It's a bit of nodes but Keras freeze layer in the top middle is everything here. I retrained last layer like this. Is this meaningful???Maybe not, I mean it didn't make the score any good nor bad. Looking at this KNIME blog post https://ww…

I realized I didn't do this before but do tend to do this to see the tree. So here is the simple workflow. So Simple and GUI by KNIME. and the result Yes, too many data points. But wanted to see how much time it takes to calculate this.600…

I occasionaly come across a situation wanting to change string by rules. So rule engine is what I use like 0 => Low, 1=> Mid, 2=> High and so on. Another one is column expression where I can modify in one go. Not a main nodes but tend to u…

本屋さんでこんな本を発見 https://www.amazon.co.jp/dp/4798157554/ref=cm_sw_em_r_mt_dp_U_gb2ADbKRSEFBN ディープラーニング検定なんてあるんだ…気になるので本を買ってみました。 内容はディープラーニングの歴史、手法、応用分野など。ディープラーニン…

in previous post I made Neural Network like workflow. I was wondering how to add descriptors as an input, so I tried it too. It was VERY easy... I thought I would have more trouble doing this. So, I added descriptors, normalizer, collect c…

KNIME 4.0.1 was released few days ago. https://www.knime.com/changelog-v40 hmmm... lots of bug fixes as I would imagine for 4.0.1. I like this enhancement though AP-12119: Copy&Paste of workflow from Hub AP-12001: UI improvements to the me…

Sometimes you want to see which factors are influencing the most. One very typical way is to use random forest and feature extract so lets see that in KNIME. I first got to know how to use this Tree Ensemble learner to extract feature impo…

What I always wanted... That's what I'm talking about!! Thanks to L. Jonsson so much!! so let't DO IT! The workflow is just like the PCA example I posted earlier BUT the result is so different! coz it's t-SNE... marvellous... just fantasti…

Finally had a time to play with KNIME keras integration. But didn't know how to use them at all so took a parts from 09_Wide_and_Deep_Learning_on_Census_Dataset which is up on EXAMPLES. So here it is I calculated ECFP and MACCS for fun thi…

Haven't been updating for a while and KNIME was upgraded to 4.0.0!! Must play with this then. So gonna play first with Bayesian Optimization new in 4.0.0 Parameter Optimization placement in the workflow is the same but I'm playing with SVM…

So, it's good that I can analyze chemical space but where is my molecules of interest in there? Simple way is to color and size by additional column like "MINE". At the bottom of this pic, I made "color vals" and "size vals" to mine column…

Time to try SOM in KNIME now... So, what I did File Reader: Reads csvRDKit Fingerprint: ECFP4Expand Bit Vector: into columnsColumn Filter: to delete all 0 valuesPCA: to speed up the processSOM: SOM by defaultCluster Assigner: assigns clust…

Why didn't I do this from first time... So let's recall, this is from Random Forest and this from SVM and lastly from XGBoost So, XGBoost gave the best accuracy, for a contest here. But I guess it's all about how you use the model. SVM may…

Move onto doing random forest because SVM wasn't so good (at this case! not always!!). And I won't bother tuning parameters for SVM too. File Reader: Read csv Column Filter: Delete unnecessary columns RDKit Fingerprint: Morgan FP as always…

Having good fun with clustering analysis, gonna move to doing some machine learning. Again, so simple to do so with KNIME. File Reader: Reads csv Column Filter: Remove unnecessary columns RDKit Fingerpring: Rocks! Expand Bit Vector: Do I n…

What's the BEST method to interpret molecules so that computer can understand. I know this sentence itself is somewhat... BUT this is what I would like to do. Isn't this what we all want to do!? Well, so far in 2019, April, I would say ECF…

Bit of modification to previous post to k-means cluster the chemicals. So these nodes are from previous workflow... File Reader: Read csv file Column Filter: Filter out non-SMILES paramters RDKit Descriptor Calculation: Used All Descriptor…

So, a simple workflow but does it's job. File Reader: Read csv file Column Filter: Filter out non-SMILES paramters RDKit Descriptor Calculation: Used All Descriptors!!!! Normalizer: Gaussian (but 0 to 1 could be good too) PCA: Into 3 Dimen…

I don't like programming, but I do want to QSAR at home. Then came across KNIME. https://www.knime.com/ Looks really cool so decided to leave posts here with what I can do at home using KNIME and sample data available from internet. gonna …