Automatic atlas catalogs computational tools from millions of papers
PaperAtlas: an automatically constructed atlas of computational methods and software from 6.4 million open-access articles
Digital Libraries
Summary
Scientific papers often describe computer programs and methods that are hard to find because there are so many and no single complete list. The authors created PaperAtlas, a large automatically built map of over a million papers about computational tools in biology and medicine. PaperAtlas groups similar tools and matches them to existing databases, finding many software mentions not yet recorded elsewhere. This resource is freely available online and helps users discover computational tools more easily.
What this means in practice
- •For bioinformatics tool developers: Find related papers and software clusters automatically to discover similar methods and reduce duplicate work in biomedical tool creation.
- •For biomedical software repository managers: Use the atlas to identify computational software not yet listed in registries, improving coverage and resource curation.
Authors
Neeti Shah, Anagha Vippagunta, Yash Bhargava
Abstract
Computational methods and software are dispersed across a literature that is increasingly difficult to review manually, while curated registries capture only a subset of available resources. We present PaperAtlas, an automatically constructed atlas derived from the PubMed Central open-access corpus. Of 6,446,741 abstracts screened, 1,074,191 were classified as computational, with schema-valid records extracted for 1,074,140. Among these, 267,893 papers describing an algorithm, software package or web server formed 1,438 clusters, with 1,000 retained after restriction to parent-level biomedical categories. In 296 clusters linked to at least five bio.tools entries, the mean concentration of the most frequent EDAM topic was 61.7%, compared with 26.4% under permutation. Of 31,180 distinct software and web-server names, 61.0% lacked a strict match in bio.tools, PyPI, CRAN, Bioconductor or Bioconda. Among 12,207 bio.tools entries with defining papers in the corpus, 56.6% were recovered end to end, increasing to 83.6% among the 8,265 entries whose defining publication entered the atlas. PaperAtlas is fully open source and available as a web server at bhargavaresearch.org/paperatlas.