@article{ahmed_wijewardane_lu_jones_kudenov_williams_villordon_kamruzzaman_2024, title={Advancing sweetpotato quality assessment with hyperspectral imaging and explainable artificial intelligence}, volume={220}, ISSN={["1872-7107"]}, url={http://dx.doi.org/10.1016/j.compag.2024.108855}, DOI={10.1016/j.compag.2024.108855}, abstractNote={The quality evaluation of sweetpotatoes is of utmost importance during postharvest handling as it significantly impacts consumer satisfaction, nutritional value, and market competitiveness. This study presents an innovative approach that integrates explainable artificial intelligence (AI) with hyperspectral imaging to enhance the assessment of three important quality attributes in sweetpotatoes, i.e., dry matter content, soluble solid content, and firmness. Sweetpotato samples of three different varieties, including "Bayou Belle", "Murasaki", and "Orleans", were imaged using a portable visible near-infrared hyperspectral imaging (VNIR-HSI) camera, with a 400–1000 nm spectral range. The extracted spectral data were used to select key wavelengths, develop multivariate regression models, and utilize SHapley Additive exPlanations (SHAP) values to ascertain model effectiveness and interpretability. The regression models (dry matter: R2p = 0.92, RMSEP = 1.50 % and RPD = 5.58; soluble solid content: R2p = 0.66, RMSEP = 0.85obrix, and RPD = 1.72; firmness: R2p = 0.85; RMSEP = 1.66 N and RPD = 2.63) developed with key wavelengths were used to generate prediction maps to visualize the spatial distribution of response attributes, facilitating an improved evaluation of sweetpotato quality. The study demonstrated that the combination of HSI, variable selection, and explainable AI has the potential to enhance the quality assessment of sweetpotatoes, ensuring supplies of higher quality products to consumers.}, journal={COMPUTERS AND ELECTRONICS IN AGRICULTURE}, author={Ahmed, Toukir and Wijewardane, Nuwan K. and Lu, Yuzhen and Jones, Daniela S. and Kudenov, Michael and Williams, Cranos and Villordon, Arthur and Kamruzzaman, Mohammed}, year={2024}, month={May} }
 @article{asafen_beseli_chen_hiremath_williams_reeves_2024, title={Dynamics of BMP signaling and stable gene expression in the early Drosophila embryo}, url={https://doi.org/10.1242/bio.061646}, DOI={10.1242/bio.061646}, abstractNote={In developing tissues, morphogen gradients are thought to initialize gene expression patterns. However, the relationship between the dynamics of morphogen-encoded signals and gene expression decisions is largely unknown. Here we examine the dynamics of the Bone Morphogenetic Protein (BMP) pathway in Drosophila blastoderm-stage embryos. In this tissue, the BMP pathway is highly dynamic: it begins as a broad and weak signal on the dorsal half of the embryo, then 20-30 min later refines into a narrow, intense peak centered on the dorsal midline. This dynamical progression of the BMP signal raises questions of how it stably activates target genes. Therefore, we performed live imaging of the BMP signal and found that dorsal-lateral cells experience only a short transient in BMP signaling, after which the signal is lost completely. Moreover, we measured the transcriptional response of the BMP target gene pannier in live embryos and found it to remain activated in dorsal-lateral cells, even after the BMP signal is lost. Our findings may suggest that the BMP pathway activates a memory, or 'ratchet' mechanism that may sustain gene expression.}, journal={Biology Open}, author={Asafen, Hadel Al and Beseli, Aydin and Chen, Hung-Yuan and Hiremath, Sharva and Williams, Cranos M. and Reeves, Gregory T.}, year={2024}, month={Sep} }
 @article{liu_hunt_yencho_pecota_mierop_williams_jones_2024, title={Predicting sweetpotato traits using machine learning: Impact of environmental and agronomic factors on shape and size}, volume={225}, ISSN={["1872-7107"]}, url={https://doi.org/10.1016/j.compag.2024.109215}, DOI={10.1016/j.compag.2024.109215}, abstractNote={Consumer preference in produce, defined by shape and size, heavily influences this market. Understanding the environmental and management factors that impact these features can improve a farmer's economic margins. Since sweetpotatoes are hand-harvested and tend to have varying shapes and sizes, this can result in unpredictable profit margins. Methods for predicting the aesthetic characteristics of sweetpotatoes using environmental and agronomic factors with machine learning have not been developed. Moreover, predicting crop shape and size using agricultural data analysis is challenging due to the need for integrating diverse and complex datasets, including genotypes, weather, field management, and spatial information, into predictive models. This study employed an iterative process involving data preparation, feature engineering, variable selection, and model selection to develop machine learning models that predict sweetpotato aesthetic traits from agronomic inputs. We collected and organized data from various sources with different formats, spatial, and temporal resolutions. After comparing the performance of different machine learning methods using cross validation, Bagging regression had the least predictive error in terms of RMSE and MAE for sweetpotato's length-to-width ratio (RMSE = 0.185, MAE = 0.147) and curvature (RMSE = 0.013, MAE = 0.010) predictions. Bagging regression outperformed a naive baseline by 29%–38% when predicting sweetpotato features Our study also determined that the Covington cultivar and GPS locations were the most important factors that influenced the shape and size of sweetpotatoes. Fertilizer prior to planting, rose as an important feature when predicting sweetpotato curvature. Precipitation had a greater impact on the prediction of length-to-width ratio when compared to predicting curvature. The methodology presented herein could be applied to other crops like cucumbers, eggplants, peppers, and potatoes, where the size and shape are important factors for determining their value.}, journal={COMPUTERS AND ELECTRONICS IN AGRICULTURE}, author={Liu, Hangjin and Hunt, Shelly and Yencho, G. Craig and Pecota, Kenneth V. and Mierop, Russell and Williams, Cranos M. and Jones, Daniela S.}, year={2024}, month={Oct} }
 @article{schloop_hiremath_shaikh_williams_reeves_2024, title={Spatiotemporal dynamics of NF-κB/Dorsal inhibitor IκBα/Cactus inDrosophilablastoderm embryos}, url={https://doi.org/10.1101/2024.02.23.581825}, DOI={10.1101/2024.02.23.581825}, abstractNote={AbstractThe NF-κB signaling pathway is a key regulatory network in mammals that controls many cellular processes, including immunity and inflammation. Of particular note is the relationship between NF-κB and its inhibitor IκBα, which sequesters NF-κB to the cytoplasm of cells until needed. It is also known that IκBα can enter nuclei, disrupt NF-κB binding to DNA, and shuttle it out to again sequester NF-κB in the cytoplasm. InDrosophila melanogaster, a homologous system between the proteins Dorsal (homologous to NF-κB) and Cactus (homologous to IκBα) is important in embryo development, specifically in establishment of the Dorsal nuclear concentration gradient. Previous work suggests Cactus also enters the nucleus; mathematical models of the Dorsal gradient fail to accurately predict the normal range of the gradient without nuclear Cactus. However, direct,in vivovisualization of Cactus spatiotemporal dynamics, including its localization to the nuclei, has been difficult to gather. Previously, imaging Cactus in live embryos was complicated by rapid protein turnover, preventing fluorescent protein fusions from fully maturing. To address this, we used the CRISPR/Cas9 system to tag Cactus with the recently developed “LlamaTag” (LT), a genetically encodable nanobody from llamas that dynamically binds to GFPin vivo. We then employed standard confocal imaging, as well as advanced optical techniques such as raster image correlation spectroscopy (RICS) and fluorescent recovery after photobleaching (FRAP) to investigate the spatiotemporal distribution of Cactus-LlamaTag inDrosophilaembryos at the blastoderm stage. Our results demonstrate that Cactus can be found in the nuclei of early embryos, consistent with its role as a transcription factor regulator. Moreover, by using the data from FRAP and RICS, we were able to estimate biophysical parameters of Cactus dynamicsin vivo, including its nuclear transport rate constants and fraction bound to GFP. These data were further used to constrain a mathematical model that allowed us to infer experimentally inaccessible biophysical parameters, such as the concentration of Cact protein and the dissociation constant of LT and GFP. Our study provides new insights into the regulation of the NF-κB pathway in earlyDrosophilaembryos and highlights the power of advanced optical techniques for investigating complex biological dynamics.}, author={Schloop, Allison E. and Hiremath, Sharva and Shaikh, Razeen and Williams, Cranos M. and Reeves, Gregory T.}, year={2024}, month={Feb} }
 @article{haverroth_gobble_bradley_harris-gilliam_fischer_williams_long_sozzani_2024, title={The Black American experience: Answering the global challenge of broadening participation in STEM/agriculture}, volume={1}, ISSN={["1532-298X"]}, url={https://doi.org/10.1093/plcell/koae002}, DOI={10.1093/plcell/koae002}, journal={PLANT CELL}, author={Haverroth, Eduardo and Gobble, Mariah and Bradley, Latosha and Harris-Gilliam, Kailyn and Fischer, Alicia and Williams, Cranos and Long, Terri and Sozzani, Rosangela}, year={2024}, month={Jan} }
 @article{schmittling_muhammad_haque_long_williams_2023, title={Cellular clarity: a logistic regression approach to identify root epidermal regulators of iron deficiency response}, volume={24}, ISSN={["1471-2164"]}, DOI={10.1186/s12864-023-09714-6}, abstractNote={Abstract
                Background
                Plants respond to stress through highly tuned regulatory networks. While prior works identified master regulators of iron deficiency responses in A. thaliana from whole-root data, identifying regulators that act at the cellular level is critical to a more comprehensive understanding of iron homeostasis. Within the root epidermis complex molecular mechanisms that facilitate iron reduction and uptake from the rhizosphere are known to be regulated by bHLH transcriptional regulators. However, many questions remain about the regulatory mechanisms that control these responses, and how they may integrate with developmental processes within the epidermis. Here, we use transcriptional profiling to gain insight into root epidermis-specific regulatory processes.
              
                Results
                Set comparisons of differentially expressed genes (DEGs) between whole root and epidermis transcript measurements identified differences in magnitude and timing of organ-level vs. epidermis-specific responses. Utilizing a unique sampling method combined with a mutual information metric across time-lagged and non-time-lagged windows, we identified relationships between clusters of functionally relevant differentially expressed genes suggesting that developmental regulatory processes may act upstream of well-known Fe-specific responses. By integrating static data (DNA motif information) with time-series transcriptomic data and employing machine learning approaches, specifically logistic regression models with LASSO, we also identified putative motifs that served as crucial features for predicting differentially expressed genes. Twenty-eight transcription factors (TFs) known to bind to these motifs were not differentially expressed, indicating that these TFs may be regulated post-transcriptionally or post-translationally. Notably, many of these TFs also play a role in root development and general stress response.
