Plant Breeding Research Articles

BerryPortraits: Phenotyping Of Ripening Traits cranberry (Vaccinium macrocarpon Ait.) with YOLOv8

AbstractBerryPortraits (Phenotyping of Ripening Traits) is open source Python-based image-analysis software that rapidly detects and segments berries and extracts morphometric data on fruit quality traits such as berry color, size, shape, and uniformity. Utilizing the YOLOv8 framework and community-developed, actively-maintained Python libraries such as OpenCV, BerryPortraits software was trained on 512 postharvest images (taken under controlled lighting conditions) of phenotypically diverse cranberry populations (Vaccinium macrocarpon Ait.) from the two largest public cranberry breeding programs in the U.S. The implementation of CIELAB, an intuitive and perceptually uniform color space, enables differentiation between berry color and berry brightness, which are confounded in classic RGB color channel measurements. Furthermore, computer vision enables precise and quantifiable color phenotyping, thus facilitating inclusion of researchers and data analysts with color vision deficiency. BerryPortraits is a phenotyping tool for researchers in plant breeding, plant genetics, horticulture, food science, plant physiology, plant pathology, and related fields. BerryPortraits has strong potential applications for other specialty crops such as blueberry, lingonberry, caneberry, grape, and more. As an open source phenotyping tool based on widely-used python libraries, BerryPortraits allows anyone to use, fork, modify, optimize, and embed this software into other tools or pipelines.

Crucial role of fungi in environmentally sustainable agriculture

To produce more, better and safer food we must be able to do so while promoting the sustainable use of agricultural resources. The increase in agricultural production is currently through the use of pesticides, fertilizers, and developments in plant breeding and genetic skills. In naturally existing ecosystems, rhizospheric soils have biological living beings to favor the plant development, nutrient assimilation, stress tolerance, disease deterrence, carbon seizing and others. Fungi are among the most widely distributed organisms on Earth and are of great environmental importance. Mycorrhizal fungi, bacteria, actinomycetes, etc. solubilize nutrients and assist the plants in uptake by roots. Amongst them, vesicular/arbuscular mycorrhizal fungi (AMF) have key roles in the natural ecosystem, as the majority of the terrestrial plants form association with AMF. This symbiosis confers benefits directly to the host plant’s growth and development through the acquisition of phosphorus (P) and other mineral nutrients from the soil. They may also enhance the protection of plants against pathogens, increase plant diversity and have the potential to enhance plant growth under stressful environments. In this article, the sustainability and environmental aspects of agriculture, and the basic concepts of fungi will be reviewed to justify our point of view about the tremendous importance of fungi towards an environmentally sustainable agriculture.

Impact of Polyploidy on Crop Improvement and Plant Breeding Strategies: A Review

Polyploidy, the condition of possessing multiple sets of chromosomes, is a widespread phenomenon in plants that has had a profound impact on crop evolution and improvement. This review explores the role of polyploidy in plant breeding strategies, emphasizing its contributions to enhancing agronomic traits, overcoming genetic barriers, and expanding genetic diversity. Polyploid crops, such as wheat, cotton, and Brassica species, exhibit superior yield, increased biomass, and enhanced stress tolerance compared to their diploid counterparts. Polyploidy can arise naturally or be induced artificially, providing breeders with opportunities to create novel crop varieties through synthetic polyploidization. The complexity of polyploid genomes poses significant challenges, including fertility issues, meiotic instability, and difficulties in genome management. Advances in genomic and biotechnological tools, such as genomic selection and CRISPR-based genome editing, are beginning to address these obstacles, allowing for precise manipulation of polyploid genomes and improved breeding outcomes. Additionally, polyploidy plays a crucial role in overcoming reproductive barriers in interspecific hybrids, facilitating the transfer of desirable traits between species that would otherwise be genetically incompatible. The potential of polyploidy for developing climate-resilient crops is particularly noteworthy, as polyploid plants often exhibit greater tolerance to drought, salinity, and extreme temperatures. This makes polyploid breeding a promising approach for addressing the challenges of climate change and ensuring food security. Future research should focus on understanding the genetic and epigenetic mechanisms underlying polyploid genome stability and trait expression, as well as integrating advanced computational tools to predict and manipulate polyploid gene function. Emerging areas such as synthetic biology and multi-omics integration will further enhance our ability to engineer polyploid crops with complex trait architectures. Polyploidy remains a powerful and versatile tool for plant breeders, offering immense potential for crop improvement, genetic innovation, and the development of resilient agricultural systems. As the understanding and technological capabilities in polyploid breeding continue to advance, polyploid crops will play a central role in sustainable agricultural development and global food production.

