MétaCan
Menu
Back to cohort
Record W4410196872 · doi:10.1101/2025.05.02.651919

BioMedTools: a language model-powered community for biomedical computational tools

2025· preprint· en· W4410196872 on OpenAlexaff
Sheng Liu, Huadong Xing, Mengying Han, Linlin Gong, Dongliang Liu, Junni Chen, Pengli Cai, Qian‐Nan Hu

Bibliographic record

VenuebioRxiv (Cold Spring Harbor Laboratory) · 2025
Typepreprint
Languageen
FieldDecision Sciences
TopicScientific Computing and Data Management
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersNational Key Research and Development Program of ChinaWestlake University
KeywordsComputer scienceLanguage modelNatural language processing

Abstract

fetched live from OpenAlex

Abstract A large number of biomedical computational tools have spawned several tool registries. However, in the face of the rapid growth in the number of tools, existing tool registries, which are manually curated or community-driven, are difficult to keep up to date, resulting in inadequate tool repository data. In this paper, we show that language models (LMs) can aid in building a community of tools. We introduce BioMedTools ( https://biomed.tools ), a community of biomedical computational tools that mainly implements LM-based tool identification and a chat assistant. Compared with existing tool registries, BioMedTools achieves excellence in terms of the number of tools, frequency of data updates, and functionality. Meanwhile, the Model Context Protocol (MCP) servers hub in BioMedTools may promote the building of agents in the biomedical field. BioMedTools enables the efficient collection of tools and enhances their findability and accessibility.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.028
metaresearch head score (Gemma)0.052
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesScholarly communication, Open science
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Software · Consensus signal: none
Teacher disagreement score0.994
Threshold uncertainty score0.148

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0280.052
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0090.005
Science and technology studies0.0030.002
Scholarly communication0.0070.011
Open science0.0060.020
Research integrity0.0030.006
Insufficient payload (model declined to judge)0.0130.013

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.115
GPT teacher head0.359
Teacher spread0.244 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designNot applicable
Domainnot available
GenreSoftware

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuebioRxiv (Cold Spring Harbor Laboratory)Same topicScientific Computing and Data ManagementFrench-language works237,207