Look Back at 2018

I started the blog site from Aug. 2012 and changed main language from Japanese to English from 2014. After changing the language, I can find access from many foreign countries. Number of visitors are increasing year by year. In 2018, number of site visitors and page views are two times greater than last year. @_@

Make original sklearn classifier-2 #sklearn #chemoinfo

After posted ‘Make original sklearn classifier’, I could get comment from my follower @yamasaKit_-san and @kzfm-san. (Thanks!) So I checked diversity of models with principal component analysis(PCA).The example is almost same as yesterday but little bit different at last part.Last part of my code is below. Extract feature importances from L1 layer classifiers and mono-random

Make original sklearn classifier #sklearn #chemoinfo

I posted and wrote code about ‘blending’ which is one of the strategy for ensemble learning. But the code had many hard coded part so it was difficult to use in my job. In this post, I tried to make new classification class of sklearn for ensemble learning and test the code. At first, most

Analysis and visualize tool kit for FMO #FMO

I and my daughter got the flu last week and now we are staying in my home…Now I read some articles and found interesting work for FMO.URL is below.https://pubs.acs.org/doi/10.1021/acs.jcim.8b00649FMO means ‘Fragment Molecular Orbital’ that is powerful method for protein-ligand interaction energy calculation. Evotec which is a drug discovery alliance and development partnership company published many

メドケムxAI 創薬化学者の今後は明るいのか? #souyakuAC2018

これは”創薬アドベントカレンダー2018″ 20日目の記事になります。去年もサイエンス色０の駄文を書いたiwatobipenです。今年もエントリーしたもののネタがないなーと思って色々彷徨った結果、論文を紹介しつつ自分の業務周りにフォーカスしようということにしました。（またサイエンスじゃないのかよ！）今回紹介するのはメドケム〜合成メドケムっぽいネタ。まずは、Drug Discovery TodayからMedicinal chemistry in drug discovery in big pharma: past, present and future内容はタイトルの通り、GSKにて長年メドケムをやられてきた著者らによる大手製薬企業（海外）のこれまでとこれからですに関する記事です。論文中のTable1”summary of the topics covered from the past to the present and then the future.”から何個か抜粋してみます。以下の文章のリストは過去＝＞現在＝＞これからの順で書いています。なお、あくまで大きな製薬企業の例なので国内の中規模以下の製薬企業には当てはまらないことも多いと思います。# 合成- ハイスキルの人材がマニュアルで実施- 50％は派遣スタッフや委託- 90％以上は派遣スタッフや委託# 合成反応- 基本的な反応セット- 同じ反応セット＋Pd反応- 現在の反応セット＋CHActivationやBioconversion# テクノロジー- ホットプレートで攪拌、Evap- ＋マイクロ波、パラレル反応キット- ？# Leads- 様々なソースから- Role of 5によるDrug like（経口投与を意識した）な構造から- Role of 5を超えたスペース、様々な投与経路# Compounds design and SAR- 論文ベース、暗黙知、経験に基づく試行錯誤- in silicoツールを活用して効率的に進める。- より人がやるよりコンピューターが行うようなり、データを活用した洗練された手法になる。#

Make interactive MMP network with Knime #Knime #chemoinformatics

I posted an example that shows making interactive scatter plot with Knime. And I would like to try MMP network with Knime. I often make network view via python package such as igraph, networkx and py2cytoscape etc. BTW, today I want to learn how to do that on knime. Recent version of Knime is provided

Make interactive plot with Knime #RDKit #Chemoinformatics #Knime

Dalia Goldman provided very cool presentation in RDKit UGM 2018 about Knime. Click to access Goldmann_KNIMEandRDKit.pdf She demonstrated interactive analysis with RDKit knime node and Javascript node. I was really interested but it was difficult to build the workflow by myself at that time. BTW, I need to learn knime for data preparation in this

Make interactive chemical space plot in jupyter notebook #cheminformatics #Altair

I often use seaborn for data visualization. With the library, user can make beautiful visualization. BTW, today I tried to use another library that can make interactive plot in jupyter notebook. Name of the library is ‘altair’. https://altair-viz.github.io/index.html The library can be installed from pip or conda and this package based vega and vega-lite. Vega

Build stacking Classification QSAR model with mlxtend #chemoinformatics #mlxtend #RDKit

I posed about the ML method named ‘blending’ somedays ago. And reader recommended me that how about try to use “mlxtend”. When I learned ensemble learning package in python I had found it but never used. So try to use the library to build model. Mlxtend is easy to install and good document is provided

Change properties of approved oral drugs

When I learned drug discovery long time ago, I read the article about Role of five which is a rule of thumb to evaluate druglikeness. https://www.sciencedirect.com/science/article/pii/S0169409X00001290?via%3Dihub You can read nice review about the druglikess scores in following URL. ( Written in Japanese ;-) ) View at Medium.com By the way, recently there are many articles