Major Principal Components Research Articles

Transcriptome- and DNA methylation-based cell-type deconvolutions produce similar estimates of differential gene expression and differential methylation

BackgroundChanging cell-type proportions can confound studies of differential gene expression or DNA methylation (DNAm) from peripheral blood mononuclear cells (PBMCs). We examined how cell-type proportions derived from the transcriptome versus the methylome (DNAm) influence estimates of differentially expressed genes (DEGs) and differentially methylated positions (DMPs).MethodsTranscriptome and DNAm data were obtained from PBMC RNA and DNA of Kenyan children (n = 8) before, during, and 6 weeks following uncomplicated malaria. DEGs and DMPs between time points were detected using cell-type adjusted modeling with Cibersortx or IDOL, respectively.ResultsMost major cell types and principal components had moderate to high correlation between the two deconvolution methods (r = 0.60–0.96). Estimates of cell-type proportions and DEGs or DMPs were largely unaffected by the method, with the greatest discrepancy in the estimation of neutrophils.ConclusionVariation in cell-type proportions is captured similarly by both transcriptomic and methylome deconvolution methods for most major cell types.

Principal Component Analysis of Cognitive Executive Function: A Predictive Model of Academic Performance of Students in Mathematics in Secondary Schools

There is a growing interest from instructional scientists in using parameters of brain executive functions to unfold cognitive disorders, Mathematical Learning Difficulties (MLD), and assessment of learners’ academic performance. Thus, it is imperative to investigates, extracts and classify the major principal components of learners’ cognitive executive functions that predict academic performance of students in Mathematics and science related courses in secondary schools. An ex post facto quasi-experimental design was adopted for the study. Students’ cognitive profile was measured using a validated and reliable cognitive assessment Battery (CAB) application. There were significant positive correlations between cognitive executive functions and academic performance of students in Mathematics. The major components of the executive functions that accounted for substantial effects on academic performance of students in Mathematics include working memory, conceptual memory, short-term memory, inhibition, updating, focus attention, divided attention, auditory perception, and visual perception. Also, processing speed, shifting, planning, hand-eye coordination and response time accounted for moderate effects on academic performance of students in Mathematics. Consequently, instructors should reinforce learners’ cognitive processes using cognitive retraining programmes, personalized learning, differentiated instructional strategies for exceptional students, and offer therapeutic interventions on the identified cognitive parameters that could reduce extraneous cognitive loads. These could facilitate mental internalization of external perception during instructional delivery and learning.

General and specific patterns of cortical gene expression as spatial correlates of complex cognitive functioning.

Gene expression varies across the brain. This spatial patterning denotes specialised support for particular brain functions. However, the way that a given gene's expression fluctuates across the brain may be governed by general rules. Quantifying patterns of spatial covariation across genes would offer insights into the molecular characteristics of brain areas supporting, for example, complex cognitive functions. Here, we use principal component analysis to separate general and unique gene regulatory associations with cortical substrates of cognition. We find that the region-to-region variation in cortical expression profiles of 8235 genes covaries across two major principal components: gene ontology analysis suggests these dimensions are characterised by downregulation and upregulation of cell-signalling/modification and transcription factors. We validate these patterns out-of-sample and across different data processing choices. Brain regions more strongly implicated in general cognitive functioning (g; 3 cohorts, total meta-analytic N = 39,519) tend to be more balanced between downregulation and upregulation of both major components (indicated by regional component scores). We then identify a further 29 genes as candidate cortical spatial correlates of g, beyond the patterning of the two major components (|β| range = 0.18 to 0.53). Many of these genes have been previously associated with clinical neurodegenerative and psychiatric disorders, or with other health-related phenotypes. The results provide insights into the cortical organisation of gene expression and its association with individual differences in cognitive functioning.

Sex Differences in the Association of Age at Hypertension Diagnosis With Brain Structure.

