The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Automatic biomarker discovery and enrichment with BRAD
Open accessAbstract
Motivation: Integrating Large Language Models (LLMs) with research tools presents technical and reproducibility challenges for biomedical research. While commercial artificial intelligence (AI) systems are easy to adopt, they obscure data provenance, lack transparency, and can generates false information, making them unfit for many research problems. To address these challenges, we developed the Bioinformatics Retrieval Augmented Digital (BRAD) agent software system. Results: Here, we introduce BRAD, an agentic system that integrates LLMs with external tools and data to streamline research workflows. BRAD’s modular agents retrieve information from literature, custom software, and online databases while maintaining transparent protocols to increase the reliability of AI generated results. We apply BRAD to a biomarker discovery pipeline, automating both execution and the generation of enrichment reports. This workflow contextualizes user data within the literature, enabling a level of interpretation and automation that surpasses conventional research tools. Beyond the workflow we highlight here, BRAD is a flexible system that has been deployed in other applications including a chatbot, video RAG, and analysis of single cell data. Availability and implementation: The source code for BRAD is available at https://github.com/Jpickard1/BRAD; Information for pip installation, tutorials, documentation, and further information can be found at: ReadTheDocs.
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
Figures

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 cited source says what the claim attributes to it.
In the citing paper
“Nine studies met the inclusion criteria.”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [25]
The cited source says what the claim attributes to it.
In the citing paper
“Study designs varied, with several studies representing proof-of-concept implementations (e.g., CBM-RAG, ENTAgents, ArgMed-AgentN, DSM5AgentFlow, and BRAD) [20,21,24,25,27].”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [25]
The cited source says what the claim attributes to it.
In the citing paper
“In addition, most systems incorporated example-based grounding, operationalized as explicit links to retrieved clinical guidelines, biomedical literature, databases, ontologies, or knowledge graph path [19,25,26].”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [25]
The cited source says what the claim attributes to it.
In the citing paper
“Retrieval-augmented generation (RAG) was frequently incorporated to ground reasoning in external evidence, particularly in systems aiming to mitigate hallucinations or enhance reliability, such as CBM-RAG, DrugAgent, DSM5AgentFlow, CASSIA, and BRAD [19,20,24,25,26].”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [25]
The cited source says what the claim attributes to it.
In the citing paper
“Systems focused on CDSSs, screening, and biomedical reasoning (e.g., ENTAgents, DrugAgent, DSM5AgentFlow, BRAD, and CASSIA) primarily relied on a “reasoning + evidence” paradigm, combining textual rationales with explicit grounding in retrieved sources [19,24,25,26,27].”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [25]
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Enrichr: a comprehensive gene set enrichment analysis web server 2016 update
Kuleshov, M. V., Jones, M. R., Rouillard, A. D., Fernandez, N. F., Duan, Q., Wang, Z., Koplev, S., Jenkins, S. L., Jagodnik, K. M., Lachmann, A., et al. (2016) · Nucleic Acids Research · doi:10.1093/nar/gkw377 · Cited by 10,799 · cited 1×
“The repetitive nature of this task and the extensive tools already developed for this purpose make it an ideal candidate for agentic automation (Kuleshov et al. 2016, Luebbert and Pachter 2023).”
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263 · cited 1×
“Then, multiple layers of Chain of Thought (CoT) reasoning, combined with the Document Chat, refine these results by providing verifiable references for the Agent’ s interpretation of the data (Wei et al. 2022) (Fig.”
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101 · cited 2×
“These chat-bots use Retrieval Augmented Generation (RAG) and agentic architectures, enabling AI models to interact with tools and access external information (Lewis et al. 2020).”
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · UCL Discovery (University College London) · Cited by 1,187
Autonomous chemical research with large language models
Boiko, D. A., MacKnight, R., Kline, B., & Gomes, G. (2023) · Nature · doi:10.1038/s41586-023-06792-0 · Cited by 1,050 · cited 1×
“From automating experiments (Boiko et al. 2023) to enabling virtual laboratories (Swanson et al. 2024), artificial intelligence (AI) and large language models (LLMs) are transforming biomedical research workflows.”
Retrieval-Augmented Generation for Large Language Models: A Survey
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876 · cited 1×
“Here we focuses on implementation rather than methodological advancements, so we refer readers to Gao et al. (2023) for a survey on RAG systems.”
Cold Spring Harbor Symposia on Quantitative Biology
H., R. G. (1935) · Science · doi:10.1126/science.81.2100.311 · Cited by 412
A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
Sahoo, P., Singh, A. K., Saha, S., Jain, V., Mondal, S., & Chadha, A. (2024) · arXiv · doi:10.48550/arxiv.2402.07927 · Cited by 288 · cited 1×
“The retrieved information is incorporated into a prompt template, such as the following, which is then passed to the LLM (Sahoo et al. 2024): System: Respond to the human based on the provided sources.”
Matsumoto, N., Moran, J., Choi, H., Hernandez, M. E., Venkatesan, M., Wang, Z. P., & Moore, J. H. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae353 · Cited by 177 · cited 1×
“Open-source implementations improve data provenance and reproducibility over commercial tools, and agentic and RAG systems reduce hallucinations (Craig and Dr � aghici 2024, Matsumoto et al. 2024, 2025).”
