Coloring molecule with RESP charge on pymol #Pymol

To visualize 3D structure of molecule, PyMol is nice tool. What I would like to write on the post is how to visualize calculated RESP charge on pymol ;)One idea is embed calculated RESP charge to b_factor of molecule pdb. PDB file can make easily from rdkit mol object.A problem for me is how toContinue reading “Coloring molecule with RESP charge on pymol #Pymol”

Draw HOMO LUMO with psikit-2 #chemoinformatics

Yesterday I wrote a post about psikit function for HOMO LUMO drawing. And @fmkz__ gave me very suggestive comment. He performed QM calculation about tetrazole and disclosed the its distribution of negative charge. I had interested in his suggestion and I tried it. By using psikit, I calculated energy of acetic acid and 5-methyl-1H-tetrazole andContinue reading “Draw HOMO LUMO with psikit-2 #chemoinformatics”

Draw HOMO LUMO with psikit #RDKit #Psi4 #PyMol

Now I and @fmkz___ are developing a thin wrapper library for Psi4 and RDKit named psikit.Today I added new function for viewing molecular orbital HOMO and LUMO with pymol. Psi4 has the function which can output cube format file of MO named ‘cubeprop’. So I try to implement the function in to psikit.By using theContinue reading “Draw HOMO LUMO with psikit #RDKit #Psi4 #PyMol”

Call Knime from Jupyter notebook! #Chemoinformatics #RDKit #Knime

I read exiting blog post yesterday! URL is below.https://www.knime.com/knime-blog-general@dr_greg_landrum developed very cool tools which can call knime from jupyter notebook and can execute jupyter notebool from knime. Details of the tool is described in the Knime blog post. I am interested the tool and I can’t wait to try it in myself. So I usedContinue reading “Call Knime from Jupyter notebook! #Chemoinformatics #RDKit #Knime”

Alignment free 3D molecular descriptor #Chemoinformatics

3D based QSAR has big challenges, first, conformation and second is alignment of 3D molecules. Major tool for 3D QSAR is ROCS which is developed by OpenEye. It is commercial for industrial. And there are some open source tool kit to do it such as shape-it and rdkit.Recently researcher from AZ and University of SheffieldContinue reading “Alignment free 3D molecular descriptor #Chemoinformatics”

Plot Chemical space with d3js based library #RDKit #Chemoinformatics

Recently I posted making interactive plot on jupyter notebook. https://iwatobipen.wordpress.com/2018/12/09/make-interactive-chemical-space-plot-in-jupyter-notebook-cheminformatics-altair/I used altair for doing it. Today, I used d3js and matplotlib based package to make scatter plot.mlpd3 is another tool for making interactive plot with python.https://mpld3.github.io/index.html In the original site, many examples are provided. It seems easy to make any kinds of plot with tooltip.Continue reading “Plot Chemical space with d3js based library #RDKit #Chemoinformatics”

Generate possible molecules from a dataset #Chemoinformatics #RDKit

Recently @dr_greg_landrum  shared very cool Knime work flow which can enumerate possible molecules from given dataset. You can get the Work flow from following URL.https://workflows.knime.com/knime/hub/workflows/99_Community%3A03_RDKit%3A10_Enumerate_Extra_Patent_CompoundsThis work flow is really useful and elegant. If you have interested in, I recommend to use it!!!And Patrick Walters disclosed nice code for Free-Wilson analysis on github.https://github.com/PatWalters/Free-Wilson Inspired these niceContinue reading “Generate possible molecules from a dataset #Chemoinformatics #RDKit”

Industrial ADME data Sets and Deep Learning #Chemoinformatcs

In pharma, predictive models are widely used such as activity, ADME, phychem and Tox. And recently many articles which use Deep Learning are published. Deep Learning is powerful tool for prediction but it is difficult to find appropriate hyper parameters. Today I read informative article published researcher from Lilly.https://pubs.acs.org/doi/10.1021/acs.jcim.8b00671 They investigated performance of DNN andContinue reading “Industrial ADME data Sets and Deep Learning #Chemoinformatcs”

Visualize pharmacophore with RDKit #RDKit #Pymol #Chemoinformatics

Some years ago, I wrote a post about how to communicate pymol and RDKit. In the post, I demonstrated how to visualize Phamarcophore in rdkit. And recently I got a query about the post and think about more efficient way.What I want to write in the post is new approach to visualize pharmacophore with RDKit.Continue reading “Visualize pharmacophore with RDKit #RDKit #Pymol #Chemoinformatics”

