Milka Kostic

@milkakostic.bsky.social

chemical biology enthusiast & strategist; I make impossible things possible - all before breakfast!

Many scientists I've been talking to are freaking out about NIH "immediate deposit" mandate and the publishers, like journals in the Nature family, telling them they have to pay ~13k to satisfy the mandate. People have been paying it - but they don't need to.

Congratulations to @nickpolizzi.bsky.social and colleagues! They combine protein structure prediction with prediction of small molecule binding to map a wide range of functional sites on proteins. Way to boost the hunt for targetable (ligandable) sites!

Dana-Farber News@danafarbernews.bsky.social · 5mo ago

In a new study published in @natmethods.nature.com, @danafarber.bsky.social’s @nickpolizzi.bsky.social uses features from a pretrained neural network to train a logistic regression model, AF2BIND, which could be used for drug discovery and uncovering functional sites in proteins. ➡️ rdcu.be/e7SnX

Nicholas Polizzi, PhD, of Dana-Farber Cancer Institute

I’m looking to hire a research technician for my lab at Harvard & DFCI, who would primarily work in the wet lab expressing and characterizing designed proteins, starting this summer. A great role for a recent college grad looking for an immersive research experience before grad school.

We are looking to hire an Assistant/Associate Professor interested in creating an innovative (and exciting) program of research in chemical biology, medicinal chemistry, ML/AI, drug discovery - all in the context of cancer biology! careers.dana-farber.org/job/11813/as...

Faculty/Health Educator Job: Assistant/Associate Professor, Chemical Biology at Dana-Farber Cancer Institute in 450 Brookline Ave, Boston, MA

Assistant/Associate Professor, Chemical Biology job

careers.dana-farber.org

Super excited to share a new preprint from our lab on design of small-molecule binding proteins using neural networks! The paper has a bit of everything. A new graph neural network, new design algorithms, and experimental validation. www.biorxiv.org/content/10.1... 🧵🧪

Zero-shot design of drug-binding proteins via neural selection-expansion

Computational design of molecular recognition remains challenging despite advances in deep learning. The design of proteins that bind to small molecules has been particularly difficult because it requ...

biorxiv.org

Potential explanation for the results of the most recent elections? Seems like H. sapiens can't fight biology? "Both male and female mice exhibit female preference (under normal conditions) but shift to male preference when confronted with survival threats." www.science.org/doi/10.1126/...

Sexually dimorphic dopaminergic circuits determine sex preference

Sociosexual preference is critical for reproduction and survival. However, neural mechanisms encoding social decisions on sex preference remain unclear. In this study, we show that both male and femal...

science.org

Ever wonder where Nobel Prize-winning AlphaFold got its training data? Read how pioneering crystallographer Helen Berman helped build the Protein Data Bank as a home for more than 200,000 protein structures that would come to shape AI and protein prediction ➡️

The huge protein database that spawned AlphaFold and biology’s AI revolution

Pioneering crystallographer Helen Berman helped to set up the massive collection of protein structures that underpins the Nobel-prize-winning tool’s success.

buff.ly