Javascript must be enabled to continue!
GEO-BERT: A Retrieval augmented LLM Framework for Intelligent Dataset Retrieval from the Gene Expression Omnibus
View through CrossRef
Abstract
The Gene Expression Omnibus (GEO) is a commonly used data repository of high throughput gene expression and other functional genomics data. This platform is globally used by researchers for submitting experimental datasets, accessing these datasets for hypothesis validation, reusing them in data-driven research, generating ideas for new research directions. Despite global usage, searching and identifying relevant and usable datasets in GEO remains challenging with an underlying keyword based search system needing manual intervention for the retrieval of desired datasets. GEO’s inconsistent metadata and varying data annotation practices across submissions, variable data quality are contributing to its challenge for building structured query tools. With the recent advancement of Large Language Models (LLMs), it is timely to revisit the GEO datasets and its query system. Here, we present an AI chat-bot, GEO-BERT, leveraging an underlying retrieval augmented generator framework on the GEO metadata with a novel hierarchical hybrid field aware retrieval system to mine the datasets. GEO-BERT is locally installable, available for programmers and project developers (
https://github.com/mrumi/GEOBERTtest
) and readily usable by regular users on subset of test data. We demonstrated that GEO-BERT enhances the semantic search performance not currently available by any of the leading existing AI-powered chatbots, while improving the performance of GEO’s traditional search performance for project development. Given the global usage of GEO and the latest advancement of the large language models, GEO-BERT fills the gap for context-aware extraction of GEO datasets.
Title: GEO-BERT: A Retrieval augmented LLM Framework for Intelligent Dataset Retrieval from the Gene Expression Omnibus
Description:
Abstract
The Gene Expression Omnibus (GEO) is a commonly used data repository of high throughput gene expression and other functional genomics data.
This platform is globally used by researchers for submitting experimental datasets, accessing these datasets for hypothesis validation, reusing them in data-driven research, generating ideas for new research directions.
Despite global usage, searching and identifying relevant and usable datasets in GEO remains challenging with an underlying keyword based search system needing manual intervention for the retrieval of desired datasets.
GEO’s inconsistent metadata and varying data annotation practices across submissions, variable data quality are contributing to its challenge for building structured query tools.
With the recent advancement of Large Language Models (LLMs), it is timely to revisit the GEO datasets and its query system.
Here, we present an AI chat-bot, GEO-BERT, leveraging an underlying retrieval augmented generator framework on the GEO metadata with a novel hierarchical hybrid field aware retrieval system to mine the datasets.
GEO-BERT is locally installable, available for programmers and project developers (
https://github.
com/mrumi/GEOBERTtest
) and readily usable by regular users on subset of test data.
We demonstrated that GEO-BERT enhances the semantic search performance not currently available by any of the leading existing AI-powered chatbots, while improving the performance of GEO’s traditional search performance for project development.
Given the global usage of GEO and the latest advancement of the large language models, GEO-BERT fills the gap for context-aware extraction of GEO datasets.
Related Results
Automating Information Retrieval from Biodiversity Literature Using Large Language Models: A Case Study
Automating Information Retrieval from Biodiversity Literature Using Large Language Models: A Case Study
Recently, Large Language Models (LLMs) have transformed information retrieval, becoming widely adopted across various domains due to their ability to process extensive textual data...
Exploring Large Language Models Integration in the Histopathologic Diagnosis of Skin Diseases: A Comparative Study
Exploring Large Language Models Integration in the Histopathologic Diagnosis of Skin Diseases: A Comparative Study
Abstract
Introduction
The exact manner in which large language models (LLMs) will be integrated into pathology is not yet fully comprehended. This study examines the accuracy, bene...
Large Language Model Empowered Automated Reservoir Agent: A Win-Win Strategy for Reservoir Intelligent Management and Transformation
Large Language Model Empowered Automated Reservoir Agent: A Win-Win Strategy for Reservoir Intelligent Management and Transformation
Abstract
The upstream oil and gas industry is currently undergoing digital transformation, presenting numerous opportunities as well as significant challenges, pa...
KEBIJAKAN OMNIBUS LAW DALAM MENATA GOOD GOVERNANCE DI INDONESIA
KEBIJAKAN OMNIBUS LAW DALAM MENATA GOOD GOVERNANCE DI INDONESIA
ABSTRAK Adanya keinginan untuk meningkatkan investasi di Indonesia, pemerintah menerapkan kebijakan Omnibus Law dalam sistem hukum di bidang bisnis, yang diduga selama ini produk h...
Omnibus Law Study on Law Changes in Indonesia in the Perspective of Legal Transplant
Omnibus Law Study on Law Changes in Indonesia in the Perspective of Legal Transplant
The idea of Omnibus Law which was initiated by President Joko Widodo was found to be pros and cons from various experts. The model for the formation of laws using the Omnibus Law t...
Maximum Entropy Source-Anchored Sparse Retrieval with LLM-Free Indexing for Graph-Augmented RAG
Maximum Entropy Source-Anchored Sparse Retrieval with LLM-Free Indexing for Graph-Augmented RAG
Graph-augmented Retrieval-Augmented Generation (RAG) commonly relies on dense knowledge-graph construction, where entities and relations are extracted from source documents and mat...
Microrna Regulation of Nodule Zone-Specific Gene Expression In Soybean
Microrna Regulation of Nodule Zone-Specific Gene Expression In Soybean
Nitrogen is a paramount important essential element for all living organisms. It has been found to bea crucial structural component of proteins, nucleic acids, enzymes and other ce...
Over-Sampling Effect in Pre-Training for Bidirectional Encoder Representations from Transformers (BERT) to Localize Medical BERT and Enhance Biomedical BERT (Preprint)
Over-Sampling Effect in Pre-Training for Bidirectional Encoder Representations from Transformers (BERT) to Localize Medical BERT and Enhance Biomedical BERT (Preprint)
BACKGROUND
Pre-training large-scale neural language models on raw texts has made a significant contribution to improving transfer learning in natural langua...

