Robert Leaman

Ling Luo, Chih-Hsuan Wei, Po-Ting Lai et al.

Biomedical named entity recognition (BioNER) seeks to automatically recognize biomedical entities in natural language text, serving as a necessary foundation for downstream text mining tasks and applications such as information extraction and question answering. Manually labeling training data for the BioNER task is costly, however, due to the significant domain expertise required for accurate annotation. The resulting data scarcity causes current BioNER approaches to be prone to overfitting, to suffer from limited generalizability, and to address a single entity type at a time (e.g., gene or disease). We therefore propose a novel all-in-one (AIO) scheme that uses external data from existing annotated resources to enhance the accuracy and stability of BioNER models. We further present AIONER, a general-purpose BioNER tool based on cutting-edge deep learning and our AIO schema. We evaluate AIONER on 14 BioNER benchmark tasks and show that AIONER is effective, robust, and compares favorably to other state-of-the-art approaches such as multi-task learning. We further demonstrate the practical utility of AIONER in three independent tasks to recognize entity types not previously seen in training data, as well as the advantages of AIONER over existing methods for processing biomedical text at a large scale (e.g., the entire PubMed data).

Qiao Jin, Robert Leaman, Zhiyong Lu · tsinghua

Biomedical research yields a wealth of information, much of which is only accessible through the literature. Consequently, literature search is an essential tool for building on prior knowledge in clinical and biomedical research. Although recent improvements in artificial intelligence have expanded functionality beyond keyword-based search, these advances may be unfamiliar to clinicians and researchers. In response, we present a survey of literature search tools tailored to both general and specific information needs in biomedicine, with the objective of helping readers efficiently fulfill their information needs. We first examine the widely used PubMed search engine, discussing recent improvements and continued challenges. We then describe literature search tools catering to five specific information needs: 1. Identifying high-quality clinical research for evidence-based medicine. 2. Retrieving gene-related information for precision medicine and genomics. 3. Searching by meaning, including natural language questions. 4. Locating related articles with literature recommendation. 5. Mining literature to discover associations between concepts such as diseases and genetic variants. Additionally, we cover practical considerations and best practices for choosing and using these tools. Finally, we provide a perspective on the future of literature search engines, considering recent breakthroughs in large language models such as ChatGPT. In summary, our survey provides a comprehensive view of biomedical literature search functionalities with 36 publicly available tools.

Robert Leaman, Rezarta Islamaj, Alexis Allot et al.

A significant percentage of COVID-19 survivors experience ongoing multisystemic symptoms that often affect daily living, a condition known as Long Covid or post-acute-sequelae of SARS-CoV-2 infection. However, identifying scientific articles relevant to Long Covid is challenging since there is no standardized or consensus terminology. We developed an iterative human-in-the-loop machine learning framework combining data programming with active learning into a robust ensemble model, demonstrating higher specificity and considerably higher sensitivity than other methods. Analysis of the Long Covid collection shows that (1) most Long Covid articles do not refer to Long Covid by any name (2) when the condition is named, the name used most frequently in the literature is Long Covid, and (3) Long Covid is associated with disorders in a wide variety of body systems. The Long Covid collection is updated weekly and is searchable online at the LitCovid portal: https://www.ncbi.nlm.nih.gov/research/coronavirus/docsum?filters=e_condition.LongCovid

Qingyu Chen, Alexis Allot, Robert Leaman et al.

The COVID-19 pandemic has been severely impacting global society since December 2019. Massive research has been undertaken to understand the characteristics of the virus and design vaccines and drugs. The related findings 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. 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 multilabel classification datasets in biomedical scientific literature. 19 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. 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.

Robert Leaman, Rezarta Islamaj, Zhiyong Lu

Biomedical named entity recognition (NER) and entity linking (EL) strongly depend on annotated corpora, but the utility of these resources for benchmarking is often assumed rather than characterized. We present a corpus-centric framework for diagnosing benchmark-relevant properties directly from corpus annotations, concept links, train-test splits, document metadata, and terminology mappings. The framework organizes standardized statistics into five families: (1) scale, density and label distribution, (2) lexical and conceptual structure, (3) train-test overlap, (4) metadata composition, and (5) terminology coverage where applicable. Applying the framework to nine corpora spanning diseases, chemicals, and cell types, we find that corpus properties can differ substantially, even when they address the same apparent task. We find differences in the evaluation signal they provide, the generalization demands they impose, the degree of train-test reuse they permit, and the regions of biomedical literature and concept space they represent. These differences suggest that commonly reported corpus statistics can be insufficient to characterize what biomedical NER and EL benchmarks evaluate. We argue that corpus-centric diagnostics provide a practical framework for analyzing corpora beyond surface descriptors such as corpus size and entity type, for identifying potential transfer risks, and for interpreting the scope of benchmarking conclusions. We release the framework as open-source code with an interactive dashboard to support reproducing our analyses and characterizing additional corpora.

