Lecture

Biological structure and function emerge from unsupervised learning

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture explores how biological structure and function can be understood by scaling unsupervised learning to analyze protein sequences. It covers topics such as the exponential growth of sequence data, metagenomics, protein language models, self-supervision, and the relationship between language modeling objectives and structure learning. The lecture also delves into the use of transformer models, self-attention mechanisms, and linear projections for tasks like structure prediction, remote homology detection, and contact precision evaluation.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Official source

Related concepts (32)

Biomolecular structure

Biomolecular structure is the intricate folded, three-dimensional shape that is formed by a molecule of protein, DNA, or RNA, and that is important to its function. The structure of these molecules may be considered at any of several length scales ranging from the level of individual atoms to the relationships among entire protein subunits. This useful distinction among scales is often expressed as a decomposition of molecular structure into four levels: primary, secondary, tertiary, and quaternary.

Threading (protein sequence)

In molecular biology, protein threading, also known as fold recognition, is a method of protein modeling which is used to model those proteins which have the same fold as proteins of known structures, but do not have homologous proteins with known structure. It differs from the homology modeling method of structure prediction as it (protein threading) is used for proteins which do not have their homologous protein structures deposited in the Protein Data Bank (PDB), whereas homology modeling is used for those proteins which do.

Protein structure prediction

Protein structure prediction is the inference of the three-dimensional structure of a protein from its amino acid sequence—that is, the prediction of its secondary and tertiary structure from primary structure. Structure prediction is different from the inverse problem of protein design. Protein structure prediction is one of the most important goals pursued by computational biology; and it is important in medicine (for example, in drug design) and biotechnology (for example, in the design of novel enzymes).

Nucleic acid structure prediction

Nucleic acid structure prediction is a computational method to determine secondary and tertiary nucleic acid structure from its sequence. Secondary structure can be predicted from one or several nucleic acid sequences. Tertiary structure can be predicted from the sequence, or by comparative modeling (when the structure of a homologous sequence is known).

Modeling language

A modeling language is any artificial language that can be used to express data, information or knowledge or systems in a structure that is defined by a consistent set of rules. The rules are used for interpretation of the meaning of components in the structure Programing language. A modeling language can be graphical or textual. Graphical modeling languages use a diagram technique with named symbols that represent concepts and lines that connect the symbols and represent relationships and various other graphical notation to represent constraints.

Related lectures (64)

Pretraining: Transformers & Models

Explores pretraining models like BERT, T5, and GPT, discussing their training objectives and applications in natural language processing.

Language Models: From Theory to Computation

Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.

Protein Composition and Structure

Explores protein composition, peptide bonds, secondary structures, and protein folding prediction.

Understanding Generative Models of Protein Sequences

Explores a unified framework for understanding and evaluating generative sequence models of DNA/RNA or Protein, covering topics like coevolution, conservation, and different models such as GREMLIN and BERT.

Protein Structure: General Principles