Перейти к содержимому
Атлас ИИ

AlphaFold

Предсказывает трёхмерную структуру белка по последовательности аминокислот

Google DeepMind Модель Открытый исходный код

Полный текст статьи представлен на английском; заголовок и аннотация локализованы.

ЧТО ЭТО

AlphaFold is Google DeepMind’s protein-structure prediction system; the second version (AlphaFold2) was announced at the CASP14 assessment in November 2020 with accuracy close to experimental methods. It takes a protein’s amino-acid sequence and a multiple sequence alignment as input, uses an attention-based Evoformer module to model relationships between residues, and outputs three-dimensional coordinates. DeepMind later open-sourced the code and model weights and, with EMBL-EBI, built the AlphaFold Protein Structure Database, which holds hundreds of millions of predicted structures.

Почему стоит запомнить

It pushed protein-structure prediction to near-experimental accuracy, released the code and weights, and built a large structure database, becoming one of the most cited cases of AI applied to scientific research.

Ключевые характеристики

Open source
Yes (code and model weights released)
Database scale
AlphaFold DB holds hundreds of millions of predicted structures
Input
Amino-acid sequence and multiple sequence alignment
Released
2020-11 (CASP14)

Связанные концепции