What are microsatellites and how to choose the best tool: a user-friendly review of SSR and 74 SSR mining tools

Microsatellites, also known as SSR or STR, are essential molecular markers in genomic research, playing crucial roles in genetic mapping, population genetics, and evolutionary studies. Their applications range from plant breeding to forensics, highlighting their diverse utility across disciplines. Despite their widespread use, traditional methods for SSR analysis are often laborious and time-consuming, requiring significant resources and expertise. To address these challenges, a variety of computational tools for SSR analysis have been developed, offering faster and more efficient alternatives to traditional methods. However, selecting the most appropriate tool can be daunting due to rapid technological advancements and the sheer number of options available. This study presents a comprehensive review and analysis of 74 SSR tools, aiming to provide researchers with a valuable resource for SSR analysis tool selection. The methodology employed includes thorough literature reviews, detailed tool comparisons, and in-depth analyses of tool functionality. By compiling and analyzing these tools, this study not only advances the field of genomic research but also contributes to the broader scientific community by facilitating informed decision-making in the selection of SSR analysis tools. Researchers seeking to understand SSRs and select the most appropriate tools for their projects will benefit from this comprehensive guide. Overall, this study enhances our understanding of SSR analysis tools, paving the way for more efficient and effective SSR research in various fields of study.

In Vitro Plant Regeneration of Sulla coronaria from Floral Explants as a Biotechnological Tool for Plant Breeding

Sulla coronaria L. Medik., a biennial forage legume typical of the Mediterranean basin, plays a significant role in foraging systems due to its high nutritional value, ability to increase ruminant live weight, and potential to reduce methane emissions. However, its allogamous nature complicates genetic improvement and the development of new varieties with desired traits. Given these challenges, this study aims to develop, for the first time, a successful protocol for the in vitro meristematic shoot regeneration of S. coronaria. The experiment utilizes four different flower explants (anther with filament, ovary, petals, and whole immature flower) collected from twenty distinct S. coronaria biotypes with three plant growth regulator (PGR) combinations and under both light and dark conditions. In terms of the regeneration response, the key factors appear to be the combinations of PGRs and the type of explant used. The interactions between all the factors do not seem to be significant.

Plant microbiome technology for sustainable agriculture

Plants establish specific interactions with microorganisms, which are vital for promoting growth and resilience. Although advancements in microbiome modulation technologies show great potential for sustainable agriculture, several challenges have hindered the wider application of plant microbiomes in the field. These challenges may include inconsistent microbial colonization, competition with native microbiota, and environmental variability. Current strategies, while promising, often yield inconsistent results in real-world agricultural settings, highlighting the need for more refined approaches. Agricultural practices and plant genotypes significantly influence the composition and function of plant-associated microbiota. A data-driven strategy that incorporates genomic profiling, environmental assessments, and optimized delivery systems is essential for selecting effective microbial strains. Additionally, refining farming practices, such as crop rotation, intercropping, and reduced tillage, along with robust plant breeding programs, can greatly enhance crop health and productivity.

Genetic Variability in Fusarium Wilt Resistant BC2F1 Lines of Yard Long Bean (Vigna unguiculata subsp. sesquipedalis (L.) Verdcourt) Variety Githika for Yield and its Related Traits

Yardlong bean is a highly popular and profitable vegetable traditionally cultivated in the humid tropics of Kerala and is an inexpensive source of vegetable protein. Developing sustainable host plant resistance mechanisms, such as using the backcross method to introduce single-gene resistance into susceptible crop varieties, is crucial for reducing losses due to Fusarium wilt. In the present study Thirty-five resistant backcross progenies (BC2F1) of Yardlong Bean (Vigna unguiculata subsp. sesquipedalis (L.) Verdcourt) variety Githika were evaluated for various genetic parameters for yield and its related traits using Completely Randomized Design at Department of Genetics and Plant Breeding, College of Agriculture, Vellayani, Trivandrum. High phenotypic coefficient of variation (PCV) and genotypic coefficient of variation (GCV) were observed for traits such as the number of pods per plant, pod weight, pod yield per plant, crude protein content. High Heritability(H) and High Genetic advance as percent mean (GAM) were observed for traits such as Number of pods per plant, Pod weight, Pod length, Number of seeds per pod, Pod Yield per plant, Crude fibre and Crude protein content. This significantly suggest that additive gene action is predominant in these traits and low reliance by environmental factors on these traits, making such character a good candidate for direct selection. The study helps in assessing genetic variability to identify traits as well as lines with maximum similarity with recurrent parent which could be used for further crop improvement program.

