CoPheScan: phenome-wide association studies accounting for linkage disequilibrium.

Phenome-wide association studies (PheWAS) facilitate the discovery of associations between a single genetic variant with multiple phenotypes. For variants which impact a specific protein, this can help identify additional therapeutic indications or on-target side effects of intervening on that protein. However, PheWAS is restricted by an inability to distinguish confounding due to linkage disequilibrium (LD) from true pleiotropy. Here we describe CoPheScan (Coloc adapted Phenome-wide Scan), a Bayesian approach that enables an intuitive and systematic exploration of causal associations while simultaneously addressing LD confounding. We demonstrate its performance through simulation, showing considerably better control of false positive rates than a conventional approach not accounting for LD. We used CoPheScan to perform PheWAS of protein-truncating variants and fine-mapped variants from disease and pQTL studies, in 2275 disease phenotypes from the UK Biobank. Our results identify the complexity of known pleiotropic genes such as APOE, and suggest a new causal role for TGM3 in skin cancer.

GILEA: In silico phenome profiling and editing using GAN Inversion.

BACKGROUND: Modeling heterogeneous disease states by data-driven methods has great potential to advance biomedical research. However, a comprehensive analysis of phenotypic heterogeneity is often challenged by the complex nature of biomedical datasets and emerging imaging methodologies. METHODS: Here, we propose a novel GAN Inversion-enabled Latent Eigenvalue Analysis (GILEA) framework and apply it to in silico phenome profiling and editing. RESULTS: We show the performance of GILEA using cellular imaging datasets stained with the multiplexed fluorescence Cell Painting protocol. The quantitative results of GILEA can be biologically supported by editing of the latent representations and simulation of dynamic phenotype transitions between physiological and pathological states. CONCLUSION: In conclusion, GILEA represents a new and broadly applicable approach to the quantitative and interpretable analysis of biomedical image data. The GILEA code and video demos are available at https://github.com/CTPLab/GILEA.

Feature engineering and parameter tuning: improving phenomic prediction ability in multi-environmental durum wheat breeding trials.

KEY MESSAGE: Optimized phenomic selection in durum wheat uses near-infrared spectra, feature engineering and parameter tuning. Our study reports improvements in predictive ability and emphasizes customized preprocessing for different traits and models. The success of plant breeding programs depends on efficient selection decisions. Phenomic selection has been proposed as a tool to predict phenotype performance based on near-infrared spectra (NIRS) to support selection decisions. In this study, we test the performance of phenomic selection in multi-environmental trials from our durum wheat breeding program for three breeding scenarios and use feature engineering as well as parameter tuning to improve the phenomic prediction ability. In addition, we investigate the influence of genotype and environment on the phenomic prediction ability for agronomic and quality traits. Preprocessing, based on a grid search over the Savitzky-Golay filter parameters based on 756,000 genotype best linear unbiased estimate (BLUE) computations, improved the phenomic prediction ability by up to 1500% (0.02-0.3). Furthermore, we show that preprocessing should be optimized depending on the dataset, trait, and model used for prediction. The phenomic prediction scenarios in our durum breeding program resulted in low-to-moderate prediction abilities with the highest and most stable prediction results when predicting new genotypes in the same environment as used for model training. This is consistent with the finding that NIRS capture both the genotype and genotype-by-environment ( G × E ) interaction variance.

Phenomics in Livestock Research: Bottlenecks and Promises of Digital Phenotyping and Other Quantification Techniques on a Global Scale.

Bottlenecks in moving genomics to real-life applications also include phenomics. This is true not only for genomics medicine and public health genomics but also in ecology and livestock phenomics. This expert narrative review explores the intricate relationship between genetic makeup and observable phenotypic traits across various biological levels in the context of livestock research. We unpack and emphasize the significance of precise phenotypic data in selective breeding outcomes and examine the multifaceted applications of phenomics, ranging from improvement to assessing welfare, reproductive traits, and environmental adaptation in livestock. As phenotypic traits exhibit strong correlations, their measurement alongside specific biological outcomes provides insights into performance, overall health, and clinical endpoints like morbidity and disease. In addition, automated assessment of livestock holds potential for monitoring the dynamic phenotypic traits across various species, facilitating a deeper comprehension of how they adapt to their environment and attendant stressors. A key challenge in genetic improvement in livestock is predicting individuals with optimal fitness without direct measurement. Temporal predictions from unmanned aerial systems can surpass genomic predictions, offering in-depth data on livestock. In the near future, digital phenotyping and digital biomarkers may further unravel the genetic intricacies of stress tolerance, adaptation and welfare aspects of animals enabling the selection of climate-resilient and productive livestock. This expert review thus delves into challenges associated with phenotyping and discusses technological advancements shaping the future of biological research concerning livestock.

