Using genome‑wide association studies in Arabidopsis thaliana, the authors identified the chromatin‑associated protein CDCA7 as a trans‑regulator that specifically controls CG methylation (mCG) and TE silencing. CDCA7 and its paralog CDCA7β bind the remodeler DDM1, modulating its activity without broadly affecting non‑CG methylation or histone variant deposition, and natural variation in CDCA7 regulatory sequences correlates with local ecological adaptation.

The study demonstrates that the chromatin remodeler DDM1 is essential for biomass heterosis in Arabidopsis thaliana hybrids, as loss of DDM1 function leads to reduced rosette growth and extensive genotype‑specific transcriptomic and DNA methylation changes. Whole‑genome bisulfite sequencing revealed widespread hypomethylation in ddm1 mutants, while salicylic acid levels were found unrelated to heterosis, indicating that epigenetic divergence, rather than SA signaling, underpins hybrid vigor.

The study examined molecular responses in grapevine leaves with and without esca symptoms, using metabolite profiling, RNA‑seq and whole‑genome bisulfite sequencing. Metabolic and transcriptomic changes were confined to symptomatic leaves and linked to local DNA‑methylation alterations, while asymptomatic leaves showed distinct but overlapping methylation patterns, some present before symptoms, indicating potential epigenetic biomarkers for early disease detection.

The study integrated weekly morphophysiological measurements with high-density genotyping-by-sequencing data and a machine‑learning pipeline to dissect flowering time variation in diverse Cannabis sativa landraces. By applying mutual information, recursive feature elimination, random forest, and support vector machine classifiers to over 234,000 combined genetic, phenotypic, and environmental features, the authors identified 53 key markers that classify early, medium, and late flowering types with 96.6% accuracy. Notable loci, including CsFT3 and CsCFL1, were highlighted as promising targets for breeding and smart‑crop strategies.

The study identifies GyrB3 as a novel nuclear factor that interacts with histone deacetylases to regulate transposable element silencing in plants, acting as a suppressor of IBM1 deficiency–induced epigenetic defects. Loss of GyrB3 reduces DNA methylation and increases H3 acetylation at TEs, demonstrating the importance of histone deacetylation for genome stability.

The study examined gene expression, DNA methylation, and small RNA profiles in a Citrus hybrid (C. reticulata × C. australasica) using haplotype‑resolved subgenome assemblies, revealing allele‑specific expression and asymmetric CHH methylation that correlated with increased transcription and 24‑nt siRNA accumulation at promoters. This unconventional association suggests RNA‑directed DNA methylation (RdDM) can activate transcription in citrus fruit and provides a pipeline for epigenomic analysis of complex hybrids relevant to disease resistance breeding.

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 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 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.