Functional organization of the human 4D Nucleome
Chen, H., Chen, J., Muir, L. A., Ronquist, S., Meixner, W., Ljungman, M. E., Ried, T., Smale, S. T., & Rajapakse, I. (2015) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1505822112 · Cited by 119 · cited 1×
“Biomarker genes were identified from bulk RNA-seq data collected from eight populations of synchronized human fibroblasts (Chen et al. 2015).”
Self-citationEmergent autonomous scientific research capabilities of large language models
Boiko, D. A., MacKnight, R., & Gomes, G. (2023) · arXiv · doi:10.48550/arxiv.2304.05332 · Cited by 72
Matsumoto, N., Choi, H., Moran, J., Hernandez, M. E., Venkatesan, M., Li, X., Chang, J.-H., Wang, Z. P., & Moore, J. H. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf031 · Cited by 43 · cited 1×
“Open-source implementations improve data provenance and reproducibility over commercial tools, and agentic and RAG systems reduce hallucinations (Craig and Dr � aghici 2024, Matsumoto et al. 2024, 2025).”
Efficient querying of genomic reference databases with gget
Luebbert, L., & Pachter, L. S. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btac836 · Cited by 42 · cited 1×
“The repetitive nature of this task and the extensive tools already developed for this purpose make it an ideal candidate for agentic automation (Kuleshov et al. 2016, Luebbert and Pachter 2023).”
Summary: Genetic Tinkering--Local Problems, Local SolutionsPreprint
Weintraub, H. (1993) · Cold Spring Harbor Symposia on Quantitative Biology · doi:10.1101/sqb.1993.058.01.089 · Cited by 8 · cited 1×
“While several answers are scientifically valid, the BRAD’s answer has the advantage of providing a verifiable reference for its source (Weintraub 1993).”
LmRaC: a functionally extensible tool for LLM interrogation of user experimental results
Craig, D. B., & Drăghici, S. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae679 · Cited by 8 · cited 1×
“Open-source implementations improve data provenance and reproducibility over commercial tools, and agentic and RAG systems reduce hallucinations (Craig and Dr � aghici 2024, Matsumoto et al. 2024, 2025).”
Dynamic sensor selection for biomarker discovery
Pickard, J., Stansbury, C. M., Surana, A., Muir, L. A., Bloch, A. M., & Rajapakse, I. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2501324122 · Cited by 1
Self-citation
Research works printed but not linked: 1
- Affarth, 2023, Generative AI with LangChain: Build Large Language Model (LLM) Apps with Python, ChatGPT, and Other LLMs
Cited by
AI Agents in Clinical Medicine: A Systematic ReviewPreprint
Gorenshtein, A., Omar, M., Glicksberg, B. S., Nadkarni, G. N., & Klang, E. (2025) · medRxiv · doi:10.1101/2025.08.22.25334232 · Cited by 94
Streamline automated biomedical discoveries with agentic bioinformatics
Zhou, J., Jiang, J., Han, Z., Wang, Z., & Gao, X. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf505 · Cited by 36
“BRAD [33] is used for automation, performing tasks ranging from gene enrichment and archival searches to automatically generating code for biomarker identification pipelines.”
Artificial Intelligence agents for biological research: a survey
Qi, C., Wang, W., Jiang, S., Liu, Q., Song, X., Fang, H., & Wei, Z. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag075 · Cited by 23
“Knowledge and tool integration remain central: systems such as BRAD [121] and AutoB A [76] link language models with curated biomedical ontologies and workflow tools to ensure traceability and reproducibility.”
A conceptual framework for human–AI collaborative genome annotation
Li, X., Whan, A., McNeil, M., Starns, D., Irons, J. L., Andrew, S. C., & Suchecki, R. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf377 · Cited by 8
Bridging diagnosis and therapeutics: The role of AI in cancer detection and drug development
Barua, S., Balaji, B., & Balaji, S. (2026) · Health Sciences Review · doi:10.1016/j.hsr.2026.100270 · Cited by 3
Metadata
- Authors
- Pickard, J., Prakash, R., Choi, M. A., Oliven, N., Stansbury, C., Cwycyshyn, J., Galioto, N., Gorodetsky, A., Velasquez, A., & Rajapakse, I.
- Affiliations
- University of Michigan (US)
- University of Colorado Boulder (US)
- Corresponding author
- Rajapakse, Indika
- ORCID
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2025-05
- Volume
- 41
- Issue
- 5
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- PMC
- PMC12064167
- OpenAlex
- W4410092171
- Cited by
- 14
- References
- 13
- Citations by year
- 2026: 9 · 2025: 5
- FWCI
- 13.94
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Bioinformatics (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Defense Advanced Research Projects Agency (HR00112490472)
- Air Force Office of Scientific Research (FA9550-22-1-0215)
- Topics
- Social Sciences › Decision Sciences › Information Systems and Management › Scientific Computing and Data Management
- Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- retrieval-augmented generation, large language models, agentic systems, biomarker discovery, literature searching, research workflow automation, reproducibility, data provenance, AI chatbots, single-cell data analysis
- MeSH terms
- Artificial Intelligence, Humans, Software, Biomarkers, Computational Biology, Workflow
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.