A comparative study of large language model-based zero-shot inference and task-specific supervised classification of breast cancer pathology reports.

OBJECTIVE: Although supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs could reduce the need for large-scale data annotations. MATERIALS AND METHODS: We curated a dataset of 769 breast cancer pathology reports, manually labeled with 12 categories, to compare zero-shot classification capability of the following LLMs: GPT-4, GPT-3.5, Starling, and ClinicalCamel, with task-specific supervised classification performance of 3 models: random forests, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model. RESULTS: Across all 12 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, LSTM-Att (average macro F1-score of 0.86 vs 0.75), with advantage on tasks with high label imbalance. Other LLMs demonstrated poor performance. Frequent GPT-4 error categories included incorrect inferences from multiple samples and from history, and complex task design, and several LSTM-Att errors were related to poor generalization to the test set. DISCUSSION: On tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of data labeling. However, if the use of LLMs is prohibitive, the use of simpler models with large annotated datasets can provide comparable results. CONCLUSIONS: GPT-4 demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for large annotated datasets. This may increase the utilization of NLP-based variables and outcomes in clinical studies.

Automatic extraction of social determinants of health from medical notes of chronic lower back pain patients.

OBJECTIVE: We applied natural language processing and inference methods to extract social determinants of health (SDoH) information from clinical notes of patients with chronic low back pain (cLBP) to enhance future analyses of the associations between SDoH disparities and cLBP outcomes. MATERIALS AND METHODS: Clinical notes for patients with cLBP were annotated for 7 SDoH domains, as well as depression, anxiety, and pain scores, resulting in 626 notes with at least one annotated entity for 364 patients. We used a 2-tier taxonomy with these 10 first-level classes (domains) and 52 second-level classes. We developed and validated named entity recognition (NER) systems based on both rule-based and machine learning approaches and validated an entailment model. RESULTS: Annotators achieved a high interrater agreement (Cohen's kappa of 95.3% at document level). A rule-based system (cTAKES), RoBERTa NER, and a hybrid model (combining rules and logistic regression) achieved performance of F1 = 47.1%, 84.4%, and 80.3%, respectively, for first-level classes. DISCUSSION: While the hybrid model had a lower F1 performance, it matched or outperformed RoBERTa NER model in terms of recall and had lower computational requirements. Applying an untuned RoBERTa entailment model, we detected many challenging wordings missed by NER systems. Still, the entailment model may be sensitive to hypothesis wording. CONCLUSION: This study developed a corpus of annotated clinical notes covering a broad spectrum of SDoH classes. This corpus provides a basis for training machine learning models and serves as a benchmark for predictive models for NER for SDoH and knowledge extraction from clinical texts.

Effects of Binaural Beat Stimulation in Adults with Stuttering.

In recent decades, several studies have demonstrated a link between stuttering and abnormal electroencephalographic (EEG) ß-power in cortex. Effects of exposure to binaural stimuli were studied in adults with stuttering (AWS, n = 6) and fluent participants (n = 6) using EEG, ECG, and speech analysis. During standard reading tasks without stimulation, in controls but not in the AWS group, EEG ß-power was significantly higher in the left hemisphere than in the right hemisphere. After stimulation, the power of the ß-band in AWS participants in the left hemisphere increased 1.54-fold. The average ß-band power within the left frontotemporal area and temporoparietal junction of the cortex after stimulation in AWS participants shows an increase by 1.65-fold and 1.72-fold, respectively. The rate of disfluency dropped significantly immediately after stimulation (median 74.70% of the baseline). Similarly, the speech rate significantly increased immediately after stimulation (median 133.15%). We show for the first time that auditory binaural beat stimulation can improve speech fluency in AWS, and its effect is proportional to boost in EEG ß-band power in left frontotemporal and temporoparietal junction of cortex. Changes in ß-power were detected immediately after exposure and persisted for 10 min. Additionally, these effects were accompanied by a reduction in stress levels.

