This research aims to extract knowledge related to COVID-19 clinical diagnosis and molecular mechanisms from COVID-19 literature by applying large language models, deepening our quantitative understanding of COVID-19 and its causative virus SARS-CoV-2, and providing foundational data resources for subsequent COVID-19 research. The knowledge extraction process is divided into three stages:The first phase: A total of 131 key documents, including COVID-19 research, vaccine clinical trials, and clinical guidelines, were selected for content extraction. Entities, relationships, entity types, and conditions were annotated, and knowledge was described in the form of triplets, using events as the unit. By summarizing the important and frequently occurring events, entities, and relationships, as well as analyzing the clinical diagnosis knowledge of COVID-19, nine COVID-19 clinical diagnosis knowledge patterns were identified. Subsequently, a corpus containing 342,287 articles was constructed using search strategies from PubMed and the CORD-19 database.The Second phase: Chain-of-thought reasoning was applied to enhance the data, simulating human experts in determining the knowledge patterns of COVID-19 sentences and extracting the COVID-19 entities and their types through a step-by-step reasoning process.The Third phase: The focus was on training large language models to achieve superior Knowledge Pattern Discrimination (KPD) and Named Entity Recognition (NER) performance, the Accuracy of the KPD model and the F1-score of the NER model reached 0.869 and 0.887 respectively, surpassing existing methods. Additionally, ablation studies indicated that the data formats used in chain-of-thought reasoning and model fine-tuning affect the performance of the models.

Acute Kidney Injury (AKI) often occurs in the intensive care units (ICU), where it is associated with high morbidity and mortality. Early and continuous prediction of AKI plays a crucial role in preventing AKI events, providing timely treatment, and reducing mortality. Continuously monitoring the high dimensional vital signs and lab measurements of the patients has always been a challenging task. In this study, we proposed a novel dual-channel deep learning approach named DC-AKI to address this challenge. DC-AKI extracts feature of temporal variables at different granularity, comprehensively and accurately obtains effective information, and finally continuous predicting risks of the patients. One channel of the model calculates corresponding local interactions of the variables with convolution kernels. The other channel uses the gated recurrent units (GRU) network and attention mechanism to obtains global interactions information among the variables. Finally, the model uses full connection layer to combine the representation vectors of the two channels, and uses Sigmoid classifier for prediction. We trained and tested our model on the MIMIC IV dataset, and the AUC ROC value of DC-AKI for predicting the risk of AKI in ICU patients 48 hours in advance was 0.9527, outperforming other methods. And our model was externally validated on the eICU dataset with an AUC ROC of 0.9054. These results demonstrate the robustness and accuracy of the model on different datasets. This finding provides clinicians with an opportunity to identify and manage patients with AKI in a timely manner, thereby improving patient prognosis. The implemented code is available online at https://github.com/BioMedBigDataCenter/DC-AKI.

Accurately extracting and classifying Chinese electronic medical record (EMR), which contain huge amounts of valuable medical information, have promising practical application and medical value in the health care of China. While the pivotal issue has gathered escalating attention, the bulk of current research is directed towards operations conducted at the document or entity level within medical records. Only a restricted body of work addresses these concerns at the sentence level, a critical aspect for downstream tasks like medical information retrieval, diagnosis normalization, and question answering. In this paper, we present a domain adaptive pre-training language model named CEMR-LM for sentence classification of Chinese EMRs. CEMR-LM acquires Chinese medical domain knowledge through the utilization of copious unlabeled clinical corpus for pre-training the language model. This is fortified by combining fine-tuning strategy and a dual-channel mechanism, which collectively contribute to the model’s heightened performance. Experiments on the benchmark dataset and real world hospital dataset both demonstrate that CEMR-LM is superior to the state-of-the-art methods. Furthermore, CEMR-LM possesses the capability to elucidate indicative elements within medical records by visualizing of the attention weights embedded within the model. The implemented code and experimental datasets are available online at https://github.com/BioMedBigDataCenter/CEMR-LM.

Abstract Summary: Pan-genome analyses have shed light on the dynamics and evolution of bacterial genome from the point of population. The explosive growth of bacterial genome sequence also brought an extremely big challenge to pan-genome profile analysis. We developed a tool, named PanGP, to complete pan-genome profile analysis for large-scale strains efficiently. PanGP has integrated two sampling algorithms, totally random (TR) and distance guide (DG). The DG algorithm drew sample strain combinations on the basis of genome diversity of bacterial population. The performance of these two algorithms have been evaluated on four bacteria populations with strain numbers varying from 30 to 200, and the DG algorithm exhibited overwhelming advantage on accuracy and stability than the TR algorithm. Availability: PanGP was developed with a user-friendly graphic interface and it was available at http://PanGP.big.ac.cn. Contact: [email protected] or [email protected] Supplementary information: Supplementary data are available at Bioinformatics online.

SUMMARY: mRNA/miRNA-seq technology is becoming the leading technology to globally profile gene expression and elucidate the transcriptional regulation mechanisms in living cells. Although there are many tools available for analyzing RNA-seq data, few of them are available as easy accessible online web tools for processing both mRNA and miRNA data for the RNA-seq based user community. As such, we have developed a comprehensive web application tool for processing mRNA-seq and miRNA-seq data. Our web tool wapRNA includes four different modules: mRNA-seq and miRNA-seq sequenced from SOLiD or Solexa platform and all the modules were tested on previously published experimental data. We accept raw sequence data with an optional reads filter, followed by mapping and gene annotation or miRNA prediction. wapRNA also integrates downstream functional analyses such as Gene Ontology, KEGG pathway, miRNA targets prediction and comparison of gene's or miRNA's different expression in different samples. Moreover, we provide the executable packages for installation on user's local server. AVAILABILITY: wapRNA is freely available for use at http://waprna.big.ac.cn. The executable packages and the instruction for installation can be downloaded from our web site. CONTACT: [email protected]; [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.