Recent advances in biomedical literature mining
Open accessThe DOI matches its Crossref record; 190 of the 192 references it cites were found in a registry or an index.
Abstract
The recent years have witnessed a rapid increase in the number of scientific articles in biomedical domain. These literature are mostly available and readily accessible in electronic format. The domain knowledge hidden in them is critical for biomedical research and applications, which makes biomedical literature mining (BLM) techniques highly demanding. Numerous efforts have been made on this topic from both biomedical informatics (BMI) and computer science (CS) communities. The BMI community focuses more on the concrete application problems and thus prefer more interpretable and descriptive methods, while the CS community chases more on superior performance and generalization ability, thus more sophisticated and universal models are developed. The goal of this paper is to provide a review of the recent advances in BLM from both communities and inspire new research directions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Traditional NLP pipelines for automated extraction require task‐specific training data [11, 12, 13] and do not generalize to the diverse parameter types in QSP modeling.”
From Structured Schemas for Provenance‐Rich, LLM ‐Assisted QSP Model Calibration (2026) · cites this paper as [11]
Experimental — accuracy not yet measuredIn the citing paper
“Traditional NLP pipelines for automated extraction require task-specific training data11,12,13 and do not generalize to the diverse parameter types in QSP modeling.”
From Structured Schemas for Provenance-Rich, LLM-Assisted QSP Model Calibration (2026) · cites this paper as [11]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“One specific model that is getting popular in NLP recently is the BERT model [13], wherein the major building block is transformer [54].”
BackgroundHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“Deep learning models such as long short-term memory (LSTM) [11], convolutional neural network (CNN) [12] and bidirectional encoder representations from transformers (BERT) [13] have been firmly established as the state-of-the-art (SOTA) approaches in NLP tasks such as named entity recognition (NER)…”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 3×
“Deep learning models such as long short-term memory (LSTM) [11], convolutional neural network (CNN) [12] and bidirectional encoder representations from transformers (BERT) [13] have been firmly established as the state-of-the-art (SOTA) approaches in NLP tasks such as named entity recognition (NER) [14] and relation e…”
BackgroundBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“Deep learning models such as long short-term memory (LSTM) [11], convolutional neural network (CNN) [12] and bidirectional encoder representations from transformers (BERT) [13] have been firmly established as the state-of-the-art (SOTA) approaches in NLP tasks such as named entity recognition (NER) [14] and relation e…”
BackgroundConvolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 9×
“More recently, a few studies have investigated the use of deep neural networks, such as CNNs (see Figure 7) and RNNs (see Figure 8), for relation extraction, which are detailed below.”
BackgroundInfluentialBidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 1×
“A BiLSTM [53] computes two separate latent embedding vectors for every word in a sequence that capture both the forward and backward semantic dependencies of the word sequence.”
MethodBioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687 · cited 1×
“[13, 52]) have been firmly established as the SOTA approaches in sequence modeling.”
Background
Research works printed but not linked: 7
- Abacha, 2011, Medical entity recognition: a comparison of semantic and statistical methods, Proceedings of the 2011 Workshop on Biomedical Natural Language Processing, 56
- Wei, 2015, Overview of the biocreative v chemical disease relation (CDR) task, Biocreative Challenge Evaluation Workshop, 154
- Segura-Bedmar, 2013, Semeval-2013 task 9: Extraction of drug-drug interactions from biomedical texts (ddiextraction 2013), 341
- Dollah, 2011, Ontology based approach for classifying biomedical text abstracts, Int. J. Data Eng., 2, 1
- Zhao, 2018, Causaltriad: toward pseudo causal relation discovery and hypotheses generation from medical text data, Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, 184
- Krallinger, 2017, Overview of the biocreative vi chemical-protein interaction track, Proceedings of the Sixth BioCreative Challenge Evaluation Workshop, 1, 141
- Chowdhury, 2011, Two different machine learning techniques for drug-drug interaction extraction, Challenge Task on Drug-Drug Interaction Extraction, 19
Cited by
Items 101–150 of 150
Fine-grained biomedical knowledge negation detection via contrastive learning
Zhu, T., Xiang, Y., Chen, Q., Qin, Y., Hu, B., & Zhang, W. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110575 · Cited by 1
Tang, Z., Lu, Y., Yang, B., Li, L., & Hao, J. (2023) · Intelligent Autonomous Systems · doi:10.1109/icoias61634.2023.00035 · Cited by 1
NLP Applications—Biomedical Literature
Zhang, R., Kastrin, A., Hristovski, D., Fiszman, M., & Kilicoglu, H. (2024) · Cognitive informatics in biomedicine and healthcare · doi:10.1007/978-3-031-55865-8_13 · Cited by 1
Advances in Biomedical Entity and Relation Extraction: Techniques and Applications
Sood, S., & Sharan, A. (2024) · Transactions on computer systems and networks · doi:10.1007/978-981-97-3962-2_12 · Cited by 1
Hou, Y., Zhan, Z., Zeng, M., Wu, Y., Zhou, S., Chen, X., Zhou, H., Song, M., & Zhang, R. (2026) · Research Square · doi:10.21203/rs.3.rs-8605899/v1 · Cited by 1
“Consequently, the development of robust, automated biomedical natural language processing (BioNLP) tools has shifted from a convenience to a necessity 6 – 8 .”
