Dataset Information

GO2Sum: Generating Human Readable Functional Summary of Proteins from GO Terms.

ABSTRACT: Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it comes to interpretation. In response to this issue, we developed GO2Sum (Gene Ontology terms Summarizer), a model that takes a set of GO terms as input and generates a human-readable summary using the T5 large language model. GO2Sum was developed by fine-tuning T5 on GO term assignments and free-text function descriptions for UniProt entries, enabling it to recreate function descriptions by concatenating GO term descriptions. Our results demonstrated that GO2Sum significantly outperforms the original T5 model that was trained on the entire web corpus in generating Function, Subunit Structure, and Pathway paragraphs for UniProt entries.

SUBMITTER: Giri SJ

PROVIDER: S-EPMC10680659 | biostudies-literature | 2023 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

GO2Sum: Generating Human Readable Functional Summary of Proteins from GO Terms.

Giri Swagarika Jaharlal SJ Ibtehaz Nabil N Kihara Daisuke D

bioRxiv : the preprint server for biology 20231115

Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it co ...[more]

PMID: 38014080

Similar Datasets

Project description:BackgroundTuberculosis (TB) is an old infectious disease caused by Mycobacterium tuberculosis infection. Vaccination is the most effective way to prevent and control TB. However, there is relatively little literature that systematically analyzes the progress of new TB vaccine research from a bibliometric perspective. This study was conducted to examine the development of TB vaccines over the past 20 years and to identify research priorities and directions for the future.MethodsThe Science Citation Index Expanded (SCI-E) of the Web of Science Core Collection (WOSCC) database was selected to search the literature related to TB vaccines. The countries, institutions, authors, journals, references, and keywords of each publication were analyzed and visualized using the VOSviewer, CiteSpace, and Bibliometrix software. Furthermore, GraphPad Prism and Microsoft Excel 365 were also used for statistical analysis.ResultsAs of 20 October 2022, 7960 publications related to TB vaccines were identified with 288,478 citations. The United States of America (USA) accounted for the largest share (2658, 33.40%), followed by the United Kingdom (UK, 1301, 16.34%), and China (685, 8.6%). Regarding affiliations, the University of London had the most publications (427) and shared the highest H-index (76) with the Statens Serum Institut of Denmark. In terms of the number of articles for the journals and authors, the journal Vaccine ranked first with 629 articles. Professor Peter Anderssen has published the highest number of papers (160). The burst keywords and thematic maps analysis showed that future trends in TB vaccine development would focus on exploring the interaction mechanisms between M. tuberculosis and the host.ConclusionThe number of publications on TB vaccines has grown over the past two decades. Developed countries play a significant role in TB vaccine research, and developing countries are fast catching up. We believe that future research will be aimed at understanding the fine molecular mechanisms of host-pathogen interaction, leading to the development of better TB vaccines.

Dataset Information

GO2Sum: Generating Human Readable Functional Summary of Proteins from GO Terms.

Publications

GO2Sum: Generating Human Readable Functional Summary of Proteins from GO Terms.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets