Kasia Kedzierska's Avatar

Kasia Kedzierska

@kasia.codes.bsky.social

AI Research Scientist @alleninstitute.org | PhD from @ox.ac.uk | prev: intern @msftresearch.bsky.social New England & Novo Nordisk | she/her | kasia.codes

562 Followers  |  143 Following  |  9 Posts  |  Joined: 10.09.2023  |  1.87

Latest posts by kasia.codes on Bluesky

Deadline extended to August 1st!
Fully funded DPhil (PhD) in Statistical Genetics at Oxford, available to international candidates!

21.07.2025 11:39 β€” πŸ‘ 1    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0
Decoding cnidarian cell type gene regulation Animal cell types are defined by differential access to genomic information, a process orchestrated by the combinatorial activity of transcription factors that bind to cis -regulatory elements (CREs) to control gene expression. However, the regulatory logic and specific gene networks that define cell identities remain poorly resolved across the animal tree of life. As early-branching metazoans, cnidarians can offer insights into the early evolution of cell type-specific genome regulation. Here, we profiled chromatin accessibility in 60,000 cells from whole adults and gastrula-stage embryos of the sea anemone Nematostella vectensis. We identified 112,728 CREs and quantified their activity across cell types, revealing pervasive combinatorial enhancer usage and distinct promoter architectures. To decode the underlying regulatory grammar, we trained sequence-based models predicting CRE accessibility and used these models to infer ontogenetic relationships among cell types. By integrating sequence motifs, transcription factor expression, and CRE accessibility, we systematically reconstructed the gene regulatory networks that define cnidarian cell types. Our results reveal the regulatory complexity underlying cell differentiation in a morphologically simple animal and highlight conserved principles in animal gene regulation. This work provides a foundation for comparative regulatory genomics to understand the evolutionary emergence of animal cell type diversity. ### Competing Interest Statement The authors have declared no competing interest. European Research Council, https://ror.org/0472cxd90, ERC-StG 851647 Ministerio de Ciencia e InnovaciΓ³n, https://ror.org/05r0vyz12, PID2021-124757NB-I00, FPI Severo Ochoa PhD fellowship European Union, https://ror.org/019w4f821, Marie SkΕ‚odowska-Curie INTREPiD co-fund agreement 75442, Marie SkΕ‚odowska-Curie grant agreement 101031767

I am very happy to have posted my first bioRxiv preprint. A long time in the making - and still adding a few final touches to it - but we're excited to finally have it out there in the wild:
www.biorxiv.org/content/10.1...
Read below for a few highlights...

06.07.2025 18:14 β€” πŸ‘ 58    πŸ” 24    πŸ’¬ 1    πŸ“Œ 2
Preview
Machine Learning in Computational Biology Youtube channel for the Machine Learning in Computational Biology conference.

Just under a week until the #MLCB2025 paper/abstract deadline on June 1st! In-person registration is full but you can join the wait list forms.gle/gnj6AAV7oWj6... or watch online at youtube.com/@mlcbconf. Sept 10-11 at @nygenome.org. Full deets at mlcb.org! Please RP.

26.05.2025 16:16 β€” πŸ‘ 10    πŸ” 4    πŸ’¬ 0    πŸ“Œ 0
Post image Post image

Come and join us! We’re hiring a new Group Leader in Generative Biology at the @sangerinstitute.bsky.social

Building AI models or the data to train them?

Core funding of >$130M a year for a faculty of ~30.

www.nature.com/naturecareer...

acrobat.adobe.com/id/urn:aaid:...

pls RT!

06.05.2025 14:59 β€” πŸ‘ 46    πŸ” 67    πŸ’¬ 1    πŸ“Œ 0
Graph at ICLR 2025 in Singapore from 24 - 28 April. Meet us there!

Graph at ICLR 2025 in Singapore from 24 - 28 April. Meet us there!

A portrait of Katherine Driscoll, Head of AI at Graph, standing in front of a blackboard with mathematical formulas.

