This webinar will explore how Large Language Models (LLMs) can streamline the extraction of critical information from scientific texts, focusing on patient-derived cancer models (PDCMs). PDCMs are vital tools for cancer research and preclinical studies, with a growing body of literature in this field. However, manually extracting and curating information from scientific texts is labor-intensive and prone to delays. In this session, we will introduce two innovative approaches: direct prompting and soft prompting. Direct prompting uses manually created instructions to extract PDCM-related entities, while soft prompting leverages machine learning to train continuous vector prompts. We will discuss our comparative evaluation using state-of-the-art proprietary and open-source LLMs, demonstrating how tailored prompt engineering can elevate the performance of smaller, open models to match proprietary counterparts. This session will highlight the potential of LLMs to enhance domain-specific knowledge extraction and accelerate research workflows.

Who is this course for?

This webinar is designed for bioinformaticians, computational biologists, data scientists, and researchers interested in applying AI and language models to biological problems.

This event is part of a webinar series exploring the revolutionary potential of Large Language Models (LLMs) in bioinformatics and computational biology. For details on all topics covered in this series and registration information, please visit the following link: Large Language Models and their applications in Bioinformatics

Outcomes

By the end of the webinar you will be able to:

• Identify the challenges of manual extraction of PDCM-related data and how LLMs provide scalable solutions

• Explore direct and soft prompting methods to extract entities from scientific texts

• Evaluate the performance of different LLMs in domain-specific tasks

• Recognise how tailored AI approaches can enhance text mining for biomedical research

DOI: 10.6019/TOL.Domain-specific-LLM-w.2025.00001.1

This webinar took place on 02 April 2025. Please click the 'Watch video' button to view the recording.