From phylogenomics to breeding: Can universal target capture probes be used in the development of SNP markers for kinship analysis?

AbstractPremiseLeveraging DNA markers, particularly single‐nucleotide polymorphisms (SNPs), in parentage analysis, sib‐ship reconstruction, and genomic relatedness analysis can enhance plant breeding efficiency. However, the limited availability of genomic information, confined to the most commonly used species, hinders the broader application of SNPs in species of lower economic interest (e.g., most tree species). We explored the possibility of using universal target capture probes, namely Angiosperms353, to identify SNPs and assess their effectiveness in genomic relatedness analysis.MethodsWe tested the approach in 11 tree species, six of which had a half‐sib family structure. Variants were called within species, and genomic relatedness analysis was conducted in species with two or more families. Scalability via amplicon sequencing was tested by designing primers and testing them in silico.ResultsAdequate SNPs for relatedness analysis were identified in all species. Relatedness values from Angiosperms353‐based SNPs highly correlated with those from thousands of genome‐wide DArTseq SNPs in Cordia africana, one of the species with a family structure. The in silico performance of designed primers demonstrated the potential for scaling up via amplicon sequencing.DiscussionUtilizing universal target capture probes for SNP identification can help overcome the limitations of genomic information availability, thereby enhancing the application of genomic markers in breeding plant species with lower economic interest.

How Many Checks Are Needed per Cycle in a Plant Breeding or Variety Testing Programme?

ABSTRACTCheck varieties are used in plant breeding and variety testing for a number of reasons. One important use of checks is to provide connectivity between years, which facilitates comparison among genotypes of interest that are tested in different years. When long‐term data are available, such comparisons allow an assessment of realized genetic gain (RGG). Here, we consider the question of how many check varieties are needed per cycle for a reliable assessment of RGG. We propose an approach that makes use of variance component estimates for relevant random effects in a linear mixed model and plugs them into an analysis of dummy datasets set up to represent the design options being considered. Our results show that it is useful to employ a larger number of checks and to keep the replacement rate low. Furthermore, there is intercycle information to be recovered, especially when there are few checks and replacement rates are high, so modelling the cycle main effect as random pays off.

Dosage-sensitive maternal siRNAs determine hybridization success in Capsella

Abstract Hybrid seed failure arising from wide crosses between plant species is a recurring obstacle in plant breeding, impeding the transfer of desirable traits. This postzygotic reproductive barrier primarily occurs in the endosperm, a tissue that nourishes the embryo and functions similarly to the placenta in mammals. We found that incompatible seeds show a loss of DNA methylation and chromatin condensation in the endosperm, similar to seeds lacking maternal RNA polymerase IV activity. This similarity is linked to a decrease in small interfering RNAs in the endosperm (sirenRNAs), maternal RNA polymerase IV-dependent short interfering RNAs that regulate DNA methylation. Several AGAMOUS-like MADS-box transcription factor genes (AGLs), key regulators of endosperm development, are targeted by sirenRNAs in cis and in trans. This finding aligns with the enrichment of AGL target genes among deregulated genes. We propose that hybrid seed failure results from reduced maternal sirenRNAs combined with increased AGL expression, leading to abnormal gene regulation in the endosperm.

The contribution of beneficial wheat seed fungal communities beyond disease‐causing fungi: Advancing heritable mycobiome‐based plant breeding

AbstractWheat (Triticum sp.) is a staple cereal crop, providing nearly a fifth of the world's protein and available calories. While fungi associated with wheat plants have been known for centuries, attention to fungi associated with wheat seeds has increased over the last hundred years. Initially, research focused on fungal taxa that cause seed‐borne diseases. Seeds act as a physical link between generations and host specialized fungal communities that affect seed dormancy, germination, quality, and disease susceptibility. Interest in beneficial, non‐disease‐causing fungal taxa associated with seeds has grown since the discovery of Epichloë in fescue, leading to a search for beneficial fungal endophytes in cereal grains. Recent studies of the wheat seed mycobiome have shown that disease, seed development, and temporal variation significantly influence the composition and structure of these fungal communities. This research, primarily descriptive, aims to better understand the wheat seed mycobiome's function in relation to the plant host. A deeper understanding of the wheat seed mycobiome's functionality may offer potential for microbiome‐assisted breeding.

