Machine learning provides specific detection of salt and drought stresses in cucumber based on miRNA characteristics
Ontology highlight
ABSTRACT:
SUBMITTER: Mohammadi P
PROVIDER: S-EPMC10631058 | biostudies-literature | 2023 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:During the last two decades, human has increased his knowledge about the role of miRNAs and their target genes in plant stress response. Biotic and abiotic stresses result in simultaneous tissue-specific up/down-regulation of several miRNAs. In this study, for the first time, feature selection algorithms have been used to investigate the contribution of individual plant miRNAs in Arabidopsis thaliana response towards different levels of several abiotic stresses including drought, salinity, cold, and heat. Results of information theory-based feature selection revealed that miRNA-169, miRNA-159, miRNA-396, and miRNA-393 had the highest contributions to plant response towards drought, salinity, cold, and heat, respectively. Furthermore, regression models, i.e., decision tree (DT), support vector machines (SVMs), and Naïve Bayes (NB) were used to predict the plant stress by having the plant miRNAs' concentration. SVM with Gaussian kernel was capable of predicting plant stress (R2 = 0.96) considering miRNA concentrations as input features. Findings of this study prove the performance of machine learning as a promising tool to investigate some aspects of miRNAs' contribution to plant stress responses that have been undiscovered until today.
| S-EPMC7033123 | biostudies-literature
Project description:Cellular senescence is a state of irreversible cell cycle arrest that contributes to age-associated decline through the accumulation of senescent cells and their senescence-associated secretory phenotype (SASP). The SASP, comprising inflammatory signaling molecules and growth factors, can induce secondary senescence in surrounding healthy cells via paracrine signaling. Additionally, secondary senescence can be induced through juxtacrine signaling via activation of NOTCH1. To further understand the progression of cells into primary and secondary senescence, we used a comprehensive single-cell RNA sequencing data set of clonal human lung fibroblasts (LF1) cell lines from different forms of senescence and quiescence. Here, we present SENTRY (SENescent TRacking sYstem), a new method that uses unsupervised clustering techniques to identify subpopulations of cells common to most major forms of senescence, revealing that the RNA profiles of these subpopulations are driven in part by markers associated with secondary senescence. Leveraging this data, we developed machine learning models using random forests to predict senescent status and subtype with exceptionally high accuracy. SHAP (SHapley Additive exPlanations) analysis identified the most informative genes for classification, many of which are unique to our model compared to existing senescent signatures like SenMayo and SenSig. We then used this classification to analyze single-cell RNA sequencing data in a time course of proliferating and senescent human lung fibroblasts. We observed that primary and secondary senescent cells exhibit distinct transcriptomic and epigenetic profiles, particularly in pathways related to cell cycle regulation, extracellular matrix remodeling and inflammatory signaling. Additionally, we performed a comparative analysis of gene-length-dependent transcription decline (GLTD) at different stages of senescence induction.
2025-09-05 | GSE306635 | GEO
Project description:The workflow of this research is based on numerous hypotheses involving the usage of pre-processing methods, wheat canopy segmentation methods, and whether the existing models from the past research can be adapted to classify wheat crop water stress. Hence, to construct an automation model for water stress detection, it was found that pre-processing operations known as total variation with L1 data fidelity term (TV-L1) denoising with a Primal-Dual algorithm and min-max contrast stretching are most useful. For wheat canopy segmentation curve fit based K-means algorithm (Cfit-kmeans) was also validated for the most accurate segmentation using intersection over union metric. For automated water stress detection, rapid prototyping of machine learning models revealed that there is a need only to explore nine models. After extensive grid search-based hyper-parameter tuning of machine learning algorithms and 10 K fold cross validation it was found that out of nine different machine algorithms tested, the random forest algorithm has the highest global diagnostic accuracy of 91.164% and is the most suitable for constructing water stress detection models.
