MSA generation is not slow. In ColabFold we generate MSAs in seconds using MMseqs2. This can be tweaked to run in < second using batch. Most of the time of AlphaFold/ColabFold is spent predicting the structure. Tweet added by Martin Steinegger 🇺🇦 @thesteinegger

Martin Steinegger 🇺🇦

2 years

MSA generation is not slow. In ColabFold we generate MSAs in seconds using MMseqs2. This can be tweaked to run in < second using batch. Most of the time of AlphaFold/ColabFold is spent predicting the structure.

Jian Peng

@peng_illinois

2 years

Without the need to search MSAs, OF is also super fast. Only a few seconds for predicting a normal-size protein. Preprint & code will be released soon. Just the pilot episode. Stay tuned for more. 5/5

17

11

136

3

4

43

Lei Wang

@NeoleiHUST

2 years

@thesteinegger Predicted structures of individual sequences appear to address point mutations

0

Lei Wang

@NeoleiHUST

2 years

@thesteinegger These prediction tools relying on MSA should be basically impossible to achieve

0

Zach Hensel

@alchemytoday

2 years

@thesteinegger Are there AF2 parameters trained without MSAs to compare against? The template-free ones perform the best for predictions without templates.

1

0

Replies