Toward Next-Generation Phenomics: Precision Medicine, Spaceflight, Astronaut Omics, and Beyond.

Large investments over many decades in genomics in diverse fields such as precision medicine, plant biology, and recently, in space life science research and astronaut omics were not accompanied by a commensurate focus on high-throughput and granular characterization of phenotypes, thus resulting in a "phenomics lag" in systems science. There are also limits to what can be achieved through increases in sample sizes in genotype-phenotype association studies without commensurate advances in phenomics. These challenges beg a question. What might next-generation phenomics look like, given that the Internet of Things and artificial intelligence offer prospects and challenges for high-throughput digital phenotyping as a key component of next-generation phenomics? While attempting to answer this question, I also reflect on governance of digital technology and next-generation phenomics. I argue that it is timely to broaden the technical discourses through a lens of political theory. In this context, this analysis briefly engages with the recent book "The Earthly Community: Reflections on the Last Utopia," written by the historian and political theorist Achille Mbembe. The question posed by the book, "Will we be able to invent different modes of measuring that might open up the possibility of a different aesthetics, a different politics of inhabiting the Earth, of repairing and sharing the planet?" is directly relevant to healing of human diseases in ways that are cognizant of the interdependency of human and nonhuman animal health, and critical and historically informed governance of digital technologies that promise to benefit next-generation phenomics.

Genomic and phenomic predictions help capture low-effect alleles promoting seed germination in oilseed rape in addition to QTL analyses.

KEY MESSAGE: Phenomic prediction implemented on a large diversity set can efficiently predict seed germination, capture low-effect favorable alleles that are not revealed by GWAS and identify promising genetic resources. Oilseed rape faces many challenges, especially at the beginning of its developmental cycle. Achieving rapid and uniform seed germination could help to ensure a successful establishment and therefore enabling the crop to compete with weeds and tolerate stresses during the earliest developmental stages. The polygenic nature of seed germination was highlighted in several studies, and more knowledge is needed about low- to moderate-effect underlying loci in order to enhance seed germination effectively by improving the genetic background and incorporating favorable alleles. A total of 17 QTL were detected for seed germination-related traits, for which the favorable alleles often corresponded to the most frequent alleles in the panel. Genomic and phenomic predictions methods provided moderate-to-high predictive abilities, demonstrating the ability to capture small additive and non-additive effects for seed germination. This study also showed that phenomic prediction estimated phenotypic values closer to phenotypic values than GEBV. Finally, as the predictive ability of phenomic prediction was less influenced by the genetic structure of the panel, it is worth using this prediction method to characterize genetic resources, particularly with a view to design prebreeding populations.

Phenome-wide identification of therapeutic genetic targets, leveraging knowledge graphs, graph neural networks, and UK Biobank data.

The ongoing expansion of human genomic datasets propels therapeutic target identification; however, extracting gene-disease associations from gene annotations remains challenging. Here, we introduce Mantis-ML 2.0, a framework integrating AstraZeneca's Biological Insights Knowledge Graph and numerous tabular datasets, to assess gene-disease probabilities throughout the phenome. We use graph neural networks, capturing the graph's holistic structure, and train them on hundreds of balanced datasets via a robust semi-supervised learning framework to provide gene-disease probabilities across the human exome. Mantis-ML 2.0 incorporates natural language processing to automate disease-relevant feature selection for thousands of diseases. The enhanced models demonstrate a 6.9% average classification power boost, achieving a median receiver operating characteristic (ROC) area under curve (AUC) score of 0.90 across 5220 diseases from Human Phenotype Ontology, OpenTargets, and Genomics England. Notably, Mantis-ML 2.0 prioritizes associations from an independent UK Biobank phenome-wide association study (PheWAS), providing a stronger form of triaging and mitigating against underpowered PheWAS associations. Results are exposed through an interactive web resource.

Field-based high-throughput phenotyping enhances phenomic and genomic predictions for grain yield and plant height across years in maize.

