Work

Biochat: a database for natural language processing of Gene Expression Omnibus data

Year: 2018

Type: preprint

Abstract: A biological dataset’s metadata profile (e.g., study description, organism name, sequencing type, etc.) typically contains terse but descriptive textual information that can be used to link it with other similar biological datasets for the purpose of integrating omics data of different types to inform hypotheses and biological questions. Here we present Biochat, a database containing a multi-omics data integration support system to aid in cross-linking Gene Expression Omnibus (GEO) records to each other by metadata similarity through a user-friendly web application. Biochat is publicly available at: http://www.biochat.ai . Biochat source code is hosted at: https://github.com/Bohdan-Khomtchouk/Bio-chat . Database URL https://github.com/Bohdan-Khomtchouk/Bio-chat

Source: bioRxiv (Cold Spring Harbor Laboratory)

DOI: 10.1101/480020

Authors: Bohdan B. Khomtchouk, Vsevolod Dyomkin, Kasra A. Vand, Themistocles Assimes, Or Gozani

Institutions: VA Palo Alto Health Care System, Stanford Medicine, Stanford University

Language: English

Topic: Biomedical Text Mining and Ontologies

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: green

Funder: Stanford Research Computing Center, Stanford University

OpenAlex ID: W2900891718

Cites: 17

Cited by: 2

Related to: 10