PubTator 3.0: an AI-powered literature resource for unlocking biomedical knowledge.

PubTator 3.0 (https://www.ncbi.nlm.nih.gov/research/pubtator3/) is a biomedical literature resource using state-of-the-art AI techniques to offer semantic and relation searches for key concepts like proteins, genetic variants, diseases and chemicals. It currently provides over one billion entity and relation annotations across approximately 36 million PubMed abstracts and 6 million full-text articles from the PMC open access subset, updated weekly. PubTator 3.0's online interface and API utilize these precomputed entity relations and synonyms to provide advanced search capabilities and enable large-scale analyses, streamlining many complex information needs. We showcase the retrieval quality of PubTator 3.0 using a series of entity pair queries, demonstrating that PubTator 3.0 retrieves a greater number of articles than either PubMed or Google Scholar, with higher precision in the top 20 results. We further show that integrating ChatGPT (GPT-4) with PubTator APIs dramatically improves the factuality and verifiability of its responses. In summary, PubTator 3.0 offers a comprehensive set of features and tools that allow researchers to navigate the ever-expanding wealth of biomedical literature, expediting research and unlocking valuable insights for scientific discovery.

Quality of Answers of Generative Large Language Models Versus Peer Users for Interpreting Laboratory Test Results for Lay Patients: Evaluation Study.

BACKGROUND: Although patients have easy access to their electronic health records and laboratory test result data through patient portals, laboratory test results are often confusing and hard to understand. Many patients turn to web-based forums or question-and-answer (Q&A) sites to seek advice from their peers. The quality of answers from social Q&A sites on health-related questions varies significantly, and not all responses are accurate or reliable. Large language models (LLMs) such as ChatGPT have opened a promising avenue for patients to have their questions answered. OBJECTIVE: We aimed to assess the feasibility of using LLMs to generate relevant, accurate, helpful, and unharmful responses to laboratory test-related questions asked by patients and identify potential issues that can be mitigated using augmentation approaches. METHODS: We collected laboratory test result-related Q&A data from Yahoo! Answers and selected 53 Q&A pairs for this study. Using the LangChain framework and ChatGPT web portal, we generated responses to the 53 questions from 5 LLMs: GPT-4, GPT-3.5, LLaMA 2, MedAlpaca, and ORCA_mini. We assessed the similarity of their answers using standard Q&A similarity-based evaluation metrics, including Recall-Oriented Understudy for Gisting Evaluation, Bilingual Evaluation Understudy, Metric for Evaluation of Translation With Explicit Ordering, and Bidirectional Encoder Representations from Transformers Score. We used an LLM-based evaluator to judge whether a target model had higher quality in terms of relevance, correctness, helpfulness, and safety than the baseline model. We performed a manual evaluation with medical experts for all the responses to 7 selected questions on the same 4 aspects. RESULTS: Regarding the similarity of the responses from 4 LLMs; the GPT-4 output was used as the reference answer, the responses from GPT-3.5 were the most similar, followed by those from LLaMA 2, ORCA_mini, and MedAlpaca. Human answers from Yahoo data were scored the lowest and, thus, as the least similar to GPT-4-generated answers. The results of the win rate and medical expert evaluation both showed that GPT-4's responses achieved better scores than all the other LLM responses and human responses on all 4 aspects (relevance, correctness, helpfulness, and safety). LLM responses occasionally also suffered from lack of interpretation in one's medical context, incorrect statements, and lack of references. CONCLUSIONS: By evaluating LLMs in generating responses to patients' laboratory test result-related questions, we found that, compared to other 4 LLMs and human answers from a Q&A website, GPT-4's responses were more accurate, helpful, relevant, and safer. There were cases in which GPT-4 responses were inaccurate and not individualized. We identified a number of ways to improve the quality of LLM responses, including prompt engineering, prompt augmentation, retrieval-augmented generation, and response evaluation.

Glutathione ligand self-assembly enables luminescence from Au15 nanoclusters for highly sensitive and selective monitoring of blood Pb(II) ions.