Sex differences exist in the likelihood of cognitive decline. The age at hypertension diagnosis is a unique contributor to brain structural changes associated with cerebral small vessel disease. However, whether this relationship differs between sexes remains unclear. Therefore, our objective was to evaluate sex differences in the association between the age at hypertension diagnosis and cerebral small vessel disease-related brain structural changes. We used data from the UK Biobank to select participants with a known age at hypertension diagnosis and brain magnetic resonance imaging (n=9430) and stratified them by sex and age at hypertension diagnosis. Control participants with magnetic resonance imaging scans but no hypertension were chosen at random matched by using propensity score matching. For morphological brain structural changes, generalized linear models were used while adjusting for other vascular risk factors. For the assessment of white matter microstructure, principal component analysis led to a reduction in the number of fractional anisotropy variables, followed by regression analysis with major principal components as outcomes. Males but not females with a younger age at hypertension diagnosis exhibited lower brain gray and white matter volume compared with normotensive controls. The volume of white matter hyperintensities was greater in both males and females with hypertension than normotensive controls, significantly higher in older females with hypertension. Compared with normotensive controls, white matter microstructural integrity was lower in individuals with hypertension, which became more prominent with increasing age. Our study demonstrates that the effect of hypertension on cerebral small vessel disease-related brain structure differs by sex and by age at hypertension diagnosis.

Evaluating the Efficacy of Type 2 Diabetes Polygenic Risk Scores in an Independent European Population.

Numerous type 2 diabetes (T2D) polygenic risk scores (PGSs) have been developed to predict individuals' predisposition to the disease. An independent assessment and verification of the best-performing PGS are warranted to allow for a rapid application of developed models. To date, only 3% of T2D PGSs have been evaluated. In this study, we assessed all (n = 102) presently published T2D PGSs in an independent cohort of 3718 individuals, which has not been included in the construction or fine-tuning of any T2D PGS so far. We further chose the best-performing PGS, assessed its performance across major population principal component analysis (PCA) clusters, and compared it with newly developed population-specific T2D PGS. Our findings revealed that 88% of the published PGSs were significantly associated with T2D; however, their performance was lower than what had been previously reported. We found a positive association of PGS improvement over the years (p-value = 8.01 × 10-4 with PGS002771 currently showing the best discriminatory power (area under the receiver operating characteristic (AUROC) = 0.669) and PGS003443 exhibiting the strongest association PGS003443 (odds ratio (OR) = 1.899). Further investigation revealed no difference in PGS performance across major population PCA clusters and when compared with newly developed population-specific PGS. Our findings revealed a positive trend in T2D PGS performance, consistently identifying high-T2D-risk individuals in an independent European population.

Pulsed electric field treatment of soymilk: Impact on Kunitz trypsin inhibitor allergenicity, antinutritional factor, and aroma characteristics.

Allergens, antinutritional factors, and lipoxygenase (LOX) enzyme present in soymilk limit its consumption as vegan milk. Therefore, the present study focuses on reducing these limiting factors using pulsed electric field (PEF) treatment. In this regard, 20-40kV/cm electric field was applied to soymilk for the effective treatment periods of 450, 1350, and 2250ms. After the treatment, a reduction in pH (6.60±0.10 to 6.47±0.12) and an increase in the conductivity (173.03±0.40 to 177.33±0.72 µS) were observed. Furthermore, FTIR (Fourier Transform Infrared Spectroscopy), UV (Ultra Violet)intrinsic spectra, and CD (Circular Dichroism)spectra (α-helix reduction and β-sheet increase) data indicated mild structural changes in the proteins of soymilk. As a result, PEF treatment reduced the soymilk allergenicity (67.33±20.48%), LOX activity (69.45±9.38%), and trypsin inhibitor activity (75.61±4.04%). Apart from that, the color, viscosity, and volatiles of soymilk also had significant changes due to PEF treatment. The aroma changes in PEF-treated soymilk were highly influenced by two major principal component (PC1 & PC2) groups and they accounted for about 70% of the aroma variations. However, these changes were mild and did not induce any off-flavors and the treatment remained effective against the quality hazards like allergens, antinutritional factors, and LOX enzyme. PRACTICAL APPLICATION: PEF treatment of soymilk reduces the possible allergic reactions in human body at least by 30%. Further, it reduces the antinutritional factor and off-odor inducing compounds. Therefore, the PEF treatment can be used in industries as a pre-treatment to produce allergen and antinutritional compounds free protein isolates from soybeans.

Utilization of black locust (Robinia pseudoacacia) sawdust as an alternative pelletization raw material

European pellet production will be a future challenge due to two effects: (1) the share of hardwood species in Europe will increase and (2) the pellet market will face raw material shortages. Therefore, we investigated the blending of conifer sawdust with black locust sawdust. Twenty-one physical and chemical pellet quality parameters were recorded, including combustion emissions. Our statistical evaluation showed a strong linear correlation (p>0.8 or p<−0.8) of the share of black locust with nine quality parameters. Fifty-three percent of the overall variation in the data was explained by the major principal component, which included the share of black locust. The cause of the decreasing pellet quality with increasing share of black locust sawdust was attributed to the heat conductance in the dye, which was affected by the hydrophobicity and rigidity of the black locust saw dust. A share of 25% black locust in blends with conifer sawdust is proposed as the limit to meet the A2 standard criteria in the European DIN EN ISO 17255-2. This would allow a black locust sawdust consumption of app. 6 mio t per year in Europe, which is far above the estimated abundance and indicates a high potential for hardwood sawdust as an alternative feedstock for pellet production in general.

