targetdiff
targetdiff copied to clipboard
guanjq
The official implementation of 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (ICLR 2023)
Great work! @guanjq a couple of questions: 1) in provided training.yml, the ligand_atom_mode is "add_aromatic" and random_rot "False". Are these settings of the provided pretrained model? 2) Have you tried...
Hi, it's nice of you to share codes! I got some puzzles about data preprocessing, that is, **how to generate the file you've shared in google disk '_crossdocked_v1.1_rmsd1.0_pocket10_processed_final.lmdb_'.** I've go...
Hi, thank you for sharing such a good work. However, I am a little confused about how can I get batch.ligand_element_batch in the def train(it): model.train() optimizer.zero_grad() for _ in...
hi, guanjq, thanks for your good works of new diffusion models. while I try to run the command line, ```bash python scripts/sample_for_pocket.py configs/sampling.yml --pdb_path examples/1h36_A_rec_1h36_r88_lig_tt_docked_0_pocket10.pdb ``` the error occured, as...
Hello, I have a question about Jensen-Shannon divergence.When calculating JSD, do we calculate the distance between all atoms or only those with bonds.
Firstly, I would like to express my gratitude for your impressive work and for making it available on GitHub. I recently utilized your pre-trained model to generate molecules for a...
Hi，guanjq， I find a code error in self.q_v_pred_one_timestep(log_vt, t, batch) of q_v_posterior function, which is for calculating the q(v_t| v_t-1) ?? **source code in gitub :** `# atom type generative...
Thanks for sharing your wonderful work! I ran the sample_diffusion.py script as per the README and received a .pt file containing 10 samples as output. I’m wondering how I can...
How are targetdiff_vina_docked.pt, pocket2mol_vina_docked.pt, ar_vina_docked.pt, etc. generated in sampling_results?
