Theodoris Lab

32 posts

Theodoris Lab banner
Theodoris Lab

Theodoris Lab

@TheodorisLab

mapping gene networks to enable network-based therapeutic discovery in cardiovascular disease

Gladstone Institutes 가입일 Eylül 2022
51 팔로잉555 팔로워
Theodoris Lab
Theodoris Lab@TheodorisLab·
Thank you to the whole team for the wonderful collaboration! Javier Gómez Ortega, @Sid_Mahesh_12, Tarak Nandi, @madduri, and @PelkaLab! x.com/TheodorisLab/s…
Theodoris Lab@TheodorisLab

We are excited to share work led by @hanimal725 and @madhavanvvs developing a quantized multitask learning strategy for network biology, built on a foundation model pretrained on ~95M single-cell transcriptomes. Manuscript: tinyurl.com/qmtl-gf Model: huggingface.co/ctheodoris/Gen…

English
0
1
1
558
Theodoris Lab
Theodoris Lab@TheodorisLab·
Overall, quantized multi-task learning enables resource-efficient context-specific modeling in gene network biology to yield contextual predictions of key network regulators and candidate therapeutic targets for human disease.
English
1
0
0
454
Theodoris Lab 리트윗함
Eric Nguyen
Eric Nguyen@exnx·
Is DNA all you need? Introducing Evo, a long context 7B foundation model for biology Evo has SOTA *zero-shot* prediction across DNA, RNA, and protein modalities Evo can generate DNA, RNA+proteins & make CRISPR-Cas systems for first time blog …n-model-tool-arc-institute.vercel.app/news/blog/evo
GIF
English
9
149
674
106.2K
Theodoris Lab
Theodoris Lab@TheodorisLab·
Wonderful work by @ChanZuckerberg Initiative releasing cell embeddings from models including Geneformer integrating up to 36M cells from CELLxGENE!
Jonah Cool@JCoolScience

🚨1/ New to CZ #CELLxGENE: models & embeddings that integrate up to 36M cells in the Census corpus. Use embeddings to explore the corpus directly, or download the models to run your own data through them to enable direct comparisons to the reference. 🧵 bit.ly/census_models

English
0
1
18
2.2K
Theodoris Lab 리트윗함
Eric Nguyen
Eric Nguyen@exnx·
Long context is cool, but long context for biology?😍🧬 Introducing HyenaDNA, a long-range genomic LLM pretrained w/ context length *1 million tokens* using a single char tokenizer on DNA 500x longer, 160x faster than prev genomic LLMs, fits on colab arxiv.org/abs/2306.15794 1/
Eric Nguyen tweet media
English
5
72
253
88.9K
Theodoris Lab
Theodoris Lab@TheodorisLab·
This work was a wonderful collaborative effort with @LingXiao_PhD, @Anantchopra, Mark Chaffin, @ZeinaALsayed78, Matt Hill, Helene Mantineo, Elizabeth Brydon, @ZexianZeng, @XShirleyLiu, and @patrick_ellinor. twitter.com/TheodorisLab/s…
Theodoris Lab@TheodorisLab

We are excited to share Geneformer, our foundation model pretrained on 30 million single cell transcriptomes to enable predictions in network biology. Manuscript: rdcu.be/ddrx0 Model: huggingface.co/ctheodoris/Gen… Pretraining corpus: huggingface.co/datasets/ctheo…

English
1
1
6
2K
Theodoris Lab
Theodoris Lab@TheodorisLab·
Overall, Geneformer is a foundation model whose fundamental understanding of network dynamics can now be democratized to a broad range of downstream applications to accelerate discovery of key network regulators and candidate therapeutic targets in settings with limited data.
English
1
0
5
1.3K

탐색

@Sid_Mahesh_12 @madduri @PelkaLab @hanimal725 @madhavanvvs @BoWang87 @mo_lotfollahi @ChanZuckerberg