Predictive Models for Length of Stay and Discharge Disposition in Elective Spine Surgery: Development, Validation, and Comparison to the ACS NSQIP Risk Calculator.

STUDY DESIGN: A retrospective study at a single academic institution. OBJECTIVE: The purpose of this study is to utilize machine learning to predict hospital length of stay (LOS) and discharge disposition following adult elective spine surgery, and to compare performance metrics of machine learning models to the American College of Surgeon's National Surgical Quality Improvement Program's (ACS NSQIP) prediction calculator. SUMMARY OF BACKGROUND DATA: A total of 3678 adult patients undergoing elective spine surgery between 2014 and 2019, acquired from the electronic health record. METHODS: Patients were divided into three stratified cohorts: cervical degenerative, lumbar degenerative, and adult spinal deformity groups. Predictive variables included demographics, body mass index, surgical region, surgical invasiveness, surgical approach, and comorbidities. Regression, classification trees, and least absolute shrinkage and selection operator (LASSO) were used to build predictive models. Validation of the models was conducted on 16% of patients (N=587), using area under the receiver operator curve (AUROC), sensitivity, specificity, and correlation. Patient data were manually entered into the ACS NSQIP online risk calculator to compare performance. Outcome variables were discharge disposition (home vs. rehabilitation) and LOS (days). RESULTS: Of 3678 patients analyzed, 51.4% were male (n=1890) and 48.6% were female (n=1788). The average LOS was 3.66 days. In all, 78% were discharged home and 22% discharged to rehabilitation. Compared with NSQIP (Pearson R2 =0.16), the predictions of poisson regression ( R2 =0.29) and LASSO ( R2 =0.29) models were significantly more correlated with observed LOS ( P =0.025 and 0.004, respectively). Of the models generated to predict discharge location, logistic regression yielded an AUROC of 0.79, which was statistically equivalent to the AUROC of 0.75 for NSQIP ( P =0.135). CONCLUSION: The predictive models developed in this study can enable accurate preoperative estimation of LOS and risk of rehabilitation discharge for adult patients undergoing elective spine surgery. The demonstrated models exhibited better performance than NSQIP for prediction of LOS and equivalent performance to NSQIP for prediction of discharge location.

Prediction of future healthcare expenses of patients from chest radiographs using deep learning: a pilot study.

Our objective was to develop deep learning models with chest radiograph data to predict healthcare costs and classify top-50% spenders. 21,872 frontal chest radiographs were retrospectively collected from 19,524 patients with at least 1-year spending data. Among the patients, 11,003 patients had 3 years of cost data, and 1678 patients had 5 years of cost data. Model performances were measured with area under the receiver operating characteristic curve (ROC-AUC) for classification of top-50% spenders and Spearman ρ for prediction of healthcare cost. The best model predicting 1-year (N = 21,872) expenditure achieved ROC-AUC of 0.806 [95% CI 0.793-0.819] for top-50% spender classification and ρ of 0.561 [0.536-0.586] for regression. Similarly, for predicting 3-year (N = 12,395) expenditure, ROC-AUC of 0.771 [0.750-0.794] and ρ of 0.524 [0.489-0.559]; for predicting 5-year (N = 1779) expenditure ROC-AUC of 0.729 [0.667-0.729] and ρ of 0.424 [0.324-0.529]. Our deep learning model demonstrated the feasibility of predicting health care expenditure as well as classifying top 50% healthcare spenders at 1, 3, and 5 year(s), implying the feasibility of combining deep learning with information-rich imaging data to uncover hidden associations that may allude to physicians. Such a model can be a starting point of making an accurate budget in reimbursement models in healthcare industries.

Empowering study of breast cancer data with application of artificial intelligence technology: promises, challenges, and use cases.