Structured Schemas for Provenance-Rich, LLM-Assisted QSP Model Calibration
Eliason, J., & Popel, A. S. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.05.709623
“Traditional NLP pipelines for automated extraction require task-specific training data 11,12,13 and do not generalize to the diverse parameter types in QSP modeling.”
Structured Schemas for Provenance‐Rich, LLM ‐Assisted QSP Model Calibration
Eliason, J., & Popel, A. S. (2026) · CPT: Pharmacometrics & Systems Pharmacology · doi:10.1002/psp4.70306
Wang, S., Mao, J., & Xie, H. (2021)
Transducer Cascades for Biological Literature-Based Discovery
Maurel, D., Chéry, S., Bidoít, N., Chatalic, P., Filali, A., Froidevaux, C., & Poupon, A. (2022) · Information · doi:10.3390/info13050262
KGSG: Knowledge Guided Syntactic Graph Model for Drug-Drug Interaction Extraction
Du, W., Zhang, Y., Yang, M. Y., Liu, D., & Liu, X. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7596-7_5
Enhancing Syntactic Resolution in Biomedical Data Processing with OpenCL: A Use Case Study
Hajhouj, M., Abık, M., & Zarnoufi, R. (2023) · International Conference on Cloud Computing Technologies and Applications (CloudTech) · doi:10.1109/cloudtech58737.2023.10366175
“It paves the way for a wide array of advancements, including but not limited to enhancing our understanding of disease mechanisms, discovering novel therapeutic targets, and personalizing patient care [10].”
BackgroundZhang, Y., Lu, J., Wang, J., Wu, R., Liu, X., He, M., Zong, H., Zhan, C., Zhang, Y., Huang, J., et al. (2024) · doi:10.2196/preprints.56294
Hao, J., Guo, Z., Peng, Q., Zhang, M., Shen, L., Cong, S., Li, J., & Sun, H. (2024) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi61247.2024.00041
“The advent of large language models (LLMs) like Bidirectional Encoder Representations from Transformers (BERT) [11], and specifically, domain-adapted models such as PubMedBERT, has significantly advanced the field of medical concept indexing [12, 13, 14].”
MethodGauging Expert Perspectives: A Survey on AI Integration in Pharmacovigilance
Nazir, H. (2024) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2024.64304
Zhang, Y., Wang, J., Wu, R., Liu, X., Zong, H., Lu, J., Zhan, C., Huang, J., & Shen, B. (2025) · Research Square · doi:10.21203/rs.3.rs-6000333/v1
Empirical Research on Statistical Data Analysis Techniques in Biomedical Applications
Gudala, L., Chandramohan, S., Ramaswamy, Y., Fallahhusein, M., & Shashidhara, K. S. (2025) · International Conference on Data Science and Information System (ICDSIS) · doi:10.1109/icdsis65355.2025.11070366
“Moreover, the model provides graphical user interface which makes it applicable for both teaching and research purposes. b) DL Pipeline: Sendong Zhao et al. [20] demonstrated a model for longitudinal Multiview data integration by using deep learning pipeline.”
Posada-Reyes, A.-B., Méndez-Cruz, C.-F., Martínez-Luna, S. B., & Varela-Vega, A. (2025) · TIES Revista de Tecnología e Innovación en Educación Superior · doi:10.22201/dgtic.26832968e.2025.13.49
Bhasuran, B., Abdulkadhar, S., & Natarajan, J. (2026) · Medinformatics · doi:10.47852/bonviewmedin62027833
Xing, J., Wang, H., Sun, Y., Su, X., & Wu, S. (2025) · Advanced Intelligent Discovery · doi:10.1002/aidi.202500038 · Cited by 1
Shariatmadari, A. H., Jafari, A., Guo, S.-K., Srinivasan, S., Sheffield, N. C., Zhang, A., & Jha, K. (2025) · Bioinform. · doi:10.1093/bioinformatics/btaf563 · Cited by 2
“Central to this is the problem of biomedical hypothesis generation (HG) (Akujuobi et al. 2020a, Zhao et al. 2021, Zhou et al. 2024b) that aims to discover cross-silo connections between two disjoint biomedical concepts by chaining together the already known and established scientific facts that…”
AI's Inroad into Medication Enhancement
-, S., Sharma, S., Singh, S., Govindarajan, S., & Sharma, A. (2025) · BENTHAM SCIENCE PUBLISHERS eBooks · doi:10.2174/9789815324457125010008
Price, E., & Dikicioǧlu, D. (2025) · npj Systems Biology and Applications · doi:10.1038/s41540-025-00630-x
“This variability in terminology creates challenges for automatic retrieval and categorisation, which are particularly relevant issues in machine learning or natural language processing (NLP) based literature mining 35 .”
Kropiwnicki, E., Lachmann, A., Clarke, D. J. B., Xie, Z., Jagodnik, K. M., & Ma’ayan, A. (2022) · Figshare · doi:10.6084/m9.figshare.19204310
Rosário‐Ferreira, N., Guimarães, V., Costa, V. S., & Moreira, I. S. (2021) · Figshare · doi:10.6084/m9.figshare.16735750
PubMed and Beyond: Biomedical Literature Search in the Age of Artificial Intelligence.
Jin, Q., Leaman, R., & Lu, Z. (2023) · Europe PMC (PubMed Central) · Cited by 2
Self-citationIntelligent Filtering in Biomedical Literature Retrieval Systems
Muhsen, O., Ali, S. A., Fallahhusein, M., Dhanoj, M., Jansirani, D., & Aravindan, P. (2025) · Indian Journal of Information Sources and Services · doi:10.51983/ijiss-2026.16.1.31
“They can recognize synonyms, automatically categorize documents by content, and can make inferences about the user intention either based on the history of past search activity or based on the query itself (Zhao et al., 2021; Dalir et al., 2017).”
dgiLIT: A Method for Prioritization and AI Curation of Drug-Gene InteractionsPreprint
Cannon, M. J., Bratulin, A., Stevenson, J., Perry, K., Coffman, A. C., Kiwala, S., Schimmelpfennig, L. E., Costello, H. M., McMichael, J. F., Griffith, M., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.01.16.699733
“The rich yet computationally inaccessible knowledge in publications has been a driving motivation for the development of many text mining, text annotation, and knowledge extraction efforts 11,12 .”
A Review of Biomedical Named Entity Recognition: Methods, Challenges, and Applications
Gannoune, N., Madani, A., & Kissi, M. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-10895-1_6
Bomgni, A. B., Donald, F. N., Aryal, S., Gurung, B. D. S., Gadhamshetty, V., & Gnimpiéba, E. Z. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356949
MetaKnogic-Alpha: A Hyper-Relational Knowledge Base for Grounded Metabolic ReasoningPreprint
Dang, P., Swaminathan, P., Guo, T., Wan, C., Cao, S., & Zhang, C. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.05.704050
“Starting from an initial pool of over 7 million PMC full-text articles, we observed that while the volume of literature is vast, the core biochemical logic is often recapitulated across numerous redundant reports[15, 37, 38].”
Varekar, G. N., Chavan, N. V., & Bharti, M. (2025) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon67554.2025.11378624
“[1] [2] [10] [8] II.”
Naqash, M. A., Amin, M., Uddin, J., Hussein, H. S., Raza, A., Alghamdi, W., Abdelhameed, H., & Alkahtani, H. K. (2026) · Scientific Reports · doi:10.1038/s41598-026-42584-y
Gonc¸alves, A., Cardoso, H. L., & Reis, L. P. (2026) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2026.3676374
“…Interactions (PPIs), Drug–Drug Interactions (DDIs), Chemical–Protein Interactions (CPIs) and genotype– phenotype relations, all of which are typically binary relations that simplify the downstream task of schematically mapping these relations in the form of knowledge graphs, for instance [70].”
Pranav, V., Karthika, S. K., & Mubeen, N. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.110149 · Cited by 1
Business relation extraction from texts
Khaldi, H. (2022) · theses.fr (ABES) · doi:10.70675/ce231ce4z5d07z4ab7z9758za927ea7b5302
Biomedical Event Extraction Based on Transformers and Knowledge Graphs
Zanella-Calzada, L. A. (2023) · theses.fr (ABES) · doi:10.70675/982498bdz45f3z4b19z9493zcce91684c91d
Romero-Vilchis, J., Barajas-Sánchez, M., Azpeitia-García, K.-I., Posada-Reyes, A.-B., Collado‐Vides, J., & Méndez-Cruz, C.-F. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1788196
Automated biomedical hypothesis generation with time-aware hypergraph contrastive learning
Shariatmadari, A. H., Guo, S., Sheffield, N. C., Zhang, A., & Jha, K. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02785-3
“Thus, the generation of biomedical hypothesis (HG) has emerged as a central task in the extraction of biomedical text [2–4], with the objective of discovering novel connections between biomedical concepts scattered between disciplines.”
