Sign in

Matthew Bernstein

@matthew-bernstein.bsky.social
1.2K followers 368 following 46 posts

Principal Scientist @ Somite AI | Computational biology and biomedical data science | Boston, MA | mbernste.github.io

PostsRepliesMedia
Matthew Bernstein @matthew-bernstein.bsky.social · 22/08/2025
Ive seen the analogy that AI is to biological intelligence as airplanes are to birds. I think that’s appropriate. And furthermore, we find that when we make better airplanes they don’t become more bird-like. We are optimizing for something that biology didn’t optimize for. I think AI will be similar
010
Matthew Bernstein @matthew-bernstein.bsky.social · 09/08/2025
Just as the field of ML has become a distinct discipline from statistics (but have a lot of overlap… it’s a continuum), I feel like there’s a new field of AI that is diverging from ML. Again they have a lot of overlap, but the study and use of these massive AI models feels like a new thing
000
Matthew Bernstein @matthew-bernstein.bsky.social · 26/07/2025
It seems that computational work is undergoing two simultaneous transitions that resemble transitions of the past: 1) The transition from coding in a programming language to describing via natural language (AI writes the code) resembles the transition from machine code to programming languages.
120
Matthew Bernstein @matthew-bernstein.bsky.social · 28/05/2025
When trying to reason or prove something in a rigorous mathematical way as it relates to a real-world problem, most of the work seems to lie in developing the right formalism. Once the formalism is established, the math becomes "disinhibited" and flows more effortlessly.
000
Matthew Bernstein @matthew-bernstein.bsky.social · 28/03/2025
Check out my recent talk on two tools I helped develop over the last few years (SpatialCorr and Monkeybread) for analyzing spatial transcriptomics data youtu.be/R8pEvndFHyo?...
youtu.be
From Data to Discovery: Computational Tools for the Analysis of Spatial Genomics Data
YouTube video by Watershed Bio
021
Matthew Bernstein @matthew-bernstein.bsky.social · 11/03/2025
Amazing (Here's the open access article: pmc.ncbi.nlm.nih.gov/articles/PMC...)
010
Matthew Bernstein @matthew-bernstein.bsky.social · 02/03/2025
A nice interface to track the status of various NIH websites and resources given the recent instability: stats.uptimerobot.com/Zrqh8AhvKn
stats.uptimerobot.com
Government Biomedical data
010
Reposted by Matthew Bernstein
Anne Carpenter @drannecarpenter.bsky.social · 01/03/2025
Screen shot of the article
719278
Reposted by Matthew Bernstein
stellaromics.bsky.social @stellaromics.bsky.social · 11/02/2025
Thrilled to share Stellaromics has raised $80M in Series B to advance 3D spatial biology & launch Pyxa! This groundbreaking platform enables unprecedented visualization & analysis of cells & molecules in thick tissue samples. bit.ly/3QaGiRN #Stellaromics #Pyxa #SpatialBiology
052
Matthew Bernstein @matthew-bernstein.bsky.social · 10/02/2025
Really interesting thesis: that the decline of American democracy and prosperity is driven largely by our declining mobility. www.theatlantic.com/magazine/arc...
theatlantic.com
How Progressives Froze the American Dream
The U.S. was once the world’s most geographically mobile society. Now we’re stuck in place—and that’s a very big problem.
7223
Matthew Bernstein @matthew-bernstein.bsky.social · 04/02/2025
Check out my recent talk on dimensionality reduction, where I try to lay out my thoughts on the topic: youtu.be/AuJzMnH78wM?...
youtu.be
Controversies & Challenges in Dimensional reduction and Vizualization in Single Cell Experiments
YouTube video by PANORAMICS - A Vision
142
Matthew Bernstein @matthew-bernstein.bsky.social · 30/01/2025
Glad to see this issue of cell segmentation errors affecting spatial transcriptomics analysis (which most users observe) is now being investigated thoroughly: www.biorxiv.org/content/10.1...
biorxiv.org
Impact of Segmentation Errors in Analysis of Spatial Transcriptomics Data
Spatial transcriptomics aims to elucidate cell coordination within biological tissues by linking the state of the cell with its local tissue microenvironment. Imaging-based assays are particularly pro...
150
Matthew Bernstein @matthew-bernstein.bsky.social · 26/01/2025
Here's a blog post on Euler's number: a constant I only ever partially understood despite it appearing in equations across all of math and science: mbernste.github.io/posts/eulers...
mbernste.github.io
Demystifying Euler’s number
Euler’s number $e := 2.71828\dots$ has, to me, always been a semi-mysterious number. While I understood many facts about $e$, I never felt I ever truly understood what it really was – it’s core essenc...
