-
Hi,here
I want to reproduce the performance of ACNN in protein-ligand binding affinity, but I can't find the pre-trained model.How can I obtain the .pth file for ACNN? Thanks for your reply.
-
To recreate
```
from dgllife.model.model_zoo.acnn import ACNN
import dgl
from rdkit import Chem
from rdkit.Chem import AllChem
import torch
from dgllife.utils import ACNN_graph_construction_and…
-
Hi,
@mapleleaf-soar and I found AI models (e.g. AtomNet #56, ACNN #287) achieve high performance on DUD-E and PDBbind data sets because they learned the bias in the data sets. REF #1008
For examp…
-
Hi,
Thank you to DeepChem team, @mapleleaf-soar and I published my [first paper](https://doi.org/10.3389/fphar.2020.00069) based on ACNN model in DeepChem to show the bias in the PDBbind data set. …
-
I would like to save a built "_AtomicConvModel_" on disk, but there is the following problem:
```
model.save()
File "/home/anaconda3/envs/acnn/lib/python3.7/site-packages/deepchem/models/tensorgr…
-
**Description:**
In ACNN paper:
> To create a model which can accurately predict ∆Gcomplex, we create three **weight-sharing**, replica networks, one each for complex, protein, and ligand (Figure 2)…
-
I was attempting to run the demo code, but I found that the checkpoint file mentioned in line 53 from "Examples/demo_segmentation.py" (see below) is unavailable. Is there a location that has not been …
-
I think something is wrong with the ACNN implementation as the entire CNN exists out of a single Conv1d layer:
```python
# (batch, channels, length)
self.cnn = nn.Conv1d(in_channels=self.in_chann…
-
I noticed that in the log file, the version "baseline+attentive pooling" can get the result: 05-10 21:12 Epoch: 21 Train: 94.81% Test: 75.19%. What are the model configurations in details for this res…
-
hello,I choose attention_pooling model when I run main.py. But I see a great difference from your results.And the train accuracy is so high, the test accuracy is so low.
My result in attention poolin…