UPDATE: Be sure to check out the follow-up to this post if you want to improve the model: Learn how to improve SMILES based molecular autoencoders with
SMILES enumeration and vectorization for Keras
The SMILES enumeration code at GitHub has been revamped and revised into an object for easier use. It can work in conjunction with a SMILES iterator object
Learn how to teach your computer to "See" Chemistry: Free Chemception models with RDKit and Keras
The film Inception with Leonardo Di Caprio is about dreams in dreams, and gave rise to the meme “We need to go deeper”. The title has also
Cheminformatics in Excel part 2: RDKit4Excel
Previously I wrote about how to use the xlwings project to get RDKit functionality directly in Excel. Well, it wasn’t that directly as there were some intermediate
Cheminformatics in Excel: linking RDKit with Xlwings
Excel is widely used in businesses all over the world and can be used for many diverse tasks due to the flexibility of the program. I’ve been
Can children fold proteins?
Can children fold proteins? During the summer holidays I volunteered to hold a workshop about protein folding at the summer camp for Gifted Children Denmark. The idea
Programming a simple molecular GUI browser with model-view architecture (MVC) using Python with PySide or PyQt and RDKit
One of the more popular blog post based on monthly visitors is the old Create a Simple Object Oriented GUIDE GUI in MatLAB, but since I don’t
Better Deep Learning Neural Networks with SMILES Enumeration of Molecular Data
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
Tune your deep tox neural network with free tools
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
A deep Tox21 neural network with RDKit and Keras
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