Field-based phenomic prediction employs novel features, like vegetation indices (VIs) from drone images, to predict key agronomic traits in maize, despite challenges in matching biomarker measurement time points across years or environments. This study utilized functional principal component analysis (FPCA) to summarize the variation of temporal VIs, uniquely allowing the integration of this data into phenomic prediction models tested across multiple years (2018-2021) and environments. The models, which included 1 genomic, 2 phenomic, 2 multikernel, and 1 multitrait type, were evaluated in 4 prediction scenarios (CV2, CV1, CV0, and CV00), relevant for plant breeding programs, assessing both tested and untested genotypes in observed and unobserved environments. Two hybrid populations (415 and 220 hybrids) demonstrated the visible atmospherically resistant index's strong temporal correlation with grain yield (up to 0.59) and plant height. The first 2 FPCAs explained 59.3 ± 13.9% and 74.2 ± 9.0% of the temporal variation of temporal data of VIs, respectively, facilitating predictions where flight times varied. Phenomic data, particularly when combined with genomic data, often were comparable to or numerically exceeded the base genomic model in prediction accuracy, particularly for grain yield in untested hybrids, although no significant differences in these models' performance were consistently observed. Overall, this approach underscores the effectiveness of FPCA and combined models in enhancing the prediction of grain yield and plant height across environments and diverse agricultural settings.

Near-infrared reflectance spectroscopy phenomic prediction can perform similarly to genomic prediction of maize agronomic traits across environments.

For nearly two decades, genomic prediction and selection have supported efforts to increase genetic gains in plant and animal improvement programs. However, novel phenomic strategies for predicting complex traits in maize have recently proven beneficial when integrated into across-environment sparse genomic prediction models. One phenomic data modality is whole grain near-infrared spectroscopy (NIRS), which records reflectance values of biological samples (e.g., maize kernels) based on chemical composition. Predictions of hybrid maize grain yield (GY) and 500-kernel weight (KW) across 2 years (2011-2012) and two management conditions (water-stressed and well-watered) were conducted using combinations of reflectance data obtained from high-throughput, F2 whole-kernel scans and genomic data obtained from genotyping-by-sequencing within four different cross-validation (CV) schemes (CV2, CV1, CV0, and CV00). When predicting the performance of untested genotypes in characterized (CV1) environments, genomic data were better than phenomic data for GY (0.689 ± 0.024-genomic vs. 0.612 ± 0.045-phenomic), but phenomic data were better than genomic data for KW (0.535 ± 0.034-genomic vs. 0.617 ± 0.145-phenomic). Multi-kernel models (combinations of phenomic and genomic relationship matrices) did not surpass single-kernel models for GY prediction in CV1 or CV00 (prediction of untested genotypes in uncharacterized environments); however, these models did outperform the single-kernel models for prediction of KW in these same CVs. Lasso regression applied to the NIRS data set selected a subset of 216 NIRS bands that achieved comparable prediction abilities to the full phenomic data set of 3112 bands predicting GY and KW under CV1 and CV00.

Abdominal CT metrics in 17,646 patients reveal associations between myopenia, myosteatosis, and medical phenotypes: a phenome-wide association study.

BACKGROUND: Deep learning facilitates large-scale automated imaging evaluation of body composition. However, associations of body composition biomarkers with medical phenotypes have been underexplored. Phenome-wide association study (PheWAS) techniques search for medical phenotypes associated with biomarkers. A PheWAS integrating large-scale analysis of imaging biomarkers and electronic health record (EHR) data could discover previously unreported associations and validate expected associations. Here we use PheWAS methodology to determine the association of abdominal CT-based skeletal muscle metrics with medical phenotypes in a large North American cohort. METHODS: An automated deep learning pipeline was used to measure skeletal muscle index (SMI; biomarker of myopenia) and skeletal muscle density (SMD; biomarker of myosteatosis) from abdominal CT scans of adults between 2012 and 2018. A PheWAS was performed with logistic regression using patient sex and age as covariates to assess for associations between CT-derived muscle metrics and 611 common EHR-derived medical phenotypes. PheWAS P values were considered significant at a Bonferroni corrected threshold (α = 0.05/1222). FINDINGS: 17,646 adults (mean age, 56 years ± 19 [SD]; 57.5% women) were included. CT-derived SMI was significantly associated with 268 medical phenotypes; SMD with 340 medical phenotypes. Previously unreported associations with the highest magnitude of significance included higher SMI with decreased cardiac dysrhythmias (OR [95% CI], 0.59 [0.55-0.64]; P < 0.0001), decreased epilepsy (OR, 0.59 [0.50-0.70]; P < 0.0001), and increased elevated prostate-specific antigen (OR, 1.84 [1.47-2.31]; P < 0.0001), and higher SMD with decreased decubitus ulcers (OR, 0.36 [0.31-0.42]; P < 0.0001), sleep disorders (OR, 0.39 [0.32-0.47]; P < 0.0001), and osteomyelitis (OR, 0.43 [0.36-0.52]; P < 0.0001). INTERPRETATION: PheWAS methodology reveals previously unreported associations between CT-derived biomarkers of myopenia and myosteatosis and EHR medical phenotypes. The high-throughput PheWAS technique applied on a population scale can generate research hypotheses related to myopenia and myosteatosis and can be adapted to research possible associations of other imaging biomarkers with hundreds of EHR medical phenotypes. FUNDING: National Institutes of Health, Stanford AIMI-HAI pilot grant, Stanford Precision Health and Integrated Diagnostics, Stanford Cardiovascular Institute, Stanford Center for Digital Health, and Stanford Knight-Hennessy Scholars.

