Tremendous efforts have been made to improve diagnosis and treatment of COVID-19, but knowledge on long-term complications is limited. In particular, a large portion of survivors has respiratory complications, but currently, experienced radiologists and state-of-the-art artificial intelligence systems are not able to detect many abnormalities from follow-up computerized tomography (CT) scans of COVID-19 survivors. Here we propose Deep-LungParenchyma-Enhancing (DLPE), a computer-aided detection (CAD) method for detecting and quantifying pulmonary parenchyma lesions on chest CT. Through proposing a number of deep-learning-based segmentation models and assembling them in an interpretable manner, DLPE removes irrelevant tissues from the perspective of pulmonary parenchyma, and calculates the scan-level optimal window, which considerably enhances parenchyma lesions relative to the lung window. Aided by DLPE, radiologists discovered novel and interpretable lesions from COVID-19 inpatients and survivors, which were previously invisible under the lung window. Based on DLPE, we removed the scan-level bias of CT scans, and then extracted precise radiomics from such novel lesions. We further demonstrated that these radiomics have strong predictive power for key COVID-19 clinical metrics on an inpatient cohort of 1,193 CT scans and for sequelae on a survivor cohort of 219 CT scans. Our work sheds light on the development of interpretable medical artificial intelligence and showcases how artificial intelligence can discover medical findings that are beyond sight.

Polycomb group (PcG) protein-mediated histone methylation (H3K27me3) controls the correct spatiotemporal expression of numerous developmental regulators in Arabidopsis. Epigenetic silencing of the stem cell factor WUS in floral meristems (FMs) depends on H3K27me3 deposition by PcG proteins. However, the role of H3K27me3 in silencing of other meristematic regulator and pluripotency genes during FM determinacy has not yet been studied. To this end, we report the genome-wide dynamics of H3K27me3 levels during FM arrest and the consequences of strongly depleted PcG activity on early flower morphogenesis including enlarged and indeterminate FMs. Strong depletion of H3K27me3 levels results in misexpression of the FM identity gene AGL24, which partially leads to floral reversion causing ap1-like flowers and indeterminate FMs expressing ectopically WUS and STM. Loss of STM can rescue supernumerary floral organs and FM indeterminacy in H3K27me3-deficient flowers indicating that the hyperactivity of the FMs is at least partially a result of ectopic STM expression. Nonetheless, WUS remained essential for the FM activity. Our results demonstrate that PcG proteins promote FM determinacy at multi-levels of the floral gene regulatory network, silencing initially floral regulators like AGL24 that promotes FM indeterminacy, and subsequently, meristematic pluripotency genes such as WUS and STM during FM arrest.

Accurate prediction of promoter regions driving miRNA gene expression has become a major challenge due to the lack of annotation information for pri-miRNA transcripts. This defect hinders our understanding of miRNA-mediated regulatory networks. Some algorithms have been designed during the past decade to detect miRNA promoters. However, these methods rely on biosignal data such as CpG islands and still need to be improved. Here, we propose miProBERT, a BERT-based model for predicting promoters directly from gene sequences without using any structural or biological signals. According to our information, it is the first time a BERT-based model has been employed to identify miRNA promoters. We use the pre-trained model DNABERT, fine-tune the pre-trained model on the gene promoter dataset so that the model includes information about the richer biological properties of promoter sequences in its representation, and then systematically scan the upstream regions of each intergenic miRNA using the fine-tuned model. About, 665 miRNA promoters are found. The innovative use of a random substitution strategy to construct a negative dataset improves the discriminative ability of the model and further reduces the false positive rate (FPR) to as low as 0.0421. On independent datasets, miProBERT outperformed other gene promoter prediction methods. With comparison on 33 experimentally validated miRNA promoter datasets, miProBERT significantly outperformed previously developed miRNA promoter prediction programs with 78.13% precision and 75.76% recall. We further verify the predicted promoter regions by analyzing conservation, CpG content and histone marks. The effectiveness and robustness of miProBERT are highlighted.

The rich and diverse architectures of plants arise from complex regulatory processes involving genetic and environmental interactions, which are the results of natural selection during long-term evolution (McSteen & Leyser, 2005). Plant architecture has important applications in changing crop planting patterns and improving agricultural production, such as breeding of dwarf crops, which is conducive to mechanized management and harvest, improving yield and production efficiency. According to branch angles and orientation of woody plants, plant architectures can be roughly classified into standard, weeping, columnar and creeping types, among others (Hollender & Dardick, 2015). Tortuousbranch plants are often referred to as plants with naturally twisted branches; their branches exhibit an overall upward growth trend, and their stems are naturally tortuous in a zigzag pattern, resulting in a peculiar but graceful shape (Zheng et al., 2018). Thus, tortuous-branch plants are widely used for ornamental purposes. Given the diverse architectures and strong plasticity of woody plants, as compared with herbaceous plants, the genetic regulation of woody plant architecture is more complex (Costes & Gion, 2015;Zheng et al., 2018;Mao et al., 2020). Therefore, decoding the complicated molecular basis underlying this phenomenon is economically valuable, scientifically interesting and also tremendously challenging (Kucukoglu et al., 2017). In this issue of New Phytologist, Zheng et al. (2022; pp. 141-156) utilized a genomics approach to identify candidate genes related to the tortuous-branch phenotype in Prunus mume (Fig. 1), a woody ornamental species that originated in China, and which has been cultivated for more than 3000 years.

No abstract