iiinova — where your digital self keeps evolving

Manu Saraswat @manusaraswat.bsky.social · 08/02/2026

Excited to share this work on mapping trans-eQTLs at single-cell resolution! Delighted to have co-conceived this project with lead author @danaivagiaki.bsky.social LIVI enables systematic discovery of genetic effects on gene regulatory networks in population-scale scRNA cohorts. Thread below 🧵👇🏼

030 0

Manu Saraswat @manusaraswat.bsky.social · 10/10/2025

Excited to be at #ASHG2025 in Boston next week. On Thursday, I will be presenting a poster (1007T) on our latest work on Personalised sequence to expression modelling. Looking forward to meeting new folks and reconnecting with old friends and colleagues.

0122 0

Reposted by Manu Saraswat

gokcen.bsky.social @gokcen.bsky.social · 19/09/2025

My team has a postdoc position available now, join us! careers.gene.com/us/en/job/20...

014 0

Manu Saraswat @manusaraswat.bsky.social · 08/09/2025

Excited to be at @aithyra.bsky.social #AIinLifeScience symposium in Vienna. What a gorgeous venue! Will be presenting posters on my latest work on personalized gene expression prediction and gene regulatory network inference

040 0

Manu Saraswat @manusaraswat.bsky.social · 01/08/2025

Dived into past, present & future of human genetics with brilliant students & mentors.Grateful for the chance to present my work on personalized sequence→expression prediction and discussions with @sashagusevposts.bsky.social @bpasaniuc.bsky.social @mashaals.bsky.social @tuuliel.bsky.social & others

0101 0

Reposted by Manu Saraswat

Gherman Novakovsky @gnovakovsky.bsky.social · 30/05/2025

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/)

15921 0

Manu Saraswat @manusaraswat.bsky.social · 22/05/2025

I am genuinely wondering and curious what you think. It’s increasingly hard to see how academia can attract or retain top talent with offers like this, especially when industry offers 2–3x more. Something structural has to change if we’re serious about advancing AI in science.

110 0

Manu Saraswat @manusaraswat.bsky.social · 22/05/2025

Hi Andrea, Thanks for sharing this, it’s an exciting and meaningful opportunity. But to be honest, the listed salary (€42–49k for postdocs) is deeply misaligned with the qualifications you're asking for- post-PhD experience, publications in top AI and biology journals, teaching, and vision.

010 0

Reposted by Manu Saraswat

Omer Ali Bayraktar @bayraktarlab.bsky.social · 16/05/2025

How does tumour heterogeneity arise? How can we predict cancer cell plasticity? In 2 new studies, we trace #glioblastoma heterogeneity to a spatial cancer cell trajectory w. multimodal cell atlassing bit.ly/4mkrWgs & predict plasticity w. snRNA/ATAC+deep learning bit.ly/3FbI6Ic 🧵

67331 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

Thanks a lot for the shoutout Stein. scDORI builds upon the insights from the foundational works in GRN inference from your lab - Cistopic, SCENIC, SCENIC+ Thanks a lot for your contributions. Very exciting time to be in the field 🚀

020 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

Thanks to all our collaborators, specially @lauraruedag.bsky.social who co-led the computational analysis and was the best partner in crime one could ask for. What a delight it was! Thanks to Elisa, Tannia and Fani for leading the experimental aspects.

141 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

14/ We believe this approach can be applied to other cancers to uncover—and exploit—plasticity brakes. Get in touch if interested! #GBM #MultiOmics #CancerResearch #deeplearning #cancerneuroscience #GRNs #Cancer #singlecell

120 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

13/ Our framework unifies regulatory and spatial logic of GB heterogeneity. While our companion paper showed subclones are intermixed across conserved tissue niches, our regulatory model explains WHY—they follow the same trajectory because they're constrained by the same regulatory rules!

110 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

12/ Beyond chromatin changes, MYT1L transformed GB cells into less aggressive neuronal-like cells with: • Enhanced neurite-like morphology • Reduced tumor microtube connectivity • Decreased proliferation • In vivo: slower growth, less invasion, longer survival!

110 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

11/ Our experimental validation was striking: • MYT1L overexpression closed >80% of differential chromatin regions • MYT1L knockout reopened access to plastic fates • MYT1L directly bound and repressed regulators of other GB states• 85% of scDORI's predicted TF targets confirmed!

