8037a454cf5854c82423c61a21032572cbdf6e33
examples/alphafold2.md
... | ... | @@ -120,6 +120,14 @@ Memory is going to be an issue with larger protein sizes. The original publicati |
120 | 120 | |
121 | 121 | "The memory usage is approximately quadratic in the number of residues, so a 2,500 residue protein involves using unified memory so that we can greatly exceed the memory of a single V100. In our cloud setup, a single V100 is used for computation on a 2,500 residue protein but we requested four GPUs to have sufficient memory." |
122 | 122 | |
123 | +The following environment variable settings may help with larger polypeptide calculations (> 1,200 aa). |
|
124 | + |
|
125 | +``` |
|
126 | +TF_FORCE_UNIFIED_MEMORY=1 |
|
127 | +XLA_PYTHON_CLIENT_MEM_FRACTION=0.5 |
|
128 | +XLA_PYTHON_CLIENT_ALLOCATOR=platform |
|
129 | +``` |
|
130 | +*Thanks Ci Ji Lim at Wisconsin for suggesting and testing these.* |
|
123 | 131 | ### pTM scores |
124 | 132 | The pTM scores are not calculated using the default model. To get pTM scored models you need to change the model names in the input. We have provided a template wrapper script (https://sbgrid.org//wiki/examples/alphafold2) which you can change to your requirements. To get pTM scores you will need to change the model_name line to "model_1_ptm,model_2_ptm" etc. |
125 | 133 |