In healthcare, artificial intelligence (AI) technologies have the potential to create significant value by improving time-sensitive outcomes while lowering error rates for each patient. Diagnostic images, clinical notes, and reports are increasingly generated and stored in electronic medical records. This heterogeneous data presenting us with challenges in data analytics and reusability that is by nature has high complexity, thereby necessitating novel ways to store, manage and process, and reuse big data. This presents an urgent need to develop new, scalable, and expandable AI infrastructure and analytical methods that can enable healthcare providers to access knowledge for individual patients, yielding better decisions and outcomes. In this review article, we briefly discuss the nature of data in breast cancer study and the role of AI for generating "smart data" which offer actionable information that supports the better decision for personalized medicine for individual patients. In our view, the biggest challenge is to create a system that makes data robust and smart for healthcare providers and patients that can lead to more effective clinical decision-making, improved health outcomes, and ultimately, managing the healthcare outcomes and costs. We highlight some of the challenges in using breast cancer data and propose the need for an AI-driven environment to address them. We illustrate our vision with practical use cases and discuss a path for empowering the study of breast cancer databases with the application of AI and future directions.

Opal: an implementation science tool for machine learning clinical decision support in anesthesia.

Opal is the first published example of a full-stack platform infrastructure for an implementation science designed for ML in anesthesia that solves the problem of leveraging ML for clinical decision support. Users interact with a secure online Opal web application to select a desired operating room (OR) case cohort for data extraction, visualize datasets with built-in graphing techniques, and run in-client ML or extract data for external use. Opal was used to obtain data from 29,004 unique OR cases from a single academic institution for pre-operative prediction of post-operative acute kidney injury (AKI) based on creatinine KDIGO criteria using predictors which included pre-operative demographic, past medical history, medications, and flowsheet information. To demonstrate utility with unsupervised learning, Opal was also used to extract intra-operative flowsheet data from 2995 unique OR cases and patients were clustered using PCA analysis and k-means clustering. A gradient boosting machine model was developed using an 80/20 train to test ratio and yielded an area under the receiver operating curve (ROC-AUC) of 0.85 with 95% CI [0.80-0.90]. At the default probability decision threshold of 0.5, the model sensitivity was 0.9 and the specificity was 0.8. K-means clustering was performed to partition the cases into two clusters and for hypothesis generation of potential groups of outcomes related to intraoperative vitals. Opal's design has created streamlined ML functionality for researchers and clinicians in the perioperative setting and opens the door for many future clinical applications, including data mining, clinical simulation, high-frequency prediction, and quality improvement.

Machine Learning Prediction of Liver Allograft Utilization From Deceased Organ Donors Using the National Donor Management Goals Registry.

Early prediction of whether a liver allograft will be utilized for transplantation may allow better resource deployment during donor management and improve organ allocation. The national donor management goals (DMG) registry contains critical care data collected during donor management. We developed a machine learning model to predict transplantation of a liver graft based on data from the DMG registry. METHODS: Several machine learning classifiers were trained to predict transplantation of a liver graft. We utilized 127 variables available in the DMG dataset. We included data from potential deceased organ donors between April 2012 and January 2019. The outcome was defined as liver recovery for transplantation in the operating room. The prediction was made based on data available 12-18 h after the time of authorization for transplantation. The data were randomly separated into training (60%), validation (20%), and test sets (20%). We compared the performance of our models to the Liver Discard Risk Index. RESULTS: Of 13 629 donors in the dataset, 9255 (68%) livers were recovered and transplanted, 1519 recovered but used for research or discarded, 2855 were not recovered. The optimized gradient boosting machine classifier achieved an area under the curve of the receiver operator characteristic of 0.84 on the test set, outperforming all other classifiers. CONCLUSIONS: This model predicts successful liver recovery for transplantation in the operating room, using data available early during donor management. It performs favorably when compared to existing models. It may provide real-time decision support during organ donor management and transplant logistics.

Assessment of a Deep Learning Model Based on Electronic Health Record Data to Forecast Clinical Outcomes in Patients With Rheumatoid Arthritis.

