Ben Busby! Profile
Ben Busby!

@DCGenomics

Followers
2K
Following
7K
Media
438
Statuses
7K

I work for NVIDIA and help out at CMU, JHU and Stanford in an effort to make Bioinformatics Better. Everything I post is my personal opinion. You're awesome!

Pittsburgh, PA
Joined July 2013
Don't wanna be here? Send us removal request.
@DCGenomics
Ben Busby!
1 year
I like this so much!
2
2
9
@NVIDIAHealth
NVIDIA Healthcare
16 hours
🤯 Discover how you can scale transformer models to billions of parameters in PyTorch - without rewriting your pipeline. Dive into NVIDIA BioNeMo Recipes to see how FP8 acceleration, efficient sequence packing, and the Transformer Engine empower breakthrough R&D on NVIDIA GPUs.
6
32
151
@BoWang87
Bo Wang
4 days
Honoured to be part of this new ⁦⁦@ScienceMagazine⁩ piece! The real goal isn’t just to mimic biology — it’s to discover new biology. At @Xaira_Thera, we’re building toward that vision — from scGPT to BioReason to the next-gen virtual cell.
Tweet card summary image
science.org
Researchers are competing to make “virtual cells” that could transform biomedicine by predicting gene activity and more
5
7
64
@razoralign
antisense.
7 days
The cell as a token: high-dimensional geometry in language models and cell embeddings https://t.co/jlUxzvQn1z
1
25
101
@fabian_theis
Fabian Theis
7 days
🧬 Excited to share Nicheformer out now in Nature Methods! A transformer foundation model linking single-cell & spatial omics, learning spatial context from gene expression to map tissue organization. Led by Ale Tejada & Anna Schaar 👏 👉 https://t.co/ba9DX7h2xg
0
54
233
@dr_alphalyrae
Vega Shah
9 days
Big news - today we are announcing that @nvidia is working with @EliLillyandCo to launch the world's largest Biopharma AI Factory. Built on over 1000 Blackwell Ultra GPUs, the AI factory will support applications across the entire R&D value chain including drug discovery,
Tweet card summary image
blogs.nvidia.com
Built with over 1,000 NVIDIA Blackwell Ultra GPUs, the AI factory will be essential to supporting modern scientific research using foundation models, as well as physical and agentic AI.
55
197
1K
@jdieramon
Jose V. Die
10 days
What a perfect wrap-up to the @corteva Agriscience Congress! 🌱 Organized entirely by PhD candidates and featuring cutting-edge genetic improvement research. The Symposia Series has reached 16 countries — and Spain joined for the first time! 🇪🇸👏 Proud of @ETSIAMCordoba family!
0
4
9
@iscb
ISCB News
8 days
🔔Coming soon: The next ISCBacademy webinar!  This roundtable webinar will explore product management as a #computationalbiology career. Learn what #bioinformatics careers in industry really look like and how to carve your own path!
2
3
6
@sedlazeck
Fritz Sedlazeck
10 days
Trio-barcoded @nanopre Adaptive Sampling (TBAS) to improve #RareDisease diagnostic at less than 1/2 the $$ & high cov: 76% solve rate across 13 trios inc. two corrections from prev. diagnosis. https://t.co/HbjvhTjTPn @fuyvei96 @GREGoR_research @BCM_HGSC #Genetics #bioinformatics
0
7
29
@tangming2005
Ming "Tommy" Tang
12 days
Predicting drug responses of unseen cell types through transfer learning with foundation models https://t.co/jvza2nbpA9
1
41
198
@fabian_theis
Fabian Theis
12 days
🚀 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.🔁
7
77
396
@deboramarks
Debora Marks
15 days
Announcing our new protein design server https://t.co/uu4co1sHhq: • End-to-end protein design for everyone! • Analyze your generated library interactively and on 3D structures • Export codon-optimized DNA sequences for experimental testing. Developed in collaboration
3
77
377
@BoWang87
Bo Wang
15 days
Cells don’t just exist — they talk, signal, and collaborate. Our work GraphComm is now out in @SciReports ! With GraphComm, we’re teaching AI to listen in on this cellular conversation — a step closer to building the virtual cell. 🧬🤖 🧬 GraphComm is a graph-based deep
3
52
331
@dr_alphalyrae
Vega Shah
17 days
Anthropic launched ‘Claude for Life Sciences’ today - announcing partnerships with Benchling, 10x Genomics and Pubmed
9
64
665
@theHumanBorch
Nick Borcherding
20 days
Amazing resource: 2 million T cells from 70 studies, 1017 biological samples, 583 individuals, and 46 disease conditions https://t.co/5mPPIN9WDf
Tweet card summary image
nature.com
Cell Discovery - A pan-disease and population-level single-cell TCRαβ repertoire reference
0
226
221
@joe_pickrell
Joe Pickrell
19 days
"Genetic architecture of 67 oral diseases and their links to systemic diseases" https://t.co/YAfvp1qY3n
0
13
43
@BoWang87
Bo Wang
21 days
The virtual cell is no longer a dream — it’s becoming reality. Great @TIME piece on how AI is transforming biology from data-driven to model-driven science. Our work on scGPT and BioReason laid early foundations for this vision, and at @Xaira_Thera , we’re now building next-gen
15
53
396
@nanopore
Oxford Nanopore
6 months
Make sure to save the date for next year's London Calling! #NanoporeConf
0
1
9
@razoralign
antisense.
24 days
SEAM uncovered latent regulatory motifs, decomposed cis-regulatory mechanisms into the contributions of specific binding sites and their surrounding context, and revealed how small numbers of mutations can reprogram regulatory logic.
0
1
3
@uk_biobank
UK Biobank
24 days
Some new exciting metabolomic work from @NgaleHealth using UK Biobank data 🔽 Metabolomic data for the full UK Biobank cohort will be made available to all researchers as part of our upcoming data release next month. https://t.co/86tiXeDSuO
Tweet card summary image
nature.com
Nature Genetics - Genome-wide association analyses of 249 circulating small molecules and lipoprotein characteristics across the allele frequency spectrum in UK Biobank advance understanding of...
0
16
53
@dr_alphalyrae
Vega Shah
24 days
when two awesome companies join forces
@benchling
Benchling
24 days
🧬 We’re teaming up with @NVIDIAHealth to bring #BioNeMo models directly into #BenchlingAI. Scientists will be able to access leading models like OpenFold2 for protein structure prediction — right inside their workflows. https://t.co/WYBrVMEgN9
1
11
180