              
                Conclusions
                This work uncovered key differences in -Fe response identified using whole root data vs. cell-specific root epidermal data. Machine learning approaches combined with additional static data identified putative regulators of -Fe response that would not have been identified solely through transcriptomic profiles and reveal how developmental and general stress responses within the epidermis may act upstream of more specialized -Fe responses for Fe uptake.
              }, number={1}, journal={BMC GENOMICS}, author={Schmittling, Selene R. and Muhammad, Durreshahwar and Haque, Samiul and Long, Terri A. and Williams, Cranos M.}, year={2023}, month={Oct} }
 @article{sulis_jiang_yang_marques_matthews_miller_lan_cofre-vega_liu_sun_et al._2023, title={Multiplex CRISPR editing of wood for sustainable fiber production}, volume={381}, ISSN={["1095-9203"]}, url={http://europepmc.org/abstract/med/37440632}, DOI={10.1126/science.add4514}, abstractNote={The domestication of forest trees for a more sustainable fiber bioeconomy has long been hindered by the complexity and plasticity of lignin, a biopolymer in wood that is recalcitrant to chemical and enzymatic degradation. Here, we show that multiplex CRISPR editing enables precise woody feedstock design for combinatorial improvement of lignin composition and wood properties. By assessing every possible combination of 69,123 multigenic editing strategies for 21 lignin biosynthesis genes, we deduced seven different genome editing strategies targeting the concurrent alteration of up to six genes and produced 174 edited poplar variants. CRISPR editing increased the wood carbohydrate-to-lignin ratio up to 228% that of wild type, leading to more-efficient fiber pulping. The edited wood alleviates a major fiber-production bottleneck regardless of changes in tree growth rate and could bring unprecedented operational efficiencies, bioeconomic opportunities, and environmental benefits.}, number={6654}, journal={SCIENCE}, author={Sulis, Daniel B. and Jiang, Xiao and Yang, Chenmin and Marques, Barbara M. and Matthews, Megan L. and Miller, Zachary and Lan, Kai and Cofre-Vega, Carlos and Liu, Baoguang and Sun, Runkun and et al.}, year={2023}, month={Jul}, pages={216-+} }
 @misc{busato_gordon_chaudhari_jensen_akyol_andersen_williams_2023, title={Compositionality, sparsity, spurious heterogeneity, and other data-driven challenges for machine learning algorithms within plant microbiome studies}, volume={71}, ISSN={["1879-0356"]}, url={https://doi.org/10.1016/j.pbi.2022.102326}, DOI={10.1016/j.pbi.2022.102326}, abstractNote={The plant-associated microbiome is a key component of plant systems, contributing to their health, growth, and productivity. The application of machine learning (ML) in this field promises to help untangle the relationships involved. However, measurements of microbial communities by high-throughput sequencing pose challenges for ML. Noise from low sample sizes, soil heterogeneity, and technical factors can impact the performance of ML. Additionally, the compositional and sparse nature of these datasets can impact the predictive accuracy of ML. We review recent literature from plant studies to illustrate that these properties often go unmentioned. We expand our analysis to other fields to quantify the degree to which mitigation approaches improve the performance of ML and describe the mathematical basis for this. With the advent of accessible analytical packages for microbiome data including learning models, researchers must be familiar with the nature of their datasets.}, journal={CURRENT OPINION IN PLANT BIOLOGY}, author={Busato, Sebastiano and Gordon, Max and Chaudhari, Meenal and Jensen, Ib and Akyol, Turgut and Andersen, Stig and Williams, Cranos}, year={2023}, month={Feb} }
 @article{asafen_beseli_hiremath_williams_reeves_2022, title={Dynamics of BMP signaling in the earlyDrosophilaembryo}, url={https://doi.org/10.1101/2022.10.20.513072}, DOI={10.1101/2022.10.20.513072}, abstractNote={AbstractIn developing tissues, morphogen gradients are thought to initialize gene expression patterns. However, the relationship between the dynamics of morphogen-encoded signals and gene expression decisions are largely unknown. Here we examine the dynamics of the Bone Morphogenetic Protein (BMP) pathway inDrosophilablastoderm-stage embryos. In this tissue, the BMP pathway is highly dynamic: it begins as a broad and weak signal on the dorsal half of the embryo, then 20-30 min later refines into a narrow, intense peak centered on the dorsal midline. This dynamical progression of the BMP signal raises questions of how it stably activates target genes. Therefore, we performed live imaging of the BMP signal and found that dorsal-lateral cells experience only a short transient in BMP signaling, after which the signal is lost completely. Moreover, we measured the transcriptional response of the BMP target genepannierin live embryos and found it to remain activated in dorsal-lateral cells, even after the BMP signal is lost. Our findings may suggest that the BMP pathway activates a memory, or “ratchet” mechanism that may sustain gene expression.}, author={Asafen, Hadel Y. Al and Beseli, Aydin and Hiremath, Sharva and Williams, Cranos M. and Reeves, Gregory T.}, year={2022}, month={Oct} }
 @article{mustamin_akyol_gordon_manggabarani_isomura_kawamura_bamba_williams_andersen_sato_2023, title={FER and LecRK show haplotype-dependent cold-responsiveness and mediate freezing tolerance in Lotus japonicus}, volume={191}, ISSN={["1532-2548"]}, url={https://doi.org/10.1093/plphys/kiac533}, DOI={10.1093/plphys/kiac533}, abstractNote={Abstract
               Many plant species have succeeded in colonizing a wide range of diverse climates through local adaptation, but the underlying molecular genetics remain obscure. We previously found that winter survival was a direct target of selection during colonization of Japan by the perennial legume Lotus japonicus and identified associated candidate genes. Here, we show that two of these, FERONIA-receptor like kinase (LjFER) and a S-receptor-like kinase gene (LjLecRK), are required for non-acclimated freezing tolerance and show haplotype-dependent cold-responsive expression. Our work suggests that recruiting a conserved growth regulator gene, FER, and a receptor-like kinase gene, LecRK, into the set of cold-responsive genes has contributed to freezing tolerance and local climate adaptation in L. japonicus, offering functional genetic insight into perennial herb evolution.}, number={2}, journal={PLANT PHYSIOLOGY}, author={Mustamin, Yusdar and Akyol, Turgut Yigit and Gordon, Max and Manggabarani, Andi Madihah and Isomura, Yoshiko and Kawamura, Yasuko and Bamba, Masaru and Williams, Cranos and Andersen, Stig Uggerhj and Sato, Shusei}, year={2023}, month={Feb}, pages={1138–1152} }
 @article{tong_chen_williams_2022, title={Identification of Transcription Factors Regulating SARS-CoV-2 Tropism Factor Expression by Inferring Cell-Type-Specific Transcriptional Regulatory Networks in Human Lungs}, volume={14}, ISSN={["1999-4915"]}, DOI={10.3390/v14040837}, abstractNote={Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the virus that caused the coronavirus disease 2019 (COVID-19) pandemic. Though previous studies have suggested that SARS-CoV-2 cellular tropism depends on the host-cell-expressed proteins, whether transcriptional regulation controls SARS-CoV-2 tropism factors in human lung cells remains unclear. In this study, we used computational approaches to identify transcription factors (TFs) regulating SARS-CoV-2 tropism for different types of lung cells. We constructed transcriptional regulatory networks (TRNs) controlling SARS-CoV-2 tropism factors for healthy donors and COVID-19 patients using lung single-cell RNA-sequencing (scRNA-seq) data. Through differential network analysis, we found that the altered regulatory role of TFs in the same cell types of healthy and SARS-CoV-2-infected networks may be partially responsible for differential tropism factor expression. In addition, we identified the TFs with high centralities from each cell type and proposed currently available drugs that target these TFs as potential candidates for the treatment of SARS-CoV-2 infection. Altogether, our work provides valuable cell-type-specific TRN models for understanding the transcriptional regulation and gene expression of SARS-CoV-2 tropism factors.}, number={4}, journal={VIRUSES-BASEL}, author={Tong, Haonan and Chen, Hao and Williams, Cranos M.}, year={2022}, month={Apr} }
 @article{muhammad_clark_haque_williams_sozzani_long_2022, title={POPEYE intercellular localization mediates cell-specific iron deficiency responses}, volume={8}, ISSN={["1532-2548"]}, url={https://doi.org/10.1093/plphys/kiac357}, DOI={10.1093/plphys/kiac357}, abstractNote={Abstract
               Plants must tightly regulate iron (Fe) sensing, acquisition, transport, mobilization, and storage to ensure sufficient levels of this essential micronutrient. POPEYE (PYE) is an iron responsive transcription factor that positively regulates the iron deficiency response, while also repressing genes essential for maintaining iron homeostasis. However, little is known about how PYE plays such contradictory roles. Under iron-deficient conditions, pPYE:GFP accumulates in the root pericycle while pPYE:PYE–GFP is localized to the nucleus in all Arabidopsis (Arabidopsis thaliana) root cells, suggesting that PYE may have cell-specific dynamics and functions. Using scanning fluorescence correlation spectroscopy and cell-specific promoters, we found that PYE–GFP moves between different cells and that the tendency for movement corresponds with transcript abundance. While localization to the cortex, endodermis, and vasculature is required to manage changes in iron availability, vasculature and endodermis localization of PYE–GFP protein exacerbated pye-1 defects and elicited a host of transcriptional changes that are detrimental to iron mobilization. Our findings indicate that PYE acts as a positive regulator of iron deficiency response by regulating iron bioavailability differentially across cells, which may trigger iron uptake from the surrounding rhizosphere and impact root energy metabolism.}, journal={PLANT PHYSIOLOGY}, publisher={Oxford University Press (OUP)}, author={Muhammad, DurreShahwar and Clark, Natalie M. and Haque, Samiul and Williams, Cranos M. and Sozzani, Rosangela and Long, Terri A.}, year={2022}, month={Aug} }