121
Matthew Bernstein @matthew-bernstein.bsky.social · 11/01/2025
More of an art project than science project, The Pink Chicken project is thought provoking nonetheless pinkchickenproject.com#what
pinkchickenproject.com
Pink Chicken Project
Pink Chicken Project suggests changing the colour of the entire species Gallus gallus domesticus to pink - using the recently invented CRISPR gene-drive technique.
101
Matthew Bernstein @matthew-bernstein.bsky.social · 08/01/2025
It’s crazy to me that this works
020
Reposted by Matthew Bernstein
stellaromics.bsky.social @stellaromics.bsky.social · 07/01/2025
Cells don’t interact in just 2 dimensions—so why study them that way? In 2D spatial analysis, critical interactions between cell types can be underestimated, leading to distorted biological insights. #3DSpatial #SpatialBiology #research Image from from Sui et al., bioRxiv
021
Reposted by Matthew Bernstein
Nikolai Slavov @slavov-n.bsky.social · 06/01/2025
Cells transport proteins in membrane vesicles. These vesicles are formed by self-assembled exoskeleton. The exoskeleton scaffolds are cuboctahedrons made of proteins. Life is amazing!
272
Reposted by Matthew Bernstein
Joris van de Haar, MD, PhD @joris-vd-haar.bsky.social · 05/01/2025
Bizarre story. Genetic Analysis of a Sarcoma Accidentally Transplanted from a Patient to a Surgeon | New England Journal of Medicine www.nejm.org/doi/full/10....
nejm.org
Genetic Analysis of a Sarcoma Accidentally Transplanted from a Patient to a Surgeon | NEJM
Modern concepts of cancer immunology originated from the classic observations by Jensen, Loeb, Tyzzer, and Little in the early years of the 20th century of the rejection of transplanted allogeneic ...
0114
Matthew Bernstein @matthew-bernstein.bsky.social · 26/12/2024
Good software engineering requires understanding human cognition to reduce cognitive load. I think all the fancy paradigms are just ways to accomplish this. minds.md/zakirullin/c...
minds.md
Cognitive load is what matters
There are so many buzzwords and best practices out there, but let's focus on something more fundamental. What matters is the amount of confusion developers feel when going through the code.
130
Matthew Bernstein @matthew-bernstein.bsky.social · 20/12/2024
As someone new to image analysis, I recently came upon this perspective that seems trivial, but is actually important: A pixel is a "point sample" and not a little square. A pixel is a data point, sampled from the world, like any other data point would be. pages.graphics.cs.wisc.edu/559-f14/2014...
pages.graphics.cs.wisc.edu
What is a Pixel? (and what is a point sample)
When we talk about image-based graphics, we talk about it being a regular collection (usually a grid) of samples (or pixels). It’s time to be a little more precise about this. The term pixel is (I’m t...
010
Matthew Bernstein @matthew-bernstein.bsky.social · 20/12/2024
I like ideas that find hidden biological information in seeming “artifacts”. A similar idea in this vein is RNA-velocity where intronic RNA can be used to estimate change in transcription rate.
251
Reposted by Matthew Bernstein
Zibo Chen @zibochen.bsky.social · 13/12/2024
Excited to finally share Perceptein, a PERCEPtron made of proTEINs: www.science.org/doi/10.1126/...
science.org
A synthetic protein-level neural network in mammalian cells
Artificial neural networks provide a powerful paradigm for nonbiological information processing. To understand whether similar principles could enable computation within living cells, we combined de n...
23917
Matthew Bernstein @matthew-bernstein.bsky.social · 14/12/2024
Understanding kernel methods, like SVMs, at a deep level requires understanding a pretty complicated mathematical object called the Reproducing kernel Hilbert Space. I wrote a blog post detailing my understanding of these objects and how they relate to kernel methods: mbernste.github.io/posts/rkhs/
mbernste.github.io
Reproducing kernel Hilbert spaces and the kernel trick
If you’re a practitioner of machine learning, then there is little doubt you have seen or used an algorithm that falls into the general category of kernel methods. The premier example of such methods ...
140
Reposted by Matthew Bernstein
Carl Zimmer @carlzimmer.com · 12/12/2024
Over 30 prominent scientists call for a ban on the creation of a "mirror cell"--a microbe made of molecules that are mirror images of their natural forms. It could cause a mind-boggling global disaster. Here's my story [gift link] 🧪https://nyti.ms/3OUCXp6
nyti.ms
A ‘Second Tree of Life’ Could Wreak Havoc, Scientists Warn (Gift Article)
Research on so-called mirror cells, which defy fundamental properties of living organisms, should be prohibited as too dangerous, biologists said.