Yang, L., Shi, Y., Han, F., & Cai, Y. (2026) · Biomedicines · doi:10.3390/biomedicines14061231
“With the rapid growth of the biomedical literature, traditional manual annotation and database maintenance approaches can no longer meet the requirements for effective DDI mining from massive textual data [7].”
Moore, B. M., Freeman, J., Millikin, R. J., Mohanty, C., George, K. W., Bal, A., Lock, C., Sauer, J., Spurgeon, M. E., Moore, D. L., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.05.730173
“Hypothesis generation algorithms present an additional challenge by producing more hypotheses (including many false positives) than can reasonably be evaluated 3–15 .”
Dual channel drug-drug interactions extraction based on cross attention
Jia, Y., Yuan, Z., Gong, Y., Yang, H., & Xiang, Z. (2026) · BMC Bioinformatics · doi:10.1186/s12859-026-06531-y
“6, 7) confirm the model’s robustness across different DDI types, with strong AUC and AUPR values.”
Data Augmentation for Clinical Multilingual Information ExtractionPreprint
Goncalves, R., & Lamúrias, A. (2026) · Research Square · doi:10.21203/rs.3.rs-8722369/v1
SigMine and OPathDb: a literature-mining pipeline and database of potential opportunistic pathogens
Rani, U., Nair, A., & Bhatnagar, S. (2026) · Archives of Microbiology · doi:10.1007/s00203-026-05045-8
“Therefore, advanced computational techniques using AI and natural language processing (NLP) have crucial applications in literature mining (Zhao et al. 2020).”
A Survey of Knowledge Graph–Based Semantic Representations for Medical Text Analysis
Amrani, M. C., Mataoui, M., & Bey, K. B. (2026) · International Conference on Speech, Multimodal and Advanced Communication Systems (ICSMACS) · doi:10.1109/icsmacs68968.2026.11628567
“Recent work spans ontology-driven modeling, data-driven extraction, and hybrid symbolic–neural paradigms tailored to domain constraints and application requirements [16].”
Artificial Intelligence in Tumor Microenvironment Research: Hype, Hope, or Both?
Yousuf, A., & Ali, F. (2025) · Journal of Biomolecules Pathogenesis and Therapeutics · doi:10.68041/jbpt.v1i1/01
“A set of these methods help to reconstruct the TME landscape on a high-resolution level that overcomes the drawbacks of the traditional histopathological analysis 6 .”
Kann, M. G., O’Connor, K., Tembei, P., Rosner, S., & Hernandez, G. G. (2026) · Bioinformatics Advances · doi:10.1093/bioadv/vbag225
“2020, Su et al. 2021)—aided by the advent of large language models (Chen et al. 2025) and generative AI-now enable precise identification of complex concepts such as gene-variant-disease relationships (Li et al. 2025), cohort attributes (Franklin et al. 2020), and outcomes, even from unstructured…”
Scaling Biomedical Text-Mining: Transformers, GenAI, and Drug Discovery
Agostinho, S. P., Santos, C., Ramalhão, D., Moreira, I. S., & Rosário‐Ferreira, N. (2026) · Methods in molecular biology · doi:10.1007/978-1-0716-5408-8_4
Torres, C., & González, C. I. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-37441-7_30
Natural language processing for drug discovery
Tyagi, P., Arya, A., Tripathi, P., Dubey, N., Tiwary, U. S., & Varadwaj, P. K. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-40338-5.00003-2
Metadata
- Authors
- Zhao, S., Su, C., Lu, Z., & Wang, F.
- Affiliations
- Cornell University (US)
- National Institutes of Health (US)
- Corresponding author
- Wang, Fei
- Venue
- Briefings in Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-05-18
- Volume
- 22
- Issue
- 3
- ISSN
- 1467-5463 (ISSN-L)
- 1477-4054
- PMC
- PMC8138828
- OpenAlex
- W3028004046
- Semantic Scholar
- d1e9e2355a5ae34aedb40c64db5f00ab06989eee
- Cited by
- 134
- References
- 192
- Citations by year
- 2026: 23 · 2025: 24 · 2024: 28 · 2023: 25 · 2022: 17 · 2021: 14 · 2020: 3
- FWCI
- 1.41
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- Briefings in Bioinformatics (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Science Foundation (IIS-1750326)
- National Institutes of Health
- Topics
- Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Text Analysis Techniques
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- biomedical text mining, biomedical informatics, scientific literature mining, domain knowledge extraction, research trends
- MeSH terms
- Algorithms, Medical Informatics, Publishing, Biomedical Research, Data Mining
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.