Zhizheng Wang, Chih-Hsuan Wei, Joey Chan et al.

Trustworthiness and transparency are essential for the clinical adoption of artificial intelligence (AI) in healthcare and biomedical research. Recent deep research systems aim to accelerate evidence-grounded scientific discovery by integrating AI agents with multi-hop information retrieval, reasoning, and synthesis. However, most existing systems lack explicit and inspectable criteria for evidence appraisal, creating a risk of compounding errors and making it difficult for researchers and clinicians to assess the reliability of their outputs. In parallel, current benchmarking approaches rarely evaluate performance on complex, real-world medical questions. Here, we introduce DeepER-Med, a Deep Evidence-based Research framework for Medicine with an agentic AI system. DeepER-Med frames deep medical research as an explicit and inspectable workflow of evidence-based generation, consisting of three modules: research planning, agentic collaboration, and evidence synthesis. To support realistic evaluation, we also present DeepER-MedQA, an evidence-grounded dataset comprising 100 expert-level research questions derived from authentic medical research scenarios and curated by a multidisciplinary panel of 11 biomedical experts. Expert manual evaluation demonstrates that DeepER-Med consistently outperforms widely used production-grade platforms across multiple criteria, including the generation of novel scientific insights. We further demonstrate the practical utility of DeepER-Med through eight real-world clinical cases. Human clinician assessment indicates that DeepER-Med's conclusions align with clinical recommendations in seven cases, highlighting its potential for medical research and decision support.

Chih-Hsuan Wei, Chi-Ping Day, Zhizheng Wang et al.

Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically plausible candidates from historically well-connected ones. Here we introduce DrugKLM, a hybrid framework that integrates biomedical knowledge graph structure with large language model-based mechanistic reasoning to enable mechanistically grounded therapeutic prioritization. Across benchmark datasets, DrugKLM outperforms knowledge graph-only and language model-only baselines, including TxGNN. Beyond improved recall, DrugKLM confidence scores exhibit functional alignment with molecular phenotypes: higher scores are associated with transcriptional signatures linked to improved survival across 12 TCGA cancers. The scoring framework preferentially captures biologically perturbational signals rather than historical indication patterns. Expert curation across five cancers further reveals systematic differences in prioritization behavior, with DrugKLM elevating candidates supported by coherent mechanistic rationale and disease-specific clinical context. Together, these results establish DrugKLM as an evidence-integrative framework that translates heterogeneous biomedical data into mechanistically interpretable and clinically grounded therapeutic hypotheses.

Po-Ting Lai, Chih-Hsuan Wei, Shubo Tian et al.

Biological relation networks contain rich information for understanding the biological mechanisms behind the relationship of entities such as genes, proteins, diseases, and chemicals. The vast growth of biomedical literature poses significant challenges updating the network knowledge. The recent Biomedical Relation Extraction Dataset (BioRED) provides valuable manual annotations, facilitating the develop-ment of machine-learning and pre-trained language model approaches for automatically identifying novel document-level (inter-sentence context) relationships. Nonetheless, its annotations lack directionality (subject/object) for the entity roles, essential for studying complex biological networks. Herein we annotate the entity roles of the relationships in the BioRED corpus and subsequently propose a novel multi-task language model with soft-prompt learning to jointly identify the relationship, novel findings, and entity roles. Our results in-clude an enriched BioRED corpus with 10,864 directionality annotations. Moreover, our proposed method outperforms existing large language models such as the state-of-the-art GPT-4 and Llama-3 on two benchmarking tasks. Our source code and dataset are available at https://github.com/ncbi-nlp/BioREDirect.

Qiao Jin, Yin Fang, Lauren He et al.

Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To efficiently perform biomedical evidence attribution, we present Med-V1, a family of small language models with only three billion parameters. Trained on high-quality synthetic data newly developed in this study, Med-V1 substantially outperforms (+27.0% to +71.3%) its base models on five biomedical benchmarks unified into a verification format. Despite its smaller size, Med-V1 performs comparably to frontier LLMs such as GPT-5, along with high-quality explanations for its predictions. We use Med-V1 to conduct a first-of-its-kind use case study that quantifies hallucinations in LLM-generated answers under different citation instructions. Results show that the format instruction strongly affects citation validity and hallucination, with GPT-5 generating more claims but exhibiting hallucination rates similar to GPT-4o. Additionally, we present a second use case showing that Med-V1 can automatically identify high-stakes evidence misattributions in clinical practice guidelines, revealing potentially negative public health impacts that are otherwise challenging to identify at scale. Overall, Med-V1 provides an efficient and accurate lightweight alternative to frontier LLMs for practical and real-world applications in biomedical evidence attribution and verification tasks. Med-V1 is available at https://github.com/ncbi-nlp/Med-V1.

Rezarta Islamaj, Robert Leaman, Joey Chan et al.

Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain discriminative as model capabilities improve. Existing biomedical question answering (QA) benchmarks are limited in this respect. Multiple-choice formats can allow models to succeed through answer elimination rather than inference, while widely circulated exam-style datasets are increasingly vulnerable to performance saturation and training data contamination. Multi-hop reasoning, defined as the ability to integrate information across multiple sources to derive an answer, is central to clinically meaningful tasks such as diagnostic support, literature-based discovery, and hypothesis generation, yet remains underrepresented in current biomedical QA benchmarks. MedHopQA is a disease-centered multi-hop reasoning benchmark consisting of 1,000 expert-curated question-answer pairs introduced as a shared task at BioCreative IX. Each question requires synthesis of information across two distinct Wikipedia articles, and answers are provided in an open-ended free-text format. Gold annotations are augmented with ontology-grounded synonym sets from MONDO, NCBI Gene, and NCBI Taxonomy to support both lexical and concept-level evaluation. MedHopQA was constructed through a structured process combining human annotation, triage, iterative verification, and LLM-as-a-judge validation. To reduce leaderboard gaming and contamination risk, the 1,000 scored questions are embedded within a publicly downloadable set of 10,000 questions, with answers withheld, on a CodaBench leaderboard. MedHopQA provides both a benchmark and a reusable framework for constructing future biomedical QA datasets that prioritize compositional reasoning, saturation resistance, and contamination resistance as core design constraints.

Rezarta Islamaj, Joey Chan, Robert Leaman et al.

Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple sources to answer complex questions. To address this problem, the BioCreative IX MedHopQA shared task was designed to benchmark in multi-hop reasoning for large language models (LLMs). We developed a novel dataset of 1,000 challenging QA pairs spanning diseases, genes, and chemicals, with particular emphasis on rare diseases. Each question was constructed to require two-hop reasoning through the integration of information from two distinct Wikipedia pages. The challenge attracted 48 submissions from 13 teams. Systems were evaluated using both surface string comparison and conceptual accuracy (MedCPT score). The results showed a substantial performance gap between baseline LLMs and enhanced systems. The top-ranked submission achieved an 89.30% F1 score on the MedCPT metric and an 87.30% exact match (EM) score, compared with 67.40% and 60.20%, respectively, for the zero-shot baseline. A central finding of the challenge was that retrieval-augmented generation (RAG) and related retrieval-based strategies were critical for strong performance. In addition, concept-level evaluation improved answer assessment when correct responses differed in surface form. The MedHopQA dataset is publicly available to support continued progress in this important area. Challenge materials: https://www.ncbi.nlm.nih.gov/research/bionlp/medhopqa and benchmark https://www.codabench.org/competitions/7609/

Robert Leaman, Zhiyong Lu

The number of unique terms in the scientific literature used to refer to either SARS-CoV-2 or COVID-19 is remarkably large and has continued to increase rapidly despite well-established standardized terms. This high degree of term variation makes high recall identification of these important entities difficult. In this manuscript we present an extensive dictionary of terms used in the literature to refer to SARS-CoV-2 and COVID-19. We use a rule-based approach to iteratively generate new term variants, then locate these variants in a large text corpus. We compare our dictionary to an extensive collection of terminological resources, demonstrating that our resource provides a substantial number of additional terms. We use our dictionary to analyze the usage of SARS-CoV-2 and COVID-19 terms over time and show that the number of unique terms continues to grow rapidly. Our dictionary is freely available at https://github.com/ncbi-nlp/CovidTermVar.

