Back

MADAME: a user-friendly bioinformatic tool for data and metadata retrieval in microbiome research

Fumagalli, S.; Soletta, G.; Agostinetto, G.; Striani, M.; Labra, M.; Casiraghi, M.; Bruno, A.

2023-10-17 bioinformatics
10.1101/2023.10.14.562335 bioRxiv
Show abstract

Microbiome research advancements have provided countless insights. Despite the massive amount of data currently stored in public repositories, these resources remain vastly underutilized due to the intricacy of data and metadata retrieval from these databases. However, leveraging data-driven approaches is crucial for microbiome research progress by overcoming variations between studies and identifying generalizable trends. We designed the open-access and user-friendly bioinformatic tool MADAME (MetADAta MicrobiomE) to streamline the data and metadata retrieval process. MADAME addresses the challenges posed by the public repositories current limitations, allowing users to retrieve publications associated with the accession codes of interest. Additionally, MADAME allows users to visually explore retrieved results through the generation of a comprehensive report with plots and statistics. These unique features of MADAME let users maximize their time and resources, enabling them to assess metadata suitability before pursuing data download. To showcase its diverse functionalities, we recreate several scenarios to meet the diverse requirements that researchers may have.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.