Distinguishing heart failure with reduced ejection fraction from heart failure with preserved ejection fraction: A phenomics approach.

AIM: Pathophysiological differences between patients with heart failure with preserved (HFpEF) and reduced (HFrEF) ejection fraction (EF) remain unclear. Therefore we used a phenomics approach, integrating selected proteomics data with patient characteristics and cardiac structural and functional parameters, to get insight into differential pathophysiological mechanisms and identify potential treatment targets. METHODS AND RESULTS: We report data from a representative subcohort of the prospective Singapore Heart Failure Outcomes and Phenotypes (SHOP), including patients with HFrEF (EF <40%, n = 217), HFpEF (EF ≥50%, n = 213), and age- and sex-matched controls without HF (n = 216). We measured 92 biomarkers using a proximity extension assay and assessed cardiac structure and function in all participants using echocardiography. We used multi-block projection to latent structure analysis to integrate clinical, echocardiographic, and biomarker variables. Candidate biomarker targets were cross-referenced with small-molecule and drug databases. The total cohort had a median age of 65 years (interquartile range 60-71), and 50% were women. Protein profiles strongly discriminated patients with HFrEF (area under the curve [AUC] = 0.89) and HFpEF (AUC = 0.94) from controls. Phenomics analyses identified unique druggable inflammatory markers in HFpEF from the tumour necrosis factor receptor superfamily (TNFRSF), which were positively associated with hypertension, diabetes, and increased posterior and relative wall thickness. In HFrEF, interleukin (IL)-8 and IL-6 were possible targets related to lower EF and worsening renal function. CONCLUSION: We identified pathophysiological mechanisms related to increased cardiac wall thickness parameters and potentially druggable inflammatory markers from the TNFRSF in HFpEF.

A hypothesis-driven study to comprehensively investigate the association between genetic polymorphisms in EPHX2 gene and cardiovascular diseases: Findings from the UK Biobank.

BACKGROUND: Epoxyeicosatrienoic acids (EETs) are protective factors against cardiovascular diseases (CVDs) because of their vasodilatory, cholesterol-lowering, and anti-inflammatory effects. Soluble epoxide hydrolase (sEH), encoded by the EPHX2 gene, degrades EETs into less biologically active metabolites. EPHX2 is highly polymorphic, and genetic polymorphisms in EPHX2 have been linked to various types of CVDs, such as coronary heart disease, essential hypertension, and atrial fibrillation recurrence. METHODS: Based on a priori hypothesis that EPHX2 genetic polymorphisms play an important role in the pathogenesis of CVDs, we comprehensively investigated the associations between 210 genetic polymorphisms in the EPHX2 gene and an array of 118 diseases in the circulatory system using a large sample from the UK Biobank (N = 307,516). The diseases in electronic health records were mapped to the phecode system, which was more representative of independent phenotypes. Survival analyses were employed to examine the effects of EPHX2 variants on CVD incidence, and a phenome-wide association study was conducted to study the impact of EPHX2 polymorphisms on 62 traits, including blood pressure, blood lipid levels, and inflammatory indicators. RESULTS: A novel association between the intronic variant rs116932590 and the phenotype "aneurysm and dissection of heart" was identified. In addition, the rs149467044 and rs200286838 variants showed nominal evidence of association with arterial aneurysm and cerebrovascular disease, respectively. Furthermore, the variant rs751141, which was linked with a lower hydrolase activity of sEH, was significantly associated with metabolic traits, including blood levels of triglycerides, creatinine, and urate. CONCLUSIONS: Multiple novel associations observed in the present study highlight the important role of EPHX2 genetic variation in the pathogenesis of CVDs.