Importance: Knowing the future condition of a patient would enable a physician to customize current therapeutic options to prevent disease worsening, but predicting that future condition requires sophisticated modeling and information. If artificial intelligence models were capable of forecasting future patient outcomes, they could be used to aid practitioners and patients in prognosticating outcomes or simulating potential outcomes under different treatment scenarios. Objective: To assess the ability of an artificial intelligence system to prognosticate the state of disease activity of patients with rheumatoid arthritis (RA) at their next clinical visit. Design, Setting, and Participants: This prognostic study included 820 patients with RA from rheumatology clinics at 2 distinct health care systems with different electronic health record platforms: a university hospital (UH) and a public safety-net hospital (SNH). The UH and SNH had substantially different patient populations and treatment patterns. The UH has records on approximately 1 million total patients starting in January 2012. The UH data for this study were accessed on July 1, 2017. The SNH has records on 65 000 unique individuals starting in January 2013. The SNH data for the study were collected on February 27, 2018. Exposures: Structured data were extracted from the electronic health record, including exposures (medications), patient demographics, laboratories, and prior measures of disease activity. A longitudinal deep learning model was used to predict disease activity for patients with RA at their next rheumatology clinic visit and to evaluate interhospital performance and model interoperability strategies. Main Outcomes and Measures: Model performance was quantified using the area under the receiver operating characteristic curve (AUROC). Disease activity in RA was measured using a composite index score. Results: A total of 578 UH patients (mean [SD] age, 57 [15] years; 477 [82.5%] female; 296 [51.2%] white) and 242 SNH patients (mean [SD] age, 60 [15] years; 195 [80.6%] female; 30 [12.4%] white) were included in the study. Patients at the UH compared with those at the SNH were seen more frequently (median time between visits, 100 vs 180 days) and were more frequently prescribed higher-class medications (biologics) (364 [63.0%] vs 70 [28.9%]). At the UH, the model reached an AUROC of 0.91 (95% CI, 0.86-0.96) in a test cohort of 116 patients. The UH-trained model had an AUROC of 0.74 (95% CI, 0.65-0.83) in the SNH test cohort (n = 117) despite marked differences in the patient populations. In both settings, baseline prediction using each patients' most recent disease activity score had statistically random performance. Conclusions and Relevance: The findings suggest that building accurate models to forecast complex disease outcomes using electronic health record data is possible and these models can be shared across hospitals with diverse patient populations.

Large Scale Semi-Automated Labeling of Routine Free-Text Clinical Records for Deep Learning.

Breast cancer is a leading cause of cancer death among women in the USA. Screening mammography is effective in reducing mortality, but has a high rate of unnecessary recalls and biopsies. While deep learning can be applied to mammography, large-scale labeled datasets, which are difficult to obtain, are required. We aim to remove many barriers of dataset development by automatically harvesting data from existing clinical records using a hybrid framework combining traditional NLP and IBM Watson. An expert reviewer manually annotated 3521 breast pathology reports with one of four outcomes: left positive, right positive, bilateral positive, negative. Traditional NLP techniques using seven different machine learning classifiers were compared to IBM Watson's automated natural language classifier. Techniques were evaluated using precision, recall, and F-measure. Logistic regression outperformed all other traditional machine learning classifiers and was used for subsequent comparisons. Both traditional NLP and Watson's NLC performed well for cases under 1024 characters with weighted average F-measures above 0.96 across all classes. Performance of traditional NLP was lower for cases over 1024 characters with an F-measure of 0.83. We demonstrate a hybrid framework using traditional NLP techniques combined with IBM Watson to annotate over 10,000 breast pathology reports for development of a large-scale database to be used for deep learning in mammography. Our work shows that traditional NLP and IBM Watson perform extremely well for cases under 1024 characters and can accelerate the rate of data annotation.

A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain.

Purpose To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 (18F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers. Materials and Methods Prospective 18F-FDG PET brain images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding. Results The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P < .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain. Conclusion By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Larvie in this issue.

Automatic Labeling of Special Diagnostic Mammography Views from Images and DICOM Headers.

