Explore the vast range of titles available.

It is well known that DNA sequence contains a certain amount of transcription factors (TF) binding sites, and only part of them are identified through biological experiments. However, these experiments are expensive and time-consuming. To overcome these problems, some computational methods, based on k-mer features or convolutional neural networks, have been proposed to identify TF binding sites from DNA sequences. Although these methods have good performance, the context information that relates to TF binding sites is still lacking. Research indicates that standard recurrent neural networks (RNN) and its variants have better performance in time-series data compared with other models. In this study, we propose a model, named KEGRU, to identify TF binding sites by combining Bidirectional Gated Recurrent Unit (GRU) network with k-mer embedding. Firstly, DNA sequences are divided into k-mer sequences with a specified length and stride window. And then, we treat each k-mer as a word and pre-trained word representation model though word2vec algorithm. Thirdly, we construct a deep bidirectional GRU model for feature learning and classification. Experimental results have shown that our method has better performance compared with some state-of-the-art methods. Additional experiments about embedding strategy show that k-mer embedding will be helpful to enhance model performance. The robustness of KEGRU is proved by experiments with different k-mer length, stride window and embedding vector dimension.

Background Newly graduated registered nurses leaving the nursing profession in the early stages of their career have enormous financial and time implications for nursing organizations and affect the quality of nursing care. Objective To identify the factors influencing newly graduated registered nurses’ intention to leave the nursing profession over the past 10 years. Methods The framework developed by Whittemore and Knafl was used to conduct this integrative review. An electronic search was conducted for English articles to identify research studies published between 2011-2022 using the following databases of PubMed, MEDLINE, CINAHL, PsycINFO, and Scopus. Eligible publications were critically reviewed and scored using the Critical Appraisal Skills Program Checklist and the Center for Evidence-Based Management appraisal. Results Twenty-one studies were analyzed. The main factors affecting newly graduated registered nurses’ intention to leave the nursing profession included demographic factors (age, educational level, year of experience, professional title, employment status, health status, shift, hospital location and size), supervisor and peer support, challenges in the workplace, cognitive and affective response to work, work environment (collegial nurse-physician relations, insufficient staffing level, person-work environment fit), gender stereotypes, autonomous motivation, role models, and resilience. Conclusions The factors affecting newly graduated registered nurses’ intention to leave the nursing profession are multifaceted and should receive continuous attention from nurse managers. The findings provide more comprehensive for nurse administrators to develop intervention strategies to mitigate newly graduated registered nurses’ turnover intention.

Modeling in-vivo protein-DNA binding is not only fundamental for further understanding of the regulatory mechanisms, but also a challenging task in computational biology. Deep-learning based methods have succeed in modeling in-vivo protein-DNA binding, but they often (1) follow the fully supervised learning framework and overlook the weakly supervised information of genomic sequences that a bound DNA sequence may has multiple TFBS(s), and, (2) use one-hot encoding to encode DNA sequences and ignore the dependencies among nucleotides. In this paper, we propose a weakly supervised framework, which combines multiple-instance learning with a hybrid deep neural network and uses k -mer encoding to transform DNA sequences, for modeling in-vivo protein-DNA binding. Firstly, this framework segments sequences into multiple overlapping instances using a sliding window, and then encodes all instances into image-like inputs of high-order dependencies using k -mer encoding. Secondly, it separately computes a score for all instances in the same bag using a hybrid deep neural network that integrates convolutional and recurrent neural networks. Finally, it integrates the predicted values of all instances as the final prediction of this bag using the Noisy-and method. The experimental results on in-vivo datasets demonstrate the superior performance of the proposed framework. In addition, we also explore the performance of the proposed framework when using k -mer encoding, and demonstrate the performance of the Noisy-and method by comparing it with other fusion methods, and find that adding recurrent layers can improve the performance of the proposed framework.

