Related Experiment Video
Updated: Jul 15, 2025
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
610
Biomedical generative pre-trained based transformer language model for age-related disease target discovery
Diana Zagirova1, Stefan Pushkov1, Geoffrey Ho Duen Leung1
1Insilico Medicine Hong Kong Ltd., Hong Kong Science and Technology Park, New Territories, Hong Kong, China.
Aging
|September 24, 2023
Summary
This study introduces a novel AI approach using a large language model (LLM) for predicting therapeutic targets. The method successfully identified potential aging and disease targets, including novel candidates like CCR5 and PTH.
Area of Science:
- Biomedical research
- Artificial intelligence in drug discovery
Background:
- Target discovery is vital for new therapeutics but current methods have limitations.
- Natural language processing (NLP) offers new ways to predict therapeutic targets.
Purpose of the Study:
- To develop and evaluate a novel approach for predicting therapeutic targets using a large language model (LLM).
- To identify potential targets for aging and age-related diseases.
Main Methods:
- Trained a domain-specific BioGPT model on biomedical literature (grant text).
- Developed a pipeline for generating therapeutic target predictions.
- Validated predictions against existing database data.
Main Results:
- Pre-training LLMs with task-specific texts enhances performance.
- Identified known aging and age-related disease targets.
- Proposed CCR5 and PTH as novel dual-purpose anti-aging and disease targets.
Conclusions:
- Transformer models show significant potential for novel target prediction.
- AI integration offers a roadmap for addressing complex biomedical challenges.
