Systemic Evolutionary Chemical Space Exploration for Drug Discovery

Last update: Dec 16, 2022

Overview

SECSE

SECSE: Systemic Evolutionary Chemical Space Explorer

Chemical space exploration is a major task of the hit-finding process during the pursuit of novel chemical entities. Compared with other screening technologies, computational de novo design has become a popular approach to overcome the limitation of current chemical libraries. Here, we reported a de novo design platform named systemic evolutionary chemical space explorer (SECSE). The platform was conceptually inspired by fragment-based drug design, that miniaturized a “lego-building” process within the pocket of a certain target. The key of virtual hits generation was then turned into a computational search problem. To enhance search and optimization, human intelligence and deep learning were integrated. SECSE has the potential in finding novel and diverse small molecules that are attractive starting points for further validation.

Tutorials and Usage

Set Environment Variables
export $SECSE=path/to/SECSE
if you use AutoDock Vina for docking: (download here)
export $VINA=path/to/AutoDockVINA
if you use Gilde for docking (additional installation & license required):
export $SCHRODINGER=path/to/SCHRODINGER
Give execution permissions to the SECSE directory
chmod -R +X path/to/SECSE
Input fragments: a tab split .smi file without header. See demo here.
Parameters in config file:
[DEFAULT]
- workdir, working directory, create if not exists, otherwise overwrite, type=str
- fragments, file path to seed fragments, smi format, type=str
- num_gen, number of generations, type=int
- num_per_gen, number of molecules generated each generation, type=int
- seed_per_gen, number of selected seed molecules per generation, default=1000, type=int
- start_gen, number of staring generation, default=0, type=int
- docking_program, name of docking program, AutoDock-Vina (input vina) or Glide (input glide) , default=vina, type=str
[docking]
- target, protein PDBQT if use AutoDock Vina; Grid file if choose Glide, type=str
- RMSD, docking pose RMSD cutoff between children and parent, default=2, type=float
- delta_score, decreased docking score cutoff between children and parent, default=-1.0, type=float
- score_cutoff, default=-9, type=float
Parameters when docking by AutoDock Vina:
- x, Docking box x, type=float
- y, Docking box y, type=float
- z, Docking box z, type=float
- box_size_x, Docking box size x, default=20, type=float
- box_size_y, Docking box size y, default=20, type=float
- box_size_z, Docking box size z, default=20, type=float
[deep learning]
- mode, mode of deep learning modeling, 0: not use, 1: modeling per generation, 2: modeling overall after all the generation, default=0, type=int
- dl_per_gen, top N predicted molecules for docking, default=100, type=int
- dl_score_cutoff, default=-9, type=float
[properties]
- MW, molecular weights cutoff, default=450, type=int
- logP_lower, minimum of logP, default=0.5, type=float
- logP_upper, maximum of logP, default=7, type=float
- chiral_center, maximum of chiral center,default=3, type=int
- heteroatom_ratio, maximum of heteroatom ratio, default=0.35, type=float
- rotatable_bound_num, maximum of rotatable bound, default=5, type=int
- rigid_body_num, default=2, type=int
Config file of a demo case phgdh_demo_vina.ini
Run SECSE
python $SECSE/run_secse.py --config path/to/config
Output files
- merged_docked_best_timestamp_with_grow_path.csv: selected molecules and growing path
- selected.sdf: 3D conformers of all selected molecules

Dependencies

GNU Parallel installation

CentOS / RHEL
yum install parallel
Ubuntu / Debian
sudo apt install parallel
From source: https://www.gnu.org/software/parallel/

numpy~=1.20.3, pandas~=1.3.3, pandarallel~=1.5.2, tqdm~=4.62.2, biopandas~=0.2.9, openbabel~=3.1.1, rdkit~=2021.03.5, chemprop~=1.3.1, torch~=1.9.0+cu111

Citation

Lu, C.; Liu, S.; Shi, W.; Yu, J.; Zhou, Z.; Zhang, X.; Lu, X.; Cai, F.; Xia, N.; Wang, Y. Systemic Evolutionary Chemical Space Exploration For Drug Discovery. ChemRxiv 2021. This content is a preprint and has not been peer-reviewed.

License

SECSE is released under Apache License, Version 2.0.

