Francesca Grisoni

Interesting talk by @fragrisoni.bsky.social at #ChemBioPhys2025. She talked about her group's exciting research into exploring the vast chemical space for #DrugDiscovery using #ArtificialIntelligence in low-data scenarios. www.nature.com/articles/s43...
#ChemBio #ChemSky

In addition, the workshop will host the annual meeting of the ELLIS Program on Machine Learning for Molecule Discovery, fostering interdisciplinary dialogue and shaping the next phase of molecular AI research.

Organizers:
🔸 Nadine Schneider
🔸 @fragrisoni.bsky.social
🔸 José Miguel Hernández Lobato

Dream Reactions Symposium – Wrap-Up Part I ✨

Our speakers are truly passionate about driving towards a positive change! 🌍

Special congratulations to @fragrisoni.bsky.social, the very first recipient of the Green Dream Reactions Award!! 🏆👏

#DreamReactions#Sustainability

It is a great pleasure to share that our extensive review on "The Chemistry and Biology of the Tetrodotoxin Natural Product Family" has been accepted for publication at Angewandte Chemie: doi.org/10.1002/anie....

Very much looking forward to the ChemBioChem and ChemPhysChem symposium "Advances in Structural Analysis of Biomolecules" in Berlin on October 23rd and 24th. If you are interested in the field, check out this conference: www.cbc-cpc2025.org (1/2)

Keynotes:
@machine.learning.bio Christian Dallago, Duke University, US
@delafuentelab.bsky.social  Cesar de la Fuente, UPenn, US
@fragrisoni.bsky.social  Francesca Grisoni - TU/e, NL
Birte Hoecker, Bayeruth University, DE

🧫Now in Bioinformatics Advances: "peptidy: A light-weight Python library for peptide representation in machine learning"   

Find it here: https://doi.org/10.1093/bioadv/vbaf058

Authors include: @fragrisoni.bsky.social

We just preprinted a fresh study on molecular machine learning on OOD molecules 🧠

Using joint modeling, we could detect distribution shifts, estimate prediction reliability, and capture meaningful molecular patterns!

doi.org/10.26434/che...

#AI #chemistry

Very much looking forward to the 25th anniversary symposium of ChemBioChem and ChemPhysChem #CBCCPC2025 in Berlin on October 23rd and 24th, 2025.

There is an ever growing list of amazing speakers confirmed for this event. (1/2)

#chemsky #ChemBio @chemistryeurope.bsky.social

www.cbc-cpc2025.org

Working on #explainable #AI #ML for #chemistry and #materials? Then join us at the special track #xAI 2025 in Istanbul this July and submit your paper by Feb 28! xaiworldconference.com/2025/explain... Co-organised with @fragrisoni.bsky.social Pascal Friederich, Geemi Wellawatte etc.

Welcome to the other side!

Very excited to share our review on "The Chemistry and Biology of the Tetrodotoxin Natural Product Family", where we discuss their potential for the development of analgesics, structure-activity relationships on NaV channels, biosynthetic hypotheses and chemical syntheses: tinyurl.com/ye6nwnwu.

Effectiveness of molecular fingerprints for exploring the chemical space of natural products - Journal of Cheminformatics Natural products are a diverse class of compounds with promising biological properties, such as high potency and excellent selectivity. However, they have different structural motifs than typical drug...

Effectiveness of molecular fingerprints for exploring the chemical space of natural products - published in jcheminf. Thanks to all the co-authors involved for this nice collaboration ! @molecularML @MiChemQSAR @fragrisoni.bsky.social
jcheminf.biomedcentral.com/articles/10....

Going beyond SMILES enumeration for generative deep learning in low data regimes Data augmentation can alleviate the limitations of small molecular datasets for generative deep learning, by ‘artificially inflating’ the number of instances available for training. SMILES enumeration...

Going beyond SMILES enumeration for generative deep learning in low data regimes | ChemRxiv - doi.org/10.26434/che... #compchem

The Jungle of Generative Drug Discovery: Traps, Treasures, and Ways Out "How to evaluate de novo designs proposed by a generative model?" Despite the transformative potential of generative deep learning in drug discovery, this seemingly simple question has no clear answer...

If you use generative #DeepLearning for molecule design, check out our latest work, where we perform a large scale analysis (~1 B designs!) and find ‘traps’, ‘treasures’ and ‘ways out’ in the jungle of generative drug discovery.
🌴 🐒

Paper: arxiv.org/abs/2501.05457
Code: github.com/molML/jungle...

Hope never dies 😂

Please note that applications submitted via email and not through the dedicated portal will not be considered.

Postdoc In Organic/Medicinal Chemistry for generative AI in Drug Discovery De TU/e is voortdurend op zoek naar wetenschappelijk en niet-wetenschappelijk personeel om haar ambities waar te maken. Kijk hier voor ons actuele vacatureaanbod.

Open #postdoc position in *Organic/Medicinal Chemistry* for generative #AI in Drug Discovery — join us @tueindhoven.bsky.social 💪🏻

Funded by the European Research Council (ERC).
Deadline: Jan 15, 25

jobs.tue.nl/nl/vacature/...

Repost appreciated!

The surprising ineffectiveness of molecular dynamics coordinates for predicting bioactivity with machine learning

Authors: Emanuele Criscuolo, Rıza Özçelik, Derek van Tilborg, Francesca Grisoni
DOI: 10.26434/chemrxiv-2024-rp81v

Automated navigation of condensate phase behavior with active machine learning

Authors: Yannick Leurs, Willem van den Hout, Andrea Gardin, Joost van Dongen, Jan van Hest, Francesca Grisoni, Luc Brunsveld
DOI: 10.26434/chemrxiv-2024-frnj3

Open postdoc position available in my group in AI-assisted molecular simulations: https://www.rug.nl/about-ug/work-with-us/job-opportunities/?details=00347-02S000B1LP&cat=wp #aichem

Welcome Barbara! 👋

Thank you for attending! 🙂

Thanks @fragrisoni.bsky.social for a great talk at the University of Amsterdam! Learned a lot about how to apply AI effectively to molecular structure generation. Strong start to the #ChemAI events this week

Learning on compressed molecular representations Last year, a preprint gained notoriety, proposing that a k-nearest neighbour classifier is able to outperform large-language models using compressed text as input and normalised compression distance (...

Fresh off the presses:
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.

TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..

Hey Ben, ML for drug discovery here 🙂

🙋🏼
🙃