• Visual signals attractive to friends may also attract enemies. The bright colors of anthers and pollen have generally been thought to attract pollinators. We hypothesize that visual crypsis of anthers, and particularly pollen, should be favored in flowering plants because protection from pollen collectors reduces the loss of male gametes. • To understand adaptive strategies relating to the color of pollen, we measured the color of pollen, undehisced anther sacs, and their background, the corolla, with a spectrometer for 104 insect-pollinated flowering species from a natural community in Hengduan Mountains, southwest China. • The colors of anthers, pollen and corollas were diverse in these species. The color diversity of exposed pollen was significantly higher than that of concealed pollen (i.e. where anthers are enclosed or shielded by corollas). The color contrast between pollen and corolla was significantly smaller in species with exposed pollen than in those with concealed pollen. Unlike anther color, exposed pollen color tended to match its background corolla color. • Our phylogenetic comparative analysis showed contrasting effects of pollen color patterns between flowers with exposed pollen and those with concealed pollen, revealing a strategy of hiding pollen from pollen thieves via visual crypsis.

Circular RNAs (circRNAs) play vital roles in transcription and translation. Identification of circRNA-RBP (RNA-binding protein) interaction sites has become a fundamental step in molecular and cell biology. Deep learning (DL)-based methods have been proposed to predict circRNA-RBP interaction sites and achieved impressive identification performance. However, those methods cannot effectively capture long-distance dependencies, and cannot effectively utilize the interaction information of multiple features. To overcome those limitations, we propose a DL-based model iCRBP-LKHA using deep hybrid networks for identifying circRNA-RBP interaction sites. iCRBP-LKHA adopts five encoding schemes. Meanwhile, the neural network architecture, which consists of large kernel convolutional neural network (LKCNN), convolutional block attention module with one-dimensional convolution (CBAM-1D) and bidirectional gating recurrent unit (BiGRU), can explore local information, global context information and multiple features interaction information automatically. To verify the effectiveness of iCRBP-LKHA, we compared its performance with shallow learning algorithms on 37 circRNAs datasets and 37 circRNAs stringent datasets. And we compared its performance with state-of-the-art DL-based methods on 37 circRNAs datasets, 37 circRNAs stringent datasets and 31 linear RNAs datasets. The experimental results not only show that iCRBP-LKHA outperforms other competing methods, but also demonstrate the potential of this model in identifying other RNA-RBP interaction sites.

Accumulating evidence suggests that circRNAs play crucial roles in human diseases. CircRNA-disease association prediction is extremely helpful in understanding pathogenesis, diagnosis, and prevention, as well as identifying relevant biomarkers. During the past few years, a large number of deep learning (DL) based methods have been proposed for predicting circRNA-disease association and achieved impressive prediction performance. However, there are two main drawbacks to these methods. The first is these methods underutilize biometric information in the data. Second, the features extracted by these methods are not outstanding to represent association characteristics between circRNAs and diseases. In this study, we developed a novel deep learning model, named iCircDA-NEAE, to predict circRNA-disease associations. In particular, we use disease semantic similarity, Gaussian interaction profile kernel, circRNA expression profile similarity, and Jaccard similarity simultaneously for the first time, and extract hidden features based on accelerated attribute network embedding (AANE) and dynamic convolutional autoencoder (DCAE). Experimental results on the circR2Disease dataset show that iCircDA-NEAE outperforms other competing methods significantly. Besides, 16 of the top 20 circRNA-disease pairs with the highest prediction scores were validated by relevant literature. Furthermore, we observe that iCircDA-NEAE can effectively predict new potential circRNA-disease associations.

Background Accumulating biological and clinical reports have indicated that imbalance of microbial community is closely associated with occurrence and development of various complex human diseases. Identifying potential microbe-disease associations, which could provide better understanding of disease pathology and further boost disease diagnostic and prognostic, has attracted more and more attention. However, hardly any computational models have been developed for large scale microbe-disease association prediction. Results In this article, based on the assumption that microbes with similar functions tend to share similar association or non-association patterns with similar diseases and vice versa, we proposed the model of Network Consistency Projection for Human Microbe-Disease Association prediction (NCPHMDA) by integrating known microbe-disease associations and Gaussian interaction profile kernel similarity for microbes and diseases. NCPHMDA yielded outstanding AUCs of 0.9039, 0.7953 and average AUC of 0.8918 in global leave-one-out cross validation, local leave-one-out cross validation and 5-fold cross validation, respectively. Furthermore, colon cancer, asthma and type 2 diabetes were taken as independent case studies, where 9, 9 and 8 out of the top 10 predicted microbes were successfully confirmed by recent published clinical literature. Conclusion NCPHMDA is a non-parametric universal network-based method which can simultaneously predict associated microbes for investigated diseases but does not require negative samples. It is anticipated that NCPHMDA would become an effective biological resource for clinical experimental guidance.