Phenome-wide association study (PheWAS) of colorectal cancer risk SNP effects on health outcomes in UK Biobank.

BACKGROUND: Associations between colorectal cancer (CRC) and other health outcomes have been reported, but these may be subject to biases, or due to limitations of observational studies. METHODS: We set out to determine whether genetic predisposition to CRC is also associated with the risk of other phenotypes. Under the phenome-wide association study (PheWAS) and tree-structured phenotypic model (TreeWAS), we studied 334,385 unrelated White British individuals (excluding CRC patients) from the UK Biobank cohort. We generated a polygenic risk score (PRS) from CRC genome-wide association studies as a measure of CRC risk. We performed sensitivity analyses to test the robustness of the results and searched the Danish Disease Trajectory Browser (DTB) to replicate the observed associations. RESULTS: Eight PheWAS phenotypes and 21 TreeWAS nodes were associated with CRC genetic predisposition by PheWAS and TreeWAS, respectively. The PheWAS detected associations were from neoplasms and digestive system disease group (e.g. benign neoplasm of colon, anal and rectal polyp and diverticular disease). The results from the TreeWAS corroborated the results from the PheWAS. These results were replicated in the observational data within the DTB. CONCLUSIONS: We show that benign colorectal neoplasms share genetic aetiology with CRC using PheWAS and TreeWAS methods. Additionally, CRC genetic predisposition is associated with diverticular disease.

Plant phenomics & precision agriculture simulation of winter wheat growth by the assimilation of unmanned aerial vehicle imagery into the WOFOST model.

The aim of this study is to optimize the simulation result of the WOFOST model and explore the possibility of assimilating unmanned aerial vehicle (UAV) imagery into this model. Field images of wheat during its key growth stages are acquired with a UAV, and the corresponding leaf area index (LAI), biomass, and final yield are experimentally measured. LAI data is retrieved from the UAV imagery and assimilated into a localized WOFOST model using least squares optimization. Sensitive parameters, i.e., specific leaf area (SLATB0, SLATB0.5, SLATB2) and maximum CO2 assimilation rate (AMAXTB1, AMAXTB1.3) are adjusted to minimize the discrepancy between the LAI obtained from the model simulation and inversion of the UAV data. The results show that the assimilated model provides a better estimation of the growth and development of winter wheat in the study area. The R2, RMSE, and NRMSE of winter wheat LAI simulated with the assimilated WOFOST model are 0.8812, 0.49, and 23.5% respectively. The R2, RMSE, and NRMSE of the simulated yield are 0.9489, 327.06 kg·hm-2, and 6.5%. The accuracy in model simulation of winter wheat growth is improved, which demonstrates the feasibility of integrating UAV data into crop models.

Using genetics to detangle the relationships between red cell distribution width and cardiovascular diseases: a unique role for body mass index.

OBJECTIVE: Red cell distribution width (RDW) is an enigmatic biomarker associated with the presence and severity of multiple cardiovascular diseases (CVDs). It is unclear whether elevated RDW contributes to, results from, or is pleiotropically related to CVDs. We used contemporary genetic techniques to probe for evidence of aetiological associations between RDW, CVDs, and CVD risk factors. METHODS: Using an electronic health record (EHR)-based cohort, we built and deployed a genetic risk score (GRS) for RDW to test for shared genetic architecture between RDW and the cardiovascular phenome. We also created GRSs for common CVDs (coronary artery disease, heart failure, atrial fibrillation, peripheral arterial disease, venous thromboembolism) and CVD risk factors (body mass index (BMI), low-density lipoprotein, high-density lipoprotein, systolic blood pressure, diastolic blood pressure, serum triglycerides, estimated glomerular filtration rate, diabetes mellitus) to test each for association with RDW. Significant GRS associations were further interrogated by two-sample Mendelian randomisation (MR). In a separate EHR-based cohort, RDW values from 1-year pre-gastric bypass surgery and 1-2 years post-gastric bypass surgery were compared. RESULTS: In a cohort of 17 937 subjects, there were no significant associations between the RDW GRS and CVDs. Of the CVDs and CVD risk factors, only genetically predicted BMI was associated with RDW. In subsequent analyses, BMI was associated with RDW by multiple MR methods. In subjects undergoing bariatric surgery, RDW decreased postsurgery and followed a linear relationship with BMI change. CONCLUSIONS: RDW is unlikely to be aetiologically upstream or downstream of CVDs or CVD risk factors except for BMI. Genetic and clinical association analyses support an aetiological relationship between BMI and RDW.

