Skip to content

Cheminformania

  • Blog
  • About
    • About Cheminformania
    • Esben Jannik Bjerrum
  • Blog
  • About
    • About Cheminformania
    • Esben Jannik Bjerrum

Building a simple QSAR model using a feed forward neural network in PyTorch

Esbenbjerrum/ May 1, 2020

In my previous blogposts I’ve entirely been using Keras for my neural networks. Keras as a stand-alone is now no longer active developed, but are instead now

Read More

Never do these mistakes when comparing regression models

Esbenbjerrum/ August 25, 2019

Some time ago I stumbled upon some work by Patrick Walters which shows that correlation coefficients have a rather large standard error when the sample sets sizes

Read More

SMILES enumeration and vectorization for Keras

Esben Jannik Bjerrum/ December 1, 2017

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

Read More

Peeking into the chemical space using free tools

Esben Jannik Bjerrum/ December 19, 2016

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

Read More

Search

Search for:

Recent Comments

  1. esbenbjerrum on A deep Tox21 neural network with RDKit and KerasJanuary 22, 2025

    Yes, it's a single-task network. For a multi-task network, you would need to increase the number of output-neurons to fit…

  2. Elon on A deep Tox21 neural network with RDKit and KerasJanuary 20, 2025

    If I understand correctly, it seems you have used a single-label approach 'SR-MMP' instead of a multi layer approach using…

  3. esbenbjerrum on Generating Unusual Molecules with Genetic AlgorithmsNovember 24, 2024

    Yes, of course that is possible;-) I wrote a follow-up blogpost using molecular log-likelihood estimation to accomplish just that Generating…

Popular Pages

  • Never do this mistake when using Feature Selection
  • rdEditor: An open-source molecular editor based using Python, PySide2 and RDKit
  • A deeper look into chemical space with neural autoencoders
  • The Good, the Bad and the Ugly RDKit molecules
  • Non-conditional De Novo molecular Generation with Transformer Encoders

Tags

AI AI drug discovery Autodock Vina autoencoders benchmarking Chemception chemical deep learning Cheminformatics CNNs computational chemistry Computational Creativity Cross Docking Deep Learning de novo design docking Drug Discovery GUI Heteroencoders Inverse QSAR ipywidgets Jupyter Keras Ligand Docking Long short term memory Machine Learning molecule generation Molecules Neural Networks Optimization PCA Python Pytorch QSAR RDKit rDock Reaction Prediction recurrent neural networks sklearn SMILES generation Spectroscopy Theano Transformers Tuning vina xlwings

The software is provided “as is”, without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose and non-infringement. In no event shall the authors or copyright holders be liable for any claim, damages or other liability, whether in an action of contract, tort or otherwise, arising from, out of or in connection with the software or the use or other dealings in the software.

Mastodon

© Esben Jannik Bjerrum, 2015-2019. Unauthorized use and/or duplication of this material without express and written permission from this site’s author and/or owner is strictly prohibited. Excerpts and links may be used, provided that full and clear credit is given to Esben Jannik Bjerrum and Cheminformania/Wildcardconsulting.dk with appropriate and specific direction to the original content.

Search

Search for:
https://www.youtube.com/watch?v=bvgz1CUzTYs
2015 - 2022 © Powered by Theme Vision.