AI Meets Biotechnology: Exploring LLM Applications
The integration of artificial intelligence (AI) and biotechnology has created unprecedented opportunities for innovation, making the adoption of AI tools essential to automate and refine complex workflows. This research stay investigates the potential applications of large language models (LLMs) in biotechnology, with a focus on their role in data analysis, knowledge extraction, and decision support. By leveraging the advanced language processing capabilities of LLMs, this research stay aims to address critical challenges in the field, including (but not limited) text summarization, scientific literature comprehension, protein design, soft sensor analysis, and bacterial production, among others. This research stay underscore the transformative potential of LLMs in advancing biotechnological processes and fostering interdisciplinary collaboration across AI and life sciences.
Objectives:
1. Explore the role of large language models (LLMs) in automating data analysis workflows in biotechnology.
2. Assess the potential of LLMs in supporting decision-making processes in biotechnological research.
3. Establish interdisciplinary frameworks that integrate LLMs into life sciences research.
4. Identify and address limitations in the current applications of LLMs in biotechnological contexts.
Approach:
This research follows a CRISP-inspired methodology, beginning with Business Understanding to identify key biotechnological challenges such as protein design and scientific text summarization. In Data Understanding and Preparation, relevant datasets are collected, cleaned, and structured for LLM processing. During Modeling, pre-trained LLMs are fine-tuned using domain-specific data and techniques like transfer learning. The Evaluation phase assesses performance based on metrics such as accuracy and applicability, while the Deployment phase focuses on creating user-friendly tools to integrate LLM-driven insights into biotechnology workflows. This iterative approach ensures practical and impactful outcomes.
6
esteban.castillojz@tec.mx
Procesamiento del Lenguaje Natural (PLN)
Aprendizaje de Máquina (Machine Learning
ML)
Biotecnología
Curación automática de datos