Qiao Jin, Nicholas Wan, Robert Leaman et al.

Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this primer paper, we propose an actionable guideline to help healthcare professionals more efficiently utilize LLMs in their work, along with a set of best practices. This approach consists of several main phases, including formulating the task, choosing LLMs, prompt engineering, fine-tuning, and deployment. We start with the discussion of critical considerations in identifying healthcare tasks that align with the core capabilities of LLMs and selecting models based on the selected task and data, performance requirements, and model interface. We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks. Deployment considerations, including regulatory compliance, ethical guidelines, and continuous monitoring for fairness and bias, are also discussed. By providing a structured step-by-step methodology, this tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice, ensuring that these powerful technologies are applied in a safe, reliable, and impactful manner.

Yifan Yang, Qiao Jin, Robert Leaman et al.

The remarkable capabilities of Large Language Models (LLMs) make them increasingly compelling for adoption in real-world healthcare applications. However, the risks associated with using LLMs in medical applications have not been systematically characterized. We propose using five key principles for safe and trustworthy medical AI: Truthfulness, Resilience, Fairness, Robustness, and Privacy, along with ten specific aspects. Under this comprehensive framework, we introduce a novel MedGuard benchmark with 1,000 expert-verified questions. Our evaluation of 11 commonly used LLMs shows that the current language models, regardless of their safety alignment mechanisms, generally perform poorly on most of our benchmarks, particularly when compared to the high performance of human physicians. Despite recent reports indicate that advanced LLMs like ChatGPT can match or even exceed human performance in various medical tasks, this study underscores a significant safety gap, highlighting the crucial need for human oversight and the implementation of AI safety guardrails.

Po-Ting Lai, Elisabeth Coudert, Lucila Aimo et al.

Expert curation is essential to capture knowledge of enzyme functions from the scientific literature in FAIR open knowledgebases but cannot keep pace with the rate of new discoveries and new publications. In this work we present EnzChemRED, for Enzyme Chemistry Relation Extraction Dataset, a new training and benchmarking dataset to support the development of Natural Language Processing (NLP) methods such as (large) language models that can assist enzyme curation. EnzChemRED consists of 1,210 expert curated PubMed abstracts in which enzymes and the chemical reactions they catalyze are annotated using identifiers from the UniProt Knowledgebase (UniProtKB) and the ontology of Chemical Entities of Biological Interest (ChEBI). We show that fine-tuning pre-trained language models with EnzChemRED can significantly boost their ability to identify mentions of proteins and chemicals in text (Named Entity Recognition, or NER) and to extract the chemical conversions in which they participate (Relation Extraction, or RE), with average F1 score of 86.30% for NER, 86.66% for RE for chemical conversion pairs, and 83.79% for RE for chemical conversion pairs and linked enzymes. We combine the best performing methods after fine-tuning using EnzChemRED to create an end-to-end pipeline for knowledge extraction from text and apply this to abstracts at PubMed scale to create a draft map of enzyme functions in literature to guide curation efforts in UniProtKB and the reaction knowledgebase Rhea. The EnzChemRED corpus is freely available at https://ftp.expasy.org/databases/rhea/nlp/.

Jash Rajesh Parekh, Wonbin Kweon, Joey Chan et al.

Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications. Existing benchmarks do not evaluate such conditional reasoning, and retrieval-augmented or graph-based methods lack explicit mechanisms to ensure that retrieved knowledge is applicable to given context. To address this gap, we propose CondMedQA, the first benchmark for conditional biomedical QA, consisting of multi-hop questions whose answers vary with patient conditions. Furthermore, we propose Condition-Gated Reasoning (CGR), a novel framework that constructs condition-aware knowledge graphs and selectively activates or prunes reasoning paths based on query conditions. Our findings show that CGR more reliably selects condition-appropriate answers while matching or exceeding state-of-the-art performance on biomedical QA benchmarks, highlighting the importance of explicitly modeling conditionality for robust medical reasoning.

Zhizheng Wang, Chi-Ping Day, Chih-Hsuan Wei et al.

