Science AI Journal
Biochemistry, Genetics and Molecular Biology · Research topic

Open research questions in Biomedical Text Mining and Ontologies

237 gap statements mined from Biomedical Text Mining and Ontologies papers in our 7.9M-paper local library, which holds 1,404 papers on the topic — drawn mostly from each paper's own stated research gap, future-work, challenge and limitation notes, and its abstract. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one.

Choosing where to publish on Biomedical Text Mining and Ontologies? See the ranked Biology journals.

What the literature leaves open

  • These results show that LLMs reasoning over unstructured scientific text can build updatable, bespoke databases that outperform expert-curated resources, although performance remains limited by agent access to full-text literature.

    The accessible human surfaceome · 2026 · DOI

  • Large language models (LLMs) offer promising capabilities for information extraction, but integrated platforms combining LLM extraction with community validation for plant regulatory databases remain scarce.

    GeneReL: a large language model-powered platform for gene regulatory relationship extraction with community curation · 2026 · DOI

  • Standardized terminologies such as Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) support semantic interoperability by providing consistent representations of clinical concepts; however, the relationship between empirical concept co-occurrence in clinical documentation and embedding-based semantic similarity remains poorly understood.

    Semantic analysis of SNOMED CT concept co-occurrences in clinical documentation using MIMIC-IV · 2026 · DOI

  • Future research should focus on expanding gold-standard datasets and developing post-processing algorithms to improve annotations' generalization.

    Leveraging sequence-to-sequence models for semantic annotation of Dutch pathology reports · 2025 · DOI

  • These relationships are organized in a highly systematic way in order to make them not only informative but also scientifically computational, enabling inferential hypotheses to be formed to address gaps in understanding.

    Integrating AI-powered text mining from PubTator into the manual curation workflow at the Comparative Toxicogenomics Database · 2025 · DOI

  • The current lack of distinction between AI as a supportive tool and as a therapeutic factor. The need for a conceptual framework to understand the role of AI in information pharmacology.

    Artificial Intelligence as an Object of Information Pharmacology: the Boundary Between a Supportive Tool and a Therapeutic Factor · 2026 · DOI

  • KGBR development must incorporate methods to align mouse experimental evidence with human bone regeneration data, including standardized ontology mappings for orthologous genes, cell types, and signaling pathways across species to support translational research from preclinical to clinical applications.

    KGBR: A Domain-Specific Knowledge Graph for Bone Regeneration Research · 2026 · DOI

  • Crucially, we show that coverage-based metrics alone are insufficient to capture these differences, underscoring the importance of deeper, task-sensitive evaluation criteria for biomedical applications.

    La benchmarking large language models for extracting biobank-derived insights into health and disease · 2026 · DOI

  • Beyond entity retrieval and semantic matching, there is a pressing need to benchmark models on complex reasoning tasks, including multi-hop inference, causal explanation, and counterfactual generation. Incorporating interpretability audits (such as attribution mapping and calibration diagnostics) will also be critical for building trust and ensuring model transparency in high-stakes settings.

    La benchmarking large language models for extracting biobank-derived insights into health and disease · 2026 · DOI

  • Extracting longer phrases remains underexplored. Conventional named entity recognition has focused on short terms. Developing more general systems that can perform many tasks without manual creation and labeling of a training dataset is a challenge.

    Evaluating Encoder and Decoder Models for Extended Clinical Concept Recognition in Japanese Clinical Texts: Comparative Study With Weighted Soft Matching · 2026 · DOI

  • The study is limited to Japanese clinical texts and may not be generalizable to other languages or domains. The dataset used is relatively small, with approximately 20,000 case reports.

    Evaluating Encoder and Decoder Models for Extended Clinical Concept Recognition in Japanese Clinical Texts: Comparative Study With Weighted Soft Matching · 2026 · DOI

  • Future work may explore finer-grained knowledge injection mechanisms, more powerful multi-hop reasoning architectures, and stricter domain-adaptive training strategies to continually improve the system's performance in complex professional domains.

    SEP-LLM: Professional QA in the SEP Domain Using Retrieval-Augmented LLMs · 2026 · DOI

  • Future work may explore hybrid approaches that combine structured alignment with generative models, as well as extensions to broader multi-domain knowledge settings. Future work will explore incorporating richer clinical context, improving robustness under sparse supervision, and extending alignment to more complex multi-hop reasoning settings.

    Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning · 2026

  • We quantify how much concept overlap survives realistic alignment, and we characterize the new failure modes introduced by the methods that practitioners reach for when ID matching is insufficient.

    Beyond Identifier Matching: An Empirical Characterization of Failure Modes in Biomedical Knowledge Graph Integration · 2026 · DOI

  • A key contribution of this review is the identification and contextualisation of the limited evidence base for Turkish breast imaging NLP within the broader low-resource clinical NLP landscape.

    Natural Language Processing in Breast Imaging Reports: A Scoping Review with Implications for Low-Resource Clinical Languages · 2026 · DOI

  • Future research should investigate the impact of knowledge graph prompt engineering on other large language models. Future research should explore the application of knowledge graph-integrated large language models in other domains.