Pollinators visiting multiple plant species may cause heterospecific pollen transfer (HPT). To test a null model that more pollinator interspecific moves result in higher HPT among interacting species, we quantified the comparative magnitudes of the two networks involving 14 co-flowering species in an alpine meadow in the eastern Himalaya, southwest China. Interspecific moves accounted for 4% of the total visits, whereas heterospecific pollen constituted 22% of the total stigmatic pollen loads. On average, plant species received interspecific moves and HPT from 6.9 and 9.7 other species, respectively. Although the two networks were largely concordant, 21.6% of interspecific move links were not correspondingly linked by HPT, and 44.1% of heterospecific pollen transfer links were not linked by moves. Plant species with more outgoing pollinator moves tended to disperse more of their own pollen to others, as expected. Surprisingly, our data reveal that plant species which received more pollinator moves from other species tended to receive less HP, implying that only species with low acceptance of HP were likely to permit frequent pollinator moves. These new findings unveil a paradoxical relation between pollinator interspecific moves and HP receipt, suggesting an adaptive strategy of co-flowering species that reduces deleterious effects of HPT.

Plant stigmas and bee pollinators are competitors for pollen. Pollen placed on a pollinator’s body can be picked up by conspecific stigmas or it can be collected by the pollinator as food. Hypothetically, one solution is for pollen to be placed on ‘safe sites’ on the pollinator’s body, sites where the pollinator cannot easily remove it, leaving the pollen for stigmas. We compared 14 sites on the bumblebee body in terms of the ability of the bee to groom off fluorescent power, a dust that may be thought of as analogous to pollen. The safest sites were along the midline of the dorsal thorax, the dorsal abdomen, and the ventral abdomen. Next, we counted how much pollen is borne on the 14 sites by bees visiting one nectariferous and three nectarless Pedicularis species. In the four species, only 7, 26, 28, and 30% of pollen found on the bees were on safe sites. Finally, we observed that the 14 sites were contacted by stigmas of the four Pedicularis species; none of the most contacted sites were safe sites. Across all four Pedicularis species, pollen is mainly positioned on sites of the bee body that were beneficial for both the plant and the bee, not on sites detrimental to either of them. Our analysis showed that the conflict of interest between flowers and bees can be solved by cooperation. Pedicularis pollen is placed where it strengthens the mutualism between plants and pollinators.

Transformer‐based models have revolutionized single cell RNA‐seq (scRNA‐seq) data analysis. However, their applicability is challenged by the complexity and scale of single‐cell multi‐omics data. Here a novel single‐cell multi‐modal/multi‐task transformer (scmFormer) is proposed to fill up the existing blank of integrating single‐cell proteomics with other omics data. Through systematic benchmarking, it is demonstrated that scmFormer excels in integrating large‐scale single‐cell multimodal data and heterogeneous multi‐batch paired multi‐omics data, while preserving shared information across batchs and distinct biological information. scmFormer achieves 54.5% higher average F1 score compared to the second method in transferring cell‐type labels from single‐cell transcriptomics to proteomics data. Using COVID‐19 datasets, it is presented that scmFormer successfully integrates over 1.48 million cells on a personal computer. Moreover, it is also proved that scmFormer performs better than existing methods on generating the unmeasured modality and is well‐suited for spatial multi‐omic data. Thus, scmFormer is a powerful and comprehensive tool for analyzing single‐cell multi‐omics data. scmFormer, a Transformer‐based model, employs multi‐task learning for single‐cell multi‐omics integration and unmeasured data generation. It excels in preserving shared information across diverse datasets, achieving a 54.5% higher average F1 score in cell‐type label transfer. Impressively scalable, scmFormer seamlessly integrates millions of cells on personal computers, outperforming existing methods in generating unmeasured modalities and excelling in spatial multi‐omic data analysis.