110 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

10/ 🔥 Can we use these GRNs to manipulate tumor identity and push GB cells into less plastic states? YES! We predicted MYT1L as the key regulatory bottleneck—a master repressor that locks cells into neuronal-like states by directly binding and suppressing the regulators of plastic states.

110 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

9/ Remarkably, our regulatory roadmap explains tumor architecture! States with easy transitions exist in close spatial proximity, while states separated by regulatory barriers are spatially distant. The regulatory rules we've uncovered directly shape how tumors are organized!

120 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

8/ This roadmap revealed striking asymmetry in GB plasticity: • OPC/NPC-like and AC-like states can easily activate multiple alternate fates • Neuronal-like states are "locked" by strong repression barriers • Transitions follow preferred directions (OPC→Neuronal easier than Neuronal→OPC)

120 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

7/ 🔑 The big question: Which tumor states can easily transition to others? We developed metrics to quantify both activation potential (what enables transitions) and repression barriers (what prevents them), creating the first regulatory roadmap of GB plasticity.

120 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

6/ The power of multi-omics: We can distinguish what a cell IS versus what it COULD BECOME. While only 16% of Topic Regulators are expressed across different tumor states, over 54% are epigenetically accessible—revealing "primed drivers" ready for activation during transitions!

120 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

5/ Applied to GB, scDORI uncovered Topics that redefine tumor heterogeneity through regulatory logic. Each Topic links specific TFs, enhancers, and target genes that work together across tumor states. We identified key "Topic Regulators" (TRs)—master TFs for each Topic.

130 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

4/ scDORI: • Scales to millions of cells • Models continuous cell state GRNs • Incorporates both activation AND repression signatures • Each cell is modeled as a mixture of regulatory Topics • Can be applied to ANY multi-omic dataset (happy to hear your feedback, separate 🧵 on soon!)

130 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

3/ To decode GB's regulatory logic, we developed scDORI—an autoencoder that decomposes multi-omic profiles into "regulatory Topics." Each Topic represents specific TF-target gene relationships, modeling cells without requiring predefined cell-types. Code: github.com/bioFAM/scDoRI

130 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

2/ Key finding: Malignant GB cells are dramatically more plastic than non-malignant cells, BUT neuronal-like tumor states show surprisingly LOW plasticity. This hints at regulatory constraints we could potentially exploit therapeutically!

130 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

1/ Glioblastoma is driven by cellular plasticity—tumor cells switching between states. With @bayraktarlab.bsky.social, we profiled >1 M nuclei with single-cell multi-ome (RNA+ATAC) from 12 GBs, capturing the full tumor heterogeneity. We asked: what regulatory mechanisms guide these transitions?

160 0

Manu Saraswat @manusaraswat.bsky.social · 16/05/2025

🧠 Excited to share my main PhD project! We mapped the regulatory rules governing Glioblastoma plasticity using single-cell multi-omics and deep learning. This work is part of a two-paper series with @bayraktarlab.bsky.social @oliverstegle.bsky.social and @moritzmall.bsky.social, Preprint at end🧵👇

17930 0

Reposted by Manu Saraswat

Lars Velten @larsplus.bsky.social · 08/05/2025

Out in Cell @cp-cell.bsky.social: Design principles of cell-state-specific enhancers in hematopoiesis 🧬🩸 screen of fully synthetic enhancers in blood progenitors 🤖 AI that creates new cell state specific enhancers 🔍 negative synergies between TFs lead to specificity! www.cell.com/cell/fulltex... 🧵

cell.com

Design principles of cell-state-specific enhancers in hematopoiesis

Screen of minimalistic enhancers in blood progenitor cells demonstrates widespread dual activator-repressor function of transcription factors (TFs) and enables the model-guided design of cell-state-sp...

414258 0

Reposted by Manu Saraswat

Niklas Kempynck @niklaskemp.bsky.social · 03/04/2025

We released our preprint on the CREsted package. CREsted allows for complete modeling of cell type-specific enhancer codes from scATAC-seq data. We demonstrate CREsted’s robust functionality in various species and tissues, and in vivo validate our findings: www.biorxiv.org/content/10.1...