Transgene effects vary among maize populations with implications for improving quantitative traits

AbstractThe goal of transgenesis in plant breeding is to make step‐change improvements in traits of interest. However, improving quantitative traits, such as yield in maize (Zea mays L.), with transgenes has been difficult. Traditionally, transgene testing is done on a few isogenic lines, and results are extrapolated to entire breeding populations. Testing on limited germplasm does not provide a robust estimate of a transgene's value. Incorporating transgenes directly into breeding populations could increase genetic variance and the rate of genetic gain. Here, we used a transgene that reduces ethylene as a case study and investigated event, transgene, family, and environment effects and their interactions. We also determined whether introduction of the transgene into a breeding population would result in transgenic lines being preferentially selected over nontransgenic lines for yield. We found significant variation in transgene effects across clustered environments and families for multiple traits including yield. In environmental Cluster 2, the transgenic lines yielded 0.4 Mg ha−1 more than nontransgenic lines in family KC22; yet, in family QY43, transgenic lines yielded 0.3 Mg ha−1 less. Similarly, within Cluster 4, the QY43 family had preferential selection of transgenic over nontransgenic lines, whereas in families YE41 and AY91, nontransgenic lines were selected more frequently. These results show the critical importance of evaluating transgenes across broad germplasm diversity to assess their general value to a program. Integrating transgenes, or using gene editing, directly in a breeding program can expand genetic variation for quantitative traits and potentially accelerate genetic gain.

Genetic Studies on Variability, Heritability and Genetic Gain of Yield and Yield Related Traits in Foxtail Millets (Setaria italic L.)

The present work comprised of 40 foxtail millet advanced breeding lines obtained from small millet scheme, MARS, Dharwad. These lines with checks viz., DHFT-109-3 and HMT-100-1 were evaluated in replicated yield trial at millet scheme, MARS, Dharwad, during rabi 2020-21 for assessing genetic variability, heritability, and genetic gain among 17 traits. Wide range of variation provides an ample scope for selection of superior and desired advanced breeding lines by the plant breeders for further improvement of these characters. The phenotypic coefficient of variation (PCV) was higher than genotypic coefficient of variation (GCV) for all the traits under study. In the present study foxtail millet advanced breeding lines exhibited moderate PCV and GCV for the most important economic traits viz., panicle length (18.01 and 15.85 % 15.85% and18.01%), panicle girth (15.25% and 15.45%), productive tiller per plant (18.44% and 19.40%) and straw yield per hectare (19.92% and 21.39%). The high phenotypic coefficient of variation and genotypic coefficient of variation were observed for characters viz., specific leaf area (21.08% and 22.44%), specific leaf weight (20.52% and 26.72%), grain yield per plant (9.32% and 10.99 %), grain yield per plot (8.85 % and 10.49%) and straw yield per ha (19.92 and 21.39). Most of the traits viz., plant height(79 %), flag leaf length(98%), flag leaf width ( 80%), number of productive tillers per plant (90%), panicle length(98%), panicle girth (97 %), SPAD at 50 per cent flowering (92%), test weight (63%), specific leaf area (88%), specific leaf weight (87%), grain yield per plant(71%) and straw yield per hectare (87%) showed the high estimates of broad sense heritability (h2 b) indicating the reliability of the estimates for variation between advanced breeding lines and effectiveness of selection.

Climate data integration into wheat performance evaluation reveals large inter-varietal responses

