CONCORD: Revealing a coherent cell state landscape across single cell datasets https://t.co/xN8xyVQSMk

interactive 3D UMAP!

correct link: interactive 3D UMAP!

Correct links: https://t.co/43dXLXrptR. Try it: https://t.co/ijkPJvsXz8.

Thrilled to see our work highlighted by @GENbio! 🙏🏿🧬 Read the paper here: https://t.co/jWnldnS4PG #CRISPR #StemCells #SyntheticBiology

9. While we focused on scRNA-seq, early results suggest CONCORD’s applicability to spatial transcriptomics & scATAC-seq. It’s open-source in Python. See galleries: https://t.co/vSyfbNjQjO.... Try it: https://t.co/2Bu5rzLDT8....

8. CONCORD integrates datasets solely on gene co-expression structures—without assuming batch-effect models or shared cellular states. It achieves robust alignment even with minimal dataset overlap, offering faster and scalable analysis from small studies to atlas-scale projects.

7. The key innovation is a probabilistic, dataset- and neighborhood-aware sampling strategy tailored for self-supervised contrastive learning, enabling the generation of coherent, denoised and high-resolution latent cell representations across diverse datasets:

6. CONCORD also provides biologically interpretable encodings representative of context-dependent gene-expression programs.

5. An intestinal development atlas demonstrated CONCORD's ability to resolve complex topologies, including differentiation trajectories intertwined with cell cycle loops (click here for interactive 3D UMAP! https://t.co/vSyfbNjQjO...):

4. We validated CONCORD on an embryonic atlas of C. elegans and C. briggsae from @jisaacmurray. CONCORD captured known bifurcations, subtle cell states, and lineage convergence events missed by other methods (click here for interactive 3D UMAP! https://t.co/vSyfbNjQjO...):

3. We evaluated CONCORD on datasets with topologies such as continuous trajectories, loops, clusters and hierarchical trees. Using scIB metrics, geometric measures, and TDA, we assessed its ability to preserve biological structure. CONCORD outperforms existing methods:

2. CONCORD is a simple but powerful ML framework tackling data integration, dimensionality reduction, and denoising in single-cell analysis, developed by @qinzhu1.

1. Struggling to integrate single-cell datasets? Finding it hard to resolve clear differentiation trajectories? Reveal the underlying structure in your data with CONCORD. https://t.co/63eZug0Dbp

🚨 We're Hiring! 🚨 At EMBL Barcelona we build tissues to understand them, and we are looking for a Group Leader in Tissue Biology & Disease Modelling! 🔬 Lead independent research on 3D tissue dynamics & engineering 📅 Apply by 24 Nov 2024 More info: https://t.co/TgBpnWWtJN

We will begin reviewing applications on October 15th, but to ensure full consideration, please submit your application by November 1st.

Inquiries and questions should be emailed to Prof. Brian Shoichet (shoichet@cgl.ucsf.edu), Prof. Jason Sello (Jason.Sello@ucsf.edu), or Balyn Zaro (Balyn.Zaro@ucsf.edu).  For department information candidates should visit  https://t.co/carPU2zxvn.

We are recruiting scientists in all areas of biophysics and chemical biology, but are particularly interested in candidates whose research focus is in computational chemistry and in artificial intelligence as they apply to chemical biology, biophysics, and drug discovery.

UCSF PharmChem is hiring!

our new preprint is live – check out our nifty MAGIC matrices! (1/7)