Skip to content
View jonswain's full-sized avatar
20 followers · 15 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Block or report jonswain

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jonswain/README.md

Jon Swain

Cheminformatician & data scientist — machine learning for drug discovery.

I build ML models and tools for drug discovery (molecular property and ADMET prediction, DNA-encoded library screening, generative de novo design, and ultra-large chemical space search) and ship them as production systems used by medicinal chemists on live projects. PhD in chemistry (Cambridge), with hands-on synthetic research experience.

Now

  • Research Software Engineer at OpenADMET (Open Molecular Software Foundation) — building the blind-challenge infrastructure behind the PXR and CYP challenges (4,000+ submissions from 400+ participants), now open-sourced and adopted by other groups.

Writing & talks

Elsewhere

Pinned Loading

  1. active-learning active-learning Public

    Using active learning to speed up molecular scoring

    Jupyter Notebook 3

  2. ga-for-ul-libraries ga-for-ul-libraries Public

    Genetic algorithms for searching ultra-large chemical libraries

    Jupyter Notebook 4 2

  3. OpenADMET_ExpansionRx_Blind_Challenge OpenADMET_ExpansionRx_Blind_Challenge Public

    Predicting chemical properties for the OpenADMET + ExpansionRx Blind Challenge

    Jupyter Notebook 3

  4. TS-for-classification TS-for-classification Public

    Using Thompson Sampling to find high scoring hits from a large, combinatorial, chemical library

    Jupyter Notebook 2

  5. tabpfn-tdc tabpfn-tdc Public

    Training TabPFN models on datasets from the TDC

    Python 1 1

  6. chemprop-rf chemprop-rf Public

    Can we combine d-MPNNs and Random Forests to outperform each of them individually?

    Jupyter Notebook