Blog

The Blog is a collection of News, Blog posts, technical tips and tricks and other writings from my sphere of interest.
- Esben Jannik Bjerrum

May

A few weeks ago I completed the 16 week "Neural Networks for Machine Learning" on-line course from University of Montreal to deepen my understanding of Artificial Neural Networks and their fascinating properties. The course is taught by Professor, Geoffrey Hinton, which is one of the grand old men in ...

May

I was recently contacted by Gaurav Chaudhary, who is the CEO of Roots Analysis,  a firm that provide market research and consulting for the pharmaceutical industry. It turns out that Wildcard Pharmaceutical Consulting was mentioned in their report: Deep Learning in Drug Discovery and Diagnostics, 2017 ...

Mar

The process of expanding an otherwise limited dataset in order to more efficiently train a neural network is known as Data Augmentation For images there have been used a variety of techniques, such as flipping, rotation, sub-segmenting and cropping, zooming. The mirror image of a cat is ...

Mar

Deep Neural Networks and Spectroscopic Data - a chemometric study A Masters project is available in a collaboration between Wildcard Pharmaceutical Consulting and Department of Food, Spectroscopy and Chemometrics, KU. We are looking for a motivated student with interest in spectroscopy and computer programming to take on a project involving ...

Mar

Medico Bazar 2017

Yesterday, Wildcard had a stand at the Medico Bazar 2017 at the Danish Technical University (DTU) in Lyngby. Medico Bazar brings together researchers, startups, investors and businesses in the medical device field. Although Wildcard is more focused on chemical and biological data, there seem to be a lot of interest in machine learning technologies, which led to a ...

Mar

Congratulations to Nadia Lund

Yesterday I had the pleasure to be external examiner at Nadia Lunds Master thesis defense. She delivered a brilliant and clear presentation of her project entitled "GPCR Structural Switches Stabilizing Specific States and Signals", where she had developed and used a sequence signature method to identify potential amino acid residues which are most likely involved in the GPCR G-Protein ...

Feb

In another blog post I demonstrated how to build a deep neural network with Keras in Python to model some toxicity dataset from the Tox21 challenge. The network was however not systematically optimized, but merely put together with a few manually selected hyper parameters. Hyper parameters are understood as the parameters which are not tuned by the data ...

Feb

New option to follow comments

A new Wordpress plugin has been installed, which enables commenters to get notified when additional comments or replys are added to the blog posts. This did only work before for registered users of the Wordpress, such as writers and admins. This was rather unfortunate. But now it is not necessary to ...

Jan

I found some interesting toxicology datasets from the Tox21 challenge, and wanted to see if it was possible to build a toxicology predictor using a deep neural network. I don't know how many layers a neural network actually has to have to be called "deep", but its a buzz word, so ...

Jan

In the last blogpost the battle tested principal components analysis (PCA) was used as a dimensionality reduction tool. This time we'll take a deeper look into chemical space by using a deep learning neural autoencoder, by testing some of the newer tools based on neural networks which has shown promising results. ...

Dec

As covered before, chemical space is huge. So it could be nice if this multidimensional molecular space could be reduced and visualized to get an idea about where how query molecules relate to one another. This small tutorial show a simple example of how this could be done with the PCA decomposition from scikit-learn and molecular fingerprints calculated with ...

Dec

Neural networks are interesting models underlying much of the newest AI applications and algorithms. Recent advances in training algorithms and GPU enabled code together with publicly available highly efficient libraries such as Google's Tensorflow or Theano makes them highly interesting for modelling molecular data. Here I explore the high level Neural Network ...

Nov

I had the pleasure and opportunity to pitch for 5 minutes at the first Meet and Greet meeting at COBIS. Its an new, regular internal event for all the companies there, where we meet and network over a cup of coffee and a croissant. I was lucky to be one of the three that got the permission to pitch and ...

Nov

Neural Networks are interesting algorithms, but sometimes also a bit spooky. In this blog post I explore the possibilities for teaching the neural networks to generate completely novel drug like molecules. I have experimented for some time with recurrent neural networks with the LSTM architecture. In short, recurrent neural networks differ from more traditional feed forward neural networks because they do ...

Nov

Pay it forward

I have volunteered as a Mentor in the Mentor-Mentee network arranged by PharmaDanmark. The idea is to match up young professionals with more experienced seniors for professional sparring and discussion focusing on promoting the Mentees career. Pharmadanmark provided an extensive guide for a successful meetings and  including many suggestions and practical tools ...

Nov

BioAgora 2016

Wildcard Pharmaceutical Consulting was represented at the Bioagora2016 at Frederiksberg Campus centered about biomarkers. Read more about the event at bioagora.dk

Oct

RDKit UGM 2016

I'm looking forward for the first to attend the RDKit user group meeting from 26-28 October 2016 in Basel, Switzerland. RDKit is an open source chemoinformatics toolkit written in c++ with python bindings and extensions. Additionally, it has a database cartridge, which makes it quite useful for handling chemical information and storage ...

Oct

Inspired by the success reported in my last blog post [Link] about the open source docking program rDock [http://rdock.sourceforge.net], I decided to investigate the docking accuracy performance of rDock more in depth. Once upon a time in the west the commercial docking program GOLD was benchmarked with two ...

Sep

Last time i tested the basics of the docking program rDock; Installation, basic setup and docking, as well as had a brief walkthrough about how to post-process the results with the rDock SD file utilities. However, as I've covered before, you should never use re-docking as an estimation of ...

Sep

rDock is an open source docking program, trying to solve the same kind of scientific questions as Autodock Vina, which I have covered in a couple of earlier blogposts. It was open sourced in 2012, but development of the earliest versions dates back to 1998. More details can be ...