 @article{kudenov_altaqui_williams_2022, title={Practical spectral photography II: snapshot spectral imaging using linear retarders and microgrid polarization cameras}, volume={30}, ISSN={["1094-4087"]}, DOI={10.1364/OE.453538}, abstractNote={Despite recent advances, customized multispectral cameras can be challenging or costly to deploy in some use cases. Complexities span electronic synchronization, multi-camera calibration, parallax and spatial co-registration, and data acquisition from multiple cameras, all of which can hamper their ease of use. This paper discusses a generalized procedure for multispectral sensing using a pixelated polarization camera and anisotropic polymer film retarders to create multivariate optical filters. We then describe the calibration procedure, which leverages neural networks to convert measured data into calibrated spectra (intensity versus wavelength). Experimental results are presented for a multivariate and channeled optical filter. Finally, imaging results taken using a red, green, and blue microgrid polarization camera and the channeled optical filter are presented. Imaging experiments indicated that the calculated spectra’s root mean square error is highest in the region where the camera’s red, green, and blue filter responses overlap. The average error of the spectral reflectance, measured of our spectralon tiles, was 6.5% for wavelengths spanning 425-675 nm. This technique demonstrates that 12 spectral channels can be obtained with a relatively simple and robust optical setup, and at minimal cost beyond the purchase of the camera.}, number={8}, journal={OPTICS EXPRESS}, author={Kudenov, Michael W. and Altaqui, Ali and Williams, Cranos}, year={2022}, month={Apr}, pages={12337–12352} }
 @article{matthews_wang_sederoff_chiang_williams_2021, title={A multiscale model of lignin biosynthesis for predicting bioenergy traits in Populus trichocarpa}, volume={19}, ISSN={["2001-0370"]}, url={http://europepmc.org/abstract/med/33425249}, DOI={10.1016/j.csbj.2020.11.046}, abstractNote={Understanding the mechanisms behind lignin formation is an important research area with significant implications for the bioenergy and biomaterial industries. Computational models are indispensable tools for understanding this complex process. Models of the monolignol pathway in Populus trichocarpa and other plants have been developed to explore how transgenic modifications affect important bioenergy traits. Many of these models, however, only capture one level of biological organization and are unable to capture regulation across multiple biological scales. This limits their ability to predict how gene modification strategies will impact lignin and other wood properties. While the first multiscale model of lignin biosynthesis in P. trichocarpa spanned the transcript, protein, metabolic, and phenotypic layers, it did not account for cross-regulatory influences that could impact abundances of untargeted monolignol transcripts and proteins. Here, we present a multiscale model incorporating these cross-regulatory influences for predicting lignin and wood traits from transgenic knockdowns of the monolignol genes. The three main components of this multiscale model are (1) a transcript-protein model capturing cross-regulatory influences, (2) a kinetic-based metabolic model, and (3) random forest models relating the steady state metabolic fluxes to 25 physical traits. We demonstrate that including the cross-regulatory behavior results in smaller predictive error for 23 of the 25 traits. We use this multiscale model to explore the predicted impact of novel combinatorial knockdowns on key bioenergy traits, and identify the perturbation of PtrC3H3 and PtrCAld5H1&2 monolignol genes as a candidate strategy for increasing saccharification efficiencies while reducing negative impacts on wood density and height.}, journal={COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL}, author={Matthews, Megan L. and Wang, Jack P. and Sederoff, Ronald and Chiang, Vincent L. and Williams, Cranos M.}, year={2021}, pages={168–182} }
 @article{haque_lobaton_nelson_yencho_pecota_mierop_kudenov_boyette_williams_2021, title={Computer vision approach to characterize size and shape phenotypes of horticultural crops using high-throughput imagery}, volume={182}, ISSN={0168-1699}, url={http://dx.doi.org/10.1016/j.compag.2021.106011}, DOI={10.1016/j.compag.2021.106011}, abstractNote={For many horticultural crops, variation in quality (e.g., shape and size) contributes significantly to the crop’s market value. Metrics characterizing less subjective harvest quantities (e.g., yield and total biomass) are routinely monitored. In contrast, metrics quantifying more subjective crop quality characteristics such as ideal size and shape remain difficult to characterize objectively at the production-scale due to the lack of modular technologies for high-throughput sensing and computation. Several horticultural crops are sent to packing facilities after having been harvested, where they are sorted into boxes and containers using high-throughput scanners. These scanners capture images of each fruit or vegetable being sorted and packed, but the images are typically used solely for sorting purposes and promptly discarded. With further analysis, these images could offer unparalleled insight on how crop quality metrics vary at the industrial production-scale and provide further insight into how these characteristics translate to overall market value. At present, methods for extracting and quantifying quality characteristics of crops using images generated by existing industrial infrastructure have not been developed. Furthermore, prior studies that investigated horticultural crop quality metrics, specifically of size and shape, used a limited number of samples, did not incorporate deformed or non-marketable samples, and did not use images captured from high-throughput systems. In this work, using sweetpotato (SP) as a use case, we introduce a computer vision algorithm for quantifying shape and size characteristics in a high-throughput manner. This approach generates 3D model of SPs from two 2D images captured by an industrial sorter 90 degrees apart and extracts 3D shape features in a few hundred milliseconds. We applied the 3D reconstruction and feature extraction method to thousands of image samples to demonstrate how variations in shape features across SP cultivars can be quantified. We created a SP shape dataset containing SP images, extracted shape features, and qualitative shape types (U.S. No. 1 or Cull). We used this dataset to develop a neural network-based shape classifier that was able to predict Cull vs. U.S. No. 1 SPs with 84.59% accuracy. In addition, using univariate Chi-squared tests and random forest, we identified the most important features for determining qualitative shape type (U.S. No. 1 or Cull) of the SPs. Our study serves as a key step towards enabling big data analytics for industrial SP agriculture. The methodological framework is readily transferable to other horticultural crops, particularly those that are sorted using commercial imaging equipment.}, journal={Computers and Electronics in Agriculture}, publisher={Elsevier BV}, author={Haque, Samiul and Lobaton, Edgar and Nelson, Natalie and Yencho, G. Craig and Pecota, Kenneth V. and Mierop, Russell and Kudenov, Michael W. and Boyette, Mike and Williams, Cranos M.}, year={2021}, month={Mar}, pages={106011} }
 @article{lin_sun_song_chen_shi_yang_liu_tunlaya-anukit_liu_loziuk_et al._2021, title={Enzyme Complexes of Ptr4CL and PtrHCT Modulate Co-enzyme A Ligation of Hydroxycinnamic Acids for Monolignol Biosynthesis in Populus trichocarpa}, volume={12}, ISSN={["1664-462X"]}, url={http://europepmc.org/abstract/med/34691108}, DOI={10.3389/fpls.2021.727932}, abstractNote={Co-enzyme A (CoA) ligation of hydroxycinnamic acids by 4-coumaric acid:CoA ligase (4CL) is a critical step in the biosynthesis of monolignols. Perturbation of 4CL activity significantly impacts the lignin content of diverse plant species. InPopulus trichocarpa, two well-studied xylem-specific Ptr4CLs (Ptr4CL3 and Ptr4CL5) catalyze the CoA ligation of 4-coumaric acid to 4-coumaroyl-CoA and caffeic acid to caffeoyl-CoA. Subsequently, two 4-hydroxycinnamoyl-CoA:shikimic acid hydroxycinnamoyl transferases (PtrHCT1 and PtrHCT6) mediate the conversion of 4-coumaroyl-CoA to caffeoyl-CoA. Here, we show that the CoA ligation of 4-coumaric and caffeic acids is modulated by Ptr4CL/PtrHCT protein complexes. Downregulation ofPtrHCTsreduced Ptr4CL activities in the stem-differentiating xylem (SDX) of transgenicP. trichocarpa. The Ptr4CL/PtrHCT interactions were then validatedin vivousing biomolecular fluorescence complementation (BiFC) and protein pull-down assays inP. trichocarpaSDX extracts. Enzyme activity assays using recombinant proteins of Ptr4CL and PtrHCT showed elevated CoA ligation activity for Ptr4CL when supplemented with PtrHCT. Numerical analyses based on an evolutionary computation of the CoA ligation activity estimated the stoichiometry of the protein complex to consist of one Ptr4CL and two PtrHCTs, which was experimentally confirmed by chemical cross-linking using SDX plant protein extracts and recombinant proteins. Based on these results, we propose that Ptr4CL/PtrHCT complexes modulate the metabolic flux of CoA ligation for monolignol biosynthesis during wood formation inP. trichocarpa.}, journal={FRONTIERS IN PLANT SCIENCE}, author={Lin, Chien-Yuan and Sun, Yi and Song, Jina and Chen, Hsi-Chuan and Shi, Rui and Yang, Chenmin and Liu, Jie and Tunlaya-Anukit, Sermsawat and Liu, Baoguang and Loziuk, Philip L. and et al.}, year={2021}, month={Oct} }
 @misc{buckner_tong_ottley_williams_2021, title={High-throughput image segmentation and machine learning approaches in the plant sciences across multiple scales}, volume={5}, ISSN={["2397-8562"]}, url={https://doi.org/10.1042/ETLS20200273}, DOI={10.1042/ETLS20200273}, abstractNote={Agriculture has benefited greatly from the rise of big data and high-performance computing. The acquisition and analysis of data across biological scales have resulted in strategies modeling inter- actions between plant genotype and environment, models of root architecture that provide insight into resource utilization, and the elucidation of cell-to-cell communication mechanisms that are instrumental in plant development. Image segmentation and machine learning approaches for interpreting plant image data are among many of the computational methodologies that have evolved to address challenging agricultural and biological problems. These approaches have led to contributions such as the accelerated identification of gene that modulate stress responses in plants and automated high-throughput phenotyping for early detection of plant diseases. The continued acquisition of high throughput imaging across multiple biological scales provides opportunities to further push the boundaries of our understandings quicker than ever before. In this review, we explore the current state of the art methodologies in plant image segmentation and machine learning at the agricultural, organ, and cellular scales in plants. We show how the methodologies for segmentation and classification differ due to the diversity of physical characteristics found at these different scales. We also discuss the hardware technologies most commonly used at these different scales, the types of quantitative metrics that can be extracted from these images, and how the biological mechanisms by which plants respond to abiotic/biotic stresses or genotypic modifications can be extracted from these approaches.}, number={2}, journal={EMERGING TOPICS IN LIFE SCIENCES}, publisher={Portland Press Ltd.}, author={Buckner, Eli and Tong, Haonan and Ottley, Chanae and Williams, Cranos}, editor={Jez, Joseph M. and Topp, Christopher N.Editors}, year={2021}, pages={239–248} }
