deep learning approaches into Ornamental Agriculture and provides useful insights for researchers studying the cultivation of money plants.

PMID:39811518 | PMC:PMC11729688 | DOI:10.1016/j.dib.2024.111216

Biol Methods Protoc. 2025 Jan 6;10(1):bpae097. doi: 10.1093/biomethods/bpae097. eCollection 2025.

ABSTRACT

A mixture-of-experts (MoE) approach has been developed to mitigate the poor out-of-distribution (OOD) generalization of deep learning (DL) models for single-sequence-based prediction of RNA secondary structure. The main idea behind this approach is to use DL models for in-distribution (ID) test sequences to leverage their superior ID performances, while relying on physics-based models for OOD sequences to ensure robust predictions. One key ingredient of the pipeline, named MoEFold2D, is automated ID/OOD detection via consensus analysis of an ensemble of DL model predictions without requiring access to training data during inference. Specifically, motivated by the clustered distribution of known RNA structures, a collection of distinct DL models is trained by iteratively leaving one cluster out. Each DL model hence serves as an expert on all but one cluster in the training data. Consequently, for an ID sequence, all but one DL model makes accurate predictions consistent with one another, while an OOD sequence yields highly inconsistent predictions among all DL models. Through consensus analysis of DL predictions, test sequences are categorized as ID or OOD. ID sequences are subsequently predicted by averaging the DL models in consensus, and OOD sequences are predicted using physics-based models. Instead of remediating generalization gaps with alternative approaches such as transfer learning and sequence alignment, MoEFold2D circumvents unpredictable ID-OOD gaps and combines the strengths of DL and physics-based models to achieve accurate ID and robust OOD predictions.

PMID:39811444 | PMC:PMC11729747 | DOI:10.1093/biomethods/bpae097

Heliyon. 2024 Dec 16;11(1):e40855. doi: 10.1016/j.heliyon.2024.e40855. eCollection 2025 Jan 15.

ABSTRACT

INTRODUCTION: The COVID-19 pandemic has created an urgent demand for research, which has spurred the development of enhanced biosafety protocols in biosafety level (BSL)-3 laboratories to safeguard against the risks associated with handling highly contagious pathogens. Laboratory management failures can pose significant hazards.

METHODS: An external system captured images of personnel entering a laboratory, which were then analyzed by an AI-based system to verify their compliance with personal protective equipment (PPE) regulations, thereby introducing an additional layer of protection. A deep learning model was trained to detect the presence of essential PPE items, such as clothing, masks, hoods, double-layer gloves, shoe covers, and respirators, ensuring adherence to World Health Organization (WHO) standards. The internal laboratory management system used a deep learning model to delineate alert zones and monitor compliance with the imposed safety protocols.

RESULTS: The external detection system was trained on a dataset consisting of 4112 images divided into 15 PPE compliance classes. The model achieved an accuracy of 97.52 % and a recall of 97.03 %. The identification results were presented in real time via a visual interface and simultaneously stored on the administrator's dashboard for future reference. We trained the internal management system on 3347 images, achieving 90 % accuracy and 85 % recall. The results were transmitted in JSON format to the internal monitoring system, which triggered alerts in response to violations of safe practices or alert zones. Real-time notifications were sent to the administrators when the safety thresholds were met.

CONCLUSION: The BSL-3 laboratory monitoring system significantly reduces the risk of exposure to pathogens for personnel during laboratory operations. By ensuring the correct use of PPE and enhancing adherence to the imposed safety protocols, this system contributes to maintaining the integrity of BSL-3 facilities and mitigates the risk of personnel becoming infection vectors.

PMID:39811271 | PMC:PMC11730239 | DOI:10.1016/j.heliyon.2024.e40855

Ophthalmol Sci. 2024 Nov 12;5(2):100653. doi: 10.1016/j.xops.2024.100653. eCollection 2025 Mar-Apr.

ABSTRACT

PURPOSE: The diagnosis of fungal keratitis using potassium hydroxide (KOH) smears of corneal scrapings enables initiation of the correct antimicrobial therapy at the point-of-care but requires time-consuming manual examination and expertise. This study evaluates the efficacy of a deep learning framework, dual stream multiple instance learning (DSMIL), in automating the analysis of whole slide imaging (WSI) of KOH smears for rapid and accurate detection of fungal infections.

DESIGN: Retrospective observational study.