931194482
Matthew Bernstein @matthew-bernstein.bsky.social · 13/12/2024
The 100 Prisoners Problem is a really nice and compact example of how a seemingly intractable problem can have a hidden structure that can be exploited, but utterly belies human intuition. When I first read it, I couldn't believe it had a non brute force solution. en.wikipedia.org/wiki/100_pri...
en.wikipedia.org
100 prisoners problem - Wikipedia
051
Matthew Bernstein @matthew-bernstein.bsky.social · 06/12/2024
I think a key quality that demonstrates scientific maturity is appropriately balancing quantitative assessments with qualitative observations. Beginners tend to err too far on one side or the other: www.scientificamerican.com/article/what...
scientificamerican.com
What This Graph of a Dinosaur Can Teach Us about Doing Better Science
“Anscombe’s quartet” and the “datasaurus dozen” demonstrate the importance of visualizing data
120
Reposted by Matthew Bernstein
owl @owlposting1.bsky.social · 04/12/2024
Can AI improve the current state of molecular simulation? www.owlposting.com/p/can-ai-imp... in my first podcast, I spend 2 hours interviewing Corin Wagen and Ari Wagen, two brothers who are building the next generation of molecular simulation for drug discovery and material science
owlposting.com
Can AI improve the current state of molecular simulation? (Corin & Ari Wagen, Ep #1)
2.1 hours listening time
15614
Matthew Bernstein @matthew-bernstein.bsky.social · 03/12/2024
Come join our team and work on exciting computational problems to advance biomedical research! jobs.gusto.com/postings/ste...
jobs.gusto.com
High Performance Computing & Image Processing Scientist at Stellaromics Inc.
021
Reposted by Matthew Bernstein
Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 03/12/2024
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!)
1615258
Matthew Bernstein @matthew-bernstein.bsky.social · 03/12/2024
It's hard for me to imagine working in a field outside of biomedical research and computational biology. Few fields offer all of the following: 1. A vast, open frontier waiting to be explored 2. The promise of saving lives and improving human health 3. Fascinating computational problems
000
Matthew Bernstein @matthew-bernstein.bsky.social · 27/11/2024
Cells are crowded spaces packed with colliding and interacting biomolecules. Despite this, intracellular functions are often described using the clean language of networks. In this post I attempt to reconcile these seemingly contradictory perspectives. mbernste.github.io/posts/intuit...
mbernste.github.io
Intuiting biology (Part 1: Order and chaos in the crowded cell)
Cells are crowded spaces packed with biomolecules colliding and interacting with one another. Despite this chaotic environment, biologists routinely describe intracellular functions using the clean ma...
253
Reposted by Matthew Bernstein
Willie Neiswanger @willieneis.bsky.social · 20/11/2024
The first list filled up, so here's a second list of AI for Science researchers on bluesky. Let me know if I missed you / if you'd like to join! bsky.app/starter-pack...
577129
Reposted by Matthew Bernstein
Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 18/11/2024
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!)
1011956
Reposted by Matthew Bernstein
owl @owlposting1.bsky.social · 08/11/2024
Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging www.owlposting.com/p/why-recurs... After over a decade,Recursion Pharmaceuticals changed its primary assay. Why is that? I answer that question over 5.6k words (26 minutes to read) first journalism-y piece!
owlposting.com
Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging
5.7k words, 26 minutes reading time
1135
Matthew Bernstein @matthew-bernstein.bsky.social · 17/11/2024
Software engineering is difficult because you have to optimize two objective functions simultaneously: 1. Maximize correctness and performance (the obvious objective) 2. Minimize the expected future effort needed to modify, fix, or enhance the code (the less obvious objective)
100
Matthew Bernstein @matthew-bernstein.bsky.social · 17/11/2024
I think a lot about this commentary about "Research Debt". This idea that humanity is drowning in a mountain of information with no easy way to understand it. Our problem isn't generating new knowledge, but rather, "distilling" the knowledge we have already generated. distill.pub/2017/researc...
distill.pub
Research Debt
Science is a human activity. When we fail to distill and explain research, we accumulate a kind of debt...
240
Matthew Bernstein @matthew-bernstein.bsky.social · 16/11/2024
As a transitionary post, my last post on X was a two-part blog post on diffusion models. I like to write pedagogical material on math and computer sciences topics I found challenging to teach myself Post 1: mbernste.github.io/posts/diffus... Post 2: mbernste.github.io/posts/diffus...
mbernste.github.io
Denoising diffusion probabilistic models (Part 1: Definition and derivation)
Diffusion models are a family of state-of-the-art probabilistic generative models that have achieved ground breaking results in a number of fields ranging from image generation to protein structure de...
052
Matthew Bernstein @matthew-bernstein.bsky.social · 16/11/2024
The experience on X is really degrading. Follow me here for thoughts on topics related to computational biology, computer science, and technology!
0141