 @article{kudenov_scarboro_altaqui_boyette_yencho_williams_2021, title={Internal defect scanning of sweetpotatoes using interactance spectroscopy}, volume={16}, ISSN={["1932-6203"]}, DOI={10.1371/journal.pone.0246872}, abstractNote={While standard visible-light imaging offers a fast and inexpensive means of quality analysis of horticultural products, it is generally limited to measuring superficial (surface) defects. Using light at longer (near-infrared) or shorter (X-ray) wavelengths enables the detection of superficial tissue bruising and density defects, respectively; however, it does not enable the optical absorption and scattering properties of sub-dermal tissue to be quantified. This paper applies visible and near-infrared interactance spectroscopy to detect internal necrosis in sweetpotatoes and develops a Zemax scattering simulation that models the measured optical signatures for both healthy and necrotic tissue. This study demonstrates that interactance spectroscopy can detect the unique near-infrared optical signatures of necrotic tissues in sweetpotatoes down to a depth of approximately 5±0.5 mm. We anticipate that light scattering measurement methods will represent a significant improvement over the current destructive analysis methods used to assay for internal defects in sweetpotatoes.}, number={2}, journal={PLOS ONE}, author={Kudenov, Michael W. and Scarboro, Clifton G. and Altaqui, Ali and Boyette, Mike and Yencho, G. Craig and Williams, Cranos M.}, year={2021}, month={Feb} }
 @article{matthews_williams_2021, title={Multiscale Modeling of Cross-Regulatory Transcript and Protein Influences}, volume={2328}, ISBN={["978-1-0716-1533-1"]}, ISSN={["1940-6029"]}, DOI={10.1007/978-1-0716-1534-8_7}, abstractNote={With the popularity of high-throughput transcriptomic techniques like RNAseq, models of gene regulatory networks have been important tools for understanding how genes are regulated. These transcriptomic datasets are usually assumed to reflect their associated proteins. This assumption, however, ignores post-transcriptional, translational, and post-translational regulatory mechanisms that regulate protein abundance but not transcript abundance. Here we describe a method to model cross-regulatory influences between the transcripts and proteins of a set of genes using abundance data collected from a series of transgenic experiments. The developed model can capture the effects of regulation that impacts transcription as well as regulatory mechanisms occurring after transcription. This approach uses a sparse maximum likelihood algorithm to determine relationships that influence transcript and protein abundance. An example of how to explore the network topology of this type of model is also presented. This model can be used to predict how the transcript and protein abundances will change in novel transgenic modification strategies.}, journal={MODELING TRANSCRIPTIONAL REGULATION}, author={Matthews, Megan L. and Williams, Cranos M.}, year={2021}, pages={115–138} }
 @article{kudenov_altaqui_williams_2021, title={Snapshot spectral imaging using Solc-based multivariate optical filters and pixelated polarization cameras}, volume={11833}, ISSN={["1996-756X"]}, DOI={10.1117/12.2596580}, abstractNote={Despite recent advances, customized multispectral cameras can be challenging or costly to deploy in some use cases. Complexities span electronic synchronization, multi-camera calibration, parallax and spatial coregistration, and data acquisition from multiple cameras, all of which can hamper their ease of use. This paper discusses a generalized procedure for multispectral sensing using a pixelated polarization camera and Solc stages to create multivariate optical filters. We then describe some preliminary experimental results of a fabricated filtered camera system. Finally, classification of the imagery is achieved using either shallow or deep neural networks. We also discuss the potential of using a color red, green, and blue microgrid polarization camera to detect upwards of 12 spectral channels using readily available standard off-the-shelf components.}, journal={POLARIZATION SCIENCE AND REMOTE SENSING X}, author={Kudenov, Michael W. and Altaqui, Ali and Williams, Cranos}, year={2021} }
 @inbook{buckner_madison_melvin_long_sozzani_williams_2020, title={BioVision Tracker: A semi-automated image analysis software for spatiotemporal gene expression tracking in Arabidopsis thaliana}, volume={160}, ISBN={9780128215333}, ISSN={0091-679X}, url={http://dx.doi.org/10.1016/bs.mcb.2020.04.017}, DOI={10.1016/bs.mcb.2020.04.017}, abstractNote={Fluorescence microscopy can produce large quantities of data that reveal the spatiotemporal behavior of gene expression at the cellular level in plants. Automated or semi-automated image analysis methods are required to extract data from these images. These data are helpful in revealing spatial and/or temporal-dependent processes that influence development in the meristematic region of plant roots. Tracking spatiotemporal gene expression in the meristem requires the processing of multiple microscopy imaging channels (one channel used to image root geometry which serves as a reference for relating locations within the root, and one or more channels used to image fluorescent gene expression signals). Many automated image analysis methods rely on the staining of cell walls with fluorescent dyes to capture cellular geometry and overall root geometry. However, in long time-course imaging experiments, dyes may fade which hinders spatial assessment in image analysis. Here, we describe a procedure for analyzing 3D microscopy images to track spatiotemporal gene expression signals using the MATLAB-based BioVision Tracker software. This software requires either a fluorescence image or a brightfield image to analyze root geometry and a fluorescence image to capture and track temporal changes in gene expression.}, booktitle={Methods in Cell Biology}, publisher={Elsevier}, author={Buckner, Eli and Madison, Imani and Melvin, Charles and Long, Terri and Sozzani, Rosangela and Williams, Cranos}, year={2020}, pages={419–436} }
 @article{haque_lobaton_nelson_yencho_pecota_mierop_kudenov_boyette_williams_2020, title={Computer vision approach to characterize size and shape phenotypes of horticultural crops using high-throughput imagery}, url={https://doi.org/10.1101/2020.07.24.199539}, DOI={10.1101/2020.07.24.199539}, abstractNote={AbstractFor many horticultural crops, variation in quality (e.g., shape and size) contribute significantly to the crop’s market value. Metrics characterizing less subjective harvest quantities (e.g., yield and total biomass) are routinely monitored. In contrast, metrics quantifying more subjective crop quality characteristics such as ideal size and shape remain difficult to characterize objectively at the production-scale due to the lack of modular technologies for high-throughput sensing and computation. Several horticultural crops are sent to packing facilities after having been harvested, where they are sorted into boxes and containers using high-throughput scanners. These scanners capture images of each fruit or vegetable being sorted and packed, but the images are typically used solely for sorting purposes and promptly discarded. With further analysis, these images could offer unparalleled insight on how crop quality metrics vary at the industrial production-scale and provide further insight into how these characteristics translate to overall market value. At present, methods for extracting and quantifying quality characteristics of crops using images generated by existing industrial infrastructure have not been developed. Furthermore, prior studies that investigated horticultural crop quality metrics, specifically of size and shape, used a limited number of samples, did not incorporate deformed or non-marketable samples, and did not use images captured from high-throughput systems. In this work, using sweetpotato (SP) as a use case, we introduce a computer vision algorithm for quantifying shape and size characteristics in a high-throughput manner. This approach generates 3D model of SPs from two 2D images captured by an industrial sorter 90 degrees apart and extracts 3D shape features in a few hundred milliseconds. We applied the 3D reconstruction and feature extraction method to thousands of image samples to demonstrate how variations in shape features across sweetptoato cultivars can be quantified. We created a sweetpotato shape dataset containing sweetpotato images, extracted shape features, and qualitative shape types (U.S. No. 1 or Cull). We used this dataset to develop a neural network-based shape classifier that was able to predict Cull vs. U.S. No. 1 sweetpotato with 84.59% accuracy. In addition, using univariate Chi-squared tests and random forest, we identified the most important features for determining qualitative shape (U.S. No. 1 or Cull) of the sweetpotatoes. Our study serves as the first step towards enabling big data analytics for sweetpotato agriculture. The methodological framework is readily transferable to other horticultural crops, particularly those that are sorted using commercial imaging equipment.}, author={Haque, Samiul and Lobaton, Edgar and Nelson, Natalie and Yencho, G Craig and Pecota, Kenneth V and Mierop, Russell and Kudenov, Michael W and Boyette, Mike and Williams, Cranos M}, year={2020}, month={Jul} }
 @article{van den broeck_gordon_inzé_williams_sozzani_2020, title={Gene Regulatory Network Inference: Connecting Plant Biology and Mathematical Modeling}, volume={11}, ISSN={1664-8021}, url={http://dx.doi.org/10.3389/fgene.2020.00457}, DOI={10.3389/fgene.2020.00457}, abstractNote={Plant responses to environmental and intrinsic signals are tightly controlled by multiple transcription factors (TFs). These TFs and their regulatory connections form gene regulatory networks (GRNs), which provide a blueprint of the transcriptional regulations underlying plant development and environmental responses. This review provides examples of experimental methodologies commonly used to identify regulatory interactions and generate GRNs. Additionally, this review describes network inference techniques that leverage gene expression data to predict regulatory interactions. These computational and experimental methodologies yield complex networks that can identify new regulatory interactions, driving novel hypotheses. Biological properties that contribute to the complexity of GRNs are also described in this review. These include network topology, network size, transient binding of TFs to DNA, and competition between multiple upstream regulators. Finally, this review highlights the potential of machine learning approaches to leverage gene expression data to predict phenotypic outputs.}, journal={Frontiers in Genetics}, publisher={Frontiers Media SA}, author={Van den Broeck, Lisa and Gordon, Max and Inzé, Dirk and Williams, Cranos and Sozzani, Rosangela}, year={2020}, month={May} }
