Haven't been updating for a while, but made conformal prediction up and running. while making this flow, found a part of KNIME which was quite difficult to overcome Loop in another loop made a same name flow variable. In this case "iterati…

There are many ways to select features for the model calculation. Previously I posted using randome forest importance. hateknime.hatenablog.com This time I used the "Feature Selection Loop". Using this loop, you can Forward select, Backwar…

In many cases, you'd have objective values being missing. That is, there are Yes and No values but also 'I don't know' values (hence null). But following the trend of neural network and deep learning, I wanted to do multi-task learning to …

Previously I had a first trial of doing R-group analysis using KNIME and got a nice table. hateknime.hatenablog.com But didn't try into detail about viewing this using KNIME because I didn't know how to transfer SMILES into nice images to …

Ok, stay home, play around from home...NO DATASET TO TRAIN!!! AHHHHH!!!! Then comes the nice deepchem dataset with variety of sample dataset. Or there is Binding DB and so on.https://github.com/deepchem/deepchem#citing-deepchemhttp://www.b…

Previously I posted active learning example. hateknime.hatenablog.com and did say I'm going to try with density label so here it is. Took a while with all sorts of problems but I had it in the end. I plotted what happens with AMES dataset.…

I posted making Random Forest, XGBoost, SVM Models previously. hateknime.hatenablog.com So how about combining them all together. Here is what I did. Top part is all learning part that can be copy and pasted from previous posts. I added sa…

Recently, I read this articlehttps://medium.com/pytorch/active-transfer-learning-with-pytorch-71ed889f08c1 Active transfer learning looked fun and do-able using KNIME too. SO had a play around with KNIME workflow and got this. Learns the p…

Had a play around with KNIME DB this time. Downloaded sqlite ChEMBL database from ChEMBL homepage. Then connected and made this simple sampling workflow. All you need to do is unzip the ChEMBL sqlite file and set the Connector node almost …

Second post of today but I though I would separte. Glancing through ChEMLB DB homepage and blogs for previous post guided me to this article. http://chembl.blogspot.com/2020/01/new-chembl-ligand-based-target.html which led me to... https:/…

Yesterday, I wondered ChEMBL all MMP is possible or not. It sure can be done but very brute force in KNIME and my home PC??? I don't think so, but where is the bottleneck? So I tried this for fun. Downloaded SDF because I didn't even want …

One day, I checked my favourite nodes group, of course, RDKit nodes and found RDKit R-Group Decomposition was (Deprecated, sayonara, ofuko-su) and another node with same name was there. OK, super excited because what I wanted was to show w…

This is basically from https://hub.knime.com/knime/spaces/Examples/latest/03_Visualization/02_JavaScript/13_Binary_Classification_Inspector which again was so educational, useful and fun! All I did was train by each learners (and using def…

OK, been playing around with active loop learn for while. This page https://hub.knime.com/knime/spaces/Examples/latest/04_Analytics/12_Active_Learning/03_Active_Learning_Uncertainty_Sampling was very useful for studying for uncertainty sco…

There are lots of if and case nodes in KNIME but too many to remember so I use Java If and write my one most of times. Very easy right? This allows to do any if-ing.

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…