Nature Reviews Methods Primers: Uniform manifold approximation and projection (UMAP) www.nature.com/articles/s43... π§¬π₯οΈπ§ͺ read free: rdcu.be/d0YZT
21.05.2025 15:31 β π 18 π 6 π¬ 0 π 0Nature Reviews Methods Primers: Uniform manifold approximation and projection (UMAP) www.nature.com/articles/s43... π§¬π₯οΈπ§ͺ read free: rdcu.be/d0YZT
21.05.2025 15:31 β π 18 π 6 π¬ 0 π 0Can we rename it to the Wayne Gretzky Border Crossing?
19.03.2025 02:29 β π 3 π 1 π¬ 3 π 0Published 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 π
13.03.2025 19:32 β π 18 π 7 π¬ 0 π 0Can't wait to see Bradford get destroyed in the next election.
12.02.2025 03:01 β π 0 π 0 π¬ 0 π 0Can we look at ways to make the road network profitable? How about turning every road into a toll road for drivers?
12.02.2025 02:59 β π 1 π 0 π¬ 0 π 01. Imagine we land a space probe on one of Jupitersβ 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? π§ͺ
13.10.2023 04:13 β π 420 π 169 π¬ 20 π 61Hey #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...
29.01.2025 22:35 β π 29 π 12 π¬ 1 π 0I wanted to write briefly about a very pleasant experience we recently had coordinating and collaborating closely on competing publications with 2 other teams. 1/
24.01.2025 19:36 β π 114 π 23 π¬ 2 π 5As someone who has been working extensively with PyTorch Ledidi: this effort is noticed and very much appreciated. I hope to have the ability eventually to contribute improvements back to the community.
07.01.2025 15:28 β π 1 π 0 π¬ 1 π 0Some 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.
03.01.2025 18:46 β π 65 π 25 π¬ 1 π 3This looks like a wonderful gift to start 2025 off right π€
31.12.2024 16:07 β π 2 π 0 π¬ 2 π 0If we could put cycling in a pill, it would be the blockbuster drug to end all blockbuster drugs. (I'm also surprised that the mortality improvements for pedestrians seem much smaller than for cyclists.)
18.12.2024 12:37 β π 2 π 0 π¬ 0 π 0A 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
18.12.2024 12:35 β π 15 π 2 π¬ 4 π 0
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 π§΅about what it can do:
#SynBio #DeepLearning #GeneRegulation
(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
11.12.2024 02:30 β π 70 π 27 π¬ 1 π 3What's gayer than spandex? #bicycling #PattieGonia
07.12.2024 21:18 β π 84 π 14 π¬ 5 π 5
So excited for this! The fight will be waged on all fronts.
Support @cycletoronto:
www.cycleto.ca/donate?utm_c...
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 governmentβs attack against life-saving active transportation infrastructure." #BikeTO #ottbike #TOpoli #ONpoli www.joelhardenmpp.ca/stay_in_your...
04.12.2024 01:32 β π 63 π 26 π¬ 1 π 0This is going into my list of "word usage that will earn you five lashings," to be deployed when I found my own venture. Already on the list are "learnings" and "overindex."
29.11.2024 22:11 β π 3 π 0 π¬ 1 π 0This led me to github.com/atongen/yolo, which seems magical. I expect my colleagues to be deeply appreciative when I integrate this into my workflow.
29.11.2024 19:07 β π 0 π 0 π¬ 1 π 0Thank you for hosting! Caroline's talk is super cool.
29.11.2024 17:20 β π 1 π 0 π¬ 0 π 0Yes -- I think this is just a temporary issue caused by their server infrastructure being overloaded. The developers have done an impressive job of scaling up with the massive influx of new users, so this will probably be resolved soon.
29.11.2024 16:51 β π 1 π 0 π¬ 2 π 0Dougie set back Ontario by ten years. Impressive that we have managed to keep re-electing our own Mini Trump.
29.11.2024 16:49 β π 1 π 0 π¬ 0 π 0Following the 2013 floods that destroyed parts of that system, I had to move the first few km of that trip to suburban roads. A couple months later, while riding that part, a driver hit me intentionally with his truck. I've been radicalized ever since.
29.11.2024 16:34 β π 0 π 0 π¬ 1 π 0I grew up in Calgary. I became passionate about cycling when I started commuting to U of C on a Raleigh Record I got for $15 on Craiglist. It was a 58 km round trip with only 500 m not on the pathway system, and significantly faster than Calgary Transit.
29.11.2024 16:32 β π 2 π 0 π¬ 1 π 0The rhetoric around "we're destroying cycling infrastructure so you can get home to your family faster" is a wonderful reminder that people on bikes don't have families, and that your life stops mattering as soon as you get on a bike.
27.11.2024 15:34 β π 10 π 0 π¬ 0 π 0A 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.
26.11.2024 15:31 β π 42 π 14 π¬ 5 π 1