Evidence of the time-varying impacts of the COVID-19 pandemic on online search activities relating to shopping products in South Korea

The COVID-19 pandemic has changed the level of the received risk of the public and their social behavior patterns since 2020. This study aims to investigate temporal changes of online search activities of the public about shopping products, harnessing the NAVER DataLab Shopping Insight (NDLSI) data (weekly online search activity volumes about +1,800 shopping products) over 2017–2021. This study conducts the singular value decomposition (SVD) analysis of the NDLSI data to extract the major principal components of online search activity volumes about shopping products. Before the pandemic, the NDLSI data shows that the first principal mode (15% of variance explained) is strongly associated with an increasing trend of search activity volumes relating to shopping products. The second principal mode (10%) is strongly associated with the seasonality of monthly temperature, but in advance of four weeks. After removing the increasing trend and seasonality in the NDLSI data, the first major mode (27%) is related to the multiple waves of the new confirm cases of corona virus variants. Generally, life/health, digital/home appliance, food, childbirth/childcare shopping products are associated with the waves of the COVID-19 pandemic. While search activities for 241 shopping products are associated with the new confirmed cases of corona virus variants after the first wave, 124 and 190 shopping products are associated after the second and third waves. These changes of the public interest in online shopping products are strongly associated with changes in the COVID-19 prevention policies and risk of being exposed to the corona virus variants. This study highlights the need to better understand changes in social behavior patterns, including but not limited to e-commerce activities, for the next pandemic preparation.

Consumer decision-making and segmentation of dates market in Saudi Arabia

The study aimed to investigate factors influencing purchasing of dates in Saudi Arabia and its market segmentation. Principal components analysis (PCA) and clustering were used on the data obtained by interviewing a sample of 280 people. The main findings indicated two major principal components (PCs) explaining consumer behaviour: marketing accounted for 51.7% of the population’s information and gender and job determine 20.83%. Clustering provided three groups of consumers: (1) poor or unemployed women interested in the lowest price, (2 ) wealthy women interested in marketing motivation and (3) less wealthy women interested in price promotion. The study recommended a pink marketing strategy for wealthy women.

Structural Condition Classification of Railway Bridge KW51 Before, During, and After Retrofitting

AbstractA linear classification algorithm for various structural states (before, during, and after retrofitting) of railway steel arch bridge KW51 based on Linear Discriminant Analysis (LDA) of principal components is proposed. The technique is typically employed in other fields, such as genetics, but its use in civil engineering is still limited. The method is applied in two steps, first, the original vibration measurements are projected to a lower dimensional subspace using Principal Component Analysis (PCA). The significant principal components are provided as inputs to LDA to constitute the newly transformed subspace. Joining PCA and LDA improves the performance aptitude of LDA when only first major principal components hold the main signature of the features. The acceleration datasets that represent bridge conditions under train passage on the steel arch railway bridge in Belgium, mentioned as bridge KW51 have been utilized for validation of the algorithm. The outcome of the visualization process is further analyzed using three clustering methods (kmeans, Fuzzy C means, and Gaussian Mixture Modelling). The confusion matrix is used to examine the performance of the clustering methods. The proposed algorithm provides promising results that outperformed other classification methods.

Organosulfurs, S-allyl cysteine and N-acetyl cysteine sequester di-carbonyls and reduces carbonyl stress in HT22 cells

Diabetes, characterized by high blood glucose level, is a progressive metabolic disease that leads to serious health complications. One of the major pathological consequences associated with diabetes is the accumulation of highly reactive carbonyl compounds called advanced glycation end products (AGEs). Most of the AGEs are dicarbonyls and have the potential to covalently modify proteins especially at the lysine residues in a non-enzymatic fashion (a process termed as glycation) resulting in the functional impairment and/or toxic gain in function. Therefore, non-toxic small molecules that can inhibit glycation are of interest for the therapeutic intervention of diabetes. In the present communication, we have investigated the effect of organosulfurs (S-allyl cysteine, SAC and N-acetyl cysteine, NAC) that are major principal components of Allium sativa against the glycation of different proteins. We discovered that both SAC and NAC are potent anti-glycating agents. We also found that both SAC and NAC reduce ROS level and inhibit apoptosis caused by protein glycation.

