The study combined cell biology, transcriptomics, and ionomics to reveal that zinc deficiency reduces root apical meristem size while preserving meristematic activity and local Zn levels, leading to enhanced cell elongation and differentiation in Arabidopsis thaliana. ZIP12 was identified as a highly induced gene in the zinc‑deficient root tip, and zip12 mutants displayed impaired root growth, altered RAM structure, disrupted Zn‑responsive gene expression, and abnormal metal partitioning, highlighting ZIP12’s role in maintaining Zn homeostasis and meristem function.

The study used extensive gravimetric load‑cell and ambient sensor data collected over seven years from hundreds of greenhouse-grown crops to train machine‑learning models for predicting daily whole‑plant transpiration. Random Forest and XGBoost achieved the highest accuracy (R² up to 0.89), with ambient temperature identified as the dominant driver. These results highlight the promise of ML‑based tools for precise agricultural water management.

The study profiled root transcriptomes of Arabidopsis wild type and etr1 gain-of-function (etr1-3) and loss-of-function (etr1-7) mutants under ethylene or ACC treatment, identifying 4,522 ethylene‑responsive transcripts, including 553 that depend on ETR1 activity. ETR1‑dependent genes encompassed ethylene biosynthesis enzymes (ACO2, ACO3) and transcription factors, whose expression was further examined in an ein3eil1 background, revealing that both ETR1 and EIN3/EIL1 pathways regulate parts of the network controlling root hair proliferation and lateral root formation.

The study used high-resolution chemical imaging to map cell-type specific metabolic changes in plant roots inoculated with a nine-strain endophyte consortium under drought, revealing that endophytes differentially alter root metabolomes across spatial domains. Machine learning identified metabolites and exudates predictive of drought and endophyte treatment, and correlation analyses showed dynamic endophyte–metabolite relationships under stress.

The study used transcriptomic and lipidomic profiling to investigate how chia (Salvia hispanica) leaves respond to short‑term (3 h) and prolonged (27 h) heat stress at 38 °C, revealing rapid activation of calcium‑signaling and heat‑shock pathways and reversible changes in triacylglycerol levels. Nearly all heat‑responsive genes returned to baseline expression after 24 h recovery, highlighting robust thermotolerance mechanisms that could inform improvement of other oilseed crops.

The study used Arabidopsis thaliana mutants with low (vtc2, vtc4) and high (vtc2/OE-VTC2) ascorbate levels to examine how ascorbate concentration affects gene expression and cellular homeostasis. Transcriptomic analysis revealed that altered ascorbate levels modulate defense and stress pathways, and that TAA1/TAR2‑mediated auxin biosynthesis is required for coping with elevated ascorbate in a light‑dependent manner.

The study introduces ENTRAP-seq, a high‑throughput in‑planta assay that couples protein‑coding libraries with a nuclear magnetic sorting‑based reporter to multiplexively assess transcriptional regulatory activity of thousands of protein variants. Using this platform and machine‑learning analysis, the authors screened 1,495 plant viral proteins, uncovering numerous novel regulatory domains, and applied machine‑guided, semi‑rational design to modify the activity of a plant transcription factor.

The study used phylogeny‑based analyses of 36 legume genomes and a newly created multiparent advanced generation intercross (MAGIC) population of common bean to predict and characterize genome‑wide deleterious mutations. Machine‑learning integration of conservation and protein features identified thousands of potentially deleterious sites, whose variation correlated negatively with flowering time, maturity, and yield, highlighting the impact of genetic load on breeding performance.

The authors introduce S²-PepAnalyst, a web-based tool that leverages plant-specific datasets and advanced machine learning to predict small signaling peptides (SSPs) with 99.5% accuracy and minimal false negatives. By integrating protein language models, geometric‑topological analysis, and reinforcement learning, the tool surpasses existing predictors such as SignalP 6.0 in classifying peptide families like CLE and RALF.

The study performed daily large-scale glycome, transcriptome, and proteome profiling of developing fibers from the two cultivated cotton species, Gossypium barbadense and G. hirsutum, across primary and secondary cell wall stages. It identified delayed cellulose accumulation and distinct compositions of xyloglucans, homogalacturonans, rhamnogalacturonan‑I, and heteroxylans in G. barbadense, along with higher expression of specific glycosyltransferases and expansins, suggesting these molecular differences underlie the superior fiber length and strength of G. barbadense.