Generated by All in One SEO v4.9.5.1, this is an llms.txt file, used by LLMs to index the site.

# Cheminformania

Chemistry and computers

## Sitemaps

- [XML Sitemap](https://www.cheminformania.com/sitemap.xml): Contains all public & indexable URLs for this website.

## Posts

- [pdChemChain - linking up chemistry processing, easily!](https://www.cheminformania.com/pdchemchain-linking-up-chemistry-processing-easily/) - Pandas dataframes, Chemistry Processing in Chains of reusable links for interactive use in Jupyter. That's pdChemChain!
- [Generating Unusual Molecules with Genetic Algorithms Part 2: Leveraging MolLL for Enhanced Generation](https://www.cheminformania.com/generating-unusual-molecules-with-genetic-algorithms-part-2-leveraging-molll-for-enhanced-generation/)
- [Update to Scikit-Mol: the power of community and open-source](https://www.cheminformania.com/update-to-scikit-mol-the-power-of-community-and-open-source/)
- [Generating Unusual Molecules with Genetic Algorithms](https://www.cheminformania.com/generating-unusual-molecules-with-genetic-algorithms/)
- [rdEditor: An open-source molecular editor based using Python, PySide2 and RDKit](https://www.cheminformania.com/rdeditor-an-open-source-molecular-editor-based-using-python-pyside2-and-rdkit/) - Manipulate RDKit molecules directly using a GUI. A brief walk-through and overview about how a molecular editor can by programmed using open-source toolkits.
- [Scikit-Mol - Easy Embedding of RDKit into Scikit-Learn](https://www.cheminformania.com/scikit-mol-easy-embedding-of-rdkit-into-scikit-learn/)
- [Master your molecule generator: Seq2seq RNN models with SMILES in Keras](https://www.cheminformania.com/master-your-molecule-generator-seq2seq-rnn-models-with-smiles-in-keras/) - Blogpost that illustrates how to implement a seq2seq model with teacher enforcing for modeling chemical properties from SMILES
- [Better Deep Learning Neural Networks with SMILES Enumeration of Molecular Data](https://www.cheminformania.com/smiles-enumeration-as-data-augmentation-for-molecular-neural-networks/) - Blog post regarding using SMILES and SMILES enumeration as data augmentation as direct input to QSAR models based on LSTM cells
- [Non-conditional De Novo molecular Generation with Transformer Encoders](https://www.cheminformania.com/non-conditional-de-novo-molecular-generation-with-transformer-encoders/) - Learn how to use Transformer decoder blocks to de novo generate molecules.
- [Deep Learning Reaction Prediction with PyTorch](https://www.cheminformania.com/deep-learning-reaction-prediction-with-pytorch/)
- [Transformer for Reaction Informatics - utilizing PyTorch Lightning](https://www.cheminformania.com/transformer-for-reaction-informatics-utilizing-pytorch-lightning/) - Learn how to build a Molecular Transformer for Reaction Prediction using Pytorch Lightning
- [Using GraphINVENT to generate novel DRD2 actives](https://www.cheminformania.com/using-graphinvent-to-generate-novel-drd2-actives/) - Molecules are better seen as graphs, rather than SMILES. Learn how to use the power of the graph generative framework GraphINVENT to make drug candidates
- [Building a simple SMILES based QSAR model with LSTM cells in PyTorch](https://www.cheminformania.com/building-a-simple-smiles-based-qsar-model-with-lstm-cells-in-pytorch/) - Learn how to build a simple SMILES based QSAR model in PyTorch using LSTM cells.
- [Building a simple QSAR model using a feed forward neural network in PyTorch](https://www.cheminformania.com/building-a-simple-qsar-model-using-a-feed-forward-neural-network-in-pytorch/) - Using a public molecular dataset for a serotine transporter a simple feed forward neural network is constructed using pytorch and trained.
- [Master your molecule generator 2. Direct steering of conditional recurrent neural networks (cRNNs)](https://www.cheminformania.com/master-your-molecule-generator-2-direct-steering-of-conditional-recurrent-neural-networks-crnns/) - Small tutorial showing how to use the Deep Drug Coder and a pretrained model to generate novel molecules with pre specified properties.
- [Learn how to make a jupyter notebook widget for annotation of atom properties](https://www.cheminformania.com/learn-how-to-make-a-jupyter-notebook-widget-for-annotation-of-atom-properties/) - A small GUI tool for annotating atom properties are built using ipywidgets and RDKit
- [Never do these mistakes when comparing regression models](https://www.cheminformania.com/never-do-these-mistakes-when-comparing-regression-models/) - Learn how to estimate uncertainties on correlation coefficient and why you should keep your validation and test sets fixed when comparing different machine learning models.
- [New Site](https://www.cheminformania.com/new-site/) - The site theme and pages has been updated to reflect the new status.
- [Learn how to teach your computer to "See" Chemistry: Free Chemception models with RDKit and Keras](https://www.cheminformania.com/learn-how-to-teach-your-computer-to-see-chemistry-free-chemception-models-with-rdkit-and-keras/) - Learn how to teach your computer to "See" Chemistry: Free Deep Learning Chemception QSAR models with RDKit and Keras
- [Learn how to improve SMILES based molecular autoencoders with heteroencoders](https://www.cheminformania.com/learn-how-to-improve-smiles-based-molecular-autoencoders-with-heteroencoders/) - Using Chemical Heteroencoders gives a more relevant latent vector space, better QSAR models and more creative molecular de-novo generation
- [Deep Chemometrics: Deep Learning for Spectroscopy](https://www.cheminformania.com/deep-chemometrics-deep-learning-for-spectroscopy/) - Surprising findings by applying deep learning in the form of Convolutional neural networks to a NIR spectroscopical pharmaceutical tablet dataset
