Arnaud Bonnaffoux

🚀 Our new Science paper is out (w/ B DeMeo, D Burkhardt, A Shalek, M Cortes): www.science.org/doi/10.1126/...
We show that active learning + transcriptomic perturbations can guide which exps to run next, boosting phenotypic hit rates >13x. AI not just predicting bio, but designing it. 🔁

Catalyzing computational biology research at an academic institute through an interest network Author summary Scientists have widely adopted computing in their research, and the relative importance of computational methods in biology continues to increase. However, a persistent gap exists betwe...

'At the Scripps Research Institute, (...) we created the Computational Biology and Bioinformatics (CBB) affinity group, a trainee-led community for the discussion of computational biology/bioinformatics with the goal of facilitating knowledge exchange.'

GraphVelo allows for accurate inference of multimodal velocities and molecular mechanisms for single cells - Nature Communications RNA velocity offers insight into cell dynamics but faces key limitations across modalities. Here, authors present GraphVelo, a machine learning framework that refines and extends RNA velocity to multi...

RNA velocities provide powerful insights into cell dynamics.
To address current limitations, Jianhua Xing and his lab created GraphVelo, a machine learning framework that extends RNA velocity to multimodal data.

Read the full paper in Nature Communications: tinyurl.com/GraphVelo

Reconstructing Waddington's Landscape from Data The development of a zygote into a functional organism requires that this single progenitor cell gives rise to numerous distinct cell types. Attempts to exhaustively tabulate the interactions within d...

Latest on Waddington Landscapes: Computational methods to fit dynamical landscapes directly to single cell data

Applied to neural tube patterning shows morphogen-signalling landscapes can be linearly interpolated

Connects interpretable landscape models with data

www.biorxiv.org/content/10.1...

Time-varying stimuli that prolong IKK activation promote nuclear remodeling and mechanistic switching of NF-κB dynamics Nature Communications - Cells rely on limited numbers of transmembrane receptors to process signals from dynamic microenvironments. Using microfluidics and endogenous reporters, the authors track...

In the complex world inside our bodies, timing can be everything.

A new study from Steven Smeal and Robin E.C. Lee reveals the timing of molecular signals can change how cells respond to their environment, with implications for cancer treatment and drug discovery.

Read more: rdcu.be/ezTxF

Human interpretable grammar encodes multicellular systems biology models to democratize virtual cell laboratories We developed a plain text modeling language—a cell behavior hypothesis grammar—to easily build virtual cell models and connect them to data, helping scientists to unlock the hidden dynamics of tissues...

Really excited to share our new @cellpress.bsky.social Cell paper with @fertiglab.bsky.social and colleagues. 1/n

www.cell.com/cell/fulltex...

@jktgfoundation.bsky.social @itcrtraining.bsky.social @smbmathbiology.bsky.social #mathbio #mathonco @mathonco.bsky.social @deniswirtz.bsky.social

How to build the virtual cell with artificial intelligence: Priorities and opportunities Advances in AI and omics enable the creation of AI virtual cells (AIVCs)—multi-scale, multimodal neural network models that simulate molecules, cells, and tissues across diverse states. This vision ou...

How to build the virtual cell with artificial intelligence: Priorities and opportunities: Cell www.cell.com/cell/fulltex...