single-cell bioinformatics lab focusing on the immune system! PI: @natstann /in {@unccs,@compmedunc}.
UNC-Chapel Hill
Joined February 2021
- Tweets65
- Following436
- Followers249
- Likes240
CompCy Lab @ UNC retweeted
Exciting week! 🎉 Next Monday, Sneha will defend her honors thesis 'Deciphering the Microglia Transcriptome: Unraveling the Consequences of Early Life Stress and Aging'. Next Tuesday Haidong will defend his PhD 'Set-based modeling and applications in single-cell bioinformatics'.
CompCy Lab @ UNC retweeted
Our 🪐SATURN method is now out in @naturemethods!
SATURN paves the way for universal cell embeddings, enabling integration of datasets across different species 🐒🐁🧍🐟🐸 Using protein language models, we encode biological meaning of genes in scRNA-seq datasets.
SATURN performs cross-species integration and analysis using both single-cell gene expression and protein representations generated by protein language models. @jure @YanayRosen @mariabrbic @yusufroohani
nature.com/articles/s41592-0…
CompCy Lab @ UNC retweeted
Super excited to introduce DELVE (github.com/jranek/delve), an unsupervised feature selection method for improving inference of developmental or disease trajectories from noisy single-cell data: biorxiv.org/content/10.1101/… 😊(1/8)
CompCy Lab @ UNC retweeted
Have you ever wondered if you could leverage RNA velocity data to better resolve biological trajectories or disease phenotypes?
Delighted to share that our benchmarking study is out today in @GenomeBiology! Biggest thank you to @natstann @purvislab 😊
genomebiology.biomedcentral.…
CompCy Lab @ UNC retweeted
Very proud of @JoleneRanek as her task oriented benchmarking study for integrating RNA velocity and gene expression for trajectory inference and outcome prediction is out today in Genome Biology! genomebiology.biomedcentral.… . 🥳
CompCy Lab @ UNC retweeted
Excited to share our new paper (to appear soon in ACM BCB!) about sketching single-cell data. 😀 Specifically, our sketches preserve cell population frequencies and of course rare populations ;), led by Vishal and @JoleneRanek arxiv.org/abs/2207.00584
CompCy Lab @ UNC retweeted
The influx of single-cell data is staggering—not just in volume but in its multiple modalities. How can we optimally combine these modalities to make biologically meaningful predictions? (1/7)
biorxiv.org/content/10.1101/…
CompCy Lab @ UNC retweeted
Congrats @mohitban47/@uncnlp on leading the efforts at @UNC on the new @NSF Institute of Artificial Intelligence Institute for Engaged Learning. Along with @NCState & other universities, researchers will create equitable educational experiences via advanced AI tools.
@unccollege
Researchers from @UNC, @NCState and other universities are forming a new $20M @NSF Artificial Intelligence Institute for Engaged Learning. Learn how Carolina’s @mohitban47 & @unccs faculty will create equitable educational experiences via advanced AI tools unc.live/377zjSZ
CompCy Lab @ UNC retweeted
Plz RT: workshop "Machine learning methods for single cell analysis" at #acm_bcb is accepting abstract submissions till 07/01. #Bioinformatics
High profile keynote speaker & panelists TBA.
Chairs @KrishnaswamyLab @LabWelch @JieLiu71768126 & me.
Details: sites.google.com/view/new-tr…
CompCy Lab @ UNC retweeted
Congratulations to faculty member, Cynthia Sturton & graduate student Rui Zhang for being recognized by @Intelsecurity for their 2nd-place paper! A well-deserved accomplishment! @IEEESSP @UNCResearch @unccollege @UNC
Congratulations to @JiyongYu1 @josep_torrellas, Namrata Mantri, Adam Morrison & Christopher Fletcher of @IllinoisCS @TelAvivUni for their award-winning paper! And to 2nd place Rui Zhang & Cynthia Sturton of @unccs! @IEEESSP #SP21 is off to a great start.
CompCy Lab @ UNC retweeted
Excited to share Schema, our tool for synthesizing multi-modal single-cell data. Schema enables fast exploratory analysis, is robust to noise, and helps generate informative visualizations. With @BrianHie, @ashwinn226 & Bonnie Berger. Tweetorial 👇 1/ genomebiology.biomedcentral.…
CompCy Lab @ UNC retweeted
In this paper that appears in @NatureBiotech today, @cgao90 and I developed an online learning algorithm for single-cell data integration. The key benefits include scalability and the ability to incrementally add new data (1/n)
rdcu.be/ciYhs
CompCy Lab @ UNC retweeted
*ExplaGraphs* --> a graph-explanation based structured+generative commonsense reasoning task!
Long (ongoing) effort by swarna+prateek+lisa on complex graph data collection+verification+refinement & metrics & models & analysis (feedback welcome🙂)
arxiv.org/abs/2104.07644
🧵👇
Excited to share our new work on "ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning"! Has been a long effort and a great learning experience too 🙂
Joint work w. @prateeky2806 @lbauer119 @mohitban47 @uncnlp
Paper: arxiv.org/abs/2104.07644
1/5
CompCy Lab @ UNC retweeted
Our first research paper as a group was preprinted today: automated cell assignment for highly multiplexed imaging and proteomic data
Paper: biorxiv.org/content/10.1101/…
CompCy Lab @ UNC retweeted
Our new opinion paper on integrative analysis of pregnancy-related pathologies is out: sciencedirect.com/science/ar…
CompCy Lab @ UNC retweeted
Great thread on a new preprint from @purvislab - digs deep into the nature of cell cycle “transitions”
1/8
There have been many helpful analogies for understanding the cell cycle—oscillator, clock, dominoes—but what if we could actually *see* the cell cycle as a complete process? What would it look like?
The structure of the human cell cycle biorxiv.org/content/10.1101/…
CompCy Lab @ UNC retweeted
Happy to share #SPARCLE (SPAtial Reassignment of spots to Cells via maximum Likelihood Estimation)
for #multiplexed #images. A new #Computational #model in #spatial #transcriptomics. Joint work with @nawy_t , @dana_peer
Excited to share our first (but not last) foray into multiplexed smFish (e.g. MerFish) #SPARCLE (SPAtial Reassignment of spots to Cells via maximum Likelihood Estimation) led by @sandhya212
biorxiv.org/cgi/content/shor…