This repository contains the code for Direct Molecular Conformation Generation (DMCG).

Related tags

Deep Learning DMCG
Overview

Direct Molecular Conformation Generation

This repository contains the code for Direct Molecular Conformation Generation (DMCG).

Dataset

Download rdkit_folder.tar.gz from this url.

tar -xvf rdkit_folder.tar.gz

Requirements and Installation

  • PyTorch
  • Torch-Geometric

You can build a Docker image with the Dockerfile. To install DMCG and develop it locally

pip install -e .

Train

The first time you run this code, you should specify the data path with --base-path, and the code will binarize data into binarized format.

bash run_training.sh --dropout 0.1 --use-bn --no-3drot  \
    --aux-loss 0.2 --num-layers 6 --lr 2e-4 --batch-size 128 --vae-beta-min 0.0001 --vae-beta-max 0.03 \
    --reuse-prior --node-attn --data-split confgf --pred-pos-residual \
    --dataset-name qm9 --remove-hs --shared-output  --base-path $yourdatapath

Test

python evaluate.py --dropout 0.1 --use-bn --lr-warmup --use-adamw --train-subset \
    --num-layers 6 --eval-from  $yourcktpath --workers 20 --batch-size 128 \
    --reuse-prior --node-attn --data-split confgf --dataset-name qm9 --remove-hs \
    --shared-output --pred-pos-residual --sample-beta 1.2
You might also like...
Few-Shot Graph Learning for Molecular Property Prediction

Few-shot Graph Learning for Molecular Property Prediction Introduction This is the source code and dataset for the following paper: Few-shot Graph Lea

Zhichun Guo 94 Dec 12, 2022
SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks (Scientific Reports)
SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks (Scientific Reports)

SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks Molecular interaction networks are powerful resources for the discovery. While dee

Kexin Huang 49 Oct 15, 2022
MolRep: A Deep Representation Learning Library for Molecular Property Prediction
MolRep: A Deep Representation Learning Library for Molecular Property Prediction

MolRep: A Deep Representation Learning Library for Molecular Property Prediction Summary MolRep is a Python package for fairly measuring algorithmic p

AI-Health @NSCC-gz 83 Dec 24, 2022
Kaggle | 9th place (part of) solution for the Bristol-Myers Squibb – Molecular Translation challenge

Part of the 9th place solution for the Bristol-Myers Squibb – Molecular Translation challenge translating images containing chemical structures into I

Erdene-Ochir Tuguldur 22 Nov 30, 2022
Fast and scalable uncertainty quantification for neural molecular property prediction, accelerated optimization, and guided virtual screening.
Fast and scalable uncertainty quantification for neural molecular property prediction, accelerated optimization, and guided virtual screening.

Evidential Deep Learning for Guided Molecular Property Prediction and Discovery Ava Soleimany*, Alexander Amini*, Samuel Goldman*, Daniela Rus, Sangee

Alexander Amini 75 Dec 15, 2022
DockStream: A Docking Wrapper to Enhance De Novo Molecular Design
DockStream: A Docking Wrapper to Enhance De Novo Molecular Design

DockStream Description DockStream is a docking wrapper providing access to a collection of ligand embedders and docking backends. Docking execution an

AstraZeneca - Molecular AI 72 Jan 2, 2023
Molecular AutoEncoder in PyTorch

MolEncoder Molecular AutoEncoder in PyTorch Install $ git clone https://github.com/cxhernandez/molencoder.git && cd molencoder $ python setup.py insta

Carlos Hernández 80 Dec 5, 2022
Automatic Differentiation Multipole Moment Molecular Forcefield

Automatic Differentiation Multipole Moment Molecular Forcefield Performance notes On a single gpu, using waterbox_31ang.pdb example from MPIDplugin wh

null 4 Jan 7, 2022
3D-Transformer: Molecular Representation with Transformer in 3D Space

3D-Transformer: Molecular Representation with Transformer in 3D Space

null 55 Dec 19, 2022
Comments
  • data problem

    data problem

    hi i run the code following your instruction and got the following bugs. do you know how to fix it?

    Traceback (most recent call last): File "train.py", line 359, in main() File "train.py", line 190, in main remove_hs=args.remove_hs, File "/net/sunlab/psunlab1/molecular_data/graphnn/DMCG/confgen/e2c/dataset.py", line 61, in init super().init(self.folder, transform, pre_transform) File "/nethome/tfu42/.conda/envs/dmcg2/lib/python3.7/site-packages/torch_geometric/data/in_memory_dataset.py", line 57, in init super().init(root, transform, pre_transform, pre_filter) File "/nethome/tfu42/.conda/envs/dmcg2/lib/python3.7/site-packages/torch_geometric/data/dataset.py", line 88, in init self._process() File "/nethome/tfu42/.conda/envs/dmcg2/lib/python3.7/site-packages/torch_geometric/data/dataset.py", line 171, in _process self.process() File "/net/sunlab/psunlab1/molecular_data/graphnn/DMCG/confgen/e2c/dataset.py", line 87, in process self.process_confgf() File "/net/sunlab/psunlab1/molecular_data/graphnn/DMCG/confgen/e2c/dataset.py", line 336, in process_confgf data, slices = self.collate(data_list) File "/nethome/tfu42/.conda/envs/dmcg2/lib/python3.7/site-packages/torch_geometric/data/in_memory_dataset.py", line 116, in collate add_batch=False, File "/nethome/tfu42/.conda/envs/dmcg2/lib/python3.7/site-packages/torch_geometric/data/collate.py", line 86, in collate increment) File "/nethome/tfu42/.conda/envs/dmcg2/lib/python3.7/site-packages/torch_geometric/data/collate.py", line 128, in _collate cat_dim = data_list[0].cat_dim(key, elem, stores[0]) TypeError: cat_dim() takes 3 positional arguments but 4 were given

    opened by futianfan 3
  • parameter number does not match in the paper

    parameter number does not match in the paper

    Hey, In your paper you claimed that the model has 13.29 million parameters but when I run training there are 128 million parameters, can you please explain such a difference? I would not believe that running the model in inference model (without the 3D encoder) would reduce the number of parameters by 10 times. Cheers, Carlen

    opened by CarlenYu 0
  • The pred conformer cannot be read by rdkit? the difference of postions between atoms is small

