Business consultant to bio-data software companies. Interests: Complexity, bio-data science, knowledge graphs, bioinformatics, Francis Bacon, Marcus Aurelius..
Synthetic biology could enable new types of programmable therapeutics. Our new preprint introduces synthetic protein circuits that selectively trigger cell death in Ras-mutant cancer cells, with interesting advantages compared to existing approaches.
biorxiv.org/content/10.1101/…
New synthetic biology / gene regulation lab opening in Zurich! We’re studying how to control cell state transitions – for example, making diseased cells healthy or creating new cellular functions – using systematic perturbations, single-cell genomics and machine learning. 🧵1/4
💡IMO one of the best use of AI Scientist is to reanalyze data to find new insights.
Introducing #CellVoyager: AI Compbio Agent that makes new discoveries by autonomously analyzing papers/data, which we then validate🚀
New findings on aging, Covid, scRNAseq etc. Open source!
How to grow (almost) any microbe. A New Hope. Using just 10% of a genome sequence, we can estimate the required environmental (salt, pH, oxygen, and temp) conditions for growing a microbe in the lab.
‼️A guide to mass spec proteomics for beginners! Peer-reviewed and published AND OPEN ACCESS FOR THE NEXT SIX MONTHS! Answers to the questions:
-How does MS proteomics work?
-How do I perform a proteomic experiment?
-Where can I learn more?
#teammassspecpubs.acs.org/doi/10.1021/acs…
Working with Parkinson's Foundation around making sense of their patient registry for themselves and their research partners has been great. Thanks Tag.bio team. lnkd.in/gssUMEjz
Excited about our new partnership with Parkinson's Foundation and Tag.bio. Through data mesh and data analytics we're helping them and their research partners really understand the fundamentals of PD. Congrats team. businesswire.com/news/home/2…
Very excited to share our new @natBME paper: graph NN discovers #tumor#spatial motifs that predict patient response to cancer treatments
We trained our #GNN on spatial proteomics of 10^6 cells from tumor samples to find disease motifs/subgraphs. Paper rdcu.be/cZpgJ
🧵
There are thousands of machine learning algorithms, but you'll rarely need more than a handful.
A good start:
• Linear/Logistic Regression
• Decision Trees
• Neural Networks
• XGBoost
• KNN
• K-Means
• PCA
Would you add anything?