Lead Pb(II) ions is a cumulative toxicant that impacts several biological systems and poses severe harm to young children. Accurate Pb(II) ions monitoring is thus of paramount importance. Here, we present the synthesis and application of glutathione-capped Au15 nanoclusters (Au15(SG)13) as a luminescence probe for the accurate and selective monitoring of blood Pb(II). The introduction of Pb(II) ions triggers orderly self-assembly of Au15 nanoclusters, resulting in the formation of rigid shell around Au nuclei. This limits the localized vibration of the glutathione ligands and their interaction with water molecules, greatly reducing non-radiative energy loss, and thereby enhancing the photoluminescence signal. Consequently, Au15(SG)13 nanoclusters exhibit high sensitivity for Pb(II) detection. The detection signal displays a linear relationship with Pb(II) over a wide detection range (0-800 µg/L), demonstrating a substantial sensitivity of 35.29 µg/L. Moreover, the developed nanoclusters show superior selectivity for Pb(II) ions, distinguishing them from other prevalent heavy metals. This work pave the way for the development of advanced Pb(II) sensors with high sensitivity and selectivity.

Quality of Answers of Generative Large Language Models vs Peer Patients for Interpreting Lab Test Results for Lay Patients: Evaluation Study.

Background: Even though patients have easy access to their electronic health records and lab test results data through patient portals, lab results are often confusing and hard to understand. Many patients turn to online forums or question and answering (Q&A) sites to seek advice from their peers. However, the quality of answers from social Q&A on health-related questions varies significantly, and not all the responses are accurate or reliable. Large language models (LLMs) such as ChatGPT have opened a promising avenue for patients to get their questions answered. Objective: We aim to assess the feasibility of using LLMs to generate relevant, accurate, helpful, and unharmful responses to lab test-related questions asked by patients and to identify potential issues that can be mitigated with augmentation approaches. Methods: We first collected lab test results related question and answer data from Yahoo! Answers and selected 53 Q&A pairs for this study. Using the LangChain framework and ChatGPT web portal, we generated responses to the 53 questions from four LLMs including GPT-4, Meta LLaMA 2, MedAlpaca, and ORCA_mini. We first assessed the similarity of their answers using standard QA similarity-based evaluation metrics including ROUGE, BLEU, METEOR, BERTScore. We also utilized an LLM-based evaluator to judge whether a target model has higher quality in terms of relevance, correctness, helpfulness, and safety than the baseline model. Finally, we performed a manual evaluation with medical experts for all the responses of seven selected questions on the same four aspects. Results: Regarding the similarity of the responses from 4 LLMs, where GPT-4 output was used as the reference answer, the responses from LLaMa 2 are the most similar ones, followed by LLaMa 2, ORCA_mini, and MedAlpaca. Human answers from Yahoo data were scored lowest and thus least similar to GPT-4-generated answers. The results of Win Rate and medical expert evaluation both showed that GPT-4's responses achieved better scores than all the other LLM responses and human responses on all the four aspects (relevance, correctness, helpfulness, and safety). However, LLM responses occasionally also suffer from lack of interpretation in one's medical context, incorrect statements, and lack of references. Conclusions: By evaluating LLMs in generating responses to patients' lab test results related questions, we find that compared to other three LLMs and human answer from the Q&A website, GPT-4's responses are more accurate, helpful, relevant, and safer. However, there are cases that GPT-4 responses are inaccurate and not individualized. We identified a number of ways to improve the quality of LLM responses including prompt engineering, prompt augmentation, retrieval augmented generation, and response evaluation.

PubTator 3.0: an AI-powered Literature Resource for Unlocking Biomedical Knowledge.