Applying state-of-the-art machine learning techniques to medical images requires a thorough selection and normalization of input data. One of such steps in digital mammography screening for breast cancer is the labeling and removal of special diagnostic views, in which diagnostic tools or magnification are applied to assist in assessment of suspicious initial findings. As a common task in medical informatics is prediction of disease and its stage, these special diagnostic views, which are only enriched among the cohort of diseased cases, will bias machine learning disease predictions. In order to automate this process, here, we develop a machine learning pipeline that utilizes both DICOM headers and images to predict such views in an automatic manner, allowing for their removal and the generation of unbiased datasets. We achieve AUC of 99.72% in predicting special mammogram views when combining both types of models. Finally, we apply these models to clean up a dataset of about 772,000 images with expected sensitivity of 99.0%. The pipeline presented in this paper can be applied to other datasets to obtain high-quality image sets suitable to train algorithms for disease detection.

The Protein Phosphatases ATUNIS1 and ATUNIS2 Regulate Cell Wall Integrity in Tip-Growing Cells.

Fast tip-growing plant cells such as pollen tubes (PTs) and root hairs (RHs) require a robust coordination between their internal growth machinery and modifications of their extracellular rigid, yet extensible, cell wall (CW). Part of this essential coordination is governed by members of the Catharanthus roseus receptor-like kinase1-like (CrRLK1L) subfamily of RLKs with FERONIA (FER) and its closest homologs, ANXUR1 (ANX1) and ANX2, controlling CW integrity during RH and PT growth, respectively. Recently, Leucine-Rich Repeat Extensin 8 (LRX8) to LRX11 were also shown to be important for CW integrity in PTs. We previously reported an anx1 anx2 suppressor screen in Arabidopsis thaliana that revealed MARIS (MRI) as a positive regulator of both FER- and ANX1/2-dependent CW integrity pathways. Here, we characterize a suppressor that exhibits a weak rescue of the anx1 anx2 PT bursting phenotype and a short RH phenotype. The corresponding suppressor mutation causes a D94N substitution in a Type One Protein Phosphatase we named ATUNIS1 (AUN1). We show that AUN1 and its closest homolog, AUN2, are nucleocytoplasmic negative regulators of tip growth. Moreover, we demonstrate that AUN1D94N and AUN1H127A harboring mutations in key amino acids of the conserved catalytic site of phosphoprotein phosphatases function as dominant amorphic variants that repress PT growth. Finally, genetic interaction studies using the hypermorph MRIR240C and amorph AUN1D94N dominant variants indicate that LRX8-11 and ANX1/2 function in distinct but converging pathways to fine-tune CW integrity during tip growth.

Genetic determinants of co-accessible chromatin regions in activated T cells across humans.

Over 90% of genetic variants associated with complex human traits map to non-coding regions, but little is understood about how they modulate gene regulation in health and disease. One possible mechanism is that genetic variants affect the activity of one or more cis-regulatory elements leading to gene expression variation in specific cell types. To identify such cases, we analyzed ATAC-seq and RNA-seq profiles from stimulated primary CD4+ T cells in up to 105 healthy donors. We found that regions of accessible chromatin (ATAC-peaks) are co-accessible at kilobase and megabase resolution, consistent with the three-dimensional chromatin organization measured by in situ Hi-C in T cells. Fifteen percent of genetic variants located within ATAC-peaks affected the accessibility of the corresponding peak (local-ATAC-QTLs). Local-ATAC-QTLs have the largest effects on co-accessible peaks, are associated with gene expression and are enriched for autoimmune disease variants. Our results provide insights into how natural genetic variants modulate cis-regulatory elements, in isolation or in concert, to influence gene expression.

Author Correction: Discovery of stimulation-responsive immune enhancers with CRISPR activation.