 @inbook{madison_melvin_buckner_williams_sozzani_long_2020, title={MAGIC: Live imaging of cellular division in plant seedlings using lightsheet microscopy}, volume={160}, ISBN={9780128215333}, ISSN={0091-679X}, url={http://dx.doi.org/10.1016/bs.mcb.2020.04.004}, DOI={10.1016/bs.mcb.2020.04.004}, abstractNote={Imaging technologies have been used to understand plant genetic and developmental processes, from the dynamics of gene expression to tissue and organ morphogenesis. Although the field has advanced incredibly in recent years, gaps remain in identifying fine and dynamic spatiotemporal intervals of target processes, such as changes to gene expression in response to abiotic stresses. Lightsheet microscopy is a valuable tool for such studies due to its ability to perform long-term imaging at fine intervals of time and at low photo-toxicity of live vertically oriented seedlings. In this chapter, we describe a detailed method for preparing and imaging Arabidopsis thaliana seedlings for lightsheet microscopy via a Multi-Sample Imaging Growth Chamber (MAGIC), which allows simultaneous imaging of at least four samples. This method opens new avenues for acquiring imaging data at a high temporal resolution, which can be eventually probed to identify key regulatory time points and any spatial dependencies of target developmental processes.}, booktitle={Methods in Cell Biology}, publisher={Elsevier}, author={Madison, Imani and Melvin, Charles and Buckner, Eli and Williams, Cranos and Sozzani, Rosangela and Long, Terri}, year={2020}, pages={405–418} }
 @article{matthews_wang_sederoff_chiang_williams_2020, title={Modeling cross-regulatory influences on monolignol transcripts and proteins under single and combinatorial gene knockdowns in Populus trichocarpa}, url={https://doi.org/10.1371/journal.pcbi.1007197}, DOI={10.1371/journal.pcbi.1007197}, abstractNote={Accurate manipulation of metabolites in monolignol biosynthesis is a key step for controlling lignin content, structure, and other wood properties important to the bioenergy and biomaterial industries. A crucial component of this strategy is predicting how single and combinatorial knockdowns of monolignol specific gene transcripts influence the abundance of monolignol proteins, which are the driving mechanisms of monolignol biosynthesis. Computational models have been developed to estimate protein abundances from transcript perturbations of monolignol specific genes. The accuracy of these models, however, is hindered by their inability to capture indirect regulatory influences on other pathway genes. Here, we examine the manifestation of these indirect influences on transgenic transcript and protein abundances, identifying putative indirect regulatory influences that occur when one or more specific monolignol pathway genes are perturbed. We created a computational model using sparse maximum likelihood to estimate the resulting monolignol transcript and protein abundances in transgenic Populus trichocarpa based on targeted knockdowns of specific monolignol genes. Using in-silico simulations of this model and root mean square error, we showed that our model more accurately estimated transcript and protein abundances, in comparison to previous models, when individual and families of monolignol genes were perturbed. We leveraged insight from the inferred network structure obtained from our model to identify potential genes, including PtrHCT, PtrCAD, and Ptr4CL, involved in post-transcriptional and/or post-translational regulation. Our model provides a useful computational tool for exploring the cascaded impact of single and combinatorial modifications of monolignol specific genes on lignin and other wood properties.}, journal={PLOS Computational Biology}, author={Matthews, Megan L. and Wang, Jack P. and Sederoff, Ronald and Chiang, Vincent L. and Williams, Cranos M.}, editor={Roy, SushmitaEditor}, year={2020}, month={Apr} }
 @article{argueso_assmann_birnbaum_chen_dinneny_doherty_eveland_friesner_greenlee_law_et al._2019, title={Directions for research and training in plant omics: Big Questions and Big Data}, volume={3}, ISSN={2475-4455}, url={http://dx.doi.org/10.1002/PLD3.133}, DOI={10.1002/PLD3.133}, abstractNote={AbstractA key remit of the NSF‐funded “Arabidopsis Research and Training for the 21st Century” (ART‐21) Research Coordination Network has been to convene a series of workshops with community members to explore issues concerning research and training in plant biology, including the role that research using Arabidopsis thaliana can play in addressing those issues. A first workshop focused on training needs for bioinformatic and computational approaches in plant biology was held in 2016, and recommendations from that workshop have been published (Friesner et al., Plant Physiology, 175, 2017, 1499). In this white paper, we provide a summary of the discussions and insights arising from the second ART‐21 workshop. The second workshop focused on experimental aspects of omics data acquisition and analysis and involved a broad spectrum of participants from academics and industry, ranging from graduate students through post‐doctorates, early career and established investigators. Our hope is that this article will inspire beginning and established scientists, corporations, and funding agencies to pursue directions in research and training identified by this workshop, capitalizing on the reference species Arabidopsis thaliana and other valuable plant systems.}, number={4}, journal={Plant Direct}, publisher={Wiley}, author={Argueso, Cristiana T. and Assmann, Sarah M. and Birnbaum, Kenneth D. and Chen, Sixue and Dinneny, José R. and Doherty, Colleen J. and Eveland, Andrea L. and Friesner, Joanna and Greenlee, Vanessa R. and Law, Julie A. and et al.}, year={2019}, month={Apr}, pages={e00133} }
 @article{wang_matthews_naik_williams_ducoste_sederoff_chiang_2019, title={Flux modeling for monolignol biosynthesis}, volume={56}, ISSN={0958-1669}, url={http://dx.doi.org/10.1016/J.COPBIO.2018.12.003}, DOI={10.1016/J.COPBIO.2018.12.003}, abstractNote={The pathway of monolignol biosynthesis involves many components interacting in a metabolic grid to regulate the supply and ratios of monolignols for lignification. The complexity of the pathway challenges any intuitive prediction of the output without mathematical modeling. Several models have been presented to quantify the metabolic flux for monolignol biosynthesis and the regulation of lignin content, composition, and structure in plant cell walls. Constraint-based models using data from transgenic plants were formulated to describe steady-state flux distribution in the pathway. Kinetic-based models using enzyme reaction and inhibition constants were developed to predict flux dynamics for monolignol biosynthesis in wood-forming cells. This review summarizes the recent progress in flux modeling and its application to lignin engineering for improved plant development and utilization.}, journal={Current Opinion in Biotechnology}, publisher={Elsevier BV}, author={Wang, Jack P and Matthews, Megan L and Naik, Punith P and Williams, Cranos M and Ducoste, Joel J and Sederoff, Ronald R and Chiang, Vincent L}, year={2019}, month={Apr}, pages={187–192} }
 @article{matthews_wang_sederoff_chiang_williams_2019, title={Modeling cross-regulatory influences on monolignol transcripts and proteins under single and combinatorial gene knockdowns in Populus trichocarpa}, volume={6}, url={https://doi.org/10.1101/677047}, DOI={10.1101/677047}, abstractNote={AbstractAccurate manipulation of metabolites in the monolignol biosynthetic pathway is a key step for controlling lignin content, structure, and other wood properties important to the bioenergy and biomaterial industries. A crucial component of this strategy is predicting how single and combinatorial knockdowns of monolignol specific gene transcripts influence the abundance of monolignol proteins, which are the driving mechanisms of monolignol biosynthesis. Computational models have been developed to estimate protein abundances from transcript perturbations of monolignol specific genes. The accuracy of these models, however, is hindered by the inability to capture indirect regulatory influences on other pathway genes. Here, we examine the manifestation of these indirect influences collectively on transgenic transcript and protein abundances, identifying putative indirect regulatory influences that occur when one or more specific monolignol pathway genes are perturbed. We created a computational model using sparse maximum likelihood to estimate the resulting monolignol transcript and protein abundances in transgenic Populus trichocarpa based on desired single or combinatorial knockdowns of specific monolignol genes. Using in-silico simulations of this model and root mean square error, we show that our model more accurately estimates transcript and protein abundances in differentiating xylem tissue when individual and families of monolignol genes were perturbed. This approach provides a useful computational tool for exploring the cascaded impact of single and combinatorial modifications of monolignol specific genes on lignin and other wood properties. Additionally, these results can be used to guide future experiments to elucidate the mechanisms responsible for the indirect influences.Author summaryEngineering trees to have desirable lignin and wood traits is of significant interest to the bioenergy and biomaterial industries. Genetically modifying the expression of the genes that drive the monolignol biosynthetic pathway is a useful method for obtaining new traits. Modifying the expression of one gene affects not only the abundance of its encoded protein, but can also indirectly impact the amount of other transcripts and proteins. These proteins drive the monolignol biosynthetic pathway. Having an accurate representation of their abundances is key to understanding how lignin and wood traits are altered. We developed a computational model to estimate how the abundance of monolignol transcripts and proteins are changed when one or more monolignol genes are knocked down. Specifying only the abundances of the targeted genes as input, our model estimates how the levels of the other, untargeted, transcripts and proteins are altered. Our model captures indirect regulatory influences at the transcript and protein levels observed in experimental data. The model is an important addition to current models of lignin biosynthesis. By incorporating our approach into the existing models, we expect to improve our ability to explore how new combinations of gene knockdowns impact lignin and many other wood properties.}, publisher={Cold Spring Harbor Laboratory}, author={Matthews, Megan L. and Wang, Jack P. and Sederoff, Ronald and Chiang, Vincent L. and Williams, Cranos M.}, year={2019}, month={Jun} }