PARTICIPANTS: Corneal scrapings from 568 patients with suspected fungal keratitis; 51% contained filamentous fungi according to human expert interpretation.

METHODS: Dual stream multiple instance learning was employed to analyze WSI of KOH smears. Due to the extensive size of these images, often exceeding 100 000 pixels, conventional computer vision methods (e.g., convolutional neural networks) are not feasible. Dual stream multiple instance learning segments the WSI into patches for analysis, extracting relevant features from each patch and aggregating these to make a comprehensive slide-level diagnosis while generating heat maps to visualize areas contributing most to the prediction. Fivefold cross-validation was used for training and validation, with a hold-out test set comprising 15% of the total samples.

MAIN OUTCOME MEASURES: Accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), F1 score, positive predictive value (PPV), and negative predictive value (NPV) in distinguishing fungal from nonfungal slides.

RESULTS: Dual stream multiple instance learning demonstrated an overall AUC of 0.88 with an accuracy of 79% and an F1 score of 0.79 in distinguishing fungal from nonfungal slides, with sensitivity of 85%, specificity of 71%, PPV of 80%, and NPV of 79%. For "consensus cases," where 2 human graders agreed on the slide interpretation, the model achieved an accuracy of 85% and an F1 score of 0.85. For "discrepant cases," the accuracy was 71% with an F1 score of 0.71. The generated heatmaps highlighted regions corresponding to fungal elements. Code and models are open-sourced and available at https://github.com/Redd-Cornea-AI/KOH-Smear-DSMIL.

CONCLUSIONS: The DSMIL framework shows significant promise in automating interpretation of KOH smears. Its capability to handle large, high-resolution WSI data and accurately detect fungal infections, while providing visual explanations through heatmaps, could enhance the scalability of KOH smear interpretation, ultimately reducing the global burden of blindness from infectious keratitis.

FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

PMID:39811263 | PMC:PMC11731208 | DOI:10.1016/j.xops.2024.100653

iScience. 2024 Dec 10;28(1):111569. doi: 10.1016/j.isci.2024.111569. eCollection 2025 Jan 17.

ABSTRACT

Successful pancreatic ductal adenocarcinoma (PDAC) immunotherapy requires therapeutic combinations that induce quality T cells. Tumor microenvironment (TME) analysis following therapeutic interventions can identify response mechanisms, informing design of effective combinations. We provide a reference single-cell dataset from tumor-infiltrating leukocytes (TILs) from a human neoadjuvant clinical trial comparing the granulocyte-macrophage colony-stimulating factor (GM-CSF)-secreting allogeneic PDAC vaccine GVAX alone, in combination with anti-PD1 or with both anti-PD1 and CD137 agonist. Treatment with GVAX and anti-PD-1 led to increased CD8+ T cell activation and expression of cytoskeletal and extracellular matrix (ECM)-interacting components. Addition of CD137 agonist increased abundance of clonally expanded CD8+ T cells and increased immunosuppressive TREM2 signaling in tumor associated macrophages (TAMs), identified by comparison of ligand-receptor networks, corresponding to changes in metabolism and ECM interactions. These findings associate therapy with GVAX, anti-PD1, and CD137 agonist with enhanced CD8+ T cell function while inducing alternative immunosuppressive pathways in patients with PDAC.

PMID:39811671 | PMC:PMC11730579 | DOI:10.1016/j.isci.2024.111569

iScience. 2024 Dec 9;28(1):111521. doi: 10.1016/j.isci.2024.111521. eCollection 2025 Jan 17.

ABSTRACT

Cellular fitness depends on multiple phenotypes that must be balanced during evolutionary adaptation. For instance, coordinating growth and motility is critical for microbial colonization and cancer invasiveness. In bacteria, these phenotypes are controlled by local regulators that target single operons, as well as by global regulators that impact hundreds of genes. However, how the different levels of regulation interact during evolution is unclear. Here, we measured in Escherichia coli how CRISPR-mediated knockdowns of global and local transcription factors impact growth and motility in three environments. We found that local regulators mostly modulate motility, whereas global regulators jointly modulate growth and motility. Simulated evolutionary trajectories indicate that local regulators are typically altered first to improve motility before global regulators adjust growth and motility following their trade-off. These findings highlight the role of pleiotropic regulators in the adaptation of multiple phenotypes.

PMID:39811663 | PMC:PMC11731283 | DOI:10.1016/j.isci.2024.111521

iScience. 2024 Dec 9;28(1):111549. doi: 10.1016/j.isci.2024.111549. eCollection 2025 Jan 17.