In this Letter, analysis of steady-state regulatory T (Treg) cell percentages from Il2ra enhancer deletion (EDEL) and wild-type (WT) mice revealed no differences between them (Extended Data Fig. 9d). This analysis included two mice whose genotypes were incorrectly assigned. Even after correction of the genotypes, no significant differences in Treg cell percentages were seen when data across experimental cohorts were averaged (as was done in Extended Data Fig. 9d). However, if we normalize the corrected data to account for variation among experimental cohorts, a subtle decrease in EDEL Treg cell percentages is revealed and, using the corrected and normalized data, we have redrawn Extended Data Fig. 9d in Supplementary Fig. 1. The Supplementary Information to this Amendment contains the corrected and reanalysed Extended Data Fig. 9d. The sentence "This enhancer deletion (EDEL) strain also had no obvious T cell phenotypes at steady state (Extended Data Fig. 9)." should read: "This enhancer deletion (EDEL) strain had a small decrease in the percentage of Treg cells (Extended Data Fig. 9).". This error does not affect any of the main figures in the Letter or the data from mice with the human autoimmune-associated single nucleotide polymorphism (SNP) knocked in or with a 12-base-pair deletion at the site (12DEL). In addition, we stated in the Methods that we observed consistent immunophenotypes of EDEL mice across three founders, but in fact, we observed consistent phenotypes in mice from two founders. This does not change any of our conclusions and the original Letter has not been corrected.

Discovery of stimulation-responsive immune enhancers with CRISPR activation.

The majority of genetic variants associated with common human diseases map to enhancers, non-coding elements that shape cell-type-specific transcriptional programs and responses to extracellular cues. Systematic mapping of functional enhancers and their biological contexts is required to understand the mechanisms by which variation in non-coding genetic sequences contributes to disease. Functional enhancers can be mapped by genomic sequence disruption, but this approach is limited to the subset of enhancers that are necessary in the particular cellular context being studied. We hypothesized that recruitment of a strong transcriptional activator to an enhancer would be sufficient to drive target gene expression, even if that enhancer was not currently active in the assayed cells. Here we describe a discovery platform that can identify stimulus-responsive enhancers for a target gene independent of stimulus exposure. We used tiled CRISPR activation (CRISPRa) to synthetically recruit a transcriptional activator to sites across large genomic regions (more than 100 kilobases) surrounding two key autoimmunity risk loci, CD69 and IL2RA. We identified several CRISPRa-responsive elements with chromatin features of stimulus-responsive enhancers, including an IL2RA enhancer that harbours an autoimmunity risk variant. Using engineered mouse models, we found that sequence perturbation of the disease-associated Il2ra enhancer did not entirely block Il2ra expression, but rather delayed the timing of gene activation in response to specific extracellular signals. Enhancer deletion skewed polarization of naive T cells towards a pro-inflammatory T helper (TH17) cell state and away from a regulatory T cell state. This integrated approach identifies functional enhancers and reveals how non-coding variation associated with human immune dysfunction alters context-specific gene programs.

Receptor-like cytoplasmic kinase MARIS functions downstream of CrRLK1L-dependent signaling during tip growth.

Growing plant cells need to rigorously coordinate external signals with internal processes. For instance, the maintenance of cell wall (CW) integrity requires the coordination of CW sensing with CW remodeling and biosynthesis to avoid growth arrest or integrity loss. Despite the involvement of receptor-like kinases (RLKs) of the Catharanthus roseus RLK1-like (CrRLK1L) subfamily and the reactive oxygen species-producing NADPH oxidases, it remains largely unknown how this coordination is achieved. ANXUR1 (ANX1) and ANX2, two redundant members of the CrRLK1L subfamily, are required for tip growth of the pollen tube (PT), and their closest homolog, FERONIA, controls root-hair tip growth. Previously, we showed that ANX1 overexpression mildly inhibits PT growth by oversecretion of CW material, whereas pollen tubes of anx1 anx2 double mutants burst spontaneously after germination. Here, we report the identification of suppressor mutants with improved fertility caused by the rescue of anx1 anx2 pollen tube bursting. Mapping of one these mutants revealed an R240C nonsynonymous substitution in the activation loop of a receptor-like cytoplasmic kinase (RLCK), which we named MARIS (MRI). We show that MRI is a plasma membrane-localized member of the RLCK-VIII subfamily and is preferentially expressed in both PTs and root hairs. Interestingly, mri-knockout mutants display spontaneous PT and root-hair bursting. Moreover, expression of the MRI(R240C) mutant, but not its wild-type form, partially rescues the bursting phenotypes of anx1 anx2 PTs and fer root hairs but strongly inhibits wild-type tip growth. Thus, our findings identify a novel positive component of the CrRLK1L-dependent signaling cascade that coordinates CW integrity and tip growth.