 @article{clark_buckner_fisher_nelson_nguyen_simmons_balaguer_butler-smith_sheldon_bergmann_et al._2019, title={Stem-cell-ubiquitous genes spatiotemporally coordinate division through regulation of stem-cell-specific gene networks}, volume={10}, ISSN={["2041-1723"]}, DOI={10.1038/s41467-019-13132-2}, abstractNote={AbstractStem cells are responsible for generating all of the differentiated cells, tissues, and organs in a multicellular organism and, thus, play a crucial role in cell renewal, regeneration, and organization. A number of stem cell type-specific genes have a known role in stem cell maintenance, identity, and/or division. Yet, how genes expressed across different stem cell types, referred to here as stem-cell-ubiquitous genes, contribute to stem cell regulation is less understood. Here, we find that, in the Arabidopsis root, a stem-cell-ubiquitous gene, TESMIN-LIKE CXC2 (TCX2), controls stem cell division by regulating stem cell-type specific networks. Development of a mathematical model of TCX2 expression allows us to show that TCX2 orchestrates the coordinated division of different stem cell types. Our results highlight that genes expressed across different stem cell types ensure cross-communication among cells, allowing them to divide and develop harmonically together.}, journal={NATURE COMMUNICATIONS}, author={Clark, Natalie M. and Buckner, Eli and Fisher, Adam P. and Nelson, Emily C. and Nguyen, Thomas T. and Simmons, Abigail R. and Balaguer, Maria A. de Luis and Butler-Smith, Tiara and Sheldon, Parnell J. and Bergmann, Dominique C. and et al.}, year={2019}, month={Dec} }
 @article{naik_wang_sederoff_chiang_williams_ducoste_2018, title={Assessing the impact of the 4CL enzyme complex on the robustness of monolignol biosynthesis using metabolic pathway analysis}, volume={13}, ISSN={1932-6203}, url={http://dx.doi.org/10.1371/journal.pone.0193896}, DOI={10.1371/journal.pone.0193896}, abstractNote={Lignin is a polymer present in the secondary cell walls of all vascular plants. It is a known barrier to pulping and the extraction of high-energy sugars from cellulosic biomass. The challenge faced with predicting outcomes of transgenic plants with reduced lignin is due in part to the presence of unique protein-protein interactions that influence the regulation and metabolic flux in the pathway. Yet, it is unclear why certain plants have evolved to create these protein complexes. In this study, we use mathematical models to investigate the role that the protein complex, formed specifically between Ptr4CL3 and Ptr4CL5 enzymes, have on the monolignol biosynthesis pathway. The role of this Ptr4CL3-Ptr4CL5 enzyme complex on the steady state flux distribution was quantified by performing Monte Carlo simulations. The effect of this complex on the robustness and the homeostatic properties of the pathway were identified by performing sensitivity and stability analyses, respectively. Results from these robustness and stability analyses suggest that the monolignol biosynthetic pathway is resilient to mild perturbations in the presence of the Ptr4CL3-Ptr4CL5 complex. Specifically, the presence of Ptr4CL3-Ptr4CL5 complex increased the stability of the pathway by 22%. The robustness in the pathway is maintained due to the presence of multiple enzyme isoforms as well as the presence of alternative pathways resulting from the presence of the Ptr4CL3-Ptr4CL5 complex.}, number={3}, journal={PLOS ONE}, publisher={Public Library of Science (PLoS)}, author={Naik, Punith and Wang, Jack P. and Sederoff, Ronald and Chiang, Vincent and Williams, Cranos and Ducoste, Joel J.}, editor={Cullen, DanielEditor}, year={2018}, month={Mar}, pages={e0193896} }
 @article{haque_ahmad_clark_williams_sozzani_2019, title={Computational prediction of gene regulatory networks in plant growth and development}, volume={47}, ISSN={1369-5266}, url={http://dx.doi.org/10.1016/J.PBI.2018.10.005}, DOI={10.1016/J.PBI.2018.10.005}, abstractNote={Plants integrate a wide range of cellular, developmental, and environmental signals to regulate complex patterns of gene expression. Recent advances in genomic technologies enable differential gene expression analysis at a systems level, allowing for improved inference of the network of regulatory interactions between genes. These gene regulatory networks, or GRNs, are used to visualize the causal regulatory relationships between regulators and their downstream target genes. Accordingly, these GRNs can represent spatial, temporal, and/or environmental regulations and can identify functional genes. This review summarizes recent computational approaches applied to different types of gene expression data to infer GRNs in the context of plant growth and development. Three stages of GRN inference are described: first, data collection and analysis based on the dataset type; second, network inference application based on data availability and proposed hypotheses; and third, validation based on in silico, in vivo, and in planta methods. In addition, this review relates data collection strategies to biological questions, organizes inference algorithms based on statistical methods and data types, discusses experimental design considerations, and provides guidelines for GRN inference with an emphasis on the benefits of integrative approaches, especially when a priori information is limited. Finally, this review concludes that computational frameworks integrating large-scale heterogeneous datasets are needed for a more accurate (e.g. fewer false interactions), detailed (e.g. discrimination between direct versus indirect interactions), and comprehensive (e.g. genetic regulation under various conditions and spatial locations) inference of GRNs.}, journal={Current Opinion in Plant Biology}, publisher={Elsevier BV}, author={Haque, Samiul and Ahmad, Jabeen S and Clark, Natalie M and Williams, Cranos M and Sozzani, Rosangela}, year={2019}, month={Feb}, pages={96–105} }
 @article{wang_matthews_williams_shi_yang_tunlaya-anukit_chen_li_liu_lin_et al._2018, title={Improving wood properties for wood utilization through multi-omics integration in lignin biosynthesis}, volume={9}, ISSN={2041-1723}, url={http://dx.doi.org/10.1038/s41467-018-03863-z}, DOI={10.1038/s41467-018-03863-z}, abstractNote={AbstractA multi-omics quantitative integrative analysis of lignin biosynthesis can advance the strategic engineering of wood for timber, pulp, and biofuels. Lignin is polymerized from three monomers (monolignols) produced by a grid-like pathway. The pathway in wood formation of Populus trichocarpa has at least 21 genes, encoding enzymes that mediate 37 reactions on 24 metabolites, leading to lignin and affecting wood properties. We perturb these 21 pathway genes and integrate transcriptomic, proteomic, fluxomic and phenomic data from 221 lines selected from ~2000 transgenics (6-month-old). The integrative analysis estimates how changing expression of pathway gene or gene combination affects protein abundance, metabolic-flux, metabolite concentrations, and 25 wood traits, including lignin, tree-growth, density, strength, and saccharification. The analysis then predicts improvements in any of these 25 traits individually or in combinations, through engineering expression of specific monolignol genes. The analysis may lead to greater understanding of other pathways for improved growth and adaptation.}, number={1}, journal={Nature Communications}, publisher={Springer Science and Business Media LLC}, author={Wang, Jack P. and Matthews, Megan L. and Williams, Cranos M. and Shi, Rui and Yang, Chenmin and Tunlaya-Anukit, Sermsawat and Chen, Hsi-Chuan and Li, Quanzi and Liu, Jie and Lin, Chien-Yuan and et al.}, year={2018}, month={Apr}, pages={1579} }
 @article{alexander_williams_2017, title={Design of digital filters}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={205–275} }
 @article{alexander_williams_2017, title={Digital signal processing systems design}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={455–517} }
 @article{alexander_williams_2017, title={Digital signal processing: principles, algorithms and system design preface}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={XXVII-} }
 @article{alexander_williams_alexander_williams_2017, title={Finite Word Length Effects}, ISBN={["978-0-12-804547-3"]}, DOI={10.1016/b978-0-12-804547-3.00006-1}, abstractNote={Chapter 6 covers methods used to represent numbers and the impact of the use of finite precision arithmetic for the implementation of discrete time systems. It discusses the representation of numbers using the IEEE floating point representation, computational errors due to rounding, and the multiplication of numbers that are represented using floating point. It covers the analytical basis for the two's complement representation of numbers and computational procedures for numbers represented using two's complement numbers. It covers the scaling of the coefficients for discrete time systems for given word sizes and for a restriction to avoid over ow during computations. It also presents a concept for statistical analysis of rounding errors due to word length effects.}, journal={DIGITAL SIGNAL PROCESSING: PRINCIPLES, ALGORITHMS AND SYSTEM DESIGN}, author={Alexander, Winser E. and Williams, Cranos M. and Alexander, WE and Williams, CM}, year={2017}, pages={351–388} }
 @article{alexander_williams_2017, title={Frequency domain analysis}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={159–204} }
 @article{alexander_williams_2017, title={Fundamental DSP concepts}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={19–157} }
 @article{alexander_williams_2017, title={Hardware implementation}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={519–561} }
 @article{alexander_williams_2017, title={Implementation of discrete time systems}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={277–350} }
 @article{alexander_williams_2017, title={Introduction to digital signal processing}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={1–17} }
 @article{alexander_williams_2017, title={Multirate digital signal processing}, journal={Digital Signal Processing: Principles, Algorithms and System Design}, author={Alexander, W. E. and Williams, C. M.}, year={2017}, pages={389–454} }
 @article{balaguer_fisher_clark_fernandez-espinosa_moller_weijers_lohmann_williams_lorenzo_sozzani_et al._2017, title={Predicting gene regulatory networks by combining spatial and temporal gene expression data in Arabidopsis root stem cells}, volume={114}, ISSN={["0027-8424"]}, DOI={10.1073/pnas.1707566114}, abstractNote={Significance
          
            We developed a computational pipeline that uses gene expression datasets for inferring relationships among genes and predicting their importance. We showed that the capacity of our pipeline to integrate spatial and temporal transcriptional datasets improves the performance of inference algorithms. The combination of this pipeline with
            Arabidopsis
            stem cell-specific data resulted in networks that capture the regulations of stem cell-enriched genes in the stem cells and throughout root development. Our combined approach of molecular biology, computational biology, and mathematical biology, led to successful findings of factors that could play important roles in stem cell regulation and, in particular, quiescent center function.
