@MoAlQuraishi 10 searchers per day on a webserver, that should not even be allowed for a method's paper. I get the limitations for commercial use but the gated use through a server with such low volume usage totally sucks for most academic research applications.

@pedrobeltrao Yes I agree it's a big limitation. Not to mention the lack of code.

@MoAlQuraishi Not releasing weights was expected but not releasing even code is pretty bad. What is the point of publishing in a scientific journal then, as opposed to the existing white paper? This is pretty close to a paid promotion imho

@MartinPacesa Not to excuse the lack of real code, but the pseudocode in the SI is reasonably detailed. Some pieces may yet be missing of course.

@MoAlQuraishi curious how the performance on protein-RNA interactions compares with RossettaNA

@chaolinzhang Protein-RNA performance for both methods remains very weak.

@MoAlQuraishi A quick one-pager:

@MoAlQuraishi Still closed source?

@MoAlQuraishi What a surprise (not) on all fronts! I doubt they'll share the model or code this time around.

@MoAlQuraishi All algorithms seem to be well described in the Supplementary Information document. Looking forward to see the OpenFold implementation soon

@MoAlQuraishi Nice!

@MoAlQuraishi The Open Source Implementation of AlphaFold3

@MoAlQuraishi But how do you download a PDB file of the 3D structure?

@MoAlQuraishi How can I reproduce AF3 results when only 10 predictions are allowed on the Alphafold Server and the source code is not provided? Science? Fiction?