ABSTRACT

Glial-vascular interactions are critical for the formation and maintenance of brain blood vessels and the blood-brain barrier (BBB) in mammals, but their role in the zebrafish BBB remains unclear. Using three glial gene promoters-gfap, glast, and glastini (a truncated glast)-we explored glial-vascular development in zebrafish. Sparse labeling showed fewer glial-vascular interactions at early stages, with glial coverage and contact area increasing with age. Stable transgenic lines for glast and glastini revealed similar developmental increases, starting at ∼30% coverage at 3 days post-fertilization (dpf) and peaking at ∼60% by 10 dpf, and consistently higher glial coverage in the forebrain and midbrain than in the hindbrain. Electron microscopy analyses showed similar progressive increases in glial-vascular interactions, with maximal coverage of ∼70% in adults-significantly lower than the ∼100% seen in mammals. These findings define the temporal and regional maturation of glial-vascular interactions in zebrafish and highlight differences from mammalian systems.

PMID:39811646 | PMC:PMC11731618 | DOI:10.1016/j.isci.2024.111549

ERJ Open Res. 2025 Jan 13;11(1):00486-2024. doi: 10.1183/23120541.00486-2024. eCollection 2025 Jan.

ABSTRACT

BACKGROUND: Pulmonary arterial hypertension (PAH) is a deadly disease without effective non-invasive diagnostic and prognostic testing. It remains unclear whether vasodilators reverse inflammatory activation, a part of PAH pathogenesis. Single-cell profiling of inflammatory cells in blood could clarify these PAH mechanisms.

METHODS: We evaluated a University of Pittsburgh Medical Center cohort consisting of idiopathic PAH (iPAH) and systemic sclerosis-associated PAH (sscPAH) patients and non-PAH controls. We performed single-cell RNA sequencing of peripheral blood mononuclear cells (PBMCs) from controls (n=3) and from PAH patients (iPAH and sscPAH) naïve to treatment (n=4), PAH patients 3 months after phosphodiesterase-5 inhibitor (PDE5i) treatment (n=7) and PAH patients 3 months after PDE5i+macitentan treatment (n=6). We compared the transcriptomes of five PBMC subtypes from iPAH and sscPAH to observe their serial responses to treatments. Furthermore, we utilised network analysis to illuminate the altered connectivity of biological networks in this complex disease.

RESULTS: We defined differential gene expression and perturbed network connectivity in PBMCs of PAH patients following treatment with PDE5i or PDE5i+macitentan. Importantly, we identified significant reversal of inflammatory transcripts and pathways in the combined PAH patient cohort after vasodilator therapy in every PBMC type assessed. The "glucagon signalling in metabolic regulation" pathway in monocytes was reversed after vasodilator therapy via two independent analysis modalities.

CONCLUSION: Via a systems-biology approach, we define inflammatory reprogramming in the blood of PAH patients and the anti-inflammatory activity of vasodilators. Such findings establish diagnostic and prognostic blood-based tools for tracking inflammatory progression of PAH and response to therapy.

PMID:39811555 | PMC:PMC11726584 | DOI:10.1183/23120541.00486-2024

Cell Prolif. 2025 Jan 14:e13772. doi: 10.1111/cpr.13772. Online ahead of print.

ABSTRACT

Due to the similarity to human hepatocytes, porcine hepatocytes play an important role in hepatic research and drug evaluation. However, once hepatocytes were cultured in vitro, it was often prone to dedifferentiate, resulting in the loss of their characteristic features and normal functions, which impede their application in liver transplantation and hepatotoxic drugs evaluation. Up to now, this process has yet to be thoroughly investigated from the single-cell resolution and multi-omics perspective. In this study, we utilized 10× multiome technology to dissect the heterogeneity of porcine hepatocytes at different time points (Days 0, 1, 3, 5 and 7) during dedifferentiation. We comprehensively investigated cell heterogeneity, cellular dynamics, signalling pathways, potential gene targets, enhancer-driven gene regulatory networks, cell-cell communications of these cells and the conservation of mechanisms across species. We found that a series of critical signalling pathways driven by ERK, PI3K, Src and TGF-β were activated during this process, especially in the early stage of dedifferentiation. Based on these discoveries, we constructed a chemical combination targeting these pathways, which effectively inhibited the dedifferentiation of porcine hepatocytes in vitro. To validate the effectiveness of this combination, we transplanted such treated hepatocytes into FRGN mice, and the results demonstrated that these cells could effectively repopulate the liver and improve the survival of mice.

