EUVIMEDEUVIMED entdecken
StudienprotokollOpen Access · CC BY 4.0

ProtocolNerd: An Interactive AI Research Assistant for Scientific Protocol Discovery

Ayush Iyer, Dennis Shasha

Information · 22.10.2026 · 17 (11) · 1057

DOI: 10.3390/info17111057 ↗

Kurz gefasst

Studienprotokoll in der Zeitschrift Information, online erschienen am 22.10.2026. Verfasst von Ayush Iyer und 1 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: United States Department of Energy, NYU Wireless.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A search for a suitable experimental protocol using keywords may not lead to the most appropriate protocol, because the keywords may not include exactly the right terms. ProtocolNerd is a web-based interactive assistant that helps biologists and chemists (so far) find relevant protocols by describing their experiment in plain English and then answering a few follow-up questions. Through these domain-specific questions, users optionally provide additional details about the experiment, such as the organism, sample type, technique, and experimental readout. The system uses these answers to build a profile describing the experiment. For biologists, the system then (i) searches Protocols.io for relevant protocols using TF-IDF (term frequency–inverse document frequency) keyword matching and embedding-based semantic search, and (ii) queries PubMed with a reformulated version of the request to retrieve related research papers. For chemists, the system searches Europe PMC and PubMed. ProtocolNerd ranks the retrieved protocols and papers based on how well they match the researcher’s intent and explains why each result may be relevant. We have evaluated ProtocolNerd on molecular biology queries with a citation-grounded benchmark of 100 papers, each of which cites a particular protocol in its Methods section. Using a short automatically (large language model)-generated query on each such paper’s abstract, ProtocolNerd placed the confirmed protocol within its top 10 results 46% of the time. A non-parametric paired test shows that this was significantly better than two strong baselines. On the same benchmark it also found the protocol significantly more often than three general AI research assistants, Elicit (20%), Consensus (8%), and Perplexity (5%). These results suggest that combining interactive profiling, multiple retrieval methods, re-ranking, and explainability can significantly improve protocol discovery for scientific research. When applied to chemistry, ProtocolNerd found 31% of the protocols (or their equivalents) using Europe PMC alone and 45% when including PubMed.

Förderung

  • United States Department of Energy
  • NYU Wireless

Zitieren

APA

Iyer, A., & Shasha, D. (2026). ProtocolNerd: An Interactive AI Research Assistant for Scientific Protocol Discovery. Information, 17(11), 1057. https://doi.org/10.3390/info17111057

Vancouver

Iyer A, Shasha D. ProtocolNerd: An Interactive AI Research Assistant for Scientific Protocol Discovery. Information. 2026;17(11):1057. doi:10.3390/info17111057

BibTeX
@article{Iyer2026,
  author = {Iyer, Ayush and Shasha, Dennis},
  title = {ProtocolNerd: An Interactive AI Research Assistant for Scientific Protocol Discovery},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {11},
  pages = {1057},
  doi = {10.3390/info17111057}
}
Kostenlos starten →