    The pred conformer cannot be read by rdkit? the difference of postions between atoms is small

    ATOM 1 N LIG 1 -0.435 -0.208 0.637 1.00 0.00 N
    ATOM 2 H LIG 1 0.992 -0.005 -0.955 1.00 0.00 H
    ATOM 3 C LIG 1 -0.445 0.027 0.067 1.00 0.00 C
    ATOM 4 O LIG 1 -0.410 0.813 0.783 1.00 0.00 O
    ATOM 5 C LIG 1 -0.986 -0.279 -0.962 1.00 0.00 C
    ATOM 6 C LIG 1 -0.428 0.520 -0.648 1.00 0.00 C
    ATOM 7 N LIG 1 0.037 0.983 0.805 1.00 0.00 N
    ATOM 8 C LIG 1 -0.147 0.998 0.511 1.00 0.00 C
    ATOM 9 N LIG 1 -0.649 -0.204 -0.644 1.00 0.00 N
    ATOM 10 H LIG 1 -0.185 -0.123 0.495 1.00 0.00 H
    ATOM 11 C LIG 1 0.881 -0.881 0.692 1.00 0.00 C
    ATOM 12 C LIG 1 -0.270 -0.257 -0.165 1.00 0.00 C
    ATOM 13 CL LIG 1 0.403 0.551 0.782 1.00 0.00 CL
    ATOM 14 N LIG 1 0.952 -0.736 0.785 1.00 0.00 N
    ATOM 15 C LIG 1 -0.955 -0.279 0.533 1.00 0.00 C
    ATOM 16 N LIG 1 -0.587 -0.227 0.710 1.00 0.00 N
    ATOM 17 C LIG 1 -0.052 -0.521 -0.493 1.00 0.00 C
    ATOM 18 C LIG 1 -0.609 0.583 -1.206 1.00 0.00 C
    ATOM 19 C LIG 1 0.998 -0.002 -0.276 1.00 0.00 C
    ATOM 20 C LIG 1 0.221 -0.265 0.275 1.00 0.00 C
    ATOM 21 C LIG 1 0.749 0.101 -0.611 1.00 0.00 C
    ATOM 22 C LIG 1 -0.482 -0.747 -0.908 1.00 0.00 C
    ATOM 23 C LIG 1 0.704 0.704 -0.239 1.00 0.00 C
    ATOM 24 C LIG 1 0.700 -0.547 0.033 1.00 0.00 C
    CONECT 1 2 3 9 CONECT 3 4 4 15 CONECT 5 6 CONECT 6 7 7 14 CONECT 7 8 CONECT 8 9 11 11 CONECT 9 10 CONECT 11 12 CONECT 12 13 14 14 CONECT 15 16 19 CONECT 16 17 20 CONECT 17 18 CONECT 18 19 CONECT 20 21 24 CONECT 21 22 CONECT 22 23 CONECT 23 24 END

    1655349225153

    opened by xxy90 0
  • Problems reproducing results

    Problems reproducing results

    Hello, this is Daniel, student of master of Artificial Intelligence at Paris-Saclay University. This is a great work and thanks for sharing the code, however, the results from the paper cannot be reproduced when executing the train command in the readme. Could you provide the precise command to train the model to obtain the paper results, or provide a pretrained model? Thank you, Daniel

    opened by danielm322 7
Owner
null
GitHub
Molecular Sets (MOSES): A benchmarking platform for molecular generation models

Molecular Sets (MOSES): A benchmarking platform for molecular generation models Deep generative models are rapidly becoming popular for the discovery

Neelesh C A 3 Oct 14, 2022
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

Molecular Sets (MOSES): A benchmarking platform for molecular generation models Deep generative models are rapidly becoming popular for the discovery

MOSES 656 Dec 29, 2022
NNR conformation conditional and global probabilities estimation and analysis in peptides or proteins fragments

NNR and global probabilities estimation and analysis in peptides or protein fragments This module calculates global and NNR conformation dependent pro

null 0 Jul 15, 2021
This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation

SO-Pose This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation This paper is basically an

shangbuhuan 52 Nov 25, 2022
This repository contains the data and code for the paper "Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors" (SPNLP@ACL2022)

GP-VAE This repository provides datasets and code for preprocessing, training and testing models for the paper: Diverse Text Generation via Variationa

Wanyu Du 18 Dec 29, 2022
This repository contains several image-to-image translation models, whcih were tested for RGB to NIR image generation. The models are Pix2Pix, Pix2PixHD, CycleGAN and PointWise.

RGB2NIR_Experimental This repository contains several image-to-image translation models, whcih were tested for RGB to NIR image generation. The models

null 5 Jan 4, 2023
source code for https://arxiv.org/abs/2005.11248 "Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics"

Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics This work will be published in Nature Biomedical

International Business Machines 71 Nov 15, 2022
Code for the paper "JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design"

JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design This repository contains code for the paper: JA

Aspuru-Guzik group repo 55 Nov 29, 2022
This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data.

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data.

null 212 Dec 25, 2022
Differentiable molecular simulation of proteins with a coarse-grained potential

Differentiable molecular simulation of proteins with a coarse-grained potential This repository contains the learned potential, simulation scripts and

UCL Bioinformatics Group 44 Dec 10, 2022