👋 I'm Katie a final year PhD candidate at the University of Cambridge and current XAI intern at Ignota Labs. Making the transition to cheminformatics/computational chemistry can be difficult. During my PhD I have accumilated a number of resources I wish someone had shown me the day I started, so here are these resources!
- RDKit - https://www.rdkit.org/docs/index.html Most common cheminformatics package
- DataMol - https://datamol.io/ Open source toolkit of cheminformatics tools, some built upon RDKit
- Exmol - https://github.com/ur-whitelab/exmol Model agnostic explainability methods for ML for chemistry
- Plotly - https://plotly.com/python/ Graphing package, can be difficult initially but it allows for a large amount of customization and can even be used to generate interactive plots
- MolVA - https://molvs.readthedocs.io/en/latest/ Package for molecule standardization
- Portal - https://portal.valencelabs.com/ Community website run by Valence labs with a variety of talks, discussions and tutorials
- TeachOpenCADD - https://projects.volkamerlab.org/teachopencadd/ Open source course on computer aided drug design from the Volkamer lab, complete with Juypter notebooks
- Practical Cheminformatics - https://practicalcheminformatics.blogspot.com/ Cheminformatics blog
- Is life worth living? - https://iwatobipen.wordpress.com/ Cheminformatics blog
- Deep Learning for Molecules and Materials - https://dmol.pub/intro.html#license-cc-by-nc-3-0 Book from Andrew White on ML for molecules
- Connected papers - https://www.connectedpapers.com Generates graphs of connected papers based off of an initial paper of interest
- FlowingData - https://flowingdata.com/ An example of how how data can be presented beautifully
- BeautifulNews - https://informationisbeautiful.net/beautifulnews/ Another example of how how data can be presented beautifully
- AFSA Masterclass - https://www.afsacollaboration.org/masterclass/ This is a bit specific but a great free course from the Animal Free Safety Assessment Collaboration on in silico tools for safety assessment
- Flat Icons - https://www.flaticon.com/icons Icons to jazz up your presentations
- The PhD knowledge base - https://www.thephdproofreaders.com/the-knowledge-base/ A number of resources to help with completing a PhD
- Medium - https://medium.com/ Publishing platform with a large amount of data science and ML/AI resouces There are SO many different platforms to learn coding/AI on I have included some of the ones I've used below
- DataCamp - https://www.datacamp.com/
- CodeAcademy - https://www.codecademy.com/
- FreeCodeCamp - https://www.freecodecamp.org/
- Mimo - https://mimo.org/ Really good if you're new to coding, like DuoLingo but for coding!
- Learn Git - https://learngitbranching.js.org/ Interactive way to learn how Git works
- Distill - https://staging.distill.pub Although it isn't updated anymore there are a lot of nice articles explaining ML and AI concepts
- Reducing Loss - https://developers.google.com/machine-learning/crash-course/reducing-loss/playground-exercise A playground from Google demonstrating how hyperparameters impact the performance of neural networks
- The Little Book of Deep Learning - https://fleuret.org/francois/lbdl.html - Free e-book on deep learning designed for people with a STEM background, designed to fit on a phone screen
- Intro to GNNs - https://www.youtube.com/watch?v=GXhBEj1ZtE8 - Really good intro to how GNNs work, sadly the author hasn't released any other videos