Lecture 21_Artificial intelligence and biotech

Question 1

What are neural networks?

Answer 1

Computational models inspired by the brain, used for pattern recognition and deep learning.

Question 2

What is Natural Language Processing (NLP)?

Answer 2

AI’s ability to process and extract insights from human language; useful in mining scientific literature.

Question 3

What is computer vision?

Answer 3

AI that interprets images, used in diagnostics like tumor detection in scans.

Question 4

What is homology modelling?

Answer 4

Using known protein structures as templates to model similar proteins

Question 5

What is ab initio modelling?

Answer 5

Predicting structure from sequence alone, with no templates; computationally intensive.

Question 6

How long does AI-based structure prediction (e.g. AlphaFold) take?

Answer 6

Minutes to hours per protein, compared to weeks or months for traditional methods

Question 7

How does AlphaFold work?

Answer 7

It uses sequence alignments and transformer-based neural networks to predict distances and angles between amino acids, building accurate 3D structures.

Question 8

What is a transformer in AI?

Answer 8

A neural network architecture that uses “attention” mechanisms to model relationships between inputs, widely used in language and now biology.