ETMO: Evolutionary Transfer Multiobjective Optimization

ETMO: Evolutionary Transfer Multiobjective Optimization To promote the research on ETMO, benchmark problems are of great importance to ETMO algorithm

0 Mar 16, 2021

Guiding evolutionary strategies by (inaccurate) differentiable robot simulators @ NeurIPS, 4th Robot Learning Workshop

Guiding Evolutionary Strategies by Differentiable Robot Simulators In recent years, Evolutionary Strategies were actively explored in robotic tasks fo

4 Dec 14, 2021

BESS: Balanced Evolutionary Semi-Stacking for Disease Detection via Partially Labeled Imbalanced Tongue Data

Balanced-Evolutionary-Semi-Stacking Code for the paper ''BESS: Balanced Evolutionary Semi-Stacking for Disease Detection via Partially Labeled Imbalan

0 Jan 16, 2022

This is the repo for the paper `SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization'. (published in Bioinformatics'21)

SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization This is the code for our paper ``SumGNN: Multi-typed Drug

58 Dec 21, 2022

Cancer Drug Response Prediction via a Hybrid Graph Convolutional Network

DeepCDR Cancer Drug Response Prediction via a Hybrid Graph Convolutional Network This work has been accepted to ECCB2020 and was also published in the

50 Dec 18, 2022

Multi-modal co-attention for drug-target interaction annotation and Its Application to SARS-CoV-2

CoaDTI Multi-modal co-attention for drug-target interaction annotation and Its Application to SARS-CoV-2 Abstract Environment The test was conducted i

7 Nov 14, 2022

The code for SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network.

SAG-DTA The code is the implementation for the paper 'SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network'. Requirements py

7 Aug 2, 2022

[ICLR 2021] Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments.

[ICLR 2021] RAPID: A Simple Approach for Exploration in Reinforcement Learning This is the Tensorflow implementation of ICLR 2021 paper Rank the Episo

48 Nov 21, 2022

A mini library for Policy Gradients with Parameter-based Exploration, with reference implementation of the ClipUp optimizer from NNAISENSE.

PGPElib A mini library for Policy Gradients with Parameter-based Exploration [1] and friends. This library serves as a clean re-implementation of the

56 Jan 1, 2023

Comments

Problem running demo

Hi!

When I try to run the demo with the command below. python $SECSE/run_secse.py --config demo/phgdh_demo_vina.ini

It generates pandas.errors.EmptyDataError: No columns to parse from file, what should I do to solve it? Thank you!

Here is the output

**************************************************************************************** 
      ____    _____    ____   ____    _____ 
     / ___|  | ____|  / ___| / ___|  | ____|
     \___ \  |  _|   | |     \___ \  |  _|  
      ___) | | |___  | |___   ___) | | |___ 
     |____/  |_____|  \____| |____/  |_____|
/home/bruce/Downloads/Softwares/Anaconda/envs/secse/lib/python3.7/site-packages/pandas/core/generic.py:2882: UserWarning: The spaces in these column names will not be changed. In pandas versions < 0.14, spaces were converted to underscores.
 method=method,
Table 'G-001' already exists.

******************************************************************
Input fragment file: /home/bruce/Work/CADD/SECSE/code/demo/demo_1020.smi
Target grid file: /home/bruce/Work/CADD/SECSE/code/demo/PHGDH_6RJ3_for_vina.pdbqt
Workdir: /home/bruce/Work/CADD/SECSE/code/res/


************************************************** 
Generation  0 ...
Step 1: Docking with Autodock Vina ...
/home/bruce/Work/CADD/SECSE/code/secse/evaluate/ligprep_vina_parallel.sh /home/bruce/Work/CADD/SECSE/code/res/generation_0 /home/bruce/Work/CADD/SECSE/code/demo/demo_1020.smi /home/bruce/Work/CADD/SECSE/code/demo/PHGDH_6RJ3_for_vina.pdbqt 20.9 -10.4 3.0 20.0 20.0 25.0 10
find /home/bruce/Work/CADD/SECSE/code/res/generation_0/sdf_files -name "*sdf" | xargs -n 100 cat > /home/bruce/Work/CADD/SECSE/code/res/generation_0/docking_outputs_with_score.sdf
Docking time cost: 0.12 min.
Step 2: Ranking docked molecules...
9 cmpds after evaluate
The evaluate score cutoff is: -9.0
9 final seeds.

************************************************** 
Generation  1 ...
Step 1: Mutation
No rule class:  B-001
No rule class:  G-003
No rule class:  G-004
No rule class:  G-005
No rule class:  G-006
No rule class:  G-007
No rule class:  M-001
No rule class:  M-002
No rule class:  M-003
No rule class:  M-004
No rule class:  M-005
No rule class:  M-006
No rule class:  M-007
No rule class:  M-008
No rule class:  M-009
No rule class:  M-010
No rule class: G-002
Step 2: Filtering all mutated mols
sh /home/bruce/Work/CADD/SECSE/code/secse/growing/filter_parallel.sh /home/bruce/Work/CADD/SECSE/code/res/generation_1 1 demo/phgdh_demo_vina.ini 10
Filter runtime: 0.00 min.
Traceback (most recent call last):
 File "/home/bruce/Work/CADD/SECSE/code/secse/run_secse.py", line 80, in <module>
   main()
 File "/home/bruce/Work/CADD/SECSE/code/secse/run_secse.py", line 65, in main
   workflow.grow()
 File "/home/bruce/Work/CADD/SECSE/code/secse/grow_processes.py", line 208, in grow
   self._filter_df = pd.read_csv(os.path.join(self.workdir_now, "filter.csv"), header=None)
 File "/home/bruce/Downloads/Softwares/Anaconda/envs/secse/lib/python3.7/site-packages/pandas/util/_decorators.py", line 311, in wrapper
   return func(*args, **kwargs)
 File "/home/bruce/Downloads/Softwares/Anaconda/envs/secse/lib/python3.7/site-packages/pandas/io/parsers/readers.py", line 586, in read_csv
   return _read(filepath_or_buffer, kwds)
 File "/home/bruce/Downloads/Softwares/Anaconda/envs/secse/lib/python3.7/site-packages/pandas/io/parsers/readers.py", line 482, in _read
   parser = TextFileReader(filepath_or_buffer, **kwds)
 File "/home/bruce/Downloads/Softwares/Anaconda/envs/secse/lib/python3.7/site-packages/pandas/io/parsers/readers.py", line 811, in __init__
   self._engine = self._make_engine(self.engine)
 File "/home/bruce/Downloads/Softwares/Anaconda/envs/secse/lib/python3.7/site-packages/pandas/io/parsers/readers.py", line 1040, in _make_engine
   return mapping[engine](self.f, **self.options)  # type: ignore[call-arg]
 File "/home/bruce/Downloads/Softwares/Anaconda/envs/secse/lib/python3.7/site-packages/pandas/io/parsers/c_parser_wrapper.py", line 69, in __init__
   self._reader = parsers.TextReader(self.handles.handle, **kwds)
 File "pandas/_libs/parsers.pyx", line 549, in pandas._libs.parsers.TextReader.__cinit__
pandas.errors.EmptyDataError: No columns to parse from file

opened by BW15061999 17

Question about running the demo code

Hi authors,

I have tried to run your demo code in README.md, but got some errors.

Command

python /home/xxx/workspace/off-SECSE/secse/run_secse.py --config ./config.ini

Output

 **************************************************************************************** 
       ____    _____    ____   ____    _____ 
      / ___|  | ____|  / ___| / ___|  | ____|
      \___ \  |  _|   | |     \___ \  |  _|  
       ___) | | |___  | |___   ___) | | |___ 
      |____/  |_____|  \____| |____/  |_____|

******************************************************************
Input fragment file: /home/xxx/workspace/off-SECSE/fy-run/demo001/ligand.smi
Target grid file: /home/xxx/workspace/off-SECSE/fy-run/demo001/receptor.pdbqt
Workdir: /home/xxx/workspace/off-SECSE/fy-run/demo001/

Step 1: Docking with Autodock Vina ...
/home/xxx/workspace/off-SECSE/secse/evaluate/ligprep_vina_parallel.sh /home/xxx/workspace/off-SECSE/fy-run/demo001/generation_0 /home/xxx/workspace/off-SECSE/fy-run/demo001/ligand.smi /home/t-yafan/workspace/off-SECSE/fy-run/demo001/receptor.pdbqt 20.9 -10.4 3.0 20.0 20.0 25.0 10
find /home/xxx/workspace/off-SECSE/fy-run/demo001/generation_0/sdf_files -name "*sdf" | xargs -n 100 cat > /home/xxx/workspace/off-SECSE/fy-run/demo001/generation_0/docking_outputs_with_score.sdf
Docking time cost: 0.11 min.
Step 2: Ranking docked molecules...
9 cmpds after evaluate
The evaluate score cutoff is: -9.0
9 final seeds.

 ************************************************** 
Generation  1 ...
Step 1: Mutation
Traceback (most recent call last):
  File "/home/xxx/workspace/off-SECSE/secse/run_secse.py", line 70, in <module>
    main()
  File "/home/xxx/workspace/off-SECSE/secse/run_secse.py", line 55, in main
    workflow.grow()
  File "/home/xxx/workspace/off-SECSE/secse/grow_processes.py", line 159, in grow
    header = mutation_df(self.winner_df, self.workdir, self.cpu_num, self.gen)
  File "/home/xxx/workspace/off-SECSE/secse/growing/mutation/mutation.py", line 166, in mutation_df
    mutation = Mutation(5000, workdir)
  File "/home/xxx/workspace/off-SECSE/secse/growing/mutation/mutation.py", line 29, in __init__
    self.load_common_rules()
  File "/home/xxx/workspace/off-SECSE/secse/growing/mutation/mutation.py", line 50, in load_common_rules
    c.execute(sql)
sqlite3.OperationalError: no such table: B-001

It seems that the file secse/growing/mutation/rules_demo.db is missing in the repo. How can I fix it?

Thanks!

opened by fyabc 5

All dockings do not work because there's no gridding process.

Hi, I was trying out the repo when I realised that neither the autodock nor glide is able to run because there was no gridding process, resulting in no grid files. >.<

opened by yipy0005 3

Releases(v1.1.0)

v1.1.0(Jul 15, 2022)

Source code(tar.gz)
Source code(zip)
v1.0.0(Feb 24, 2022)

Source code(tar.gz)
Source code(zip)

Owner

GitHub Repository

Easy and Efficient Object Detector

EOD Easy and Efficient Object Detector EOD (Easy and Efficient Object Detection) is a general object detection model production framework. It aim on p

381 Jan 01, 2023

A framework to train language models to learn invariant representations.

Invariant Language Modeling Implementation of the training for invariant language models. Motivation Modern pretrained language models are critical co

6 Nov 16, 2022

[CVPR'21] DeepSurfels: Learning Online Appearance Fusion

DeepSurfels: Learning Online Appearance Fusion Paper | Video | Project Page This is the official implementation of the CVPR 2021 submission DeepSurfel

52 Nov 14, 2022

The deployment framework aims to provide a simple, lightweight, fast integrated, pipelined deployment framework that ensures reliability, high concurrency and scalability of services.

savior是一个能够进行快速集成算法模块并支持高性能部署的轻量开发框架。能够帮助将团队进行快速想法验证（PoC），避免重复的去github上找模型然后复现模型；能够帮助团队将功能进行流程拆解，很方便的提高分布式执行效率；能够有效减少代码冗余，减少不必要负担。

125 Dec 22, 2022

Image Super-Resolution by Neural Texture Transfer

SRNTT: Image Super-Resolution by Neural Texture Transfer Tensorflow implementation of the paper Image Super-Resolution by Neural Texture Transfer acce

413 Nov 30, 2022

Code for pre-training CharacterBERT models (as well as BERT models).

Pre-training CharacterBERT (and BERT) This is a repository for pre-training BERT and CharacterBERT. DISCLAIMER: The code was largely adapted from an o

31 Dec 05, 2022

Data and Code for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning"

Introduction Code and data for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning". We cons

81 Dec 27, 2022

Keras Image Embeddings using Contrastive Loss

Keras-Image-Embeddings-using-Contrastive-Loss Image to Embedding projection in vector space. Implementation in keras and tensorflow for custom data. B

5 Mar 21, 2022

LLVM-based compiler for LightGBM gradient-boosted trees. Speeds up prediction by ≥10x.

183 Jan 02, 2023

Official Repository for our ECCV2020 paper: Imbalanced Continual Learning with Partitioning Reservoir Sampling

Imbalanced Continual Learning with Partioning Reservoir Sampling This repository contains the official PyTorch implementation and the dataset for our

40 Sep 18, 2022

Relative Human dataset, CVPR 2022

Relative Human (RH) contains multi-person in-the-wild RGB images with rich human annotations, including: Depth layers (DLs): relative depth relationsh

112 Dec 02, 2022

TensorFlow Implementation of Unsupervised Cross-Domain Image Generation

Domain Transfer Network (DTN) TensorFlow implementation of Unsupervised Cross-Domain Image Generation. Requirements Python 2.7 TensorFlow 0.12 Pickle

864 Dec 30, 2022

StackNet is a computational, scalable and analytical Meta modelling framework

StackNet This repository contains StackNet Meta modelling methodology (and software) which is part of my work as a PhD Student in the computer science

1.3k Dec 15, 2022

Hitters Linear Regression - Hitters Linear Regression With Python

Hitters_Linear_Regression Kullanacağımız veri seti Carnegie Mellon Üniversitesi'

2 Jan 26, 2022

An API-first distributed deployment system of deep learning models using timeseries data to analyze and predict systems behaviour

Gordo Building thousands of models with timeseries data to monitor systems. Table of content About Examples Install Uninstall Developer manual How to

26 Dec 27, 2022