MétaCan
Menu
Back to cohort
Record W4388509054 · doi:10.1101/2023.11.08.566195

ChatGPT usage in the Reactome curation process

2023· preprint· en· W4388509054 on OpenAlexafffund
Krishna Kumar Tiwari, Lisa Matthews, Bruce May, Veronica Shamovsky, M Orlic-Milacic, Karen Rothfels, Eliot Ragueneau, Chuqiao Gong, Ralf Stephan, Nancy T. Li, Guanming Wu, Lincoln Stein, Peter D’Eustachio, Henning Hermjakob

Bibliographic record

VenuebioRxiv (Cold Spring Harbor Laboratory) · 2023
Typepreprint
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsOntario Institute for Cancer Research
FundersNational Institutes of HealthUniversity of TorontoEuropean Bioinformatics Institute
KeywordsComputer scienceData curationAnnotationWorkflowProcess (computing)Context (archaeology)Pipeline (software)AutomationData scienceInformation retrievalSoftware engineeringArtificial intelligenceDatabaseProgramming languageEngineering

Abstract

fetched live from OpenAlex

Appreciating the rapid advancement and ubiquity of generative AI, particularly ChatGPT, a chatbot using large language models like GPT, we endeavour to explore the potential application of ChatGPT in the data collection and annotation stages within the Reactome curation process. This exploration aimed to create an automated or semi-automated framework to mitigate the extensive manual effort traditionally required for gathering and annotating information pertaining to biological pathways, adopting a Reactome "reaction-centric" approach. In this pilot study, we used ChatGPT/GPT4 to address gaps in the pathway annotation and enrichment in parallel with the conventional manual curation process. This approach facilitated a comparative analysis, where we assessed the outputs generated by ChatGPT against manually extracted information. The primary objective of this comparison was to ascertain the efficiency of integrating ChatGPT or other large language models into the Reactome curation workflow and helping plan our annotation pipeline, ultimately improving our protein-to-pathway association in a reliable and automated or semi-automated way. In the process, we identified some promising capabilities and inherent challenges associated with the utilisation of ChatGPT/GPT4 in general and also specifically in the context of Reactome curation processes. We describe approaches and tools for refining the output given by ChatGPT/GPT4 that aid in generating more accurate and detailed output.

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)0.033
metaresearch head score (Gemma)0.081
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.967
Threshold uncertainty score0.174

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0330.081
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0020.004
Bibliometrics0.0040.003
Science and technology studies0.0020.002
Scholarly communication0.0050.005
Open science0.0040.008
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0140.012

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 head0.120
GPT teacher head0.372
Teacher spread0.252 · 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 designBench or experimental
DomainMethods
GenreEmpirical

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

Citations13
Published2023
Admission routes2
Has abstractyes

Explore more

Same venuebioRxiv (Cold Spring Harbor Laboratory)Same topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207