Gene set analysis (GSA) is a foundational approach for interpreting genomic data of diseases by linking genes to biological processes. However, conventional GSA methods overlook clinical context of the analyses, often generating long lists of enriched pathways with redundant, nonspecific, or irrelevant results. Interpreting these requires extensive, ad-hoc manual effort, reducing both reliability and reproducibility. To address this limitation, we introduce cGSA, a novel AI-driven framework that enhances GSA by incorporating context-aware pathway prioritization. cGSA integrates gene cluster detection, enrichment analysis, and large language models to identify pathways that are not only statistically significant but also biologically meaningful. Benchmarking on 102 manually curated gene sets across 19 diseases and ten disease-related biological mechanisms shows that cGSA outperforms baseline methods by over 30%, with expert validation confirming its increased precision and interpretability. Two independent case studies in melanoma and breast cancer further demonstrate its potential to uncover context-specific insights and support targeted hypothesis generation.

Chih-Hsuan Wei, Alexis Allot, Po-Ting Lai et al.

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.

Qingyu Chen, Robert Leaman, Alexis Allot et al.

The COVID-19 pandemic has had a significant impact on society, both because of the serious health effects of COVID-19 and because of public health measures implemented to slow its spread. Many of these difficulties are fundamentally information needs; attempts to address these needs have caused an information overload for both researchers and the public. Natural language processing (NLP), the branch of artificial intelligence that interprets human language, can be applied to address many of the information needs made urgent by the COVID-19 pandemic. This review surveys approximately 150 NLP studies and more than 50 systems and datasets addressing the COVID-19 pandemic. We detail work on four core NLP tasks: information retrieval, named entity recognition, literature-based discovery, and question answering. We also describe work that directly addresses aspects of the pandemic through four additional tasks: topic modeling, sentiment and emotion analysis, caseload forecasting, and misinformation detection. We conclude by discussing observable trends and remaining challenges.

Lana Yeganova, Rezarta Islamaj, Qingyu Chen et al.

Timely access to accurate scientific literature in the battle with the ongoing COVID-19 pandemic is critical. This unprecedented public health risk has motivated research towards understanding the disease in general, identifying drugs to treat the disease, developing potential vaccines, etc. This has given rise to a rapidly growing body of literature that doubles in number of publications every 20 days as of May 2020. Providing medical professionals with means to quickly analyze the literature and discover growing areas of knowledge is necessary for addressing their question and information needs. In this study we analyze the LitCovid collection, 13,369 COVID-19 related articles found in PubMed as of May 15th, 2020 with the purpose of examining the landscape of literature and presenting it in a format that facilitates information navigation and understanding. We do that by applying state-of-the-art named entity recognition, classification, clustering and other NLP techniques. By applying NER tools, we capture relevant bioentities (such as diseases, internal body organs, etc.) and assess the strength of their relationship with COVID-19 by the extent they are discussed in the corpus. We also collect a variety of symptoms and co-morbidities discussed in reference to COVID-19. Our clustering algorithm identifies topics represented by groups of related terms, and computes clusters corresponding to documents associated with the topic terms. Among the topics we observe several that persist through the duration of multiple weeks and have numerous associated documents, as well several that appear as emerging topics with fewer documents. All the tools and data are publicly available, and this framework can be applied to any literature collection. Taken together, these analyses produce a comprehensive, synthesized view of COVID-19 research to facilitate knowledge discovery from literature.

Chih-Hsuan Wei, Kyubum Lee, Robert Leaman et al.

Automatically locating named entities in natural language text - named entity recognition - is an important task in the biomedical domain. Many named entity mentions are ambiguous between several bioconcept types, however, causing text spans to be annotated as more than one type when simultaneously recognizing multiple entity types. The straightforward solution is a rule-based approach applying a priority order based on the precision of each entity tagger (from highest to lowest). While this method is straightforward and useful, imprecise disambiguation remains a significant source of error. We address this issue by generating a partially labeled corpus of ambiguous concept mentions. We first collect named entity mentions from multiple human-curated databases (e.g. CTDbase, gene2pubmed), then correlate them with the text mined span from PubTator to provide the context where the mention appears. Our corpus contains more than 3 million concept mentions that ambiguous between one or more concept types in PubTator (about 3% of all mentions). We approached this task as a classification problem and developed a deep learning-based method which uses the semantics of the span being classified and the surrounding words to identify the most likely bioconcept type. More specifically, we develop a convolutional neural network (CNN) and along short-term memory (LSTM) network to respectively handle the semantic syntax features, then concatenate these within a fully connected layer for final classification. The priority ordering rule-based approach demonstrated F1-scores of 71.29% (micro-averaged) and 41.19% (macro-averaged), while the new disambiguation method demonstrated F1-scores of 91.94% (micro-averaged) and 85.42% (macro-averaged), a very substantial increase.