Costa Lab

Very 🔥 science on DNA acessibility and TF footprinting from the @lucapinello.bsky.social lab!

4/ ACCESS-ATAC significantly improves TF binding site prediction, and in single-cell ACCESS-ATAC experiments, we resolve TF binding profiles at equal sensitivity to ATAC-seq with 2-3x fewer cells.

A Bioprinted and Scalable Model of Human Tubulo-Interstitial Kidney Fibrosis Chronic kidney disease (CKD) affects more than 10 % of the global population. As kidney function negatively correlates with the presence of interstiti…

Our new paper out today: A bioprinted and scalable model of human tubulointerstitial kidney fibrosis. Led by Daphne Bouwens, Nazanin Kabgani and Jitske Jansen www.sciencedirect.com/science/arti...

I would trust that BPNet does better than linear models, but I am not sure about the LM models, which are often published by only compare among themselves. See the study on DL models in insilico pertubation: www.biorxiv.org/content/10.1...
Maybe a 1-layer BPnet would do the job here?

Very nice benchmarking Anshul! I just missed a weak baseline (linear model?). Experience shown that they might still be better or as good as a lot of DL/LM models.

We are recruiting a Tenure-track Assistant Professor "Machine Learning in the Life Sciences" at the Medical University of Vienna. We will nominate the top candidate for a € 1.8 million starting grant by a Viennese foundation. Deadline: Dec 31st. Details: medical-epigenomics.org/files/Tenure...

Have AI or ML skills? Have applied them to biological problems or high dimensional data problems? Want to get to a mechanistic understanding of animal behaviour and environmental influences on life? Want to live in Rome, work in an international, english speaking institute? Apply below!

GitHub - CostaLab/sigurd: Using single cell genotype data, the cells are annotated and analysed. Using single cell genotype data, the cells are annotated and analysed. - CostaLab/sigurd

SIGURD is implemented as an R package with associated pre-processing scripts. It is available on github.com/CostaLab/sig.... Amazing collaborative work with M. Kalmer, S. Koschmieder, @brummendorf within the #CRU344 #genotyping #singlecell #MPN 5/5

We build on MAEGATK for delineation of mitochondria derived clones. We observed an increase in clonality in MPN compared to HC, as supported by diversity measures. As before, we can functionally characterize clones with GSEA and enrichment analysis 4/5

We demonstrated SIGURD in scRNA-seq and JAK2V617F amplicon data from Myeloproliferative Neoplasms. Combined analysis with scRNA-seq allowed us to find an enrichment of JAK2V617F cells in late erythroid cells and an increase in heme metabolism 3/5

SIGURD combines distinct genotyping tools (cellSNP-lite, VarTrix, MAEGATK) into a single reproducible framework. Genotyping results are stored in a data container and can be used for integrative analysis with single cell RNA #Seurat 2/5

We are happy to present SIGURD, a framework for single cell level analysis of somatic and mitochondrial variants from scRNA-seq data. This end-to-end framework allows genotyping, QC, functional analysis and data integration academic.oup.com/bib/article/... 1/5

✋

And we get no break ... Saturday morning at home and I found another low dimensional embbeding (HATCH-MAP) in the floor.