Risk assessment of toxic metals and groundwater quality assessment in an industrial hotspot of Bengaluru, India – case study

The present study was conducted across 28 sampling locations in an industrial zone (Peenya) of Bengaluru city to characterize the various chemical parameters of groundwater. Groundwater chemistry was evaluated using Water Quality Index (WQI) and Piper plots. The WQI results showed that around 78% of sampling points were unfit for drinking water consumption. Results of Piper plots categorized groundwater samples principally into Ca·Mg-HCO3 type (39%) and mixed Ca·Mg − Cl · SO4 type (53.5%). The study used principal component analysis and hierarchical cluster analysis to evaluate possible sources of water pollution. The five major principal components were extracted, and it showed that the water quality in the study area was likely influenced by both natural geogenic and anthropogenic sources. Water was not typically used for drinking purposes, but was used for various industrial uses. Human health risk assessment showed that in most sampling locations (86%), values of the Hazard Index were greater than 1, which indicated that water was not suitable for drinking because of its potential to cause non-carcinogenic health effects in adults and children. Long-term monitoring of contamination in the study area revealed that the concentration of Cr(VI) still existed at concerning levels in groundwater. Thus, the current study aids in identifying risks associated with heavy metal contamination and serves as a foundation for developing a remediation plan to address environmental issues.

Unraveling the Relationship between Fruit Yield and Yield Related Components in Snake Gourd Genotypes using Multivariate Analysis

Background: Snake gourd is a monoecious crop that prefers cross pollination. Snake gourd has a lot of potential for genetic improvement. A large variation can be produced when genetically diverse and geographically distant lines are combined. To examine the genetic diversity and connection between essential agronomic features in snake gourd, multivariate methods such as principal component analysis and cluster analysis were used. This study will use multivariate analysis to determine the genetic diversity and link between critical agronomic aspects of snake gourd. Methods: A total of sixteen genotypes and two varieties of snake gourd genotypes were subjected to boxplot, principal component analysis and cluster analysis based on eleven quantitative traits. Boxplot analysis, Principal component analysis and cluster analysis were performed using R version of 4.2.1. Result: Boxplot analysis depicted the frequency distribution of eleven quantitative traits among 18 snake gourd accessions. The overall variation was split into eleven principal components, out of which five major principal components contributed for variability of snake gourd genotypes by exhibiting 90.05 per cent of variability. The squared cosine variables inferred that the traits viz., days to first male flowering, days to first female flowering and days to first harvest contributed more for variability in the first component. The ward D2 method of hierarchical clustering cluster the 16 genotypes and 2 varieties in two clusters based on cluster sum of squares.

Optical Identification of Diabetic Retinopathy Using Hyperspectral Imaging.

The severity of diabetic retinopathy (DR) is directly correlated to changes in both the oxygen utilization rate of retinal tissue as well as the blood oxygen saturation of both arteries and veins. Therefore, the current stage of DR in a patient can be identified by analyzing the oxygen content in blood vessels through fundus images. This enables medical professionals to make accurate and prompt judgments regarding the patient's condition. However, in order to use this method to implement supplementary medical treatment, blood vessels under fundus images need to be determined first, and arteries and veins then need to be differentiated from one another. Therefore, the entire study was split into three sections. After first removing the background from the fundus images using image processing, the blood vessels in the images were then separated from the background. Second, the method of hyperspectral imaging (HSI) was utilized in order to construct the spectral data. The HSI algorithm was utilized in order to perform analysis and simulations on the overall reflection spectrum of the retinal image. Thirdly, principal component analysis (PCA) was performed in order to both simplify the data and acquire the major principal components score plot for retinopathy in arteries and veins at all stages. In the final step, arteries and veins in the original fundus images were separated using the principal components score plots for each stage. As retinopathy progresses, the difference in reflectance between the arteries and veins gradually decreases. This results in a more difficult differentiation of PCA results in later stages, along with decreased precision and sensitivity. As a consequence of this, the precision and sensitivity of the HSI method in DR patients who are in the normal stage and those who are in the proliferative DR (PDR) stage are the highest and lowest, respectively. On the other hand, the indicator values are comparable between the background DR (BDR) and pre-proliferative DR (PPDR) stages due to the fact that both stages exhibit comparable clinical-pathological severity characteristics. The results indicate that the sensitivity values of arteries are 82.4%, 77.5%, 78.1%, and 72.9% in the normal, BDR, PPDR, and PDR, while for veins, these values are 88.5%, 85.4%, 81.4%, and 75.1% in the normal, BDR, PPDR, and PDR, respectively.

