Chilibot: Powerful Text Mining for Biology, on the web

Author(s): LucianoSphere (Luciano Abriata, PhD)

Originally published on Towards AI.

Predating the Large Language Model Era Yet Widely Used and Acclaimed

Chilibot, a free web-based application for mining PubMed literature and developed well before the advent of large language models (LLMs), stands out as a remarkably powerful tool for bioinformaticians. Despite its pre-LLM origins (it dates from 2004), Chilibot enjoys widespread use within the bioinformatics community, boasting over 400 citations as of 2024. It is so much acclaimed, that a few times the website was down, researchers plead to have it back!

Let’s see what makes Chilibot so valuable, even today, as it competes with LLMs and LLM-based tools tuned for scientific text mining.

Chilibot excels at mining the rich repository of information within the PubMed database of biomedical abstracts. It allows you to query for specific relationships between genes, proteins, or even keywords. The results are presented visually as a graph, making it easier to grasp the intricate connections within your area of interest.

Chilibot goes beyond basic keyword searches. It offers a variety of search methods to tailor your exploration:

Search for relationships between two or more entitiesExplore relationships between predefined lists of entitiesGenerate automated hypothesis suggestions based on the identified networks of informationRefine searches by incorporating context through keywordsProvide your own synonyms or leverage Chilibot’s synonym suggestionsColor-code nodes based on gene expression… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI