Make mdtools for openmm #moleculardynamics #TeachOpenCADD #rdkit #openmm #chemoinformatics

As chemoinformatitians know that TeachOpenCADD(TOCADD) is one of the really useful site for learning in-silico drug discovery pipeline. It supports wide range of chemoinformatics not only LBDD but also SBDD. New version of TOCADD supports Molecular dynamics(MD) tutorial with openmm. The talktorial T019 and T020 show how to run and analyse MD with openmm andContinue reading “Make mdtools for openmm #moleculardynamics #TeachOpenCADD #rdkit #openmm #chemoinformatics”

Advertisement

Create desktop chemoinformatics application with JS #chemoinformatics #RDKit #JS

Long time ago, I wrote post about the same topic. The code used old version of rdkitjs and electron. Recently rdkitjs is maintained in official repository so I would like to re-test the approach. My old post is here. To do the following approach, I installed node.js, electron and npm at first. Then init theContinue reading “Create desktop chemoinformatics application with JS #chemoinformatics #RDKit #JS”

Compare shape and electrostatic similarity of molecules #RDKit #espsim #python

There are lots of way to define molecular similarity, for example fingerprint based, descriptor based, graph based, shape based etc. etc… In the 2D world, circular fingerprint based similarity is used in many case. However, 3D based similarity approach is also useful for drug design. As you now, OpenEye provides useful software named ‘ROCS’. ROCSContinue reading “Compare shape and electrostatic similarity of molecules #RDKit #espsim #python”

Calculate Atom-Atom-Path Fingerprint with RDKit #Chemoinformatics #RDKit

Recently there are lots of publications and codes for feature extraction with GCN of molecules. But fingerprint based approach is still useful due to GCN approach isn’t perfect. I often use the circular fingerprint such as ECFP / MorganFP for machine learning, clustering or other chemoinformatics tasks. Fingerprint based approach is still important I thinkContinue reading “Calculate Atom-Atom-Path Fingerprint with RDKit #Chemoinformatics #RDKit”

Reinforcement learning with docking score #RDKit #reinvent #chemoinforamtics

Previously I posted automated docking system called dockstream. It supports many compound-protein docking software and recent version of reinvent supports dockstream as scoring method. From the dockstream documentation, reinvent v3.0 supports dockstream but it didn’t work due to some issue of reinvent-scoring which manage scoring function of reinvent. I modified source code to use dockdreamContinue reading “Reinforcement learning with docking score #RDKit #reinvent #chemoinforamtics”

Update RDKit and use new contrib #RDKit #Chemoinformatics

As chemoinformatitians know ;) recently new version of rdkit is released. I appreciate the great work for developpers! One of the interesting point for me is that, FreeWilson(FW) analysis was added to Contrib. FW analysis is a traditional approach of chemoinformatics but I think it’s really MedChem friendly approach. You can get lots of informationContinue reading “Update RDKit and use new contrib #RDKit #Chemoinformatics”

Attentive FP with PyG #RDKit #PyG #pytorch_geometric #Chemoinformatics

As you know PyG is one of the useful package for graph based neural network as same as DGL-lifesci. Fortunately recent version of PyG is easy to install because it supports conda. So to install PyG, user don’t need to install related package such as pytorch_scatter, pytorch-cluster etc. etc. And PyG has lots of predefinedContinue reading “Attentive FP with PyG #RDKit #PyG #pytorch_geometric #Chemoinformatics”

Plot calibration curve with scikit-learn 1.0 #chemoinformatics #scikit-learn #memo

Recently scikit-learn ver. 1.0(nightly build) is released. I often use sklearn for my ask. So I would like to use new version ;) Current stable version is 0.24 so I installed 1.0.rc2 via pip. Here is a release Highlights and notes. https://scikit-learn.org/dev/auto_examples/release_highlights/plot_release_highlights_1_0_0.html https://scikit-learn.org/dev/whats_new/v1.0.html#changes-1-0 Ver 1.0 CalibrationDisplay method which can make calibration-curve plot easily. So IContinue reading “Plot calibration curve with scikit-learn 1.0 #chemoinformatics #scikit-learn #memo”

Convert bit-vector to comma separated strings #memo #chemoinformatics #RDKit

Today’s post will be very short :) I had an MRI scan for my knee at the hospital today. It took almost 6 moths after my surgery. And the result was very well. So I could be able to running as same as before getting the surgery. I’m not young but I would like toContinue reading “Convert bit-vector to comma separated strings #memo #chemoinformatics #RDKit”

Probabilistic Random Forest approach to predict experimental value #RDKit #chemoinformatics #machine_learning

