Make learning process with human in the loop #optuna #memo #python #rdkit

Many chemofinromaticians have checked Greg’s great blog post which describes how to draw draw molecules in various way. https://greglandrum.github.io/rdkit-blog/posts/2023-05-26-drawing-options-explained.html Rendering molecule doesn’t directly contribute drug design but it’s really importnt for us because medicinal chemists have their own preferences for drawing moleucles such as font size, highlight color etc, etc. It’s too difficult to parametarize

Optimize ML model with few line code #chemoinformatics #ML #RDKit #falcon

Machine learning is democratizing, and there are many great libraries available in Python such as scikit-lean pycaret. Recenlty we can build ML model without writing lots of code. Today I found new package named ‘falcon‘ which can build optimized model few lines. One of the famous package for AutoML is auto-scikitlearn, the package is also

Use jupyternotebook from knime #knime #chemoinformatics #memo

Recently I posted an example to build custom knime node with python. It was a nice experience for me. And I’m still reading knime documentation. Today I tried to use jupyter notebook from knime. There is a good example to do that with workflow and dataset.https://docs.knime.com/latest/python_installation_guide/index.html#jupyter-notebooks The example described avobe reads dataset and do some

Try to use recent version exmol #exmol #rdkit #chemoinformatics

Previously I wrote blog post about ‘exmol’ which is useful package for ML related task. Examol is developed by Andrew White. I installed it almost 2 years ago and Didn’t check the update, recently I found new verson of exmol is released and new versoin have new functions. Following code is bollowed from original documentation

Develop new knime node with python #chemoinformatics #knime

The Golden Week is a collection of four national holidays within seven days. My kid graduated the elementary school and his favorite dodgeball team and he joined vollyball team. I quit coaching the dodgeball team at same time. So I have time for coding and drinking beer again ;) I watched knime summit about new

Run Knime workflow without GUI #chemoinfo #knime #RDKit

I enjoyed knime summit last week. I could learn lots of useful features of new version of Knime (ver5). Knime is useful tool for chemoinformatics but I mainly write code with python so I’m not heavy user of knime but recently I’m interested in Knime and learning to apply it in my projects. As reader

Visualize MMP data with OSS webapp! #chemoinformatics #rdkit #mmpdb

Matched molecular pairs (MMPs) are old but still useful approach for not only retrospective analysis but also forward compound design. As many chemoinformatitians know that mmpdb is the one of famous MMP CLI tool. I like tha package because it’s easy to make own MMP db. However mmpdb doesn’t have visualization tool for chemists. So

Can LLM understand Chemistry? #memo #journal #JCIM

Recently we can use LLMs(Large langues models) such as ChatGPT. And they return(make) plausible answer against questions. There are lots of chat bot systems have been used in many services but the use cases are limited. LLMs seem be really powerful tools not only general task but also life science. So many people try to

Run RDKit task in parallel #rdkit #chemoinformatics

Recently we can get huge amout of molecules and can use it for drug discovery tasks. It’s really good news however, we need computational resources more and more… When I wrote code for chemoinformatics task with python, ‘for loop’ approach is often used. But it is straight way, it’s not so efficient. Long time ago,

Make QSAR model with PyG and pytorch2.0 #RDKit #Chemoinfo

Recently, I updated version of pytorch on my env from 1.x to 2.0. I think it’s worth to update because, original site says…. PYTORCH 2.X: FASTER, MORE PYTHONIC AND AS DYNAMIC AS EVER Today, we announce torch.compile, a feature that pushes PyTorch performance to new heights and starts the move for parts of PyTorch from C++

Make multi target predictive model for Knime #RDKit #Knime #DeepLearning

I participated my kid’s elemenary school graduation ceremony today. It was nice ceremony. …Time pasts very fast ;) In the season in Japan is very good. Beautiful cherry blossoms start to bloom. It’s good time to start anything ;-) I would like to say thank to my kid. BTW, recently chembl ver32 was released. As

Calculate atomic property with new chemoinformatics package♪ #RDKit #Jazzy

It have been long time since my last post ;) Now we are in Feburary… I hope every reader have nice start of this year. I’m enjoying my day but really busy. This is the first post of the year! Thinking the strength of hydrogen donoer and acceptor is important for drug design but difficult

Calculate similarity of popular bioisosters #RDKit #espsim #memo

It will take 3 years after changing job. Fortunately, I’m still working at early drug discovery field as chemoinformatician ;) As many drug hunter know that bioisosteric replacement is one of the major way for designing novel molecules from known biologically active molecules. Transformations from carboxylic acid to tetorazole, from amide to oxazole are major

Make pptx file from Python #chemoinformatics #memo #python-pptx

I hope all reader enjoying chemoinformatics ;)Unfortunately I’m struggling to make PPTX file in this year. So I can’t have enought time to coding. But It’s same for medicinal chemists. Because they often make presentation slide for project team, theier boss, senior etc…. They transfer SAR data from spread sheet to pptx. Sometime it seems

CLI tool for making ssslib #chemoinformatics #rdkit

As many RDKitter know that rdSubstructLibrary is one of the cool tool for conductiong substructure search. Greg Landrum introduced how to use it in his great blog post. I love the method because it works very fast for substructure searching. So I would like to make CLI tool for making substructure library database. To do

Use mmpdblib on jupyter notebook #rdkit #mmpdb #chemoinformatics

I introduced MMPDB v3 few days ago. The package is CLI tool. So user can do MMPA by typing command line. However the tool doesn’t provide API interface. I think, if we can use MMPDB on jupyter-notebook it’ll be more useful because output data can be used directly in coding process. MMPDB Cli interface is

Let’s use mmpdb v3 #memo #rdkit #chemoinformatics

Matched molecular pair (MMP) is not AI based compound design method however it’s still useful and powerful approach to do compound design. MMPDB is one of the cool package for MMP analysis. And Andrew who is developer of MMPDB preseted new version of MMPDB at RDKit UGM 2022. Version 3 is still developing state but

Embed mols2grid to web page #mols2grid #RDKit #webapp

I often use flask for my web app development because the package is light weight web framework and easy to write. BTW rendering molecules as grid image is easy in jupyter notebook by using RDKit’s Draw.MolsToGridImage function. And also recently developed package named mols2grid is really cool for rendering molecules on jupyter notebook. mols2grid generaetes

FW analysis make easily with rdkit contrib FW package #rdkit #chemoinformatics #memo

Last week I enjoyed RDKit UGM 2022. It was really great and exciting evenif I participated there from online. I hope I could participate RDKIT UGM 2023 locally ;) As you know RDKit is one of the useful OSS package for chemoinformatician. It has nice community and be developed actively. I respect the community and

Make chemoinformatics coding more easily ! #RDKit #datamol

I love RDKit because it supports lots of chemoinformatics features and it is supported top level scientific community. But for eary chemoinformacian, it’s required to learn python or C++ to write chemoinformatics code. As you know, Knime is good option for no-code chemoinformtatics. And another option for beginner is good wrapper of rdkit Recently the