Abstract There is an urgent need to adapt crop breeding strategies to boost resilience in the face of a growing food demand and a changing climate. Achieving this requires an understanding of how weather and climate variability impacts crop growth and development. Using the United Kingdom (UK) as an example, we evaluate changes in the UK agroclimate and analyse how these have influenced domestic wheat production. Here we quantify spatial and temporal variability and changes in weather and climate across growing seasons over the last four decades (1981-2020). Drawing on variety trial data, we then use statistical modelling to explore the interaction between genotype and agroclimate variation. 
We show that changes in the UK agroclimate present both risks, and opportunities for wheat growers, depending on location. From 1981-2020, in Wales, the West Midlands, large parts of the North West, and Northern Ireland, there was an overall increase in frost risk in early spring of 0.15 additional frost days per year, whilst in the East early frost risk decreased by up to 0.29 days per year. Meanwhile, over the period 1987-2020, surface incoming shortwave radiation during grainfill increased in the East by up to 13% but decreased in Western areas by up to 15%. We show significant inter-varietal differences in yield responses to growing degree days, heavy rainfall and the occurrence of late frost. This highlights the importance of evaluating variety-climate interactions in variety trial analyses, and in climate-optimised selection of crops and varieties by growers. This work provides guidance for future research on how climate change is affecting the UK agroclimate and resulting impacts on winter cereal production.

Refining penalized ridge regression: a novel method for optimizing the regularization parameter in genomic prediction

Abstract The popularity of genomic selection as an efficient and cost-effective approach to estimate breeding values continues to increase, due in part to the significant saving in phenotyping. Ridge regression is one of the most popular methods used for genomic prediction; however, its efficiency (in terms of prediction performance) depends on the appropriate tunning of the penalization parameter. In this paper we propose a novel, more efficient method to select the optimal penalization parameter for Ridge regression. We compared the proposed method with the conventional method to select the penalization parameter in 14 real data sets and we found that in 13 of these, the proposed method outperformed the conventional method and across data sets the gains in prediction accuracy in terms of Pearson's correlation was of 56.15%, with not-gains observed in terms of normalized mean square error. Finally, our results show evidence of the potential of the proposed method, and we encourage its adoption to improve the selection of candidate lines in the context of plant breeding.

Participatory research at scale: A comparative analysis of four approaches to large-scale agricultural technology testing with farmers

Tailoring agricultural technology options to the diverse conditions of smallholder farmers requires innovative approaches for testing these technologies with farmers across varied contexts, while incorporating their feedback into learning and decision-making processes. This study compares four such approaches: the Farmer Field School on Participatory Plant Breeding (FFS-PPB), Farmer Research Network (FRN), Crowdsourcing–Triadic comparisons of technologies (Tricot), and adapted Mother–Baby Trial (MBT) as implemented by four concrete projects. The objectives are to provide detailed descriptions of these approaches and their project-specific implementations, identify and analyze common aspects and differences, and derive insights to guide future farmer-inclusive projects aiming at contextual scaling of agricultural technologies. A literature review, key informant interviews, and a systematic content analysis were conducted for the analysis. Common features include cascade training models, simple farmer-managed experiments, and the use of digital tools for data collection. Major differences lie in the extent of farmer–researcher collaboration and decision-making, as well as how technology option-by-context interactions are addressed. The FRN, FFS-PPB, and adapted MBT approaches involve farmers in decision-making throughout most stages of research, including co-learningcycles that adapt the research design and technology options to farmers’ needs. Although these approaches require more training and expertise, they increase the likelihood of achieving relevant results that farmers can implement in practice. In contrast, more standardized approaches like the Crowdsourcing–Tricot streamline the implementation, data management and analysis of large-scale trials, but have limitations in capturing the underlying reasons for farmers’ preferences. Among the studied approaches, the FRN as implemented by the Women's Fields project in Niger is particularly effective in identifying which options best suit specific farming contexts.

Omics based approaches to decipher the leaf ionome and transcriptome changes in Solanum lycopersicum L. upon Tomato Brown Rugose Fruit Virus (ToBRFV) infection.

The Tomato Brown Rugose Fruit Virus (ToBRFV) is a pathogen that mostly affects plants from the Solanaceae family. This virus severely affects the yield of tomato (Solanum lycopersicum L.) plants, thus creating an urgent need to research the basis of resistance to manage the disease. To understand the molecular basis of resistance, we employed omics-based approaches involving leaf ionomics and transcriptomics to help us decipher the interaction between elemental and nutritional composition and investigate its effect on the gene expression profile upon the ToBRFV infection in tomatoes. Ionomics was used to investigate the accumulation of trace elements in leaves, showcasing that the plants resistant to the virus had significantly higher concentrations of iron (p-value = 0.039) and nickel (p-value = 0.042) than the susceptible ones. By correlating these findings with transcriptomics, we identified some key genes involved in iron homeostasis and abscisic acid pathways, potentially responsible for conferring resistance against the pathogen. From the obtained list of differentially expressed genes, a panel of mutation profile was discovered with three important genes-Solyc02g068590.3.1 (K+ transporter), Solyc01g111890.3.1 (LRR), and Solyc02g061770.4.1 (Chitinase) showing persistent missense mutations. We ascertain the role of these genes and establish their association with plant resistance using genotyping assays in various tomato lines. The targeted selection of these genetic determinants can further enhance plant breeding and crop yield management strategies.