          }, number={36}, journal={PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA}, author={Balaguer, M. A. D. and Fisher, A. P. and Clark, N. M. and Fernandez-Espinosa, M. G. and Moller, B. K. and Weijers, D. and Lohmann, J. U. and Williams, C. and Lorenzo, O. and Sozzani, Rosangela and et al.}, year={2017}, month={Sep}, pages={E7632–E7640} }
 @misc{muhammad_schmittling_williams_long_2017, title={More than meets the eye: Emergent properties of transcription factors networks in Arabidopsis}, volume={1860}, ISSN={["0006-3002"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84995470767&partnerID=MN8TOARS}, DOI={10.1016/j.bbagrm.2016.07.017}, abstractNote={Uncovering and mathematically modeling Transcription Factor Networks (TFNs) are the first steps in engineering plants with traits that are better equipped to respond to changing environments. Although several plant TFNs are well known, the framework for systematically modeling complex characteristics such as switch-like behavior, oscillations, and homeostasis that emerge from them remain elusive. This review highlights literature that provides, in part, experimental and computational techniques for characterizing TFNs. This review also outlines methodologies that have been used to mathematically model the dynamic characteristics of TFNs. We present several examples of TFNs in plants that are involved in developmental and stress response. In several cases, advanced algorithms capture or quantify emergent properties that serve as the basis for robustness and adaptability in plant responses. Increasing the use of mathematical approaches will shed new light on these regulatory properties that control plant growth and development, leading to mathematical models that predict plant behavior. This article is part of a Special Issue entitled: Plant Gene Regulatory Mechanisms and Networks, edited by Dr. Erich Grotewold and Dr. Nathan Springer.}, number={1}, journal={BIOCHIMICA ET BIOPHYSICA ACTA-GENE REGULATORY MECHANISMS}, author={Muhammad, Durreshahwar and Schmittling, Selene and Williams, Cranos and Long, Terri A.}, year={2017}, month={Jan}, pages={64–74} }
 @article{lin_wang_li_chen_liu_loziuk_song_williams_muddiman_sederoff_et al._2015, title={4-Coumaroyl and Caffeoyl Shikimic Acids Inhibit 4-Coumaric Acid: Coenzyme A Ligases and Modulate Metabolic Flux for 3-Hydroxylation in Monolignol Biosynthesis of Populus trichocarpa}, volume={8}, ISSN={["1752-9867"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84925201417&partnerID=MN8TOARS}, DOI={10.1016/j.molp.2014.12.003}, abstractNote={Downregulation of 4-coumaric acid:coenzyme A ligase (4CL) can reduce lignin content in a number of plant species. In lignin precursor (monolignol) biosynthesis during stem wood formation in Populus trichocarpa, two enzymes, Ptr4CL3 and Ptr4CL5, catalyze the coenzyme A (CoA) ligation of 4-coumaric acid to 4-coumaroyl-CoA and caffeic acid to caffeoyl-CoA. CoA ligation of 4-coumaric acid is essential for the 3-hydroxylation of 4-coumaroyl shikimic acid. This hydroxylation results from sequential reactions of 4-hydroxycinnamoyl-CoA:shikimic acid hydroxycinnamoyl transferases (PtrHCT1 and PtrHCT6) and 4-coumaric acid 3-hydroxylase 3 (PtrC3H3). Alternatively, 3-hydroxylation of 4-coumaric acid to caffeic acid may occur through an enzyme complex of cinnamic acid 4-hydroxylase 1 and 2 (PtrC4H1 and PtrC4H2) and PtrC3H3. We found that 4-coumaroyl and caffeoyl shikimic acids are inhibitors of Ptr4CL3 and Ptr4CL5. 4-Coumaroyl shikimic acid strongly inhibits the formation of 4-coumaroyl-CoA and caffeoyl-CoA. Caffeoyl shikimic acid inhibits only the formation of 4-coumaroyl-CoA. 4-Coumaroyl and caffeoyl shikimic acids both act as competitive and uncompetitive inhibitors. Metabolic flux in wild-type and PtrC3H3 downregulated P. trichocarpa transgenics has been estimated by absolute protein and metabolite quantification based on liquid chromatography–tandem mass spectrometry, mass action kinetics, and inhibition equations. Inhibition by 4-coumaroyl and caffeoyl shikimic acids may play significant regulatory roles when these inhibitors accumulate.}, number={1}, journal={MOLECULAR PLANT}, author={Lin, Chien-Yuan and Wang, Jack P. and Li, Quanzi and Chen, Hsi-Chuan and Liu, Jie and Loziuk, Philip and Song, Jina and Williams, Cranos and Muddiman, David C. and Sederoff, Ronald R. and et al.}, year={2015}, month={Jan}, pages={176–187} }
 @article{koryachko_matthiadis_muhammad_foret_brady_ducoste_tuck_long_williams_2015, title={Clustering and Differential Alignment Algorithm: Identification of Early Stage Regulators in the Arabidopsis thaliana Iron Deficiency Response}, volume={10}, ISSN={["1932-6203"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84943338816&partnerID=MN8TOARS}, DOI={10.1371/journal.pone.0136591}, abstractNote={Time course transcriptome datasets are commonly used to predict key gene regulators associated with stress responses and to explore gene functionality. Techniques developed to extract causal relationships between genes from high throughput time course expression data are limited by low signal levels coupled with noise and sparseness in time points. We deal with these limitations by proposing the Cluster and Differential Alignment Algorithm (CDAA). This algorithm was designed to process transcriptome data by first grouping genes based on stages of activity and then using similarities in gene expression to predict influential connections between individual genes. Regulatory relationships are assigned based on pairwise alignment scores generated using the expression patterns of two genes and some inferred delay between the regulator and the observed activity of the target. We applied the CDAA to an iron deficiency time course microarray dataset to identify regulators that influence 7 target transcription factors known to participate in the Arabidopsis thaliana iron deficiency response. The algorithm predicted that 7 regulators previously unlinked to iron homeostasis influence the expression of these known transcription factors. We validated over half of predicted influential relationships using qRT-PCR expression analysis in mutant backgrounds. One predicted regulator-target relationship was shown to be a direct binding interaction according to yeast one-hybrid (Y1H) analysis. These results serve as a proof of concept emphasizing the utility of the CDAA for identifying unknown or missing nodes in regulatory cascades, providing the fundamental knowledge needed for constructing predictive gene regulatory networks. We propose that this tool can be used successfully for similar time course datasets to extract additional information and infer reliable regulatory connections for individual genes.}, number={8}, journal={PLOS ONE}, author={Koryachko, Alexandr and Matthiadis, Anna and Muhammad, Durreshahwar and Foret, Jessica and Brady, Siobhan M. and Ducoste, Joel J. and Tuck, James and Long, Terri A. and Williams, Cranos}, year={2015}, month={Aug} }
 @article{koryachko_matthiadis_ducoste_tuck_long_williams_2015, title={Computational approaches to identify regulators of plant stress response using high-throughput gene expression data}, volume={3-4}, ISSN={2214-6628}, url={http://dx.doi.org/10.1016/J.CPB.2015.04.001}, DOI={10.1016/J.CPB.2015.04.001}, abstractNote={Insight into biological stress regulatory pathways can be derived from high-throughput transcriptomic data using computational algorithms. These algorithms can be integrated into a computational approach to provide specific testable predictions that answer biological questions of interest. This review conceptually organizes a wide variety of developed algorithms into a classification system based on desired type of output predictions. This classification is then used as a structure to describe completed approaches in the literature, with a focus on project goals, overall path of implemented algorithms, and biological insight gained. These algorithms and approaches are introduced mainly in the context of research on the model plant species Arabidopsis thaliana under stress conditions, though the nature of computational techniques makes these approaches easily applicable to a wide range of species, data types, and conditions.}, journal={Current Plant Biology}, publisher={Elsevier BV}, author={Koryachko, Alexandr and Matthiadis, Anna and Ducoste, Joel J. and Tuck, James and Long, Terri A. and Williams, Cranos}, year={2015}, month={Sep}, pages={20–29} }
 @article{balaguer_williams_2014, title={Hierarchical Modularization Of Biochemical Pathways Using Fuzzy-C Means Clustering}, volume={44}, ISSN={["2168-2275"]}, DOI={10.1109/tcyb.2013.2286679}, abstractNote={Biological systems that are representative of regulatory, metabolic, or signaling pathways can be highly complex. Mathematical models that describe such systems inherit this complexity. As a result, these models can often fail to provide a path toward the intuitive comprehension of these systems. More coarse information that allows a perceptive insight of the system is sometimes needed in combination with the model to understand control hierarchies or lower level functional relationships. In this paper, we present a method to identify relationships between components of dynamic models of biochemical pathways that reside in different functional groups. We find primary relationships and secondary relationships. The secondary relationships reveal connections that are present in the system, which current techniques that only identify primary relationships are unable to show. We also identify how relationships between components dynamically change over time. This results in a method that provides the hierarchy of the relationships among components, which can help us to understand the low level functional structure of the system and to elucidate potential hierarchical control. As a proof of concept, we apply the algorithm to the epidermal growth factor signal transduction pathway, and to the C3 photosynthesis pathway. We identify primary relationships among components that are in agreement with previous computational decomposition studies, and identify secondary relationships that uncover connections among components that current computational approaches were unable to reveal.}, number={8}, journal={IEEE TRANSACTIONS ON CYBERNETICS}, author={Balaguer, Maria A. de Luis and Williams, Cranos M.}, year={2014}, month={Aug}, pages={1473–1484} }
 @article{chen_song_wang_lin_ducoste_shuford_liu_li_shi_nepomuceno_et al._2014, title={Systems Biology of Lignin Biosynthesis in Populus trichocarpa: Heteromeric 4-Coumaric Acid:Coenzyme A Ligase Protein Complex Formation, Regulation, and Numerical Modeling}, volume={26}, ISSN={1040-4651 1532-298X}, url={http://dx.doi.org/10.1105/tpc.113.119685}, DOI={10.1105/tpc.113.119685}, abstractNote={This work shows that 4CL, an enzyme in monolignol biosynthesis, is found as a heterotetrameric complex of two isoforms in Populus trichocarpa. The activity of the heterotetramer can be described by a mathematical model that explains the effects of each isoform with mixtures of substrates and three types of inhibition, providing insights into the regulation of metabolic flux for this pathway. As a step toward predictive modeling of flux through the pathway of monolignol biosynthesis in stem differentiating xylem of Populus trichocarpa, we discovered that the two 4-coumaric acid:CoA ligase (4CL) isoforms, 4CL3 and 4CL5, interact in vivo and in vitro to form a heterotetrameric protein complex. This conclusion is based on laser microdissection, coimmunoprecipitation, chemical cross-linking, bimolecular fluorescence complementation, and mass spectrometry. The tetramer is composed of three subunits of 4CL3 and one of 4CL5. 4CL5 appears to have a regulatory role. This protein–protein interaction affects the direction and rate of metabolic flux for monolignol biosynthesis in P. trichocarpa. A mathematical model was developed for the behavior of 4CL3 and 4CL5 individually and in mixtures that form the enzyme complex. The model incorporates effects of mixtures of multiple hydroxycinnamic acid substrates, competitive inhibition, uncompetitive inhibition, and self-inhibition, along with characteristic of the substrates, the enzyme isoforms, and the tetrameric complex. Kinetic analysis of different ratios of the enzyme isoforms shows both inhibition and activation components, which are explained by the mathematical model and provide insight into the regulation of metabolic flux for monolignol biosynthesis by protein complex formation.}, number={3}, journal={The Plant Cell}, publisher={Oxford University Press (OUP)}, author={Chen, Hsi-Chuan and Song, Jina and Wang, Jack P. and Lin, Ying-Chung and Ducoste, Joel and Shuford, Christopher M. and Liu, Jie and Li, Quanzi and Shi, Rui and Nepomuceno, Angelito and et al.}, year={2014}, month={Mar}, pages={876–893} }