PMID:39810466 | DOI:10.1111/cpr.13772

Environ Sci Technol. 2025 Jan 14. doi: 10.1021/acs.est.4c10242. Online ahead of print.

ABSTRACT

Plants can recruit microorganisms to enhance soil arsenic (As) removal and nitrogen (N) turnover, but how microbial As methylation in the rhizosphere is affected by N biotransformation is not well understood. Here, we used acetylene reduction assay, arsM gene amplicon, and metagenome sequencing to evaluate the influence of N biotransformation on As methylation in the rhizosphere of Vetiveria zizanioides, a potential As hyperaccumulator. V. zizanioides was grown in mining soils (MS) and artificial As-contaminated soils (AS) over two generations in a controlled pot experiment. Results showed that the content of dimethylarsinic acid in the rhizosphere was significantly positively correlated with the rate of N fixation and the activity of nitrite reductase. The As-methylating species (e.g., Flavisolibacter and Paraflavitalea) were significantly enriched in the root-associated compartments in the second generation of MS and AS. Notably, higher abundance of genes involved in N fixation (nifD, nifK) and dissimilatory nitrate reduction to ammonium (narG/H, nirB/D/K/S) was detected in the second generation of MS than in the first generation. The metabolic pathway analysis further demonstrated that N fixing-stimulative and DNRA-stimulative As-methylating species could provide ammonium to enhance the synthesis of S-adenosyl-l-methionine, serving as methyl donors for soil As methylation. This study highlights two important N conversion-stimulative As-methylating pathways and has important implications for enhancing phytoremediation in As-contaminated soils.

PMID:39810418 | DOI:10.1021/acs.est.4c10242

Drug Metab Rev. 2025 Jan 15:1-34. doi: 10.1080/03602532.2025.2453521. Online ahead of print.

ABSTRACT

Idiosyncratic drug reactions (IDRs) pose severe threats to patient health. Unlike conventionally dose-dependent side effects, they are unpredictable and frequently manifest as life-threatening conditions, such as severe cutaneous adverse reactions (SCARs) and drug-induced liver injury (DILI). Some HLA alleles, such as HLA-B*57:01, HLA-B*15:02, and HLA-B*58:01, are known risk factors for adverse reactions induced by multiple drugs. However, the structural basis underlying most HLA-associated adverse events remains poorly understood. This review summarizes the application of molecular docking to reveal the mechanisms of IDR-related HLA associations, covering studies using this technique to examine drug-HLA binding pockets and identify key binding residues. We provide a comprehensive overview of risk HLA alleles associated with IDRs, followed by a discussion of the utility and limitations of commonly used molecular docking tools in simulating complex molecular interactions within the HLA binding pocket.Through examples, including the binding of abacavir to HLA-B*57:01, carbamazepine to HLA-B*15:02, and allopurinol to HLA-B*58:01, we demonstrate how docking analyses can provide insights into the drug and HLA allele-specificity of adverse events. Furthermore, the use of molecular docking to screen drugs with unknown IDR liability is examined, targeting either multiple HLA variants or a single specific variant. Despite multiple challenges, molecular docking presents a promising toolkit for investigating drug-HLA interactions and understanding IDR mechanisms, with significant implications for preemptive HLA typing and safer drug development.

PMID:39811883 | DOI:10.1080/03602532.2025.2453521

Notice NOT-HL-25-004 from the NIH Guide for Grants and Contracts

Funding Opportunity RFA-DK-26-007 from the NIH Guide for Grants and Contracts. This Notice of Funding Opportunity (NOFO) invites applications for studies of type 1 diabetes etiology and pathogenesis using data and samples from clinical trials and studies. This opportunity is intended to fund investigative teams collaborating to answer important questions about disease mechanisms leading to improved prevention of type 1 diabetes.

NIH has issued agency-specific information regarding its implementation of the U.S. Government Policy for Oversight of Dual Use Research of Concern and Pathogens with Enhanced Pandemic Potential (DURC/PEPP Policy). The policy, which goes into effect May 6, 2025, is a unified federal oversight framework for conducting and managing certain types of federally funded life sciences research on biological agents and toxins.

The DURC/PEPP Policy requirements apply to all NIH-funded research, including grants and cooperative agreements, Research and Development (R&D) contracts, NIH intramural research projects, and other funding agreements (e.g., Other Transactions). For more details, see the full Guide Notice.

