GHCU, a Molecular Chaperone, Regulates Leaf Curling by Modulating the Distribution of KNGH1 in Cotton.

Leaf shape is considered to be one of the most significant agronomic traits in crop breeding. However, the molecular basis underlying leaf morphogenesis in cotton is still largely unknown. In this study, through genetic mapping and molecular investigation using a natural cotton mutant cu with leaves curling upward, the causal gene GHCU is successfully identified as the key regulator of leaf flattening. Knockout of GHCU or its homolog in cotton and tobacco using CRISPR results in abnormal leaf shape. It is further discovered that GHCU facilitates the transport of the HD protein KNOTTED1-like (KNGH1) from the adaxial to the abaxial domain. Loss of GHCU function restricts KNGH1 to the adaxial epidermal region, leading to lower auxin response levels in the adaxial boundary compared to the abaxial. This spatial asymmetry in auxin distribution produces the upward-curled leaf phenotype of the cu mutant. By analysis of single-cell RNA sequencing and spatiotemporal transcriptomic data, auxin biosynthesis genes are confirmed to be expressed asymmetrically in the adaxial-abaxial epidermal cells. Overall, these findings suggest that GHCU plays a crucial role in the regulation of leaf flattening through facilitating cell-to-cell trafficking of KNGH1 and hence influencing the auxin response level.

METTL14 is a chromatin regulator independent of its RNA N6-methyladenosine methyltransferase activity.

METTL3 and METTL14 are two components that form the core heterodimer of the main RNA m6A methyltransferase complex (MTC) that installs m6A. Surprisingly, depletion of METTL3 or METTL14 displayed distinct effects on stemness maintenance of mouse embryonic stem cell (mESC). While comparable global hypo-methylation in RNA m6A was observed in Mettl3 or Mettl14 knockout mESCs, respectively. Mettl14 knockout led to a globally decreased nascent RNA synthesis, whereas Mettl3 depletion resulted in transcription upregulation, suggesting that METTL14 might possess an m6A-independent role in gene regulation. We found that METTL14 colocalizes with the repressive H3K27me3 modification. Mechanistically, METTL14, but not METTL3, binds H3K27me3 and recruits KDM6B to induce H3K27me3 demethylation independent of METTL3. Depletion of METTL14 thus led to a global increase in H3K27me3 level along with a global gene suppression. The effects of METTL14 on regulation of H3K27me3 is essential for the transition from self-renewal to differentiation of mESCs. This work reveals a regulatory mechanism on heterochromatin by METTL14 in a manner distinct from METTL3 and independently of m6A, and critically impacts transcriptional regulation, stemness maintenance, and differentiation of mESCs.

Pancancer analysis of a potential gene mutation model in the prediction of immunotherapy outcomes.

Background: Immune checkpoint blockade (ICB) represents a promising treatment for cancer, but predictive biomarkers are needed. We aimed to develop a cost-effective signature to predict immunotherapy benefits across cancers. Methods: We proposed a study framework to construct the signature. Specifically, we built a multivariate Cox proportional hazards regression model with LASSO using 80% of an ICB-treated cohort (n = 1661) from MSKCC. The desired signature named SIGP was the risk score of the model and was validated in the remaining 20% of patients and an external ICB-treated cohort (n = 249) from DFCI. Results: SIGP was based on 18 candidate genes (NOTCH3, CREBBP, RNF43, PTPRD, FAM46C, SETD2, PTPRT, TERT, TET1, ROS1, NTRK3, PAK7, BRAF, LATS1, IL7R, VHL, TP53, and STK11), and we classified patients into SIGP high (SIGP-H), SIGP low (SIGP-L) and SIGP wild type (SIGP-WT) groups according to the SIGP score. A multicohort validation demonstrated that patients in SIGP-L had significantly longer overall survival (OS) in the context of ICB therapy than those in SIGP-WT and SIGP-H (44.00 months versus 13.00 months and 14.00 months, p < 0.001 in the test set). The survival of patients grouped by SIGP in non-ICB-treated cohorts was different, and SIGP-WT performed better than the other groups. In addition, SIGP-L + TMB-L (approximately 15% of patients) had similar survivals to TMB-H, and patients with both SIGP-L and TMB-H had better survival. Further analysis on tumor-infiltrating lymphocytes demonstrated that the SIGP-L group had significantly increased abundances of CD8+ T cells. Conclusion: Our proposed model of the SIGP signature based on 18-gene mutations has good predictive value for the clinical benefit of ICB in pancancer patients. Additional patients without TMB-H were identified by SIGP as potential candidates for ICB, and the combination of both signatures showed better performance than the single signature.