Canadian Organic Wheat Breeding with On-farm Selection: A Case Study using Landrace and Modern Parents

Participatory plant breeding (PPB) has the potential to be an alternative to a centralized breeding model for niche markets that are historically underserved. Our objectives were to evaluate the performance of two parental cultivars from a Canadian PPB program: a modern spring wheat (Triticum aestivum L.) cultivar (5602HR) and a landrace (Red Fife) - with the progeny of the cross when selected by two farmers located 1800 km apart (denoted Farm1 and Farm2) and evaluate progeny differences from each other under organic conditions. Red Fife was 18 cm taller, matured 5 days later, had greater lodging susceptibility, greater seed mass, and 3.5% lower protein concentration than 5602HR. Farmer genotypes were similar to 5602HR in protein concentration and lodging severity, and similar to Red Fife in plant height (14 cm taller than 5602HR) and seed mass. Farmer genotypes did not yield differently from either parent. Farmer genotypes did not differ from each other in most parameters measured, however, Farm1 had greater lodging resistance under high fertility conditions than Farm2 despite similar plant height. This research provides a proof of concept for the role that farmer selectors can play in selecting for positive traits for organic production and provide insight into organic farmers’ preferences. The research also demonstrated that using an older landrace (ie., Red Fife) allowed positive features such as tall stature to be incorporated into the resulting progeny.

Genetic Variability Studies in Chickpea (Cicer arietinum L.) for Yield and Contributing Traits Through Half-diallel Mating Strategy under Late-sown Conditions

Background: One of the oldest cultivated legumes, chickpeas (Cicer arietinum L.), are essential for world nutrition, especially with climate change. Chickpea output is poor despite rising demand for its nutritional value. Improved genetics can enhance yields to fulfil local and global demands. By selecting better parents and potential hybrids utilising half-diallel mating, breeders can hasten the development of high-yielding, durable cultivars. Methods: This study examined 55 half-diallel mating genotypes, comprising 10 parental lines and 45 F1 hybrids. At the Acharya Narendra Deva University of Agriculture and Technology Genetics and Plant Breeding Farm in Ayodhya, U.P., these were evaluated using a randomised block design with three replications under late-sown circumstances in 2022-23 rabi. Normal agricultural procedures were used. A four-meter row of each genotype was planted with 30 cm between rows and 10 cm between plants. Genetic indices like GCV, PCV, heritability, genetic progress, correlation coefficient and path analysis were evaluated. Result: ANOVA revealed significant genetic variability across all traits. Biological yield plant-1 had the highest PCV and GCV, followed by seed yield plant-1. Heritability and genetic progress were highest for days to 50% flowering and biological yield plant-1, indicating strong genetic control. Days to 50% flowering and maturity inversely linked with most yield-related characteristics. Seed yield was closely associated with primary and secondary branches plant-1, plant height, pods per plant, seeds pod-1, 100-seed weight and biological yield. Path coefficient study showed that all characteristics except days to 50% flowering, days to maturity and plant height influenced grain yield.

Masculinities in a feminist pedagogy: lessons for transformative gender and agriculture training

Masculinities and femininities are closely interconnected with men and women farmers’ everyday lives; hence critical reflection on these interconnections should be central in gender training in agriculture. While a focus on men and masculinities is crucial for sustainable transformation of deep-rooted gender norms and practices that limit the attainment of gender equality, there are insufficient empirically tested pedagogical models for this purpose. We share a case study, the Gender Responsive Researchers Equipped for Agricultural Transformation (GREAT) model, which incorporates masculinities in a feminist pedagogy. We use external monitoring, evaluation, and learning data for two case study courses that integrate gender in plant breeding, seed systems, and agronomy to demonstrate the efficacy of integrating the concept of masculinity and reflections on male farmers’ expectations, behaviors, and practices within a feminist approach to gender training. We conclude that feminist pedagogical practices offer insights into how gender training can integrate a masculinities perspective to move beyond divisive and narrow gender polarities towards addressing masculine norms that often hinder the attainment of gender transformation.