Cavel, E. | bioRxiv Science

bioRxiv2025

Botanic Spectrum Analyser: A Deep Learning GUI for Plant Image Segmentation in Hyperspectral and RGB Phenotyping

Plant phenotyping systematically quantifies plant traits such as growth, morphology, physiology, or yield, assessing genetic and environmental influences on plant performance. The integration of advanced phenotyping technologies, including imaging sensors and data analytics, facilitates the non-destructive and longitudinal acquisition of high-throughput data. Nevertheless, the sheer volume of such phenotyping data introduces significant challenges for researchers, particularly related to data processing. To overcome these challenges, researchers are turning to artificial intelligence (AI), a tool that can autonomously process and learn from large amounts of data. Despite this advantage, accurate image segmentation remains a key hurdle due to the complexity of plant morphology and environmental noise. In this study, we present the Botanical Spectrum Analyser (BSA), a user-friendly graphical user interface (GUI) that integrates a modified U-Net deep neural network for plant image segmentation. Designed for accessibility, BSA enables non-technical users to apply advanced AI segmentation to RGB and hyperspectral (VNIR and SWIR) imagery. We evaluated BSAs performance across three case studies involving wheat, barley, and Arabidopsis, demonstrating its robustness across species and imaging modalities. Our results show that BSA achieves an average accuracy of 99.7%, with F1-scores consistently exceeding 98% and strong Jaccard and recall performance across datasets. For challenging root segmentation tasks, BSA outperformed commercial algorithms, achieving a 76% F1-score compared to 24%, representing a 50% improvement. These results highlight the adaptability of the BSA framework for diverse phenotyping scenarios, bridging the gap between advanced deep learning methods and accessible plant science applications.

plant biology↗

bioRxiv2019

Molecular framework for TIR1/AFB-Aux/IAA-dependent auxin sensing controlling adventitious rooting in Arabidopsis

In Arabidopsis thaliana, canonical auxin-dependent gene regulation is mediated by 23 transcription factors from the AUXIN RESPONSE FACTOR (ARF) family, most of which interact with 29 auxin/indole acetic acid (Aux/IAA) repressors, themselves forming, in the presence of auxin, coreceptor complexes with one of six TRANSPORT INHIBITOR1/AUXIN-SIGNALLING F-BOX PROTEINS (TIR1/AFB). Different combinations of co-receptors drive specific sensing outputs, allowing auxin to control a myriad of processes. Considerable efforts have been made to discern the temporal and spatial specificity of auxin action. However, owing to a lack of obvious phenotype in single loss-of-function mutants in Aux/IAA genes, most genetic studies have relied on gain-of-function mutants, which are highly pleiotropic. In this article, we describe a molecular framework for the role of several members of the auxin sensing machinery. Using loss-of-function mutants, we demonstrate that TIR1 and AFB2 are positive regulators, whereas IAA6, IAA9 and IAA17 are negative regulators of adventitious root (AR) formation. The three Aux/IAA proteins interact with ARF6 and/or ARF8, which we have previously shown to be positive regulators of AR formation upstream of jasmonate, and likely repress their activity. Our data also suggest a dual role for TIR1 in the control of JA biosynthesis and conjugation, as revealed by upregulation of several JA biosynthesis genes in the tir1-1 mutant. In conclusion, we propose that in the presence of auxin, TIR1 and AFB2 form specific sensing complexes with IAA6, IAA9 and/or IAA17 that modulate JA homeostasis to control AR initiation.\n\nSignificanceAdventitious root (AR) formation is a quantitative trait with high phenotypic plasticity and auxin plays a major role in its control. In previous studies, we have shown that, in Arabidopsis hypocotyls, AR formation is negatively regulated by jasmonate, whose homeostasis is controlled by a regulatory module composed of three AUXIN RESPONSE FACTORS (ARF), two of which are positive regulators of three auxin inducible Gretchen Hagen3 (GH3) genes. The present work demonstrates that the two F-box proteins, i.e., TIR1 and AFB2, together with at least three Aux/IAA proteins are likely to interact in a combinatorial manner to control the activity of the two activator ARFs upstream of JA biosynthesis and/or homeostasis, thereby controlling AR initiation in Arabidopsis hypocotyls.

plant biology↗