Sign in

Jeff Wintersinger

@jwintersinger.bsky.social
735 followers 3.3K following 26 posts

Senior Research Scientist in comp bio at @deepgenomics. Did PhD work on cancer evolution. My three favourite things are bananas, riding my bike very fast, and vim.

PostsRepliesMedia
Reposted by Jeff Wintersinger
Stephen Turner @stephenturner.us · 21/05/2025
Nature Reviews Methods Primers: Uniform manifold approximation and projection (UMAP) www.nature.com/articles/s43... 🧬🖥️🧪 read free: rdcu.be/d0YZT
0196
Reposted by Jeff Wintersinger
Vikram Agarwal @vagar.bsky.social · 13/03/2025
Published in today's issue! OPEN ACCESS article, FREE massive dataset, FREE code, FREE pre-trained AI/ML model. #OpenScience was a mountain of work to make this happen: check it out if you haven't already 😉
nature.com
Massively parallel characterization of transcriptional regulatory elements - Nature
Lentivirus-based reporter assays for 680,000 regulatory sequences from three cell lines coupled to machine-learning models lead to insights into the grammar of cis-regulatory elements.
0187
Reposted by Jeff Wintersinger
Carl T. Bergstrom @carlbergstrom.com · 13/10/2023
1. Imagine we land a space probe on one of Jupiters’ moons, take up a sample of material, and find it is full of organic molecules. How can we tell whether those molecules are just randomly assembled goo or the outcome of some evolutionary process taking place there? 🧪
20419169
Reposted by Jeff Wintersinger
Robert Zaichkowski @rzaichkowski.bsky.social · 29/01/2025
Hey #BikeTO! @cycletoronto.bsky.social has launched a campaign shaming Stantec Consulting Ltd for being retained to do work associated with Doug Ford's bike lane removal efforts. Please sign & spread the word. #TOpoli #ONpoli #VoteFordOut www.cycleto.ca/shame_on_you...
cycleto.ca
Shame on you, Stantec
12912
Reposted by Jeff Wintersinger
Anshul Kundaje @anshulkundaje.bsky.social · 24/01/2025
I wanted to write briefly about a very pleasant experience we recently had coordinating and collaborating closely on competing publications with 2 other teams. 1/
211523
Reposted by Jeff Wintersinger
Ewan Birney @ewanbirney.bsky.social · 03/01/2025
Some thoughts about what I am looking forward this year from my vantage point of computational molecular biology. One mega-trend for me; we will definitely see more AI methods of all sorts emerge.
16525
Jeff Wintersinger @jwintersinger.bsky.social · 31/12/2024
This looks like a wonderful gift to start 2025 off right 🤗
220
Jeff Wintersinger @jwintersinger.bsky.social · 18/12/2024
A Scottish study of 83k individuals over 17 years found commuting by bike halves the risk of early death: bmjpublichealth.bmj.com/content/2/1/.... The one outlier hazard ratio for people on bikes casts a harsh light on the Ford government's quest to destroy safe infrastructure in Toronto. #BikeTO
4152
Reposted by Jeff Wintersinger
Judith Kribelbauer @jk-swietek.bsky.social · 16/12/2024
Finally out! We present EXTRA-seq, a new EXTended Reporter Assay to quantify endogenous enhancer-promoter communication at kb scale! www.biorxiv.org/content/10.1... A 🧵about what it can do: #SynBio #DeepLearning #GeneRegulation
biorxiv.org
EXTRA-seq: a genome-integrated extended massively parallel reporter assay to quantify enhancer-promoter communication
Precise control of gene expression is essential for cellular function, but the mechanisms by which enhancers communicate with promoters to coordinate this process are not fully understood. While seque...
58334
Reposted by Jeff Wintersinger
Austin Wang @austintwang.bsky.social · 11/12/2024
(1/10) Excited to announce our latest work! @arpita-s.bsky.social, @amanpatel100.bsky.social , and I will be presenting DART-Eval, a rigorous suite of evals for DNA Language Models on transcriptional regulatory DNA at #NeurIPS2024. Check it out! arxiv.org/abs/2412.05430
arxiv.org
DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA
Recent advances in self-supervised models for natural language, vision, and protein sequences have inspired the development of large genomic DNA language models (DNALMs). These models aim to learn gen...
17027
Reposted by Jeff Wintersinger
ednl🇪🇺 @ee1.nl · 07/12/2024
What's gayer than spandex? #bicycling #PattieGonia
58715
Reposted by Jeff Wintersinger
The Biking Lawyer LLP @thebikinglawyer.bsky.social · 03/12/2024
So excited for this! The fight will be waged on all fronts. Support @cycletoronto: www.cycleto.ca/donate?utm_c...
013022
Reposted by Jeff Wintersinger
Robert Zaichkowski @rzaichkowski.bsky.social · 04/12/2024
In response to last Monday's passing of Bill 212, @joelharden.bsky.social launched a new petition to repeal the legislation and "immediately stop the government’s attack against life-saving active transportation infrastructure." #BikeTO #ottbike #TOpoli #ONpoli www.joelhardenmpp.ca/stay_in_your...
joelhardenmpp.ca
Premier Ford: Stay In Your Lane
MPP / Député, Ottawa Centre
16226
Reposted by Jeff Wintersinger
hope2hope.bsky.social @hope2hope.bsky.social · 30/11/2024
28759171
Reposted by Jeff Wintersinger
John Doench @johndoench.bsky.social · 26/11/2024
A pair of graphs I think about a lot. On the topic of pooled CRISPR screens, the left is "replicate correlation" when simply examining the abundance of guide RNAs, i.e. log-normalized read counts. On the right is taking those same data and subtracting from a common starting point, i.e. pDNA.
54214
Reposted by Jeff Wintersinger
Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 26/11/2024