- [SMILES enumeration and vectorization for Keras](https://www.cheminformania.com/smiles-enumeration-and-vectorization-for-keras/) - A SMILES iterator object that give on-the-fly enumeration and vectorization for training of SMILES based Recurrent Neural Network (RNN) models of molecules for Keras.
- [Cheminformatics in Excel part 2: RDKit4Excel](https://www.cheminformania.com/cheminformatics-in-excel-part-2-rdkit4excel/)
- [Cheminformatics in Excel: linking RDKit with Xlwings](https://www.cheminformania.com/cheminformatics-in-excel-linking-rdkit-with-xlwings/)
- [Can children fold proteins?](https://www.cheminformania.com/can-children-fold-proteins/)
- [Programming a simple molecular GUI browser with model-view architecture (MVC) using Python with PySide or PyQt and RDKit](https://www.cheminformania.com/rdkit-gui-browser-with-mvc-using-pyside/) - Learn how to program a simple RDKit based molecular browser with an extensible Model-View-Controller MVC architecture
- [Tune your deep tox neural network with free tools](https://www.cheminformania.com/tune-your-deep-tox-neural-network-with-free-tools/) - Short tutorial on how to tune the hyper parameters of a Keras deep neural network model with Bayesian Optimization with Gaussian Processes through GPyOpt
- [A deep Tox21 neural network with RDKit and Keras](https://www.cheminformania.com/a-deep-tox21-neural-network-with-rdkit-and-keras/) - Simple example of how to build a toxicology predictor with deep neural networks using free tools and public datasets.
- [A deeper look into chemical space with neural autoencoders](https://www.cheminformania.com/a-deeper-look-into-chemical-space-with-neural-autoencoders/) - Small testurial of keras-molecules and investigation of high information kompression of molecules encoded with SMILES strings
- [Peeking into the chemical space using free tools](https://www.cheminformania.com/peeking-into-the-chemical-space-using-free-tools/) - Plotting and visualization of Chemical using RDkit and PCA from Scikit-learn
- [Molecular neural network models with RDKit and Keras in Python](https://www.cheminformania.com/molecular-neural-network-models-with-rdkit-and-keras-in-python/) - Small tutotoral showing how a molecular QSPR predictor can be built with a neural network made with Keras/Theano using molecular descriptors calculated with RDKIT
- [Teaching Computers Molecular Creativity](https://www.cheminformania.com/teaching-computers-molecular-creativity/) - Computers can be turned into creative drug designers by the use of recurrent neural networks. Generating suggestions for novel DHFR inhibitors.
- [RDKit UGM 2016](https://www.cheminformania.com/rdkit-ugm-2016/) - Wildcard will be represented at the RDkit UGM 2016.
- [Wildcard scoring function beaten by rDock!](https://www.cheminformania.com/wildcard-scoring-function-beaten-by-rdock/) - ranking of two open source docking programs, rDock and Smina, and four scoring functions by their cross docking performance using the Astex non native set.
- [Cross docking test with rDock](https://www.cheminformania.com/cross-docking-test-with-rdock/) - Short tutorial and report of the results of a cross docking experiment using the open source docking program rDock
- [Test drivin' rDock](https://www.cheminformania.com/test-drivin-rdock/) - Test docking using PDBid 1OYT and rDock docking program.
- [Machine Learning optimization of Smina cross docking accuracy](https://www.cheminformania.com/machine-learning-optimization-of-smina-cross-docking-accuracy/) - Short tutorial on how to Smina with custom parameters optimized for cross-docking.
- [Never use re-docking for estimation of docking accuracy](https://www.cheminformania.com/never-use-re-docking-for-estimation-of-docking-accuracy/) - Short tutorial showing how to use cross docking evaluation with Smina or Autodock vina.
- [Ligand docking with Smina](https://www.cheminformania.com/ligand-docking-with-smina/)
- [How to solve problems with coordinate bonds in Rdkit](https://www.cheminformania.com/how-to-solve-problems-with-coordinate-bonds-in-rdkit/) - Patch for RDKit to enable load and save of coordinate and hydrogen bond types in molfile v3000 format
- [Learn how to map a simple Ames mutagenicity model to molecular features using RDkit.](https://www.cheminformania.com/learn-how-to-map-a-simple-ames-mutagenicity-model-to-molecular-features-using-rdkit/)
- [Learn how to hack RDKit to handle peptides with pseudo atoms](https://www.cheminformania.com/learn-how-to-hack-rdkit-to-handle-peptides-with-pseudo-atoms/) - Handle peptides and proteins in RDKit with support for Pseudo atoms. The small tutorial shows how to modify the source code and test out the capabilities
- [Never do this mistake when using Feature Selection](https://www.cheminformania.com/never-do-this-mistake-when-using-feature-selection/)
- [Safer fitting through regularization](https://www.cheminformania.com/safer-fitting-through-regularization/)
- [Wash that gold: Modelling solubility with Molecular fingerprints....](https://www.cheminformania.com/wash-that-gold-modelling-solubility-with-molecular-fingerprints/)
- [Fetch the Sherif! I found a fingerprint!](https://www.cheminformania.com/fetch-the-sherif-i-found-a-fingerprint/)
- [The Good, the Bad and the Ugly RDKit molecules](https://www.cheminformania.com/the-good-the-bad-and-the-ugly-rdkit-molecules/)
- [Scripting Molecular Mechanics Calculations using Tinker and sdf2xyz2sdf](https://www.cheminformania.com/scripting-molecular-mechanics-calculations-using-tinker-and-sdf2xyz2sdf/)
- [Create a Simple Object Oriented GUIDE GUI in MatLAB](https://www.cheminformania.com/object-oriented-gui-programming-with-matlab/)