Multidimensional Risk-Based Real Options Valuation for Low-Carbon Cogeneration Pathways

Energy price fluctuations pose a significant risk and uncertainty to financial investments for new developments in conventional power and freshwater cogeneration facilities. This study attempts to address the problem of making robust valuation for low-carbon energy project investments subject to multi-dimensional price risk, particularly looking at some key research questions: (a) how does the correlation structure, or independence, between the price risks affect the project value; and (b) does adding flexibility in investment enhance or worsen the project valuation, given (a). This study identified three price factors with significant fluctuations that impact conventional power generation, namely: wholesale electricity spot price, natural gas spot price, and CO2 market price. The price factors were used to construct a multidimensional risk model and evaluate investment decisions for cogeneration project expansion in the future based on a low-carbon energy mix. To this end, five cogeneration configurations using combined-cycle gas turbine (CCGT) integrated with solar photovoltaics (PV) and carbon capture and storage (CCS) technologies were assessed. A combined price risk was initially estimated by transforming the given price factors representing maximum covariance using principal component analysis (PCA). The trend and volatilities in the major principal component scores (the combined price risk indicator) were modelled using the geometric Brownian motion stochastic process, whose parameters were determined and then used to perform time-series simulation and generate multiple realisations of the principal component. A back transformation was then applied to obtain the simulated values representing future uncertainties in the price factors. The effect of price risk and uncertainties were subsequently evaluated using a recombining binomial lattice model for real options analysis (ROA). There were financial gains when PV was mixed with conventional natural gas-fired technology. Investment in cogeneration configurations with (a) 25% PV share provided a 53% gain in the extended net present value (e–NPV); and (b) 50% PV share provided a 124% e–NPV gain when compared to the baseline cogeneration system with no PV shares. The analyses demonstrate that PV technology is a better hedging option than CCS against future market uncertainty and price volatility.

Multivariate analysis of morpho-physiological traits in bread wheat genotypes under terminal heat stress

Terminal heat stress has great impact on the quantity and quality of bread wheat that ultimately pose a serious concern about the food security. The presence of the genetic variability and suitable selection criteria is imperative for screening of genotypes for heat tolerance. Therefore, 60 advanced breeding lines and four standard checks were evaluated for morpho-physiological traits under late sown condition to understand the importance of the principal component analysis in reduction of the large correlated data into few major principal components that account for maximum genetic variability. Out of twenty principal components, only three were retained having 67.10% contribution towards total variability on the basis of eigen values and scree plot. Grain yield (0.995), days to heading (0.912) and plant height (0.752) were having maximum positive loading in the first, second and third principal component respectively. Therefore, principal component analysis holds great promise in the crop improvement programme. Keywords: terminal heat stress, wheat, genetic variability, principal component and scree plot

Morphological characterization and diversity analysis of local mango (Mangifera indica L.) genotypes from far western hill of Nepal

Mango is an important tropical fruit of Nepal. Nepal is rich in mango diversity and large numbers of local genotypes have been identified in different parts of the country. Such diversity of local mango genotypes are in verge of danger and needs to properly identified, evaluated and conserved. Morphological characterization is an important step in the characterization, evaluation and further utilization of genotypes. The current study aimed to characterize 33 local mango genotypes from Doti district of Far Western Region in Nepal using 14 quantitative morphological traits. The results of the study showed variation in terms tree, leaf, fruit, stone and seed character among the genotypes. The average fruit weight of genotypes was found to be 51.61g with maximum weight of 90.92g in Gude genotype. The four major principal components were formed with Eigen value &gt;1 with cumulative diversity of 88.2%. Results of the cluster analysis grouped 33 mango genotypes into four major clusters with similarity level of 41.27% to 96.29% showing diversity among the genotypes. The variability seen among the genotypes in the present study can be a source of gene pool for systematic mango breeding program and thus these genotypes need to be properly conserved. SAARC J. Agric., 20(2): 57-67 (2022)

Neuroendocrine correlates of juvenile amphibian behaviors across a latitudinal cline

