Bernardo Almeida
@deAlmeida_BP
Followers
702
Following
3K
Media
37
Statuses
762
Senior research scientist at @instadeepai, interested in building computational models that can read the human genome and interpret it's variation
Joined September 2017
Really happy to see our work making the cover of @NatMachIntell !! Big thanks to the whole @instadeepai team! If you missed it check out our new ChatNT model in the links below 👇
ChatNT has been featured on the front cover of @NatMachIntell! This exciting opportunity allows us to share our proof-of-concept for a generalist genomics AI with a wider community of scientists and researchers around the world. 🎊
0
1
13
Excited to see our work on SegmentNT published in @naturemethods ! Built on the Nucleotide Transformer (NT), SegmentNT combines large-scale pretraining with segmentation principles to achieve state-of-the-art single-nucleotide annotation across genic, splicing & regulatory
1
2
4
As seen in @NatureMethods, meet SegmentNT, our transformer model for fast, single-nucleotide, multi-task genome annotation. 🧬
1
5
10
📍 SegmentNT can handle 50,000-nucleotide sequences and predict 14 different genomic and regulatory elements, all at once! 🧠 Built on our Nucleotide Transformer foundation, it detects features across scales in a single pass.
1
2
5
See more details at
📍 SegmentNT can handle 50,000-nucleotide sequences and predict 14 different genomic and regulatory elements, all at once! 🧠 Built on our Nucleotide Transformer foundation, it detects features across scales in a single pass.
0
0
1
Very happy to see our SegmentNT paper published. A fun work on the genome annotation field. Great team work with @thomas_pierrot and all colleagues at @instadeepai!
SegmentNT: a general segmentation model for genome annotation that can process DNA sequences up to 50-kb long and shows strong generalization across unseen species. @deAlmeida_BP @thomas_pierrot
https://t.co/c3nPKSbHLc
1
0
1
The first large language health model that predicts >1,000 diseases and the time they will occur in a person was just published @Nature, by @MoritzGerstung @artem_shmatko and colleagues https://t.co/Bp6ZJ25PKF This, along with other recent groundbreaking reports, represents the
13
220
633
Latest genomic AI models report near-perfect prediction of pathogenic variants (e.g. AUROC>0.97 for Evo2). We ran extensive independent evals and found these figures are true, but very misleading. A breakdown of our new preprint: 🧵
9
118
486
Join @LenPennacchio, @ZhipingWeng, @xielablife, me and all speakers in beautiful Suzhou, China for this year's CSH Asia Systems Biology of Gene Regulation & Genome Editing meeting, Oct 20-24. Let's bring the international communities together! Abstract deadline Sept 5! More infos
2
16
46
⚡️Thrilled that #VirtualLab is published in @Nature! https://t.co/BwAsLFAeua We created a team of AI agents to mirror my Stanford lab🤖. Led by a PI agent, the AI scientists ran their own group meetings and discovered effective binders to new CoVID variants that we validated.
24
246
972
A multimodal conversational agent for DNA, RNA and protein tasks https://t.co/LZainxfIhX 🧬🖥️🧪 https://t.co/fC3n13R3fj
0
31
137
Thrilled to open-source the dataset behind our @NatMachIntell cover paper! 🧬 The ChatNT training data is now open-source on @huggingface. It's the first large-scale dataset for training conversational agents on biological sequences. A thread on what's inside 👇
1
8
16
Our ChatNT work just made the cover of the June issue of @NatureMachIntell 🤯 "A conversational agent fluent in biological sequences" So incredibly proud of the dream team at @InstaDeepAI! What a milestone ⭐
1
4
19
We made the cover of @NatMachIntell! 🌱 ChatNT is a Conversational Agent analysing genomics sequences to answer key biological questions, assisting scientists in their work 👩🔬 Kudos to @deAlmeida_BP, @thomas_pierrot & the @instadeepai research team for this huge milestone!✨
0
2
18
ChatNT has been featured on the front cover of @NatMachIntell! This exciting opportunity allows us to share our proof-of-concept for a generalist genomics AI with a wider community of scientists and researchers around the world. 🎊
1
5
20
A multimodal conversational agent for DNA, RNA and protein tasks @NatMachIntell １．ChatNT is a new conversational AI system that understands DNA, RNA and protein sequences, enabling biologists to solve complex genomics tasks simply by asking questions in English. ２．Unlike
0
13
43
ChatNT can optimise multiple tasks simultaneously, in conversational English. Trained on a dataset spanning 27 biological functions and species, including 600 million DNA tokens and 273 million English tokens, ChatNT is designed to be a useful agent for scientists without coding
2
2
7
Yup. Data curation, sanitization, QC, harmonization & uniform processing with robust & technically robust approaches are absolutely critical to push ML models to the next level. 1/
Most interesting part of the Boltz-2 paper was how important curation was to achieve competitive results with FEP As we move "upwards" from molecular interactions to more complex disease mechanisms - pathway dynamics, cell-cell interactions, whole tissue biomarkers - think about
3
7
49
🧬DNA meets Dialogue! Introducing ChatNT, our groundbreaking multimodal AI that fluently translates genomics into everyday language, unlocking powerful insights for scientists, no coding needed! Published today in @NatMachIntell 🚀, ChatNT was crafted by the visionary
2
2
18
Introducing ChatNT: The first biological sequence-language model, published in @NatMachIntell ! 🧬🎉 Inspired by vision-language models, ChatNT's architecture combines biological and language foundation models, using Nucleotide Transformer (NT) and Llama to answer questions
0
5
12