## Pages

- [Cheminformania Consulting](https://www.cheminformania.com/cheminformania-consulting/)
- [Esben Jannik Bjerrum](https://www.cheminformania.com/about/esben-jannik-bjerrum/) - Esben Jannik Bjerrum - Contact Information
- [Contact](https://www.cheminformania.com/contact/)
- [Cookie Policy](https://www.cheminformania.com/cookie-policy/)
- [Fulgur MATLAB GUI application for working with near infrared calibration sets](https://www.cheminformania.com/fulgur_matlab_gui_application_for_working_with_near-_infrared_calibration_sets/)

## My Templates

- [Default Kit](https://www.cheminformania.com/?elementor_library=default-kit)

## Categories

- [Uncategorized](https://www.cheminformania.com/category/uncategorized/)
- [Blog](https://www.cheminformania.com/category/blog/)
- [Cheminformatics](https://www.cheminformania.com/category/cheminformatics/)
- [Computational Chemistry](https://www.cheminformania.com/category/computational-chemistry/)
- [Database](https://www.cheminformania.com/category/database/)
- [Deep Chemometrics](https://www.cheminformania.com/category/deep-chemometrics/)
- [docking](https://www.cheminformania.com/category/computational-chemistry/docking/)
- [Excel tips](https://www.cheminformania.com/category/excel-tips/)
- [Machine Learning](https://www.cheminformania.com/category/machine-learning/)
- [Machine Learning and Chemoinformatics](https://www.cheminformania.com/category/chemical-machine-learning/)
- [Matlab](https://www.cheminformania.com/category/matlab-programming/)
- [Neural Network](https://www.cheminformania.com/category/neural-network/)
- [News](https://www.cheminformania.com/category/news/)
- [RDkit](https://www.cheminformania.com/category/rdkit/)
- [rDock](https://www.cheminformania.com/category/computational-chemistry/rdock-computational-chemistry/)
- [Science](https://www.cheminformania.com/category/science/)
- [SMILES enumeration](https://www.cheminformania.com/category/neural-network/smiles-enumeration/)
- [Spectroscopy](https://www.cheminformania.com/category/spectroscopy/)
- [Autodock Vina](https://www.cheminformania.com/category/computational-chemistry/autodock-vina/)
- [PyTorch](https://www.cheminformania.com/category/pytorch/)
- [Graph Neural Network](https://www.cheminformania.com/category/neural-network/graph-neural-network/)
- [Molecular Generation](https://www.cheminformania.com/category/molecular-generation/)
- [Reaction Prediction](https://www.cheminformania.com/category/reaction-prediction/)