PubTator 3.0 (https://www.ncbi.nlm.nih.gov/research/pubtator3/) is a biomedical literature resource using state-of-the-art AI techniques to offer semantic and relation searches for key concepts like proteins, genetic variants, diseases, and chemicals. It currently provides over one billion entity and relation annotations across approximately 36 million PubMed abstracts and 6 million full-text articles from the PMC open access subset, updated weekly. PubTator 3.0's online interface and API utilize these precomputed entity relations and synonyms to provide advanced search capabilities and enable large-scale analyses, streamlining many complex information needs. We showcase the retrieval quality of PubTator 3.0 using a series of entity pair queries, demonstrating that PubTator 3.0 retrieves a greater number of articles than either PubMed or Google Scholar, with higher precision in the top 20 results. We further show that integrating ChatGPT (GPT-4) with PubTator APIs dramatically improves the factuality and verifiability of its responses. In summary, PubTator 3.0 offers a comprehensive set of features and tools that allow researchers to navigate the ever-expanding wealth of biomedical literature, expediting research and unlocking valuable insights for scientific discovery.

Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health.

ChatGPT has drawn considerable attention from both the general public and domain experts with its remarkable text generation capabilities. This has subsequently led to the emergence of diverse applications in the field of biomedicine and health. In this work, we examine the diverse applications of large language models (LLMs), such as ChatGPT, in biomedicine and health. Specifically we explore the areas of biomedical information retrieval, question answering, medical text summarization, information extraction, and medical education, and investigate whether LLMs possess the transformative power to revolutionize these tasks or whether the distinct complexities of biomedical domain presents unique challenges. Following an extensive literature survey, we find that significant advances have been made in the field of text generation tasks, surpassing the previous state-of-the-art methods. For other applications, the advances have been modest. Overall, LLMs have not yet revolutionized biomedicine, but recent rapid progress indicates that such methods hold great potential to provide valuable means for accelerating discovery and improving health. We also find that the use of LLMs, like ChatGPT, in the fields of biomedicine and health entails various risks and challenges, including fabricated information in its generated responses, as well as legal and privacy concerns associated with sensitive patient data. We believe this survey can provide a comprehensive and timely overview to biomedical researchers and healthcare practitioners on the opportunities and challenges associated with using ChatGPT and other LLMs for transforming biomedicine and health.

Loading IrOx Clusters on MnO2 Boosts Acidic Water Oxidation via Metal-Support Interaction.

Noble metal-based electrocatalysts are crucial for efficient acidic water oxidation to develop green hydrogen energy. However, traditional noble metal catalysts loaded on inactive substrates show limited intrinsic catalytic activity, and their large sizes have compromised the atom efficiency of these noble metals. Herein, IrOx nanoclusters with sizes below 2 nm, displaying high atom-utilization efficiency of Ir species, were supported on a redox-active MnO2 nanosubstrate (IrOx/MnO2) with different phases (α-MnO2, δ-MnO2, and ε-MnO2) to explore the optimal combination. Electrochemical measurements showed that IrOx/ε-MnO2 had excellent OER performance with a low overpotential of 225 mV at 10 mA cm-2 in 0.5 M H2SO4, superior to its counterpart, IrOx/α-MnO2 (242 mV) and IrOx/δ-MnO2 (286 mV). Moreover, it also delivered robust stability with no obvious change in operating potential at 10 mA cm-2 during 50 h of continuous operation. Combining the XPS results and Bader charge analysis, we demonstrated that the strong metal-support interactions of IrOx/ε-MnO2 could effectively regulate the electronic structures of the active Ir atoms and stabilize IrOx nanoclusters on supports to suppress their detachment, resulting in significantly enhanced catalytic activity and stability for acidic OER. DFT calculations further supported that the enhanced catalytic OER performance of IrOx/ε-MnO2 could be ascribed to the appropriate strength of interactions between the active Ir sites and the reaction intermediates of the potential-determining step (*O and *OOH) regulated by the redox-active substrates.

Towards Interpretable Multimodal Predictive Models for Early Mortality Prediction of Hemorrhagic Stroke Patients.