Deep graph convolutional network for US birth data harmonization.

In this paper, we developed a feasible and efficient deep-learning-based framework to combine the United States (US) natality data for the last five decades, with changing variables and factors, into a consistent database. We constructed a graph based on the property and elements of databases, including variables, and conducted a graph convolutional network (GCN) to learn the embeddings of variables on the constructed graph, where the learned embeddings implied the similarity of variables. Specifically, we devised a loss function with a slack margin and a banlist mechanism (for a random walk) to learn the desired structure (two nodes sharing more information were more similar to each other.), and developed an active learning mechanism to conduct the harmonization. Toward a total of 9,321 variables from 49 databases (i.e., 783 stemmed variables, from 1970 to 2018), we applied our model iteratively together with human reviews for four rounds, then obtained 323 hyperchains of variables. During the harmonization, the first round of our model achieved recall and precision of 87.56%, 57.70%, respectively. Our harmonized graph neural network (HGNN) method provides a feasible and efficient way to connect relevant databases at a meta-level. Adapting to the database's property and characteristics, HGNN can learn patterns globally, which is powerful to discover the similarity between variables among databases. Our proposed method provides an effective way to reduce the manual effort in database harmonization and integration of fragmented data into useful databases for future research.

A deep learning solution to recommend laboratory reduction strategies in ICU.

OBJECTIVE: To build a machine-learning model that predicts laboratory test results and provides a promising lab test reduction strategy, using spatial-temporal correlations. MATERIALS AND METHODS: We developed a global prediction model to treat laboratory testing as a series of decisions by considering contextual information over time and across modalities. We validated our method using a critical care database (MIMIC III), which includes 4,570,709 observations of 12 standard laboratory tests, among 38,773 critical care patients. Our deep-learning model made real-time laboratory reduction recommendations and predicted the properties of lab tests, including values, normal/abnormal (whether labs were within the normal range) and transition (normal to abnormal or abnormal to normal from the latest lab test). We reported area under the receiver operating characteristic curve (AUC) for predicting normal/abnormal, evaluated accuracy and absolute bias on prediction vs. observation against lab test reduction proportion. We compared our model against baseline models and analyzed the impact of variations on the recommended reduction strategy. RESULTS: Our best model offered a 20.26 % reduction in the number of laboratory tests. By applying the recommended reduction policy on the hold-out dataset (7755 patients), our model predicted normality/abnormality of laboratory tests with a 98.27 % accuracy (AUC, 0.9885; sensitivity, 97.84 %; specificity, 98.80 %; PPV, 99.01 %; NPV, 97.39 %) on 20.26 % reduced lab tests, and recommended 98.10 % of transitions to be checked. Our model performed better than the greedy models, and the recommended reduction strategy was robust. DISCUSSION: Strong spatial and temporal correlations between laboratory tests can be used to optimize policies for reducing laboratory tests throughout the hospital course. Our method allows for iterative predictions and provides a superior solution for the dynamic decision-making laboratory reduction problem. CONCLUSION: This work demonstrates a machine-learning model that assists physicians in determining which laboratory tests may be omitted.

Developing an automated mechanism to identify medical articles from wikipedia for knowledge extraction.

Wikipedia contains rich biomedical information that can support medical informatics studies and applications. Identifying the subset of medical articles of Wikipedia has many benefits, such as facilitating medical knowledge extraction, serving as a corpus for language modeling, or simply making the size of data easy to work with. However, due to the extremely low prevalence of medical articles in the entire Wikipedia, articles identified by generic text classifiers would be bloated by irrelevant pages. To control the false discovery rate while maintaining a high recall, we developed a mechanism that leverages the rich page elements and the connected nature of Wikipedia and uses a crawling classification strategy to achieve accurate classification. Structured assertional knowledge in Infoboxes and Wikidata items associated with the identified medical articles were also extracted. This automatic mechanism is aimed to run periodically to update the results and share them with the informatics community.

Predict or draw blood: An integrated method to reduce lab tests.

Serial laboratory testing is common, especially in Intensive Care Units (ICU). Such repeated testing is expensive and may even harm patients. However, identifying specific tests that can be omitted is challenging. The search space of different lab tests is large and the optimal reduction is hard to determine without modeling the time trajectory of decisions, which is a nontrivial optimization problem. In this paper, we propose a novel deep-learning method with a very concise architecture to jointly predict future lab test events to be omitted and the values of the omitted events based on observed testing values. Using our method, we were able to omit 15% of lab tests with <5% prediction accuracy loss. Although the application is specific to repeated lab tests, our proposed framework is highly generalizable and can be used to tackle a family of similar business decision making problems.