A portrait of Katherine Driscoll, Head of AI at Graph, standing in front of a blackboard with mathematical formulas.

Hey Singapore, @kdris.bsky.social will be at ICLR 2025 from 24 - 28 April! We’re looking forward to hearing about the latest discoveries in biology, AI, and deep learning. Let us know if you’ll be around! πŸ‡ΈπŸ‡¬

22.04.2025 09:13 β€” πŸ‘ 5    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0

I get "page not found" -- could you repost the link?

19.03.2025 01:27 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Ai2 ScholarQA logo

Ai2 ScholarQA logo

Can AI really help with literature reviews? 🧐
Meet Ai2 ScholarQA, an experimental solution that allows you to ask questions that require multiple scientific papers to answer. It gives more in-depth and contextual answers with table comparisons and expandable sections πŸ’‘
Try it now: scholarqa.allen.ai

21.01.2025 19:30 β€” πŸ‘ 33    πŸ” 12    πŸ’¬ 1    πŸ“Œ 6

πŸ“’ Calling all researchers! The #LMRL workshop is now accepting paper submissions! 🧬✨

🎯 Showcase complete works / early-stage ideas πŸ’‘ via your chance to inspire & connect with a non-traditional AIxBio #ICLR2025 audience 🌍

πŸ‘‰ Help us spread the word of lmrl.org πŸ™Œ

06.01.2025 15:00 β€” πŸ‘ 13    πŸ” 6    πŸ’¬ 0    πŸ“Œ 0
Preview
ICLR 2025 Workshop Proposals Welcome to the OpenReview homepage for ICLR 2025 Workshop Proposals

The list of accepted workshops for ICLR 2025 is available at openreview.net/group?id=ICL...
@iclr-conf.bsky.social

We received 120 wonderful proposals, with 40 selected as workshops.

03.12.2024 16:29 β€” πŸ‘ 57    πŸ” 15    πŸ’¬ 1    πŸ“Œ 5

Three BioML starter packs now!

Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
Pack 3: go.bsky.app/NAKYUok

DM if you want to be included (or nominate people who should be!)

03.12.2024 03:27 β€” πŸ‘ 147    πŸ” 60    πŸ’¬ 16    πŸ“Œ 6

It’s already December 2nd, which means 2 Advent of Code 2024 puzzles are out! I’m sharing my solutions on my blog: kasia.codes/posts/aoc24/. If you’ve got a bit of time, highly recommend giving it a shotβ€”it's quite fun! πŸŽ„πŸ’» adventofcode.com #AdventOfCode #aoc2024

02.12.2024 15:58 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image Post image Post image Post image

🎨 In case anyone need…

The NIH BioArt Source is an awesome library of *free* professionally drawn illustrations for scientific presentations or figures. Downloadable in HD. Thank you NIH for this invaluable tool πŸ™!

Check it out πŸ‘‡
bioart.niaid.nih.gov

23.11.2024 15:49 β€” πŸ‘ 1208    πŸ” 495    πŸ’¬ 45    πŸ“Œ 28

Thank you for posting this. 😊 I saw this on the other app some time ago but didn't manage to bookmark it, and Google was no help.

24.11.2024 19:29 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Search Jobs | Microsoft Careers

In the spirit of trying to be more active on here... the deadline for our BioML internship is tomorrow 11/22.

If you are currently a PhD student please consider applying --- all we need is a CV and research statement!

jobs.careers.microsoft.com/global/en/jo...

21.11.2024 17:57 β€” πŸ‘ 6    πŸ” 3    πŸ’¬ 1    πŸ“Œ 1

Two BioML starter packs now:

Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc

DM if you want to be included (or nominate people who should be!)