The increasing death rate over the past eight years due to stroke has prompted clinicians to look for data-driven decision aids. Recently, deep-learning-based prediction models trained with fine-grained electronic health record (EHR) data have shown superior promise for health outcome prediction. However, the use of EHR-based deep learning models for hemorrhagic stroke outcome prediction has not been extensively explored. This paper proposes an ensemble deep learning framework to predict early mortality among ICU patients with hemorrhagic stroke. The proposed ensemble model achieved an accuracy of 83%, which was higher than the fusion model and other baseline models (logistic regression, decision tree, random forest, and XGBoost). Moreover, we used SHAP values for interpretation of the ensemble model to identify important features for the prediction. In addition, this paper follows the MINIMAR (MINimum Information for Medical AI Reporting) standard, presenting an important step towards building trust among the AI system and clinicians.

Prediction of Outcomes After Heart Transplantation in Pediatric Patients Using National Registry Data: Evaluation of Machine Learning Approaches.

BACKGROUND: The prediction of posttransplant health outcomes for pediatric heart transplantation is critical for risk stratification and high-quality posttransplant care. OBJECTIVE: The purpose of this study was to examine the use of machine learning (ML) models to predict rejection and mortality for pediatric heart transplant recipients. METHODS: Various ML models were used to predict rejection and mortality at 1, 3, and 5 years after transplantation in pediatric heart transplant recipients using United Network for Organ Sharing data from 1987 to 2019. The variables used for predicting posttransplant outcomes included donor and recipient as well as medical and social factors. We evaluated 7 ML models-extreme gradient boosting (XGBoost), logistic regression, support vector machine, random forest (RF), stochastic gradient descent, multilayer perceptron, and adaptive boosting (AdaBoost)-as well as a deep learning model with 2 hidden layers with 100 neurons and a rectified linear unit (ReLU) activation function followed by batch normalization for each and a classification head with a softmax activation function. We used 10-fold cross-validation to evaluate model performance. Shapley additive explanations (SHAP) values were calculated to estimate the importance of each variable for prediction. RESULTS: RF and AdaBoost models were the best-performing algorithms for different prediction windows across outcomes. RF outperformed other ML algorithms in predicting 5 of the 6 outcomes (area under the receiver operating characteristic curve [AUROC] 0.664 and 0.706 for 1-year and 3-year rejection, respectively, and AUROC 0.697, 0.758, and 0.763 for 1-year, 3-year, and 5-year mortality, respectively). AdaBoost achieved the best performance for prediction of 5-year rejection (AUROC 0.705). CONCLUSIONS: This study demonstrates the comparative utility of ML approaches for modeling posttransplant health outcomes using registry data. ML approaches can identify unique risk factors and their complex relationship with outcomes, thereby identifying patients considered to be at risk and informing the transplant community about the potential of these innovative approaches to improve pediatric care after heart transplantation. Future studies are required to translate the information derived from prediction models to optimize counseling, clinical care, and decision-making within pediatric organ transplant centers.

Opportunities and challenges for ChatGPT and large language models in biomedicine and health.

ChatGPT has drawn considerable attention from both the general public and domain experts with its remarkable text generation capabilities. This has subsequently led to the emergence of diverse applications in the field of biomedicine and health. In this work, we examine the diverse applications of large language models (LLMs), such as ChatGPT, in biomedicine and health. Specifically, we explore the areas of biomedical information retrieval, question answering, medical text summarization, information extraction and medical education and investigate whether LLMs possess the transformative power to revolutionize these tasks or whether the distinct complexities of biomedical domain presents unique challenges. Following an extensive literature survey, we find that significant advances have been made in the field of text generation tasks, surpassing the previous state-of-the-art methods. For other applications, the advances have been modest. Overall, LLMs have not yet revolutionized biomedicine, but recent rapid progress indicates that such methods hold great potential to provide valuable means for accelerating discovery and improving health. We also find that the use of LLMs, like ChatGPT, in the fields of biomedicine and health entails various risks and challenges, including fabricated information in its generated responses, as well as legal and privacy concerns associated with sensitive patient data. We believe this survey can provide a comprehensive and timely overview to biomedical researchers and healthcare practitioners on the opportunities and challenges associated with using ChatGPT and other LLMs for transforming biomedicine and health.

Annotation and Information Extraction of Consumer-Friendly Health Articles for Enhancing Laboratory Test Reporting.

