Shen Lab at Texas A&M University

Thank you for the interest in DeepAffinity. Given the new data, you may want to re-train the model(s). Note that we removed four protein classes including GPCRs from our training...

We did not use any structures for DeepAffinity. But what you did, using relative solvent accessibility > 0.25 as the threshold, is consistent with Scratch's practice: https://onlinelibrary.wiley.com/doi/abs/10.1002/prot.10069 (Page 144) The...

For training the model with custom dataset, you can use https://github.com/Shen-Lab/DeepAffinity/blob/master/Joint_models/joint_attention/joint_warm_start/joint-Model.py Note that Line 281-313 load six sets of our data from a data folder in the same parent folder...

@psuriana Google scholar recommended your latest preprint to me today. Congrats! Here are a few points related to DeepAffinity for your consideration: 1. The DeepAffinity model you ran is probably...

Thank you @psuriana for the very informative comments! Sure, based on your description, the DeepAffinity model you used was RNN/RNN-CNN. The way we name various models for DeepAffinity is ProteinEncoder/CompoundEncoder-AffinityPredictor....

We may not have a convenient command ready for re-training seq2seq. I imagine that one version under https://github.com/Shen-Lab/DeepAffinity/tree/master/seq2seq_models needs to be re-trained with some length values changed in the script...

Thank you for your interest in our package. For the mapping between internal DeepAffinity IDs and external public IDs, you can find in cleared data description (https://github.com/Shen-Lab/DeepAffinity/blob/master/data/README.md) that, for each...

The number of the protein sequences and that of compound files are asked to be equal because we are predicting given *pairs* of proteins and compounds. So the k-th row...

Thank you for the feedback. We noted that the download links to the TU dataset have become obsolete. See https://github.com/Shen-Lab/GraphCL/issues/71#issuecomment-2221847005 please.

Hi @gabrielbianchin: Thank you for the interest in our code. The first author Yue would be a better candidate to answer the question, but before he does, my two cents...