| S-EPMC10280683 | biostudies-literature
Project description:RNA-sequencing (RNA-seq) is widely used for analysis of alternative splicing, but in practice, has inherent biases which hinder its ability to detect and quantify splicing events. To address this, we present a targeted RNA-seq method that specifically enriches for splicing-informative junction-spanning reads. Local Splicing Variation sequencing (LSV-seq) utilizes multiplexed reverse transcription from highly scalable pools of primers anchored near splice junctions of interest. Primers are designed using Optimal Prime, a novel dedicated machine learning algorithm trained on the performance of thousands of primer sequences. LSV-seq achieves high on-target capture rates and concordance with RNA-seq, while requiring several-fold lower sequencing depth. We use LSV-seq to target events with low coverage in GTEx RNA-seq data and discover hundreds of previously hidden tissue-specific splicing events. Our results demonstrate the ability of LSV-seq to capture alternative splicing with exceptional sensitivity and highlight its potential to improve the detection of other RNA features of interest.
2024-12-27 | GSE246294 | GEO
Project description:The basic leucine zipper (bZIP) family of transcription factors plays an important role in the growth and developmental process as well as responds to various abiotic stresses, such as drought and high salinity. Our previous work identified GmFDL19, a bZIP transcription factor, as a flowering promoter in soybean, and the overexpression of GmFDL19 caused early flowering in transgenic soybean plants. Here, we report that GmFDL19 also enhances tolerance to drought and salt stress in soybean. GmFDL19 was determined to be a group A member, and its transcription expression was highly induced by abscisic acid (ABA), polyethylene glycol (PEG 6000) and high salt stresses. Overexpression of GmFDL19 in soybean enhanced drought and salt tolerance at the seedling stage. The relative plant height (RPH) and relative shoot dry weight (RSDW) of transgenic plants were significantly higher than those of the WT after PEG and salt treatments. In addition, the germination rate and plant height of the transgenic soybean were also significantly higher than that of WT plants after various salt treatments. Furthermore, we also found that GmFDL19 could reduce the accumulation of Na+ ion content and up-regulate the expression of several ABA/stress-responsive genes in transgenic soybean. We also found that GmFDL19 overexpression increased the activities of several antioxidative enzyme and chlorophyll content but reduced malondialdehyde content. These results suggested that GmFDL19 is involved in soybean abiotic stress responses and has potential utilization to improve multiple stress tolerance in transgenic soybean.
| S-EPMC5480881 | biostudies-literature
Project description:Bermudagrass (Cynodon dactylon) is one of tolerant grass species to drought and salt. The comparative analyses of bermudagrass in response to drought and salt stresses at the physiological, proteomic, and metabolomic levels were performed in this study. The physiological results indicated that osmolytes accumulation, ROS level and antioxidant enzyme activities were extensively changed by drought and salt stresses. Through comparative proteomic analyses, we successfully identified a total of 77 proteins involved in photosynthesis, oxidative pentose phosphate, glycolysis, and redox metabolic pathways when exposed to drought and salt stresses. Among them, 36 proteins were commonly regulated by both treatments, while other 40 and 13 proteins were specifically regulated by drought and salt, respectively. Totally 15 proteins were involved in carbon metabolic pathway. Moreover, contents of 37 metabolites including amino acids, organic acids, sugars, and sugar alcohols were regulated by drought and salt treatments. Among them, 18 commonly modulated metabolites were involved in carbon and amino acid metabolic pathways. Drought treatment for 21 days caused less accumulation of sugars and sugar alcohols and increased ROS level in bermudagrass which led to relatively more severe cell membrane reflected by high EL-value and lower survival rate when compared to 400 mM salt treatment for 21 days. These results suggested that drought and 400 mM NaCl stresses for 21 days treatment affected common and specific changes in bermudagrass, which would provide new insights to understand the underlying molecular mechanisms and metabolic homeostasis of bermudagrass in responses to abiotic stresses.