To build predictive model, input value(X) and target value(y) is required. But in the drug discovery area target value always has experimental error. So any experimental value (target value) may have uncertainly and it makes difficult to build predictive model. Recently Ola Engkvist group who is in AZ published interesting article in Jounral of chemoinformatics.Continue reading “Probabilistic Random Forest approach to predict experimental value #RDKit #chemoinformatics #machine_learning”

Self docking study workflow with vina #chemoinformatics #vina #RDKit #pdb-tools

I posted about how to run vina from python. But I split receptor and ligand with pymol GUI at previous post, Hmm…. it’s not automated process. I tried to write code for full auto self docking with vina. It will work only very limited option and case but It’ll be first step for Virtual screeningContinue reading “Self docking study workflow with vina #chemoinformatics #vina #RDKit #pdb-tools”

Get environment SMILES around cutting points #chemoinformatics #memo #RDKit

In this week, I’m in summer vacation but can’t go travel due to COVID19 pandemic and heavy rain. It’s really unusual summer vacation. I hope everyone stay safe. BTW, I often use R-Group decomposition and Matched molecular pairs and these method generate many fragment smiles which has [*] at attachment points. And I would likeContinue reading “Get environment SMILES around cutting points #chemoinformatics #memo #RDKit”

Comparison of rdMMPA cut rules #RDKit #Chemoinformatics #memo

RDKit has code for making mmp in Contrib folder. And also rdkit provides rdMMPA class which can make MMP which is based on user defined cutting rules. Today I checked the rule and modified it with GetSubstructMatches. Default cutting rule is described in rdMMPA document and it’s defined as SMARTS pattern. pattern=’[#6+0;!$(=,#[!#6])]!@!=!#[]’  >> It meansContinue reading “Comparison of rdMMPA cut rules #RDKit #Chemoinformatics #memo”

Draw molecules on jupyter notebook #RDKit #mols2grid

As you know, jupyter-notebook (or lab) is not only powerful but also useful tool for chemoinformatics. And I can’t do any chemonformatics tasks without RDKit. RDKit has many useful tools of course rdkit can render high quality molecules on jupyter notebook. Today I would like to share new tool for rendering molecules on jupter notebook.Continue reading “Draw molecules on jupyter notebook #RDKit #mols2grid”

Generate all combinations of RGroups from molecules #RDKit #chemoinformatics

I posted an example to generate all compounds from molecules and their scaffold long time ago ;) https://iwatobipen.wordpress.com/2019/01/18/generate-possible-molecules-from-a-dataset-chemoinformatics-rdkit/ This code generates possible molecules from given scaffold and compounds set. The concept is same as Free Wilson approach I think. The code was jupyter notebook. So it is useful for ad hoc analysis but it’s notContinue reading “Generate all combinations of RGroups from molecules #RDKit #chemoinformatics”

Modify version of RDKit/Contrib/pzc #chemoinformatics #RDKit #ChEMBL #pychembldb

In 2013, Dr. Paul Czodrowski published nice article in JCIM. And the code is available from github. And also Paul contributed rdkit with the code. https://github.com/pzc/rdkit/tree/master/Contrib/pzc This code can build model from chembl activity data set with given accession number as a query. I had interest the code however, the code is old. So itContinue reading “Modify version of RDKit/Contrib/pzc #chemoinformatics #RDKit #ChEMBL #pychembldb”

Useful package for users who love chemoinformatics and google colab #chemoinformatics #RDKit #make_env

This post is really short but I think it’s useful who uses google colab. Google colab is useful but it’s difficult to install rdkit and any conda packages in to its env. But if you use condacolab, you can build chemoinformatics env very easily. After installing the condacolab in to the notebook, any packages canContinue reading “Useful package for users who love chemoinformatics and google colab #chemoinformatics #RDKit #make_env”

How different energy between unbound and bound conformation of molecules? #memo #journal #JCIM

As we know that, ligand conformation is very important factor of drug design and also it’s difficult to predict binding pose of ligand. So ligand conformational strain energy(LCSE) is very important factor. In the LBDD, we can’t know ligand binding pose so, CompChemists try to generate 3D conformation with several ligand based techniques such asContinue reading “How different energy between unbound and bound conformation of molecules? #memo #journal #JCIM”

Make SMILES with atomic information #RDKit #chemoinformatics

SMILES is widely used in chemoinformatics area due to its small datasize and easy to handle it in compound generation etc. However SMILES string can’t keep many kinds of atomic information except of chirality, charge, atom_mapping number. ChemAxon developed Extended SMILES strings named CXSMILES. The details are described following URL.https://docs.chemaxon.com/display/docs/chemaxon-extended-smiles-and-smarts-cxsmiles-and-cxsmarts.md And recent version of rdkitContinue reading “Make SMILES with atomic information #RDKit #chemoinformatics”