We assessed the macrogeographic and neuroendocrine correlates of behavioral variation exhibited by juveniles, an important life stage for dispersal, across the expansive range of the wood frog. By rearing animals from eggs in a common garden then using a novel environment test, we uniquely demonstrated differential expression of juvenile behaviors among 16 populations spanning 8° latitude. On the individual level, cluster analysis indicated three major behavior profiles and principal component analysis resolved four unique axes of behavior, including escape, foraging, food intake, feeding efficiency. We found that increased escape behavior was associated with lower adrenocorticotropic hormone (ACTH)-induced circulating corticosterone (CORT) levels, however, foraging and food intake behaviors were not associated with either resting or ACTH-induced CORT. At the population level, the expression of foraging behaviors increased with latitude while food intake behaviors declined with latitude, which raised several hypotheses of eco-evolutionary processes likely driving this variation. Given that these behaviors covary along the same ecological gradient as locally adapted developmental traits, genomic studies in this species could provide deep insights into how HPA/I activity is associated with the eco-evolutionary processes that structure intraspecific variation in morphology and behavior.

Exposomic Analysis of Organic Pollutants in Seminal Plasma and Male Reproductive Parameters

Previous studies of environmental exposures and male reproductive health have typically examined limited sets of exposures in the urine, which may not accurately capture the chemical burden in relevant tissues and do not consider a large range of concurrent exposures. Here, we used a combined targeted and untargeted exposome approach to identify novel associations of environmental pollutants found in seminal plasma, as individual metabolites and co-exposure patterns, with male reproductive parameters. Semen samples were collected from male partners from 100 heterosexual couples undergoing assisted reproductive treatment in Tel Aviv after 2-7 day abstinence. Semen parameters were assessed for sperm concentration, percent motility, and total motile sperm. Using a novel QuEChERS (quick, easy, cheap, efficient, rugged, and safe) extraction method, 118 targeted and 2005 untargeted organic pollutant exposures were measured from seminal plasma using gas chromatography. We used linear regression, principal component pursuit (PCP), and Bayesian Kernel Machine Regression (BKMR) to estimate the associations of organic pollutants with semen parameters. Using an exposome-wide association approach, we found that etriadizole, a common pesticide, was negatively associated with total motile sperm (p&amp;#x3c;0.001), concentration (p=0.002), and percent motility (p=0.04). Using PCP, a machine learning pattern recognition approach, we derived a low-rank matrix with one major principal component. This principal component was primarily loaded by one phthalate (diethyl phthalate) and three PAHs (anthracene, pyrene, phenanthrene) and was associated with lower total sperm (p=0.03) and percent motility (p=0.05). BKMR results confirmed that as an overall mixture, these four pollutants were negatively associated with percent motility, although anthracene was not important to the mixture effect. Seminal plasma levels of etridiazole, diethyl phthalate, and polycyclic aromatic hydrocarbons (PAHs) are negatively associated with semen parameters. Future exposomic investigations using seminal plasma are warranted. Keywords: exposomics; exposome; seminal plasma; reproduction; reproductive health; semen; sperm; pesticide, etridiazole, phthalates, PAH

Genomic regions associate with major axes of variation driven by gas exchange and leaf construction traits in cultivated sunflower (Helianthus annuus L.).

SUMMARYStomata and leaf veins play an essential role in transpiration and the movement of water throughout leaves. These traits are thus thought to play a key role in the adaptation of plants to drought and a better understanding of the genetic basis of their variation and coordination could inform efforts to improve drought tolerance. Here, we explore patterns of variation and covariation in leaf anatomical traits and analyze their genetic architecture via genome‐wide association (GWA) analyses in cultivated sunflower (Helianthus annuus L.). Traits related to stomatal density and morphology as well as lower‐order veins were manually measured from digital images while the density of minor veins was estimated using a novel deep learning approach. Leaf, stomatal, and vein traits exhibited numerous significant correlations that generally followed expectations based on functional relationships. Correlated suites of traits could further be separated along three major principal component (PC) axes that were heavily influenced by variation in traits related to gas exchange, leaf hydraulics, and leaf construction. While there was limited evidence of colocalization when individual traits were subjected to GWA analyses, major multivariate PC axes that were most strongly influenced by several traits related to gas exchange or leaf construction did exhibit significant genomic associations. These results provide insight into the genetic basis of leaf trait covariation and showcase potential targets for future efforts aimed at modifying leaf anatomical traits in sunflower.