Karina Pikalyova

Harnessing Medicinal Chemical Intuition from Collective Intelligence Over the past decade, collective intelligence, i.e., the intelligence that emerges from collective efforts, has transformed complex problem-solving and decision-making. In drug discovery, decision-making often relies on medicinal chemistry intuition. The present study explores the application of collective intelligence in drug discovery, focusing on lead optimization. Ninety-two Sanofi researchers with diverse expertise participated anonymously in an exercise centered on ADMET-related questions. Their feedback was used to build a collective intelligence agent, which was compared to an artificial intelligence model. The study led to three major conclusions: first, collective intelligence improves decision-making in optimizing ADMET endpoints, compared to individual decisions. Second, collective intelligence outperforms artificial intelligence for all other endpoints but hERG inhibition. Finally, we observe complementarity between collective human and artificial intelligence. Overall, this research highlights the potential of collective intelligence in drug discovery and the importance of a synergistic approach combining human and artificial intelligence in project decision making.

A single chemist might guess—but can a collective outsmart AI in drug discovery?

In our recent study at Sanofi (J. Med. Chem.), 92 researchers put collective intelligence to the test against AI models on lead optimization tasks.

The results? Click below!
pubs.acs.org/doi/full/10....

Artificial intelligence-open science symbiosis in chemoinformatics In chemoinformatics, artificial intelligence (AI) continues to grow a symbiosis with open science (OS). Such a close AI-OS interaction brings substant…

Thanks for siting my blog post ;)
www.sciencedirect.com/science/arti...

PhD student - Machine learning in bio- and cheminformatics

Here's a first:
I'm hiring a PhD student.
If you have (or know someone who has) a strong background and interest in computational (bio)chemistry or computer science (especially 3D computer vision), let's work together 😊

www.wur.nl/nl/vacature/...

Ordinal Confidence Level Assignments for Regression Model Predictions We present a simple method for assigning accurate confidence levels to molecular property predictions from regression models. These confidence levels are easy to interpret and useful for making decisi...

Excellent new paper (with code) by my former colleagues Steven Kearnes and Patrick Riley describing a procedure for associating confidence levels with regression model predictions in drug discovery. pubs.acs.org/doi/10.1021/...

Everything related to #xLSTM at #NeurIPS2024 collected here

linktr.ee/xLSTM

Talks, poster session, Bio-xLSTM, xLSTM for reinforcement learning,..

Check out our pre-print on an interpretable ML pipeline using a Wasserstein Autoencoder & Generative Topographic Mapping for designing anti-biofilm peptides. Experimentally validated peptides show up to 10x improved IC50 against MRSA biofilms vs. reference standards. More soon! #peptides #AMPs