New scalable Flow photo Chemistry Platform New Flow Chemistry Platform #photochemistry #flowchemistry

Recently visible light used organic reaction is attractive area for me. Because it can make difficult bond in short steps under mild reaction conditions.But scale up is difficult because key factor of photo reaction is light. It means photo absorbance is important and so it is difficult to scale up. One approach is Plug FlowContinue reading “New scalable Flow photo Chemistry Platform New Flow Chemistry Platform #photochemistry #flowchemistry”

Cryo-EM data analysis with deep learning #arXiv

Recently number of publications with cryo-EM is growing. And also number of data storage is growing.From EMDB, http://www.ebi.ac.uk/pdbe/emdb/statistics_main.html/I could get following statistics. And now, Cryo-EM is collecting a lot of attention in drug discovery area because the method has possibility of determination for difficult targets that can not accessible to X-ray analysis. I’m not sureContinue reading “Cryo-EM data analysis with deep learning #arXiv”

明けましておめでとうございます

2019年に入りました。2018年後半の指骨折に始まり年末年始のインフルエンザ、インフルエンザ明けの謎の発熱&咳からやっと復活しつつあります。健康の大切さを改めて痛感する年末年始となりました。また、抗インフルエンザ薬を飲み回復が早かったのを実感し、薬を作れる仕事に携われる事は改めて素晴らしいなと思った次第です。 まあ、今年は何はともあれ自己管理を徹底したいです。昨年は業務内容がガラッと変わり自分のやりたいことと、アサイメントが比較的同じベクトルになっていて自分にとって、とても良い年でした。ただチョット自分の興味に突っ込みすぎた部分もあり、もう少し創薬研究をどうやったら加速できるかという部分を強く意識していきたいと思います。また、昨年は出張が多い年でもあり、スケジュール管理の甘さが露呈しました今年はこの辺も意識しよう。 社会人になってから今までを振り返ると、分野のフロント行ってる方と議論できる機会を持てて恵まれてるなって思います。今年も、積極的に外にも目を向けたいなと思います。いやほんと周りはみんな優秀な方ばかりなので勉強たくさんできて感謝感謝です。 で、今年の目標1. Githubにもっとコードあげる Githubでコード管理しておくとあれなんだっけって時に振り返れていいですよね。ということで今まで以上にうまく利用したいと思います。2. 英語 まあコレはもう必須ですよね、、、海外出張行ってディスカッションするにも下手でもいいから話せないことにはなんともなりませんし、、、3. pytorch なんとなく使ったことはあるけどあまり深く勉強はしてなかったので今年はコレでなんか作りたいですね。今まで僕はTensorflowまたはKerasメインでしたので一度Define by runの方も触ってみようと思います4.数学 コレはまあ前からなんですが論文読んで自分で実装できるくらいの素養をつけたい。5.体調管理+体力作り! 最近運動不足で10kmも走ると満足してしまうようになってしまったのでもう一度体鍛えてフルマラソンに挑戦したいですね。。。 つらつらと駄文を書いてしまいましたがまあ今年もぼちぼちやっていこうと思っています。いつも家でパソコンばっかりいじっている私を受け入れてくれる家族に感謝を述べて今日の投稿を終わりにしたいと思います。 皆様にとって今年が昨年以上に良い年になりますように!

Open Source Lilly’s Chemoinformatics Package

In 2012, lilly’s researchers published Lilly-MedChem Rules in J. Med. Chem. and disclosed their code on github. After the publication, the rules are used in many applications, papers and chemoinformatics applications. Open source tool made a big impact on chemoinformatics. Several hours ago I found an interesting tweet from @jcheminf. They reported an algorithm ofContinue reading “Open Source Lilly’s Chemoinformatics Package”

New functionality of psikit #Chemoinformatics #RDKit #Psi4

Happy new year! ‘Akemashite Omedetou Gozaimasu’ in Japanese! I and @kzfm_ -san are developing a library which uses a rdkit & psi4 named psikit. You can find brief introduction the concept following URL.http://blog.kzfmix.com/entry/1536978824 Today I added new function that can calculate RESP charge of give molecule. RESP charge means ‘Restraints for Deriving Atomic Charges’. DetailsContinue reading “New functionality of psikit #Chemoinformatics #RDKit #Psi4”