| 13 | * SSD drives on plato |
| 14 | - Each of 4 plato nodes now has a 4 TB SSD drive mounted at /scratch. |
| 15 | - Scooter is using this to build BLAST databases with makeblastdb which fails to run on beegfs file system. |
| 16 | |
| 17 | * Martin Steinegger talk |
| 18 | - Martin created BFD (big fantastic database) metagenomics database that DeepMind then used for AlphaFold 2. |
| 19 | - Trained network to run Foldseek directly on a sequence with the network directly translating sequence to 3Di spatial alphabet. This takes seconds instead of minutes to make a ColabFold prediction. |
| 20 | - Martin has clustered AlphaFold database of 214 million structures down to 2-3 million clusters using foldseek-clust. |
| 21 | - About 35% of clusters have no annotations. |
| 22 | - Looked at how many clusters are specialized to bacteria or eukaryotes or archaea, cluster.foldseek.com. |
| 23 | - Martin made pitch strongly advocating open source software. Said they made foldseek open source in 2021 3 years before publication. |
| 24 | |