    Enhancing Medical Question-Answering Systems with Knowledge Graph-Integrated Large Language Models: A Comparative Analysis · 2026 · DOI

  • Current large language models are constrained by the scarcity of domain-specific expertise and the lack of deep contextual comprehension.

    Enhancing Medical Question-Answering Systems with Knowledge Graph-Integrated Large Language Models: A Comparative Analysis · 2026 · DOI

  • Strategies for rare events need to be developed. Explainability methods need to be applied to improve decision-making transparency. Refining text segmentation techniques to handle mixed outcomes is necessary.

    RescueGPT : An Automated System for Detecting Adverse Safety Events in Prehospital Emergency Medical Service Notes With a Zero‐Shot Approach With Large Language Models: A Proof‐of‐Concept Study · 2026 · DOI

  • Conventional ontology driven approaches based on the Human Phenotype Ontology (HPO) enable structured phenotype comparison but often limited by the incomplete annotations and reduced ability to capture the contextual information contained in free-text clinical narratives.

    RDEmbed: A Sentence-Embedding Framework for Rare Disease Phenotype Representation and Phenotypic Similarity Analysis · 2026 · DOI

  • Stress, arising from the dynamic interaction between external stressors, individual appraisals, and physiological or psychological responses, significantly impacts health yet is often underreported and inconsistently documented.

    Feasibility of ontology-guided structuring of stress information from narrative text: An exploratory study using large language models · 2026 · DOI

  • Study designs are highly heterogeneous, making it difficult to compare findings across studies.

    KGBR: A Domain-Specific Knowledge Graph for Bone Regeneration Research · 2026 · DOI

  • There is no accessible, standardized framework for systematic comparison of omics representations with different text encoders. Existing implementations of multimodal omics/text models remain difficult to customize and are not integrated into widely supported ecosystems.

    mmContext: an open framework for multimodal contrastive learning of omics and text data · 2026 · DOI

  • Genes/proteins and the three Gene Ontology categories aligned cleanly across PrimeKG and Hetionet (mutual coverage 94-99%), but disease overlap was sparse: only 0.

    Beyond Identifier Matching: An Empirical Characterization of Failure Modes in Biomedical Knowledge Graph Integration · 2026 · DOI

  • The explain stage therefore surfaced a biomaterial-inspired mRNA-LNP depot bridge, but it still marked the pack as insufficient evidence for direct claims about vaccine adjuvant inclusion and long-term efficacy.

    Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine · 2026

  • Specialized cell-type models trained exclusively on single-cell data or domain-specific subsets. Incorporation of additional omics modalities to construct richer joint embedding spaces for unpaired data. Applying the model as a classifier or guiding signal for generative diffusion models of transcriptomes.

    mmContext: an open framework for multimodal contrastive learning of omics and text data · 2026 · DOI

Most-cited papers in Biomedical Text Mining and Ontologies

Most recent work

Find a gap in your own Biomedical Text Mining and Ontologies sub-topic

This page shows what the Biomedical Text Mining and Ontologies literature already flags as unresolved. To narrow it to your specific question, search the Research Gap Finder: the search is free with a free account and lists the papers closest to your topic first. Unlocking that topic (50 credits, charged once) fills the comparison table from our 7.9M-paper local library and writes the gaps from its rows.

Open the Research Gap Finder →

Related topics in Biochemistry, Genetics and Molecular Biology

Gut microbiota and health
4,284 open questions
Extracellular vesicles in disease
1,862 open questions
Antibiotic Resistance in Bacteria
1,778 open questions
Inflammatory Bowel Disease
1,518 open questions
RNA modifications and cancer
1,209 open questions
Single-cell and spatial transcriptomics
1,178 open questions
Genetic Associations and Epidemiology
1,146 open questions
Epigenetics and DNA Methylation
1,090 open questions
Open questions raised by papers listed on this page include: (1) These results show that LLMs reasoning over unstructured scientific text can build updatable, bespoke databases that outperform expert-curated resources, although performance remains limited by agent access to full-text literature (“The accessible human surfaceome”, 2026); (2) Large language models (LLMs) offer promising capabilities for information extraction, but integrated platforms combining LLM extraction with community validation for plant regulatory databases remain scarce (“GeneReL: a large language model-powered platform for gene regulatory…”, 2026); (3) The current lack of distinction between AI as a supportive tool and as a therapeutic factor (“Artificial Intelligence as an Object of Information Pharmacology: the Boundary…”, 2026); (4) Future research should investigate the impact of knowledge graph prompt engineering on other large language models (“Enhancing Medical Question-Answering Systems with Knowledge Graph-Integrated…”, 2026); (5) There is no accessible, standardized framework for systematic comparison of omics representations with different text encoders (“mmContext: an open framework for multimodal contrastive learning of omics and…”, 2026). 237 gap statements have been mined from Biomedical Text Mining and Ontologies papers in our 7.9M-paper local library, which holds 1,404 papers on the topic; the gaps come from whichever of those papers state one. They are mostly the research gaps the authors state and the papers' abstracts, plus future-work, limitations and challenges passages. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 1,100,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? Acceptance odds for top, mid and open/emerging journals, in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck for prior publication across 7 sources and our local library.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

How Pre-Check worksHow AI Review works

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.