## Tags

- [AI](https://www.cheminformania.com/tag/ai/)
- [Autodock Vina](https://www.cheminformania.com/tag/autodock-vina/)
- [autoencoders](https://www.cheminformania.com/tag/autoencoders/)
- [benchmarking](https://www.cheminformania.com/tag/benchmarking/)
- [Chemception](https://www.cheminformania.com/tag/chemception/)
- [chemical deep learning](https://www.cheminformania.com/tag/chemical-deep-learning/)
- [Cheminformatics](https://www.cheminformania.com/tag/cheminformatics/)
- [CNNs](https://www.cheminformania.com/tag/cnns/)
- [computational chemistry](https://www.cheminformania.com/tag/computational-chemistry/)
- [Computational Creativity](https://www.cheminformania.com/tag/computational-creativity/)
- [Cross Docking](https://www.cheminformania.com/tag/cross-docking/)
- [de novo design](https://www.cheminformania.com/tag/de-novo-design/)
- [Deep Chemometrics](https://www.cheminformania.com/tag/deep-chemometrics/)
- [Deep Learning](https://www.cheminformania.com/tag/deep-learning/)
- [docking](https://www.cheminformania.com/tag/docking/)
- [Drug Design](https://www.cheminformania.com/tag/drug-design/)
- [Drug Discovery](https://www.cheminformania.com/tag/drug-discovery/)
- [Excel](https://www.cheminformania.com/tag/excel/)
- [GUI](https://www.cheminformania.com/tag/gui/)
- [Heteroencoders](https://www.cheminformania.com/tag/heteroencoders/)
- [Keras](https://www.cheminformania.com/tag/keras/)
- [Ligand Docking](https://www.cheminformania.com/tag/ligand-docking/)
- [Long short term memory](https://www.cheminformania.com/tag/long-short-term-memory/)
- [Machine Learning](https://www.cheminformania.com/tag/machine-learning/)
- [Model-View-Controller](https://www.cheminformania.com/tag/model-view-controller/)
- [Molecule Browser](https://www.cheminformania.com/tag/molecule-browser/)
- [molecule generation](https://www.cheminformania.com/tag/molecule-generation/)
- [Molecules](https://www.cheminformania.com/tag/molecules/)
- [MVC](https://www.cheminformania.com/tag/mvc/)
- [Neura Nets](https://www.cheminformania.com/tag/neura-nets/)
- [Neural Nets](https://www.cheminformania.com/tag/neural-nets/)
- [Neural Network](https://www.cheminformania.com/tag/neural-network/)
- [Neural Networks](https://www.cheminformania.com/tag/neural-networks/)
- [Optimization](https://www.cheminformania.com/tag/optimization/)
- [PCA](https://www.cheminformania.com/tag/pca/)
- [Python](https://www.cheminformania.com/tag/python/)
- [QSAR](https://www.cheminformania.com/tag/qsar/)
- [RDKit](https://www.cheminformania.com/tag/rdkit/)
- [rDock](https://www.cheminformania.com/tag/rdock/)
- [recurrent neural networks](https://www.cheminformania.com/tag/recurrent-neural-networks/)
- [sklearn](https://www.cheminformania.com/tag/sklearn/)
- [Spectroscopy](https://www.cheminformania.com/tag/spectroscopy/)
- [Theano](https://www.cheminformania.com/tag/theano/)
- [Tuning](https://www.cheminformania.com/tag/tuning/)
- [vina](https://www.cheminformania.com/tag/vina/)
- [xlwings](https://www.cheminformania.com/tag/xlwings/)
- [Jupyter](https://www.cheminformania.com/tag/jupyter/)
- [ipywidgets](https://www.cheminformania.com/tag/ipywidgets/)
- [Inverse QSAR](https://www.cheminformania.com/tag/inverse-qsar/)
- [SMILES generation](https://www.cheminformania.com/tag/smiles-generation/)
- [AI drug discovery](https://www.cheminformania.com/tag/ai-drug-discovery/)
- [Pytorch](https://www.cheminformania.com/tag/pytorch/)
- [Reaction Prediction](https://www.cheminformania.com/tag/reaction-prediction/)
- [Transformers](https://www.cheminformania.com/tag/transformers/)