Since it is inefficient to attempt to educate every reviewer individually, I am yeeting into your feed this clear paper from Gelman, Hill, and Yajima on how Bayesians can do even better than correcting for multiple comparisons. arxiv.org/abs/0907.2478
arxiv.org
Why we (usually) don't have to worry about multiple comparisons
Applied researchers often find themselves making statistical inferences in settings that would seem to require multiple comparisons adjustments. We challenge the Type I error paradigm that underlies t...
1730166
Reposted by Jeff Wintersinger
François Fleuret @francois.fleuret.org · 26/11/2024
My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch. fleuret.org/dlc/ And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!) fleuret.org/lbdl/
461252247
Reposted by Jeff Wintersinger
David Ho @davidho.bsky.social · 24/11/2024
A person on a bicycle is by far the most energy-efficient among animals and machines per distance traveled relative to body weight. The bicycle is magic. www.jstor.org/stable/24923...
A graph titled "Cost of Transport" showing the relationship between body weight (in kilograms) and energy consumption for distance traveled (calories per gram per kilometer) for various animals and machines. It highlights that a person on a bicycle ranks first in efficiency.
26977861690
Jeff Wintersinger @jwintersinger.bsky.social · 24/11/2024
I don't understand why Santa had to close down all of University for his little parade today. He should just take the side streets. #biketo
Santa Clause Parade
0404
Reposted by Jeff Wintersinger
Inigo Martincorena @imartincorena.bsky.social · 20/11/2024
Resharing here a recent X post. In this preprint, we introduce an improved version of NanoSeq, a duplex sequencing protocol with <5 errors per billion bp in single DNA molecules, and use it to study the somatic mutation landscape of oral epithelium in >1000 people. 1/ www.medrxiv.org/content/10.1...
medrxiv.org
Somatic mutation and selection at epidemiological scale
As we age, many tissues become colonised by microscopic clones carrying somatic driver mutations ([1][1]–[10][2]. Some of these clones represent a first step towards cancer whereas others may contribu...
28838
Reposted by Jeff Wintersinger
Why @why.bsky.world · 19/11/2024
833340559
Reposted by Jeff Wintersinger
David Shaywitz @dshaywitz.bsky.social · 20/11/2024
Such an interesting read from @math-rachel.bsky.social who has a remarkable gift for making complex topics (like AI ∩ immunology) accessible as well as engaging -> rachel.fast.ai/posts/2024-0... #biosky #medsky
rachel.fast.ai
Rachel Thomas, PhD - AI’s Quest to Predict T Cell Binding– The Holy Grail of Immunology
an AI researcher going back to school for immunology
2103
Jeff Wintersinger @jwintersinger.bsky.social · 19/11/2024
Wow! I had no idea that Colonel Sanders lived close to Toronto for his final years. I'm honoured ☺️🐔☺️ That gives me one more fun fact to tell visitors, right after I show them the insulin exhibit in the MaRS entrance.
040
Reposted by Jeff Wintersinger
Kieran Campbell @kieranrcampbell.bsky.social · 17/11/2024
I found so many great papers from posts on the other place, will try to pay it back here 🖥️🧬 1/? Benchmarking machine learning methods for synthetic lethality prediction in cancer www.nature.com/articles/s41...
nature.com
Benchmarking machine learning methods for synthetic lethality prediction in cancer - Nature Communications
A comprehensive benchmarking of existing synthetic lethality (SL) prediction methods is lacking. Here, the authors compare 12 recently developed machine learning methods for SL prediction, assess thei...
0253
Reposted by Jeff Wintersinger
Peter Koo @pkoo562.bsky.social · 16/11/2024
🧬 Genomic DNNs can be trained to learn a lot of different aspects of gene regulation, but they're not perfect and we don't know which predictions are reliable and which ones aren't. We introduce DEGU: Uncertainty-aware Genomic Deep Learning with Knowledge Distillation. 1/n
1339
Reposted by Jeff Wintersinger
Shai @shaibiran.bsky.social · 15/11/2024
BSA in 0.6 molar NaCl
A cow, standing in the ocean
410518
Reposted by Jeff Wintersinger
Anshul Kundaje @anshulkundaje.bsky.social · 16/11/2024
arena3-chapter1-transformer-interp.streamlit.app Great interactive tutorial on several current interpretation approaches for transformers. A must read. Other great tutorials on ML fundamentals, model eval, reinforcement learning as well www.arena.education #machinelearning #AI
arena3-chapter1-transformer-interp.streamlit.app
1395
Reposted by Jeff Wintersinger
Anshul Kundaje @anshulkundaje.bsky.social · 13/11/2024
An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures arxiv.org/html/2407.09... Phenomenal review of modern ML with a very intuitive geometric, topological and algebraic perspective. An absolute must-read. #machinelearning #review
arxiv.org
Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
110815
Reposted by Jeff Wintersinger
Matt Elliott @graphicmatt.com · 13/11/2024
In summary, Ford's bike lane removals will, according to a new City Hall report: - Cost $75 million in direct costs and sunk costs. - Make traffic much, much worse for at least nine months during construction to remove lanes - Have minimal long-term impact on car travel times.
21360171
Reposted by Jeff Wintersinger
Greg Medlock @gregmedlock.bsky.social · 10/11/2024
I’m creating a drug development starter pack, reach out to join or suggest additions: go.bsky.app/B2pzQm2
214926