Rotate molecule and visualize it #RDKit #Chemoinformatics

Some days ago, I found an interesting question in rdkit mailing list. The question is how to rotate molecule around an axis. I do not have any idea to do it. But RDKit has a function to do it. I read API and try to do it. rdMolTransforms.TransformConformer function can rotate molecue with transform matrix.Continue reading “Rotate molecule and visualize it #RDKit #Chemoinformatics”

Advertisement

Memo

Recently I transferred to the computational chemistry team from the medicinal chemistry team. And now I’m busy…. So the blog update frequency slow down now. But I would like to write new post soon..

東海ブロックジュニアドッジボール選手権 #Dodgeball

今日はエコパアリーナで開催される東海ブロックジュニアドッジボール選手権の応援に行ってきました。ジュニアドッジボールとは小学4年生までの子供達で編成されるチームによる競技ドッジです。チームにより4年が多いところや、まだ2、3年生が中心のチームがあったりするので結構デコボコしている感じはあるのですが競合はやはりどこもパス回しも、アタックも強烈です。 長男が所属しているチームは残念ながら今回は予選敗退となってしまいました。現4年生はこの選手権と次の桜杯がジュニアとして出られる最後の試合になります。全力を出しきりオフィシャルへ進んで欲しいものです。 予選で敗退してしまったものの、長男は高学年の球も頑張ってキャッチして自信をつけてきました。投げる球もだいぶ早くなってきましたしこれからも色々壁にぶつかるだろうけどへこたれずに頑張って欲しいと思います。 一年から始めた競技ドッジ。最初は強い球が取れず泣いたりすることが多かったですが、試合に起用して頂き、そこでキャッチできたり、色々経験してだんだん自信をつけてきたようです。小学生でエコパアリーナ、このはなアリーナなどの大きな体育館で大勢の観客のいる前でプレーできる機会なんてなかなかないと思います。これからも貪欲に練習して成長して欲しいなと思っています。まあ勉強はボロボロですがね、、、 レベルの高いチームと比べるとまだまだ課題もある気がしますが、これからもっともっと伸びていけるチームだと思います。今日の結果はしっかりと受け止め、次に向かってまた楽しく練習して強いチームになって欲しいです! 次の桜杯は私も審判で出る予定なのでもう長男の試合をゆっくり応援はできないかな。w

Make interactive dashboard with Dash2 #chemoinformatcs #RDKit

Still I am playing with dash. And I would like to write document about py4chemoinfomatics in this weekend (tonight). Before I posted about how to make interactive 2D plot with Dash. And today I added file up loader and structure renderer to the code. All code can find following URL.https://github.com/iwatobipen/chemo_dash For usage in closed environment,Continue reading “Make interactive dashboard with Dash2 #chemoinformatcs #RDKit”

Make interactive dashboard with Dash #chemoinformatcs #RDKit

I am happy that I could have fruitful discussions in mishima.syk #13 held on last Saturday.And I knew the new package for data visualization named dash.From the document, dash can provide interactive dashboard for data analysis. I read the documents and wrote sample code. Following code provides 2D scatter plot with two descriptors which areContinue reading “Make interactive dashboard with Dash #chemoinformatcs #RDKit”

Convert fingerprint to numpy array and convert numpy array to fingerprint #RDKit #memorandum

This is just memorandum for my self.RDKit has ConvertToNumpyArray method for converting rdkit fp to numpy array. But there is not direct method for convert numpy array to rdkit fp.However, rdkit has CreateFromBitString method. So, I tried to convert numpy array to rdkit fp with the method. Then convert fp to numpy array. Next convertContinue reading “Convert fingerprint to numpy array and convert numpy array to fingerprint #RDKit #memorandum”

Virtual Screening(VS) with over hundred million compound in a few days! #Chemoinformatics

Recently virtual screening often is used for first screening for drug discovery project. Because it can screen huge amount of compound very fast compared to wet screening. I thought docking score is not reflect binding affinity of ligand and target protein. But today I read interesting article and I changed my mind.The title was ‘Ultra-largeContinue reading “Virtual Screening(VS) with over hundred million compound in a few days! #Chemoinformatics”

3D printing technology for science #memorandum

Recently, 3D printing technology is wildly used in many area not only chemical but also pharmaceutical.Here is a nice review for 3D printing applications. https://www.nature.com/articles/s41570-018-0058-y I know only a little bit about the application of 3D printing for pharmaceutical company, for example micro reactor or labo on tip. Also Cronin group published exciting articles aboutContinue reading “3D printing technology for science #memorandum”

Try GCN QSPR with pytorch based graph library #RDKit #Pytorch #dgl

Recently many machine learning articles use pytorch for their implementation. And I found very attractive package for graph based deep learning, named ‘DGL;Deep Graph Library’. The package supports pytorch and mxnet for backend. The author provides not only package but also very nice documentation. I read the document and try GCN for QSPR with DGL.Continue reading “Try GCN QSPR with pytorch based graph library #RDKit #Pytorch #dgl”