A calcium dialog mediated by the FERONIA signal transduction pathway controls plant sperm delivery.

Sperm delivery for double fertilization of flowering plants relies on interactions between the pollen tube (PT) and two synergids, leading to programmed cell death (PCD) of the PT and one synergid. The mechanisms underlying the communication among these cells during PT reception is unknown. We discovered that the synergids control this process by coordinating their distinct calcium signatures in response to the calcium dynamics and growth behavior of the PT. Induced and spontaneous aberrant calcium responses in the synergids abolish the two coordinated PCD events. Components of the FERONIA (FER) signaling pathway are required for initiating and modulating these calcium responses and for coupling the PCD events. Intriguingly, the calcium signatures are interchangeable between the two synergids, implying that their fates of death and survival are determined by reversible interactions with the PT. Thus, complex intercellular interactions involving a receptor kinase pathway and calcium-mediated signaling control sperm delivery in plants.

Patterning of the angiosperm female gametophyte through the prism of theoretical paradigms.

The FG (female gametophyte) of flowering plants (angiosperms) is a simple highly polar structure composed of only a few cell types. The FG develops from a single cell through mitotic divisions to generate, depending on the species, four to 16 nuclei in a syncytium. These nuclei are then partitioned into three or four distinct cell types. The mechanisms underlying the specification of the nuclei in the FG has been a focus of research over the last decade. Nevertheless, we are far from understanding the patterning mechanisms that govern cell specification. Although some results were previously interpreted in terms of static positional information, several lines of evidence now show that local interactions are important. In the present article, we revisit the available data on developmental mutants and cell fate markers in the light of theoretical frameworks for biological patterning. We argue that a further dissection of the mechanisms may be impeded by the combinatorial and dynamical nature of developmental cues. However, accounting for these properties of developing systems is necessary to disentangle the diversity of the phenotypic manifestations of the underlying molecular interactions.

ANXUR receptor-like kinases coordinate cell wall integrity with growth at the pollen tube tip via NADPH oxidases.

It has become increasingly apparent that the extracellular matrix (ECM), which in plants corresponds to the cell wall, can influence intracellular activities in ways that go far beyond their supposedly passive mechanical support. In plants, growing cells use mechanisms sensing cell wall integrity to coordinate cell wall performance with the internal growth machinery to avoid growth cessation or loss of integrity. How this coordination precisely works is unknown. Previously, we reported that in the tip-growing pollen tube the ANXUR receptor-like kinases (RLKs) of the CrRLK1L subfamily are essential to sustain growth without loss of cell wall integrity in Arabidopsis. Here, we show that over-expression of the ANXUR RLKs inhibits growth by over-activating exocytosis and the over-accumulation of secreted cell wall material. Moreover, the characterization of mutations in two partially redundant pollen-expressed NADPH oxidases coupled with genetic interaction studies demonstrate that the ANXUR RLKs function upstream of these NADPH oxidases. Using the H2O2-sensitive HyPer and the Ca²âº-sensitive YC3.60 sensors in NADPH oxidase-deficient mutants, we reveal that NADPH oxidases generate tip-localized, pulsating H2O2 production that functions, possibly through Ca²âº channel activation, to maintain a steady tip-focused Ca²âº gradient during growth. Our findings support a model where ECM-sensing receptors regulate reactive oxygen species production, Ca²âº homeostasis, and exocytosis to coordinate ECM-performance with the internal growth machinery.