Artur Szałata Profile
Artur Szałata

@arturszalata

Followers
776
Following
1K
Media
11
Statuses
165

Machine learning for molecular biology. @ELLISforEurope PhD student @fabian_theis lab. @EPFL_en alumnus.

Joined August 2020
Don't wanna be here? Send us removal request.
@arturszalata
Artur Szałata
1 year
Interested in predicting transcriptomic effects of perturbations? Check out our @NeurIPSConf D&B spotlight living perturbation prediction benchmark & new drug perturbation dataset: - paper: https://t.co/GBZZGmbtes ! - benchmarking platform: https://t.co/HsXMMVAMrc🧵1/8
3
5
38
@Waymo
Waymo
7 days
Hello London! 👋 Our vehicles are now driving in London as we prepare for commercial service in 2026.
240
342
4K
@karpathy
Andrej Karpathy
21 days
A number of people are talking about implications of AI to schools. I spoke about some of my thoughts to a school board earlier, some highlights: 1. You will never be able to detect the use of AI in homework. Full stop. All "detectors" of AI imo don't really work, can be
@karpathy
Andrej Karpathy
22 days
Gemini Nano Banana Pro can solve exam questions *in* the exam page image. With doodles, diagrams, all that. ChatGPT thinks these solutions are all correct except Se_2P_2 should be "diselenium diphosphide" and a spelling mistake (should be "thiocyanic acid" not "thoicyanic") :O
945
3K
17K
@wildtypehuman
Jake P. Taylor-King
22 days
@elocinationn Great analysis... many of these problems are why I started blogging... for example,
1
2
7
@suragnair
Surag Nair
1 month
Excited to share Nona: a unifying multimodal masking framework for functional genomics. Models for DNA have evolved along separate paths: sequence-to-function (AlphaGenome), language models (Evo2), and generative models (DDSM). Can these be unified under a single paradigm? 1/15
5
51
228
@pkoo562
Peter Koo
1 month
🔥It takes domain expertise to navigate a field and assess progress. Building (mediocre) AI models is easy—the challenge is rigorous evals. Beware of new benchmarks that are half baked or exclusion of SOTA to make performance seem impressive. THIS IS A PERVASIVE ISSUE IN AI x BIO
3
4
47
@MDLuecken
Malte Luecken
1 month
Interested in longitudinal spatial (multi)omics applied to an unmet clinical need? Want to work in academia, together with industry to see your research translated into a drug development context? Join us to investigate early signatures of fibrogenesis https://t.co/hddILOK2cX
1
4
6
@i000
Marcin Cieslik
2 months
@kenbwork The modern bio literature is effectively depleted of debate and controversy. Incorrect results are not challenged but ignored. As a result LLMs take too much at face value, and have no way of learning the insider scoops you mention.
4
3
14
@fchollet
François Chollet
2 months
The bottleneck for deep skill isn't usually intelligence, but boredom tolerance. Learning has an activation energy: below a certain skill threshold, practice is tedious, but above it, it becomes a self-sustaining flow state. The entire battle is persisting until that transition.
122
906
7K
@anshulkundaje
Anshul Kundaje
2 months
@willyakah @ron_alfa Anyone who thinks ML engineering is the main bottleneck in building better cellular models is going to be sorely disappointed. Better problem formulation & the right data collection strategy will win any day of the year.
5
24
237
@fabian_theis
Fabian Theis
2 months
🚀 Our new Science paper is out (w/ B DeMeo, D Burkhardt, A Shalek, M Cortes): https://t.co/NSfnCblwHh We show that active learning + transcriptomic perturbations can guide which exps to run next, boosting phenotypic hit rates >13x. AI not just predicting bio, but designing it.🔁
8
78
399
@arturszalata
Artur Szałata
2 months
Active learning with DrugReflector beats SotA in phenotypic hit-rate for virtual screening. Includes a sc pert dataset with 10 lines and 104 compounds. Out in @ScienceMagazine! Grateful to @cellaritybio & @fabian_theis for the opportunity to contribute! Link below
1
0
2
@AndrewYNg
Andrew Ng
2 months
Readers responded with both surprise and agreement last week when I wrote that the single biggest predictor of how rapidly a team makes progress building an AI agent lay in their ability to drive a disciplined process for evals (measuring the system’s performance) and error
Tweet card summary image
deeplearning.ai
DeepLearning.AI | Andrew Ng | Join over 7 million people learning how to use and build AI through our online courses. Earn certifications, level up your skills, and stay ahead of the industry.
85
291
2K
@andrewgwils
Andrew Gordon Wilson
2 months
I'm going to start adding "humanity's last" to every new paper. "Humanity's last Gaussian process", "Humanity's last batch size"...
6
10
167
@anshulkundaje
Anshul Kundaje
3 months
This is insufficient verification of perturbation prediction. These are like positive controls. Plenty of correlation in gene expression. High likelihood of extensive false positives if perturbations are done systematically for all genes due to correlation != causality.
@KSusztak
Katalin Susztak
3 months
Because it is multimodal, Nephrobase goes beyond clustering. In silico gene perturbations simulate biology: CCL2 → immune chemotaxis VCAM1 → endothelial migration GDF15 → growth regulation SOX4 → morphogenesis + energy metabolism
3
8
86
@anshulkundaje
Anshul Kundaje
3 months
This is a nice dataset and model, but this is an apples & oranges comparison. The Nephrobase model is literally trained on cell labels with a supervised loss but I'm pretty sure the other models are totally unsupervised. Guess which will do better at separating cell labels?
@KSusztak
Katalin Susztak
3 months
In both human & mouse, Nephrobase produces tight, biologically correct clusters. ARI 0.82 vs ~0.3–0.5 for others Perfect batch mixing This works because it integrates multispecies + multimodal inputs into one latent map.
2
5
38
@rasbt
Sebastian Raschka
3 months
@growing_daniel “The best minds of my generation are thinking about how to make people click ads.”
7
35
698
@giffmana
Lucas Beyer (bl16)
3 months
Wow this is a disappointingly bad take/comic. To all the students, PhD or earlier: If you spend a week trying out things that don't work, you didn't do nothing! If you ran your experiments properly, you should have confidence in the result, and at least some intuition as to why
@PHDcomics
PHD Comics
3 months
Anything to report?
37
46
780
@pdhsu
Patrick Hsu
3 months
Today in @ScienceMagazine, we report a new DNA editing technology to seamlessly write massive changes into the right place in the human genome. The reason gene editing hasn't transformed human health is that current gene editing technologies like CRISPR are very limited. The
@pdhsu
Patrick Hsu
1 year
What if we could universally recombine, insert, delete, or invert any two pieces of DNA? In back-to-back @Nature papers, we report the discovery of bridge RNAs and 3 atomic structures of the first natural RNA-guided recombinase - a new mechanism for programmable genome design
76
673
3K