Viewing laboratory test results is patients' most frequent activity when accessing patient portals, but lab results can be very confusing for patients. Previous research has explored various ways to present lab results, but few have attempted to provide tailored information support based on individual patient's medical context. In this study, we collected and annotated interpretations of textual lab result in 251 health articles about laboratory tests from AHealthyMe.com. Then we evaluated transformer-based language models including BioBERT, ClinicalBERT, RoBERTa, and PubMedBERT for recognizing key terms and their types. Using BioPortal's term search API, we mapped the annotated terms to concepts in major controlled terminologies. Results showed that PubMedBERT achieved the best F1 on both strict and lenient matching criteria. SNOMED CT had the best coverage of the terms, followed by LOINC and ICD-10-CM. This work lays the foundation for enhancing the presentation of lab results in patient portals by providing patients with contextualized interpretations of their lab results and individualized question prompts that they can, in turn, refer to during physician consults.

BioKG: a comprehensive, large-scale biomedical knowledge graph for AI-powered, data-driven biomedical research.

To cope with the rapid growth of scientific publications and data in biomedical research, knowledge graphs (KGs) have emerged as a powerful data structure for integrating large volumes of heterogeneous data to facilitate accurate and efficient information retrieval and automated knowledge discovery (AKD). However, transforming unstructured content from scientific literature into KGs has remained a significant challenge, with previous methods unable to achieve human-level accuracy. In this study, we utilized an information extraction pipeline that won first place in the LitCoin NLP Challenge to construct a largescale KG using all PubMed abstracts. The quality of the large-scale information extraction rivals that of human expert annotations, signaling a new era of automatic, high-quality database construction from literature. Our extracted information markedly surpasses the amount of content in manually curated public databases. To enhance the KG's comprehensiveness, we integrated relation data from 40 public databases and relation information inferred from high-throughput genomics data. The comprehensive KG enabled rigorous performance evaluation of AKD, which was infeasible in previous studies. We designed an interpretable, probabilistic-based inference method to identify indirect causal relations and achieved unprecedented results for drug target identification and drug repurposing. Taking lung cancer as an example, we found that 40% of drug targets reported in literature could have been predicted by our algorithm about 15 years ago in a retrospective study, demonstrating that substantial acceleration in scientific discovery could be achieved through automated hypotheses generation and timely dissemination. A cloud-based platform (https://www.biokde.com) was developed for academic users to freely access this rich structured data and associated tools.

Deep learning-based predictions of older adults' adherence to cognitive training to support training efficacy.

As the population ages, the number of older adults experiencing mild cognitive impairment (MCI), Alzheimer's disease, and other forms of dementia will increase dramatically over the next few decades. Unfortunately, cognitive changes associated with these conditions threaten independence and quality of life. To address this, researchers have developed promising cognitive training interventions to help prevent or reverse cognitive decline and cognitive impairment. However, the promise of these interventions will not be realized unless older adults regularly engage with them over the long term, and like many health behaviors, adherence to cognitive training interventions can often be poor. To maximize training benefits, it would be useful to be able to predict when adherence lapses for each individual, so that support systems can be personalized to bolster adherence and intervention engagement at optimal time points. The current research uses data from a technology-based cognitive intervention study to recognize patterns in participants' adherence levels and predict their future adherence to the training program. We leveraged the feature learning capabilities of deep neural networks to predict patterns of adherence for a given participant, based on their past behavior. A separate, personalized model was trained for each participant to capture individualistic features of adherence. We posed the adherence prediction as a binary classification problem and exploited multivariate time series analysis using an adaptive window size for model training. Further, data augmentation techniques were used to overcome the challenge of limited training data and enhance the size of the dataset. To the best of our knowledge, this is the first research effort to use advanced machine learning techniques to predict older adults' daily adherence to cognitive training programs. Experimental evaluations corroborated the promise and potential of deep learning models for adherence prediction, which furnished highest mean F-scores of 75.5, 75.5, and 74.6% for the Convolution Neural Network (CNN), Long Short-Term Memory (LSTM) network, and CNN-LSTM models respectively.

