Zum Inhalt springen
KI-Atlas

AlphaFold

Sagt die dreidimensionale Struktur von Proteinen aus ihrer Aminosäuresequenz voraus

Google DeepMind Modell Open Source

Der vollständige Artikel liegt auf Englisch vor; Titel und Zusammenfassung sind lokalisiert.

WAS ES IST

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.

Warum es wichtig ist

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.

Wichtige Eckdaten

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)

Verwandte Konzepte