| S-EPMC5105639 | biostudies-literature
Project description:Phospholipase C (PLC) performs significant functions in a variety of biological processes, including plant growth and development. The PLC family of enzymes principally catalyze the hydrolysis of phospholipids in organisms. This exhaustive exploration of soybean GmPLC members using genome databases resulted in the identification of 15 phosphatidylinositol-specific PLC (GmPI-PLC) and 9 phosphatidylcholine-hydrolyzing PLC (GmNPC) genes. Chromosomal location analysis indicated that GmPLC genes mapped to 10 of the 20 soybean chromosomes. Phylogenetic relationship analysis revealed that GmPLC genes distributed into two groups in soybean, the PI-PLC and NPC groups. The expression patterns and tissue expression analysis showed that GmPLCs were differentially expressed in response to abiotic stresses. GmPI-PLC7 was selected to further explore the role of PLC in soybean response to drought and salt stresses by a series of experiments. Compared with the transgenic empty vector (EV) control lines, over-expression of GmPI-PLC7 (OE) conferred higher drought and salt tolerance in soybean, while the GmPI-PLC7-RNAi (RNAi) lines exhibited the opposite phenotypes. Plant tissue staining and physiological parameters observed from drought- and salt-stressed plants showed that stress increased the contents of chlorophyll, oxygen free radical (O2 -), hydrogen peroxide (H2O2) and NADH oxidase (NOX) to amounts higher than those observed in non-stressed plants. This study provides new insights in the functional analysis of GmPLC genes in response to abiotic stresses.
| S-EPMC7982816 | biostudies-literature
Project description:SENTRY: Machine Learning Detection of Secondary Senescence
| PRJNA1311543 | ENA
Project description:BackgroundPancreatic cancer is often diagnosed at advanced stages, and early-stage diagnosis of pancreatic cancer is difficult because of nonspecific symptoms and lack of available biomarkers.MethodsWe performed comprehensive serum miRNA sequencing of 212 pancreatic cancer patient samples from 14 hospitals and 213 non-cancerous healthy control samples. We randomly classified the pancreatic cancer and control samples into two cohorts: a training cohort (N = 185) and a validation cohort (N = 240). We created ensemble models that combined automated machine learning with 100 highly expressed miRNAs and their combination with CA19-9 and validated the performance of the models in the independent validation cohort.ResultsThe diagnostic model with the combination of the 100 highly expressed miRNAs and CA19-9 could discriminate pancreatic cancer from non-cancer healthy control with high accuracy (area under the curve (AUC), 0.99; sensitivity, 90%; specificity, 98%). We validated high diagnostic accuracy in an independent asymptomatic early-stage (stage 0-I) pancreatic cancer cohort (AUC:0.97; sensitivity, 67%; specificity, 98%).ConclusionsWe demonstrate that the 100 highly expressed miRNAs and their combination with CA19-9 could be biomarkers for the specific and early detection of pancreatic cancer.
| S-EPMC11442445 | biostudies-literature
Project description:BACKGROUND: Aquaporin (AQP) proteins function in transporting water and other small molecules through the biological membranes, which is crucial for plants to survive in drought or salt stress conditions. However, the precise role of AQPs in drought and salt stresses is not completely understood in plants. RESULTS: In this study, we have identified a PIP1 subfamily AQP (MaPIP1;1) gene from banana and characterized it by overexpression in transgenic Arabidopsis plants. Transient expression of MaPIP1;1-GFP fusion protein indicated its localization at plasma membrane. The expression of MaPIP1;1 was induced by NaCl and water deficient treatment. Overexpression of MaPIP1;1 in Arabidopsis resulted in an increased primary root elongation, root hair numbers and survival rates compared to WT under salt or drought conditions. Physiological indices demonstrated that the increased salt tolerance conferred by MaPIP1;1 is related to reduced membrane injury and high cytosolic K+/Na+ ratio. Additionally, the improved drought tolerance conferred by MaPIP1;1 is associated with decreased membrane injury and improved osmotic adjustment. Finally, reduced expression of ABA-responsive genes in MaPIP1;1-overexpressing plants reflects their improved physiological status. CONCLUSIONS: Our results demonstrated that heterologous expression of banana MaPIP1;1 in Arabidopsis confers salt and drought stress tolerances by reducing membrane injury, improving ion distribution and maintaining osmotic balance.
| S-EPMC4015420 | biostudies-literature