
Jacob Ulirsch, PhD
@julirsch
Followers
766
Following
2K
Media
42
Statuses
589
Genetics person at @Illumina. Previously @BBS_Harvard, @broadinstitute, Patch Bio, and @NCSSM. he/him. Black lives still matter.
Cambridge, MA
Joined February 2014
I am a strong believer that depth of data can be just as powerful as scale of data. Deep analysis of small groups of humans, and even individuals, can lead to novel biological insights and principles. Today I am the guinea pig. In my own blood, @CalebLareau finds strong evidence
3
27
235
Excited to share my first contribution here at Illumina! We developed PromoterAI, a deep neural network that accurately identifies non-coding promoter variants that disrupt gene expression.🧵 (1/)
2
31
111
We're thrilled to introduce PromoterAI — a tool for accurately identifying promoter variants that impact gene expression. 🧵 (1/)
9
138
517
Though the coarse tree topologies may appear similar between versions, the relative placement of cells (color bar) in the two trees is ~random! We therefore disagree that ReDeeM is “robust and reliable” between versions as edge variants in -1 remains a large driving signal. 5/n
1
3
16
In addition to the technical points raised by @CalebLareau, several biological questions remain after this preprint. We would appreciate your thoughts as these were not addressed @chenweng1991, @jswlab, @bloodgenes. 1/n
Thank you @chenweng1991, @jswlab, @bloodgenes for the feedback on our work. @LeifLudwig and I agree that the “-2” filtering method that mitigates edge bias is a critical development for ReDeeM. Nevertheless, we stand by our original preprint, noting the following: 1/n
1
7
40
Tools that predict the causal genes in GWAS loci are too complex! Many use XGBoost models with >45 features (i.e. L2G, Ei). CALDERA achieves better performance despite using LASSO regression and only 12 features. This makes it much easier to understand why a gene was chosen.
Simplifying causal gene identification in GWAS loci https://t.co/3cGfDEIESW
#medRxiv
1
3
7
Any white hats out there want to make a virus that gets famous scientists to tweet about my recent papers? Unrelated, I just got a new MacBook for cheap ask me how.
1
0
7
Hello Berlin students, we are looking for a motivated student assistant to support our research team at @berlinnovation and @BIMSB_MDC: https://t.co/4mnSJuUYKz. Please apply by July 20! What we do: https://t.co/6twsZ2hCms and https://t.co/uD1ZdHwF99 Retweets welcome 🙂
1
24
30
Huge congrats to 🌟@broadinstitute postdoc @ZhiYu_ACGT for starting as an Investigator & faculty member @MGH_CTEU @MGHMedicine @harvardmed on Sep 1!
16
9
98
The Leena Peltonen Prize of 2024 goes to @SashaGusevPosts 🎉! I was honored to announce this and introduce Sasha just minutes ago at #ESHG24. Huge congrats!
22
23
215
An independent benchmarking study comparing 84 variant effect predictors ranked our method, CPT, at the top for DMS data, beating AlphaMissense. Many thanks to @jmarshlab for conducting this study! Marsh lab paper: https://t.co/a2zsZD5N3T Our CPT paper: https://t.co/Sop1kUF8u6
2
29
127
There's no Teams in team
0
0
5
Could not be more delighted to present our work investigating how over 220,000 complex and molecular trait-associated genetic variants affect transcriptional regulation using massively parallel reporter assays! https://t.co/1eoN4OxAvd See below for a 🧵. 1/n
biorxiv.org
Identifying the causal variants and mechanisms that drive complex traits and diseases remains a core problem in human genetics. The majority of these variants have individually weak effects and lie...
9
90
319
Reminder that we're back at it again tonight with a talk from @julirsch (Illumina AI) on gene variant ID + interpretation. So so excited to have cool genomics content in our lineup 🥰 Register for location or watch via Zoom (link inside) 👋
luma.com
[IN PERSON EVENT IN BERKELEY] Join us for the 11th seminar from the BioML group in Machine Learning at Berkeley, sponsored by Pillar VC. We're hosting Jacob…
1
4
25
1) Spend more time on problem choice. In science and (non-software) engineering, a typical project for a grad student might involve 1-2 weeks of planning and 2-5 years of execution. That is way out of balance, especially considering that… 4/53
1
8
68
What a PERFFect day to share our new preprint! With @tsion_abay #BobStickels @MerilTakizawa @ChaligneRonan and @Satpathology, we introduce PERFF-seq, a new experimental approach to studying rare cells with scRNA-seq via transcript-specific enrichment. https://t.co/woKvdEdOf0 1/n
biorxiv.org
Single-cell genomics technologies have accelerated our understanding of cell-state heterogeneity in diverse contexts. Although single-cell RNA sequencing (scRNA-seq) identifies many rare populations...
21
151
455
Excited to share our preprint: Integration of transcriptomics and long-read genomics prioritizes structural variants in rare disease. https://t.co/51w8F8qnS8.
medrxiv.org
Rare structural variants (SVs) — insertions, deletions, and complex rearrangements — can cause Mendelian disease, yet they remain difficult to accurately detect and interpret. We sequenced and...
1
26
68
Congratulations to JB Michel, Uri Laserson & the brilliant team at Patch Biosciences on their acquisition by @Ginkgo Excited to bring Patch together with @jrkelly & Team Ginkgo to use AI to develop more effective, specific & durable genetic medicines. https://t.co/ag0PgXDIXI
5
9
59