Abstract
AbstractMotivationThousands of genomes are publicly available, however, most genes in those genomes have poorly defined functions. This is partly due to a gap between previously published, experimentally-characterized protein activities and activities deposited in databases. This activity deposition is bottlenecked by the time-consuming biocuration process. The emergence of large language models (LLMs) presents an opportunity to speed up text-mining of protein activities for biocuration.ResultsWe developed FuncFetch — a workflow that integrates NCBI E-Utilities, OpenAI’s GPT-4 and Zotero — to screen thousands of manuscripts and extract enzyme activities. Extensive validation revealed high precision and recall of GPT-4 in determining whether the abstract of a given paper indicates presence of a characterized enzyme activity in that paper. Provided the manuscript, FuncFetch extracted data such as species information, enzyme names, sequence identifiers, substrates and products, which were subjected to extensive quality analyses. Comparison of this workflow against a manually curated dataset of BAHD acyltransferase activities demonstrated a precision/recall of 0.86/0.64 in extracting substrates. We further deployed FuncFetch on nine large plant enzyme families. Screening 27,120 papers, FuncFetch retrieved 32,242 entries from 5547 selected papers. We also identified multiple extraction errors including incorrect associations, non-target enzymes, and hallucinations, which highlight the need for further manual curation. The BAHD activities were verified, resulting in a comprehensive functional fingerprint of this family. FuncFetch represents an advance in biocuration and lays the groundwork for predicting functions of uncharacterized enzymes.Availability and ImplementationAll scripts are available at:https://github.com/moghelab/funcfetch. Minimally-curated activities are also deposited on the website:https://tools.moghelab.org/funczymedb/curated
Publisher
Cold Spring Harbor Laboratory