17538 0

Reposted by Manu Saraswat

Gavin Sherlock @gsherloc.bsky.social · 15/02/2025

On January 6th, 1995, my (now ex) wife and I boarded a flight from Heathrow to JFK on a one way ticket. We had two suitcases and about $900 in cash - this was everything we owned and we were moving to the US. We thought it was maybe for 2-3 years. I had visited the US once, for a conference, and

181134346 0

Reposted by Manu Saraswat

Moritz Mall @moritzmall.bsky.social · 13/02/2025

#CellPlasticity—the ability of cells to change their identity—is vital for tissue growth and repair. But when it goes unchecked, it can fuel #cancer. Our latest study examines how to block #LiverCancer by actively suppressing plasticity. www.nature.com/articles/s41... #CancerBiology

89531 0

Reposted by Manu Saraswat

Anshul Kundaje @anshulkundaje.bsky.social · 11/02/2025

Given that science funding is under attack, it might be as good a time as any to reflect on how we spend our precious dollars. Cutting out expenditure publishing papers in overpriced journals might be a good thing to seriously consider once again.

1447 0

Manu Saraswat @manusaraswat.bsky.social · 27/01/2025

Both. Say for gene exp. pred, one can imagine diff. splits - seen donors- unseen genes, unseen donors- seen genes, unseen donors & genes. If you bring seen and unseen celltypes into equation, then another layer. I do all of this now with custom loaders but having it all in 1 place would be cleaner

010 0

Manu Saraswat @manusaraswat.bsky.social · 27/01/2025

My comment was meant generally for the sequence modelling ecosystem. Would be great to efficiently store and retrieve data from different donors, make train/val splits based on donors. Generate sequence on the fly for a locus using vcf etc It's possible to do all of this now, but not so seamless

110 0

Manu Saraswat @manusaraswat.bsky.social · 27/01/2025

Are you considering extending these libraries for personalised genomes? Current setup works well for ref. data but needs rethinking for efficient storage, retrieval and training on pers. genome. For now we have ad-hoc data structures, on the fly seq from SNPs etc but def. needs improvement

210 0

Manu Saraswat @manusaraswat.bsky.social · 26/01/2025

Exciting work from @jkpritch.bsky.social lab combining perturbation screens with genetic associations 🚀

020 0

Manu Saraswat @manusaraswat.bsky.social · 12/01/2025

Package links for reference Tangermeme tangermeme.readthedocs.io/en/latest/in... GRelu genentech.github.io/gReLU/readme...

genentech.github.io

gReLU — gReLU

010 0

Manu Saraswat @manusaraswat.bsky.social · 12/01/2025

Huge shoutout to @avantikalal.bsky.social (Grelu) and @jmschreiber91.bsky.social (tangermeme) for making sequence model training, evaluation, interpretation and de-novo design so seamless. Finally getting rid of my own clunky scripts i have been using for years for each of these tasks separately

2162 0

Manu Saraswat @manusaraswat.bsky.social · 26/12/2024

Congratulations team @anshulkundaje.bsky.social Can't wait to dive into the details

010 0

Reposted by Manu Saraswat

Saez-Rodriguez Group @saezlab.bsky.social · 23/12/2024

We present Gene Regulatory nETwork Analsyis (GRETA), a framework to infer, compare and evaluate gene regulatory networks #GRNs. With it, we have benchmarked multimodal and unimodal GRN inference methods. Check the results here 👇 Paper: doi.org/10.1101/2024.12.20.629764 Code: github.com/saezlab/greta

112746 0

Reposted by Manu Saraswat

Jeff Spence @jeffspence.github.io · 17/12/2024

What do GWAS and rare variant burden tests discover, and why? Do these studies find the most IMPORTANT genes? If not, how DO they rank genes? Here we present a surprising result: these studies actually test for SPECIFICITY! A 🧵on what this means... (🧪🧬) www.biorxiv.org/content/10.1...

biorxiv.org

Specificity, length, and luck: How genes are prioritized by rare and common variant association studies

Standard genome-wide association studies (GWAS) and rare variant burden tests are essential tools for identifying trait-relevant genes. Although these methods are conceptually similar, we show by anal...

420695 0