Notice NOT-OD-25-063 from the NIH Guide for Grants and Contracts

Cell Death Dis. 2025 Jan 14;16(1):15. doi: 10.1038/s41419-025-07337-1.

ABSTRACT

The orphan nuclear receptor NR2E3 has emerged as a potential tumor suppressor, yet its precise mechanisms in tumorigenesis require further investigation. Here, we demonstrate that the full-length protein isoform of NR2E3 instead of its short isoform activates wild-type p53 and is capable of rescuing certain p53 mutations in various cancer cell lines. Importantly, we observe a higher frequency of NR2E3 mutations in three solid tumors compared to the reference population, highlighting its potential significance in tumorigenesis. Specifically, we identify a cancer-associated NR2E3R97H mutation, which not only fails to activate p53 but also impedes NR2E3WT-mediated p53 acetylation. Moreover, we show that the small-molecule agonist of NR2E3, 11a, penetrates tumor mass of uterine cancer patients and increases p53 activation. Additionally, both NR2E3 and 11a exhibit similar multifaceted anti-cancer properties, underscoring NR2E3 as a novel molecular vulnerability in cancer cells. We further explore drug repurposing screens of FDA-approved anti-cancer drugs to develop NR2E3-targeted combinatorial treatments, such as the 11a-Romidepsin combination in HeLa cells. The underlying molecular mechanisms of these drug synergies include the activation of p53 pathway and inhibition of oncogenic pathway like MYC. Overall, our findings suggest that NR2E3 holds promise as a therapeutic target for cancer treatment, offering new avenues for effective anti-cancer strategies.

PMID:39809731 | DOI:10.1038/s41419-025-07337-1

Comput Biol Med. 2025 Jan 13;186:109665. doi: 10.1016/j.compbiomed.2025.109665. Online ahead of print.

ABSTRACT

BACKGROUND: Effective drugs for tendinopathy are lacking, resulting in significant morbidity and re-tearing rate after operation. Applying systems biology to identify new applications for current pharmaceuticals can decrease the duration, expenses, and likelihood of failure associated with the development of new drugs.

METHODS: We identify tendinopathy signature genes employing a transcriptomics database encompassing 154 clinical tendon samples. We then proposed a systems biology based drug prediction strategy that encompassed multiplex transcriptional drug prediction, systematic review assessment, deep learning based efficacy prediction and Mendelian randomization (MR). Finally, we evaluated the effects of drug target using gene knockout mice.

RESULTS: We demonstrate that sirolimus is a repurposable drug for tendinopathy, supported by: 1) Sirolimus achieves top ranking in drug-gene signature-based multiplex transcriptional drug efficacy prediction, 2) Consistent evidence from systematic review substantiates the efficacy of sirolimus in the management of tendinopathy, 3) Genetic prediction indicates that plasma proteins inhibited by mTOR (the target of sirolimus) are associated with increased tendinopathy risk. The effectiveness of sirolimus is further corroborated through in vivo testing utilizing tendon tissue-specific mTOR gene knockout mice. Integrative pathway enrichment analysis suggests that mTOR inhibition can regulate heterotopic ossification-related pathways to ameliorate clinical tendinopathy.

CONCLUSIONS: Our study assimilates knowledge of system-level responses to identify potential drugs for tendinopathy, and suggests sirolimus as a viable candidate. A systems biology approach could expedite the repurposing of drugs for human diseases that do not have well-defined targets.

PMID:39809087 | DOI:10.1016/j.compbiomed.2025.109665

Pharmacogenomics. 2025 Jan 14:1-4. doi: 10.1080/14622416.2025.2452835. Online ahead of print.

ABSTRACT

AIMS: Clopidogrel exhibits substantial variability in therapeutic response, largely contributed by genetic factors. The pharmacogenomic variants data on clopidogrel metabolism in South Asians have been sparsely studied. This study explores the impact of CYP2C19 and CES1 gene variants on clopidogrel metabolism in Sri Lankans, revealing significant pharmacogenomic insights with broader implications for South Asians.

MATERIALS & METHODS: Genotype data were filtered out from an anonymized database of 690 Sri Lankans, and minor allele frequencies (MAFs) were calculated. Five variants of CYP2C19 and one variant of CES1 gene were studied.