 @article{chen_song_williams_shuford_liu_wang_li_shi_gokce_ducoste_et al._2013, title={Monolignol Pathway 4-Coumaric Acid: Coenzyme A Ligases in Populus trichocarpa: Novel Specificity, Metabolic Regulation, and Simulation of Coenzyme A Ligation Fluxes}, volume={161}, ISSN={["0032-0889"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84874626790&partnerID=MN8TOARS}, DOI={10.1104/pp.112.210971}, abstractNote={Abstract
               4-Coumaric acid:coenzyme A ligase (4CL) is involved in monolignol biosynthesis for lignification in plant cell walls. It ligates coenzyme A (CoA) with hydroxycinnamic acids, such as 4-coumaric and caffeic acids, into hydroxycinnamoyl-CoA thioesters. The ligation ensures the activated state of the acid for reduction into monolignols. In Populus spp., it has long been thought that one monolignol-specific 4CL is involved. Here, we present evidence of two monolignol 4CLs, Ptr4CL3 and Ptr4CL5, in Populus trichocarpa. Ptr4CL3 is the ortholog of the monolignol 4CL reported for many other species. Ptr4CL5 is novel. The two Ptr4CLs exhibited distinct Michaelis-Menten kinetic properties. Inhibition kinetics demonstrated that hydroxycinnamic acid substrates are also inhibitors of 4CL and suggested that Ptr4CL5 is an allosteric enzyme. Experimentally validated flux simulation, incorporating reaction/inhibition kinetics, suggested two CoA ligation paths in vivo: one through 4-coumaric acid and the other through caffeic acid. We previously showed that a membrane protein complex mediated the 3-hydroxylation of 4-coumaric acid to caffeic acid. The demonstration here of two ligation paths requiring these acids supports this 3-hydroxylation function. Ptr4CL3 regulates both CoA ligation paths with similar efficiencies, whereas Ptr4CL5 regulates primarily the caffeic acid path. Both paths can be inhibited by caffeic acid. The Ptr4CL5-catalyzed caffeic acid metabolism, therefore, may also act to mitigate the inhibition by caffeic acid to maintain a proper ligation flux. A high level of caffeic acid was detected in stem-differentiating xylem of P. trichocarpa. Our results suggest that Ptr4CL5 and caffeic acid coordinately modulate the CoA ligation flux for monolignol biosynthesis.}, number={3}, journal={PLANT PHYSIOLOGY}, author={Chen, Hsi-Chuan and Song, Jina and Williams, Cranos M. and Shuford, Christopher M. and Liu, Jie and Wang, Jack P. and Li, Quanzi and Shi, Rui and Gokce, Emine and Ducoste, Joel and et al.}, year={2013}, month={Mar}, pages={1501–1516} }
 @inproceedings{nabavi_williams_2012, title={A novel cost function for parameters estimation in oscillatory biochemical systems}, DOI={10.1109/secon.2012.6196978}, abstractNote={Oscillatory pathways are among the most important classes of biochemical systems with examples ranging from circadian rhythms and cell cycle maintenance. Mathematical modeling of these highly interconnected biochemical networks is needed to meet numerous objectives such as investigating, predicting and controlling the dynamics of these systems. Identifying the kinetic rate parameters is essential for fully modeling these and other biological processes. These kinetic parameters, however, cannot be measured directly and most of them have to be estimated using parameter fitting techniques. One of the issues with estimating kinetic parameters in oscillatory systems is the irregularities in the Least Square (LS) cost function surface used to estimate these parameters, which is caused by the periodicity of the measurements. These irregularities result in numerous local minima, which limit the performance of even some of the most robust global optimization algorithms. We proposed a cost function to address these issues by integrating temporal information with periodic information embedded in the measurements. This new cost function has better surface properties leading to fewer local minima and better performance of global optimization algorithms. We verified for two oscillatory biochemical systems that our method results in an increased ability to estimate accurate kinetic parameters as compared to the traditional LS cost function. This will eventually lead to biochemical models that are more precise, predictable and controllable.}, booktitle={2012 Proceedings of IEEE Southeastcon}, author={Nabavi, S. and Williams, Cranos}, year={2012} }
 @article{wang_shuford_li_song_lin_sun_chen_williams_muddiman_sederoff_et al._2012, title={Functional redundancy of the two 5-hydroxylases in monolignol biosynthesis of Populus trichocarpa: LC-MS/MS based protein quantification and metabolic flux analysis}, volume={236}, ISSN={["1432-2048"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84865584315&partnerID=MN8TOARS}, DOI={10.1007/s00425-012-1663-5}, abstractNote={Flowering plants have syringyl and guaiacyl subunits in lignin in contrast to the guaiacyl lignin in gymnosperms. The biosynthesis of syringyl subunits is initiated by coniferaldehyde 5-hydroxylase (CAld5H). In Populus trichocarpa there are two closely related CAld5H enzymes (PtrCAld5H1 and PtrCAld5H2) associated with lignin biosynthesis during wood formation. We used yeast recombinant PtrCAld5H1 and PtrCAld5H2 proteins to carry out Michaelis-Menten and inhibition kinetics with LC-MS/MS based absolute protein quantification. CAld5H, a monooxygenase, requires a cytochrome P450 reductase (CPR) as an electron donor. We cloned and expressed three P. trichocarpa CPRs in yeast and show that all are active with both CAld5Hs. The kinetic analysis shows both CAld5Hs have essentially the same biochemical functions. When both CAld5Hs are coexpressed in the same yeast membranes, the resulting enzyme activities are additive, suggesting functional redundancy and independence of these two enzymes. Simulated reaction flux based on Michaelis-Menten kinetics and inhibition kinetics confirmed the redundancy and independence. Subcellular localization of both CAld5Hs as sGFP fusion proteins expressed in P. trichocarpa differentiating xylem protoplasts indicate that they are endoplasmic reticulum resident proteins. These results imply that during wood formation, 5-hydroxylation in monolignol biosynthesis of P. trichocarpa requires the combined metabolic flux of these two CAld5Hs to maintain adequate biosynthesis of syringyl lignin. The combination of genetic analysis, absolute protein quantitation-based enzyme kinetics, homologous CPR specificity, SNP characterization, and ER localization provides a more rigorous basis for a comprehensive systems understanding of 5-hydroxylation in lignin biosynthesis.}, number={3}, journal={PLANTA}, publisher={Springer Science + Business Media}, author={Wang, Jack P. and Shuford, Christopher M. and Li, Quanzi and Song, Jina and Lin, Ying-Chung and Sun, Ying-Hsuan and Chen, Hsi-Chuan and Williams, Cranos M. and Muddiman, David C. and Sederoff, Ronald R. and et al.}, year={2012}, month={Sep}, pages={795–808} }
 @inproceedings{matthews_williams_2012, title={Region of attraction estimation of biological continuous Boolean models}, DOI={10.1109/icsmc.2012.6377982}, abstractNote={Quantitative analysis of biological systems has become an increasingly important research field as scientists look to solve current day health and environmental problems. The development of modeling and model analysis approaches that are specifically geared toward biological processes is a rapidly growing research area. Continuous approximations of Boolean models, for example, have been identified as a viable method for modeling such systems. This is because they are capable of generating dynamic models of biochemical pathways using inferred dependency relationships between components. The resulting nonlinear equations and therefore nonlinear dynamics, however, can present a challenge for most system analysis approaches such as region of attraction (ROA) estimation. Continued progress in the area of biosystems modeling will require that computational techniques used to analyze simple nonlinear systems can still be applied to nonlinear equations typically used to model the dynamics associated with biological processes. In this paper, we assess the applicability of a state of the art ROA estimation technique based on interval arithmetic to a subnetwork of the Rb-E2F signaling pathway modeled using continuous Boolean functions. We show that this method can successfully be used to provide an estimate of the ROA for dynamic models described using Hillcube continuous Boolean approximations.}, booktitle={Ieee international conference on systems man and cybernetics conference}, author={Matthews, M. L. and Williams, Cranos}, year={2012}, pages={1700–1705} }
 @article{marvel_williams_2012, title={Set membership experimental design for biological systems}, volume={6}, ISSN={["1752-0509"]}, DOI={10.1186/1752-0509-6-21}, abstractNote={Experimental design approaches for biological systems are needed to help conserve the limited resources that are allocated for performing experiments. The assumptions used when assigning probability density functions to characterize uncertainty in biological systems are unwarranted when only a small number of measurements can be obtained. In these situations, the uncertainty in biological systems is more appropriately characterized in a bounded-error context. Additionally, effort must be made to improve the connection between modelers and experimentalists by relating design metrics to biologically relevant information. Bounded-error experimental design approaches that can assess the impact of additional measurements on model uncertainty are needed to identify the most appropriate balance between the collection of data and the availability of resources. In this work we develop a bounded-error experimental design framework for nonlinear continuous-time systems when few data measurements are available. This approach leverages many of the recent advances in bounded-error parameter and state estimation methods that use interval analysis to generate parameter sets and state bounds consistent with uncertain data measurements. We devise a novel approach using set-based uncertainty propagation to estimate measurement ranges at candidate time points. We then use these estimated measurements at the candidate time points to evaluate which candidate measurements furthest reduce model uncertainty. A method for quickly combining multiple candidate time points is presented and allows for determining the effect of adding multiple measurements. Biologically relevant metrics are developed and used to predict when new data measurements should be acquired, which system components should be measured and how many additional measurements should be obtained. The practicability of our approach is illustrated with a case study. This study shows that our approach is able to 1) identify candidate measurement time points that maximize information corresponding to biologically relevant metrics and 2) determine the number at which additional measurements begin to provide insignificant information. This framework can be used to balance the availability of resources with the addition of one or more measurement time points to improve the predictability of resulting models.}, journal={BMC SYSTEMS BIOLOGY}, author={Marvel, Skylar W. and Williams, Cranos M.}, year={2012}, month={Mar} }
 @inproceedings{marvel_williams_2012, title={Set membership state and parameter estimation for nonlinear differential equations with sparse discrete measurements}, DOI={10.1109/icsmc.2012.6377679}, abstractNote={This paper presents a method to perform parameter and state estimation in a bounded-error context for nonlinear continuous-time systems with sparse, discrete measurements. Direct application of a guaranteed parameter estimation method can be fruitless when few data measurements are available. This lack of measurements results in what we term “phantom” sets of parameter values that cannot be correctly discarded due to instability in the estimation method caused by the lack of information. Preprocessing the measurements through the addition of application specific stabilizing bounds vastly improves bounded parameter and state estimations. Comparisons between applying guaranteed estimation methods to raw and preprocessed data measurements are illustrated with an example application.}, booktitle={Ieee international conference on systems man and cybernetics conference}, author={Marvel, S. W. and Williams, Cranos}, year={2012}, pages={72–77} }