18.11.2024 17:09 β€” πŸ‘ 119    πŸ” 58    πŸ’¬ 10    πŸ“Œ 11

The @bsky.app is feeling more and more like the lost #sci-Twitter and I am all for it! 🀞 Missed the science space and Twitter or X hasn't been that ever since the sink incident. #exodus #science #twitter

18.11.2024 01:44 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Screenshot of a terminal session showing a greeting message with the current date, time, and a piece of wisdom: 'You can't mend a wristwatch while falling from an airplane.' Below the text, there's a colorful ASCII art depiction of a pony with a rainbow mane and tail.

Screenshot of a terminal session showing a greeting message with the current date, time, and a piece of wisdom: 'You can't mend a wristwatch while falling from an airplane.' Below the text, there's a colorful ASCII art depiction of a pony with a rainbow mane and tail.

✨ Brighten up your terminal! ✨

Who wouldn’t want to be greeted by a pony 🐎 or a cow πŸ„ during in their terminal?! πŸ™ˆ

I wrote a post on adding some fun and color to your console: kasia.codes/posts/pony_i...

#bash #zsh #ponysay #cowsay #TerminalFun

17.11.2024 19:00 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

who knew it would be easier to get everyone to switch social media platforms than getting them to use hg38

14.11.2024 18:45 β€” πŸ‘ 254    πŸ” 62    πŸ’¬ 15    πŸ“Œ 13

Here's hoping to having enough time to solve all 25x2 puzzles! 🀞

16.11.2024 13:31 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
A festive holiday scene with a laptop displaying glowing code, surrounded by Christmas decorations like fairy lights, ornaments, a candy cane, and a small tree. Snowfall is visible through a window, creating a cozy atmosphere with subtle coding elements woven into the decor.

A festive holiday scene with a laptop displaying glowing code, surrounded by Christmas decorations like fairy lights, ornaments, a candy cane, and a small tree. Snowfall is visible through a window, creating a cozy atmosphere with subtle coding elements woven into the decor.

December's coming, and so is my favorite recent tradition: #AdventOfCode! πŸŽ„πŸ‘©β€πŸ’» Excited to solve coding puzzles in the spirit of helping elves and saving holidays. Highly recommend! adventofcode.com

16.11.2024 13:30 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 1    πŸ“Œ 1
This is a summary figure of the evaluation setup where two foundation models, Geneformer and scGPT, together with baselines such as no model (HVG) and scVI were evaluated on 5 datasets in 3 tasks for cell type clustering, batch integration, and pretraining objective. The figure illustrates the expected good and bad cases for each task. In cell type clustering a good outcome is when cell types separate in the embedding space, while bad is when they are intermixed. In batch integration, expected is the separation across cell types, not batches. In the pretraining objective, a positive correlation is expected between input and predicted values.

This is a summary figure of the evaluation setup where two foundation models, Geneformer and scGPT, together with baselines such as no model (HVG) and scVI were evaluated on 5 datasets in 3 tasks for cell type clustering, batch integration, and pretraining objective. The figure illustrates the expected good and bad cases for each task. In cell type clustering a good outcome is when cell types separate in the embedding space, while bad is when they are intermixed. In batch integration, expected is the separation across cell types, not batches. In the pretraining objective, a positive correlation is expected between input and predicted values.

How robust are proposed foundation models in single-cell biology?

Here, we assessed two models: Geneformer and scGPT. We focus on evaluating their zero-shot capabilities.

πŸ“„ biorxiv.org/content/10.1...
πŸ’» github.com/microsoft/ze...
πŸ’ͺ with Alex Lu, Ava Amini, and Lorin Crawford

18.10.2023 15:43 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
photo of me holding flowers with congratulations balloons behind.

photo of me holding flowers with congratulations balloons behind.

Yay, I passed my viva today! πŸŽ“πŸ’ͺ

I had to take a photo home, as thanks to Oxford's weather, I only dried up after the pub. :) Had great fun celebrating and will take my well-deserved time off from my thesis (before submitting the corrections, of course). #phdone #phdchat

12.09.2023 22:08 β€” πŸ‘ 4    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

@kasia.codes is following 20 prominent accounts