RESULTS: Among the five CYP2C19 variants studied, rs12769205 (A>G) and rs4244285 (G>A) had the highest MAF of 42.1% and 42.0%, respectively. The CES1 variant rs71647871 (C>T) showed a MAF of 0.2%. Sri Lankans exhibited significantly higher MAFs for key variants compared to populations such as Europeans, African Americans, and East Asians (p < 0.05).

CONCLUSION: Given that South Asians share genetic similarities, these findings suggest that a substantial proportion of the region's population may also be poor responders to clopidogrel, increasing the risk of adverse outcomes. This highlights the importance of genotype-guided antiplatelet therapy, which could improve clinical outcomes across South Asia amidst rising cardiovascular disease rates.

PMID:39809701 | DOI:10.1080/14622416.2025.2452835

Anesth Pain Med (Seoul). 2025 Jan 15. doi: 10.17085/apm.24067. Online ahead of print.

ABSTRACT

Immunonutrition, which uses specific nutrients to modulate the immune response, has emerged as a vital adjunct to perioperative care. Surgery-induced stress triggers immune responses that can lead to complications, such as infections and delayed wound healing. Traditional nutritional support often overlooks the immunological needs of surgical patients. Immunonutrition addresses this oversight by providing key nutrients, such as arginine, omega-3 fatty acids, glutamine, nucleotides, and antioxidants (vitamins C and E) to enhance immune function and support tissue repair. This review examined the efficacy and safety of immunonutrition in surgical settings, guided by the recommendations of the American Society for Parenteral and Enteral Nutrition and the European Society for Clinical Nutrition and Metabolism. Both organizations recommend immunonutrition for high-risk or malnourished patients undergoing major surgery and support its use in reducing complications and improving recovery. The key nutrients in immunonutrition aim to improve immune cell function, reduce inflammation, and enhance wound healing. Clinical studies and meta-analyses have demonstrated that immunonutrition lowers the infection rate, shortens the length of hospital stay, and accelerates recovery. Challenges hindering the clinical application of immunonutrition include cost, logistics, and a lack of standardized and personalized protocols. Future studies should focus on biomarker-driven approaches, pharmacogenomics, and innovative nutrient formulations. Addressing these issues will help to integrate immunonutrition into clinical practice, ultimately improving surgical outcomes and patient recovery.

PMID:39809503 | DOI:10.17085/apm.24067

Cancer Cell Int. 2025 Jan 14;25(1):13. doi: 10.1186/s12935-025-03642-z.

ABSTRACT

BACKGROUND: Patients with lung adenocarcinoma (LUAD) receiving drug treatment often have an unpredictive response and there is a lack of effective methods to predict treatment outcome for patients. Dendritic cells (DCs) play a significant role in the tumor microenvironment and the DCs-related gene signature may be used to predict treatment outcome. Here, we screened for DC-related genes to construct a prognostic signature to predict prognosis and response to immunotherapy in LUAD patients.

METHODS: DC-related biological functions and genes were identified using single-cell RNA sequencing (scRNA-seq) and bulk RNA sequencing. DCs-related gene signature (DCRGS) was constructed using integrated machine learning algorithms. Expression of key genes in clinical samples was examined by real-time q-PCR. Performance of the prognostic model, DCRGS, for the prognostic evaluation, was assessed using a multiple time-dependent receiver operating characteristic (ROC) curve, the R package, "timeROC", and validated using GEO datasets.

RESULTS: Analysis of scRNA-seq data showed that there is a significant upregulation of LGALS9 expression in DCs isolated from malignant pleural effusion samples. Leveraging the Coxboost and random survival forest combination algorithm, we filtered out six DC-related genes on which a prognostic prediction model, DCRGS, was established. A high predictive capability nomogram was constructed by combining DCRGS with clinical features. We found that patients with a high-DCRGS score had immunosuppression, activated tumor-associated pathways, and elevated somatic mutational load and copy number variant load. In contrast, patients in the low-DCRGS subgroup were resistant to chemotherapy but sensitive to the CTLA-4 immune checkpoint inhibitor and targeted therapy.

CONCLUSION: We have innovatively established a deep learning-based prediction model, DCRGS, for the prediction of the prognosis of patients with LUAD. The model possesses a strong prognostic prediction performance with high accuracy and sensitivity and could be clinically useful to guide the management of LUAD. Furthermore, the findings of this study could provide an important reference for individualized clinical treatment and prognostic prediction of patients with LUAD.

PMID:39810206 | DOI:10.1186/s12935-025-03642-z