High-Throughput Phenotyping Methods for Breeding Drought-Tolerant Crops.

Drought is a main factor limiting crop yields. Modern agricultural technologies such as irrigation systems, ground mulching, and rainwater storage can prevent drought, but these are only temporary solutions. Understanding the physiological, biochemical, and molecular reactions of plants to drought stress is therefore urgent. The recent rapid development of genomics tools has led to an increasing interest in phenomics, i.e., the study of phenotypic plant traits. Among phenomic strategies, high-throughput phenotyping (HTP) is attracting increasing attention as a way to address the bottlenecks of genomic and phenomic studies. HTP provides researchers a non-destructive and non-invasive method yet accurate in analyzing large-scale phenotypic data. This review describes plant responses to drought stress and introduces HTP methods that can detect changes in plant phenotypes in response to drought.

A phenomics approach for antiviral drug discovery.

BACKGROUND: The emergence and continued global spread of the current COVID-19 pandemic has highlighted the need for methods to identify novel or repurposed therapeutic drugs in a fast and effective way. Despite the availability of methods for the discovery of antiviral drugs, the majority tend to focus on the effects of such drugs on a given virus, its constituent proteins, or enzymatic activity, often neglecting the consequences on host cells. This may lead to partial assessment of the efficacy of the tested anti-viral compounds, as potential toxicity impacting the overall physiology of host cells may mask the effects of both viral infection and drug candidates. Here we present a method able to assess the general health of host cells based on morphological profiling, for untargeted phenotypic drug screening against viral infections. RESULTS: We combine Cell Painting with antibody-based detection of viral infection in a single assay. We designed an image analysis pipeline for segmentation and classification of virus-infected and non-infected cells, followed by extraction of morphological properties. We show that this methodology can successfully capture virus-induced phenotypic signatures of MRC-5 human lung fibroblasts infected with human coronavirus 229E (CoV-229E). Moreover, we demonstrate that our method can be used in phenotypic drug screening using a panel of nine host- and virus-targeting antivirals. Treatment with effective antiviral compounds reversed the morphological profile of the host cells towards a non-infected state. CONCLUSIONS: The phenomics approach presented here, which makes use of a modified Cell Painting protocol by incorporating an anti-virus antibody stain, can be used for the unbiased morphological profiling of virus infection on host cells. The method can identify antiviral reference compounds, as well as novel antivirals, demonstrating its suitability to be implemented as a strategy for antiviral drug repurposing and drug discovery.

High-throughput phenotyping to dissect genotypic differences in safflower for drought tolerance.

Drought is one of the most severe and unpredictable abiotic stresses, occurring at any growth stage and affecting crop yields worldwide. Therefore, it is essential to develop drought tolerant varieties to ensure sustainable crop production in an ever-changing climate. High-throughput digital phenotyping technologies in tandem with robust screening methods enable precise and faster selection of genotypes for breeding. To investigate the use of digital imaging to reliably phenotype for drought tolerance, a genetically diverse safflower population was screened under different drought stresses at Agriculture Victoria's high-throughput, automated phenotyping platform, Plant Phenomics Victoria, Horsham. In the first experiment, four treatments, control (90% field capacity; FC), 40% FC at initial branching, 40% FC at flowering and 50% FC at initial branching and flowering, were applied to assess the performance of four safflower genotypes. Based on these results, drought stress using 50% FC at initial branching and flowering stages was chosen to further screen 200 diverse safflower genotypes. Measured plant traits and dry biomass showed high correlations with derived digital traits including estimated shoot biomass, convex hull area, caliper length and minimum area rectangle, indicating the viability of using digital traits as proxy measures for plant growth. Estimated shoot biomass showed close association having moderately high correlation with drought indices yield index, stress tolerance index, geometric mean productivity, and mean productivity. Diverse genotypes were classified into four clusters of drought tolerance based on their performance (seed yield and digitally estimated shoot biomass) under stress. Overall, results show that rapid and precise image-based, high-throughput phenotyping in controlled environments can be used to effectively differentiate response to drought stress in a large numbers of safflower genotypes.