E3 ubiquitin ligase TRIM55 promotes metastasis of gastric cancer cells by mediating epithelial-mesenchymal transition.

BACKGROUND: Gastric cancer (GC) is considered a major global health problem. The role of TRIM55, a member of the three-domain protein family, in GC is unknown. AIM: To determine the expression of TRIM55 in GC tissues and its relationship with clinicopathological characteristics, and to investigate the effects of TRIM55 on the malignant biological behavior of GC cells. METHODS: Differential expression of TRIM55 in GC and para-cancer tissues was detected by immunohistochemistry, and the relationship between TRIM55 level and clinicopathological characteristics and prognosis was analyzed. Gain-of-function, loss-of-function, cell counting kit-8 assay, colony formation, transwell assay, wound healing assay, and western blot analysis were used to assess the potential role of TRIM55 in the development of GC. RESULTS: TRIM55 expression was significantly increased in GC tissues compared with adjacent normal tissues. High expression of TRIM55 was associated with advanced pathological stage and poor prognosis. Overexpression of TRIM55 promoted invasion and metastasis of GC cells in vitro by regulating epithelial-mesenchymal transition (EMT), whereas knockdown of TRIM55 had the opposite effect. Our data showed that TRIM55 is highly expressed in GC tissues, and is associated with poor prognosis. TRIM55 plays the role of an oncogene in GC, and it promotes metastasis of GC through the regulation of EMT. CONCLUSION: TRIM55 may be a possible target for the diagnosis and prognosis of GC patients.

A Machine-Learning Based Approach for Predicting Older Adults' Adherence to Technology-Based Cognitive Training.

Adequate adherence is a necessary condition for success with any intervention, including for computerized cognitive training designed to mitigate age-related cognitive decline. Tailored prompting systems offer promise for promoting adherence and facilitating intervention success. However, developing adherence support systems capable of just-in-time adaptive reminders requires understanding the factors that predict adherence, particularly an imminent adherence lapse. In this study we built machine learning models to predict participants' adherence at different levels (overall and weekly) using data collected from a previous cognitive training intervention. We then built machine learning models to predict adherence using a variety of baseline measures (demographic, attitudinal, and cognitive ability variables), as well as deep learning models to predict the next week's adherence using variables derived from training interactions in the previous week. Logistic regression models with selected baseline variables were able to predict overall adherence with moderate accuracy (AUROC: 0.71), while some recurrent neural network models were able to predict weekly adherence with high accuracy (AUROC: 0.84-0.86) based on daily interactions. Analysis of the post hoc explanation of machine learning models revealed that general self-efficacy, objective memory measures, and technology self-efficacy were most predictive of participants' overall adherence, while time of training, sessions played, and game outcomes were predictive of the next week's adherence. Machine-learning based approaches revealed that both individual difference characteristics and previous intervention interactions provide useful information for predicting adherence, and these insights can provide initial clues as to who to target with adherence support strategies and when to provide support. This information will inform the development of a technology-based, just-in-time adherence support systems.

Multi-label classification for biomedical literature: an overview of the BioCreative VII LitCovid Track for COVID-19 literature topic annotations.

The coronavirus disease 2019 (COVID-19) pandemic has been severely impacting global society since December 2019. The related findings such as vaccine and drug development have been reported in biomedical literature-at a rate of about 10 000 articles on COVID-19 per month. Such rapid growth significantly challenges manual curation and interpretation. For instance, LitCovid is a literature database of COVID-19-related articles in PubMed, which has accumulated more than 200 000 articles with millions of accesses each month by users worldwide. One primary curation task is to assign up to eight topics (e.g. Diagnosis and Treatment) to the articles in LitCovid. The annotated topics have been widely used for navigating the COVID literature, rapidly locating articles of interest and other downstream studies. However, annotating the topics has been the bottleneck of manual curation. Despite the continuing advances in biomedical text-mining methods, few have been dedicated to topic annotations in COVID-19 literature. To close the gap, we organized the BioCreative LitCovid track to call for a community effort to tackle automated topic annotation for COVID-19 literature. The BioCreative LitCovid dataset-consisting of over 30 000 articles with manually reviewed topics-was created for training and testing. It is one of the largest multi-label classification datasets in biomedical scientific literature. Nineteen teams worldwide participated and made 80 submissions in total. Most teams used hybrid systems based on transformers. The highest performing submissions achieved 0.8875, 0.9181 and 0.9394 for macro-F1-score, micro-F1-score and instance-based F1-score, respectively. Notably, these scores are substantially higher (e.g. 12%, higher for macro F1-score) than the corresponding scores of the state-of-art multi-label classification method. The level of participation and results demonstrate a successful track and help close the gap between dataset curation and method development. The dataset is publicly available via https://ftp.ncbi.nlm.nih.gov/pub/lu/LitCovid/biocreative/ for benchmarking and further development. Database URL https://ftp.ncbi.nlm.nih.gov/pub/lu/LitCovid/biocreative/.

