Large Language Models for Computational Biology - A Primer

Overview

Explore the intersection of large language models and computational biology in this 49-minute lecture by Jian Ma at the Computational Genomics Summer Institute (CGSI). Delve into the recent history of large language models and foundation models, understanding their architecture and applications in genomics. Learn about the Transformer model, self-attention mechanisms, and various tokenization techniques specific to biological sequences. Discover specialized models like DNA Bird 2, nucleotide Transformer, SD Bert Model, and SCGPT, designed for genomic data analysis. Examine the concept of generative pretraining and its relevance to computational biology. Conclude with a discussion on open questions and a summary of the potential impact of these technologies on genomic research.

Syllabus

Introduction
Antonio Van Lovin Hook
CGSI YouTube
Presentation Preparation
Recent History
Large Language Models
Foundation Models
Transformer
Selfattention
Attention
Transformer Architecture
Pretraining
Applications
Models
Tokenization
Masking
DNA Bird 2
nucleotide Transformer
SD Bert Model
SCGPT
generative pretraining
SC Foundation model
Open question
Summary

Taught by

Computational Genomics Summer Institute CGSI

Reviews

Start your review of Large Language Models for Computational Biology - A Primer

Taught by

Create a Large Language Model from Scratch with Python – Tutorial

The Flaws of Others: Large Language Models in Biomedical Research

Leveraging Large Datasets and Large Language Models for Healthcare

Information Retrieval in the Era of Large Language Models

Never Stop Learning.