zhaoqichang / attentiondta_bibm Goto Github PK

Hi, your developed AttentionDTA is very useful for the Interpretability of DTA prediction task!
but I didn't find the corresponding Attention module from your published project
(eg. how to calculate and output the attention weights after model training,
as well as how to map the regions with high attention weight values calculated
from the attention model onto a known 3D protein structure or a compound structure...
just like what your paper described in Case Study for Interpretability)
I believe it's the key point in your published paper which introduce the novel DTA model based on attention method.
Looking forward to your quick reponse! Thanks in advance！

InvalidArgumentError (see above for traceback): indices[56,57] = 66 is not in [0, 65)
[[Node: smi_embedding/embedding_lookup = GatherV2[Taxis=DT_INT32, Tindices=DT_INT32, Tparams=DT_FLOAT, _class=["loc:@train_step/Adam/update_smi_embedding/smi_word_embedding/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](smi_embedding/smi_word_embedding/read, input/IteratorGetNext, smi_embedding/embedding_lookup/axis)]]

InvalidArgumentError (see above for traceback): indices[56,57] = 66 is not in [0, 65)
[[Node: smi_embedding/embedding_lookup = GatherV2[Taxis=DT_INT32, Tindices=DT_INT32, Tparams=DT_FLOAT, _class=["loc:@train_step/Adam/update_smi_embedding/smi_word_embedding/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](smi_embedding/smi_word_embedding/read, input/IteratorGetNext, smi_embedding/embedding_lookup/axis)]]