Pre-trained models, data augmentation, and ensemble learning for biomedical information extraction and document classification.

Large volumes of publications are being produced in biomedical sciences nowadays with ever-increasing speed. To deal with the large amount of unstructured text data, effective natural language processing (NLP) methods need to be developed for various tasks such as document classification and information extraction. BioCreative Challenge was established to evaluate the effectiveness of information extraction methods in biomedical domain and facilitate their development as a community-wide effort. In this paper, we summarize our work and what we have learned from the latest round, BioCreative Challenge VII, where we participated in all five tracks. Overall, we found three key components for achieving high performance across a variety of NLP tasks: (1) pre-trained NLP models; (2) data augmentation strategies and (3) ensemble modelling. These three strategies need to be tailored towards the specific tasks at hands to achieve high-performing baseline models, which are usually good enough for practical applications. When further combined with task-specific methods, additional improvements (usually rather small) can be achieved, which might be critical for winning competitions. Database URL: https://doi.org/10.1093/database/baac066.

Iridium Doped Pyrochlore Ruthenates for Efficient and Durable Electrocatalytic Oxygen Evolution in Acidic Media.

Developing highly active, durable, and cost-effective electrocatalysts for the oxygen evolution reaction (OER) is of prime importance in proton exchange membrane (PEM) water electrolysis techniques. Ru-based catalysts have high activities but always suffer from severe fading and dissolution issues, which cannot satisfy the stability demand of PEM. Herein, a series of iridium-doped yttrium ruthenates pyrochlore catalysts is developed, which exhibit better activity and much higher durability than commercial RuO2 , IrO2 , and most of the reported Ru or Ir-based OER electrocatalysts. Typically, the representative Y2 Ru1.2 Ir0.8 O7 OER catalyst demands a low overpotential of 220 mV to achieve 10 mA cm-2 , which is much lower than that of RuO2 (300 mV) and IrO2 (350 mV). In addition, the catalyst does not show obvious performance decay or structural degradation over a 2000 h stability test. EXAFS and XPS co-prove the reduced valence state of ruthenium and iridium in pyrochlore contributes to the improved activity and stability. Density functional theory reveals that the potential-determining steps barrier of OOH* formation is greatly depressed through the synergy effect of Ir and Ru sites by balancing the d band center and oxygen intermediates binding ability.

Temporal Subtyping of Alzheimer's Disease Using Medical Conditions Preceding Alzheimer's Disease Onset in Electronic Health Records.

Subtyping of Alzheimer's disease (AD) can facilitate diagnosis, treatment, prognosis and disease management. It can also support the testing of new prevention and treatment strategies through clinical trials. In this study, we employed spectral clustering to cluster 29,922 AD patients in the OneFlorida Data Trust using their longitudinal EHR data of diagnosis and conditions into four subtypes. These subtypes exhibit different patterns of progression of other conditions prior to the first AD diagnosis. In addition, according to the results of various statistical tests, these subtypes are also significantly different with respect to demographics, mortality, and prescription medications after the AD diagnosis. This study could potentially facilitate early detection and personalized treatment of AD as well as data-driven generalizability assessment of clinical trials for AD.