PSICHIC

PSICHIC copied to clipboard

screening mode

1

Hi, The screening script uses a CSV file containing in each row the sequence of the protein. However, it is not very efficient when you want to screen let say...

CLG68

Questions about the SMILES of hit1, hit2, hit3 mentioned in the paper

1

Listen-lei

Hello, great work. How should I organize the input csv file when predicting binding affinity for a protein with multiple ligands?

lizhanwei

Hi， In the case of multiple chains in a PDB file, how should sequence information be handled, such as calculating ESM embeddings and constructing the contact map?

jaminzzz

Hi, great work! In the PDB2020/train.csv, most of the "Target_Chain" s are "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA". What do they mean? Additionally, does the regression label represent a Kd or Ki value? How can...

MiaJY-Yang

hi, I found that predicted binding affinity does NOT match between The PSICHIC webserver and Colab(locally deployed version). However results from running Colab matches results of locally deployed model. for...

mhaiyue