Sign in

Kyle Tretina

@allthingsapx.bsky.social
740 followers 694 following 40 posts

Product Marketing Lead @NVIDIA | PhD @UMBaltimore | omics, immuno/micro, AI/ML | 🇺🇸🇸🇰 | Posts are my own views, not those of my employer.

PostsRepliesMedia
Reposted by Kyle Tretina
Albert Vilella, PhD. @albertvilella.bsky.social · 09/11/2025
@allthingsapx.bsky.social on the new Biohub initiative by the Zucks
442
Reposted by Kyle Tretina
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 21/09/2025
MMseqs2-GPU sets new standards in single query search speed, allows near instant search of big databases, scales to multiple GPUs and is fast beyond VRAM. It enables ColabFold MSA generation in seconds and sub-second Foldseek search against AFDB50. 1/n 📄 www.nature.com/articles/s41... 💿 mmseqs.com
nature.com
GPU-accelerated homology search with MMseqs2 - Nature Methods
Graphics processing unit-accelerated MMseqs2 offers tremendous speedups for homology retrieval from metagenomic databases, query-centered multiple sequence alignment generation for structure predictio...
417463
Kyle Tretina @allthingsapx.bsky.social · 16/09/2025
Preprint: Highly efficient protein structure prediction on NVIDIA RTX Blackwell and Grace-Hopper nvda.ws/4n4xzz9 Visit the NVIDIA Digital Biology Labs website to find more information like this: t.co/R9ufEZrGEA
nvda.ws
0154
Kyle Tretina @allthingsapx.bsky.social · 16/09/2025
Near-real-time protein structures change science: It means: → Next-gen protein AI data waves → Interactive protein design loops (DMTA in hours) → Proteome-scale insights with fewer resources It means the bottleneck doesn't have to be compute. It's close (preprint below).
150
Kyle Tretina @allthingsapx.bsky.social · 30/08/2025
+1
000
Kyle Tretina @allthingsapx.bsky.social · 30/08/2025
Does anyone here care about biomolecular AI? Who should I follow?
010
Kyle Tretina @allthingsapx.bsky.social · 15/07/2025
It looks like each per‑residue latent captures almost exclusively local information When the authors perturb the latent of a single residue, only that residue’s reconstruction quality changes, while others stay intact
010
Kyle Tretina @allthingsapx.bsky.social · 15/07/2025
Paper: arxiv.org/html/2507.09... Project: t.co/TuplU054vw
arxiv.org
La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching
100
Kyle Tretina @allthingsapx.bsky.social · 15/07/2025
🧬 Introducing La‑Proteina: a partially‑latent flow‑matching model that co‑generates sequence + all‑atom structure for proteins up to 800 aa 🧬 Side‑chains live in latents, backbone explicit → 75 % codesign & SOTA motif scaffolds 🔥
110
Kyle Tretina @allthingsapx.bsky.social · 15/07/2025
I'm at ICML 2025! DM me if you want to chat. @icmlconf.bsky.social #ICML2025 #icml25 #BioNeMo
000
Kyle Tretina @allthingsapx.bsky.social · 13/06/2025
To learn more about the impact of MMseqs2-GPU and test it out (for free), here's a blog I wrote: developer.nvidia.com/blog/acceler...
developer.nvidia.com
Accelerated Sequence Alignment for Protein Science with MMseqs2-GPU and NVIDIA NIM | NVIDIA Technical Blog
Protein sequence alignment—comparing protein sequences for similarities—is fundamental to modern biology and medicine. It illuminates gene functions by reconstructing evolutionary relationships…
0104
Kyle Tretina @allthingsapx.bsky.social · 13/06/2025
Boltz-2 just dropped: open-source AI that predicts both protein complex folds ✚ binding affinities in one shot 🚀 This is a win for protein AI, but let's not forget MSAs, the bioinformatics backbone many structure models lean on.
172
Kyle Tretina @allthingsapx.bsky.social · 13/06/2025
Try it out: build.nvidia.com/colabfold/ms... Blog: developer.nvidia.com/blog/acceler...
build.nvidia.com
msa-search Model by Colabfold | NVIDIA NIM
Generates a multiple sequence alignment from a query sequence and a protein sequence database search.
000
Kyle Tretina @allthingsapx.bsky.social · 13/06/2025
MMseqs2-GPU is available as a downloadable NVIDIA NIM microservice (MSA-Search)!
100
Reposted by Kyle Tretina
Karsten Kreis @karstenkreis.bsky.social · 04/03/2025
📢📢 "Proteina: Scaling Flow-based Protein Structure Generative Models" #ICLR2025 (Oral Presentation) 🔥 Project page: research.nvidia.com/labs/genair/... 📜 Paper: arxiv.org/abs/2503.00710 🛠️ Code and weights: github.com/NVIDIA-Digit... 🧵Details in thread... (1/n)
13910
Kyle Tretina @allthingsapx.bsky.social · 23/12/2024
Please add me 😄 scholar.google.com/citations?us...
scholar.google.com
Kyle Tretina, Ph.D.
‪Insilico Medicine‬ - ‪‪Cited by 802‬‬ - ‪Molecular Microbiology and Immunology‬
110
Kyle Tretina @allthingsapx.bsky.social · 10/12/2024
I’m @neurips24! Let’s chat😁
110
Reposted by Kyle Tretina
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 07/12/2024
"Are there at least 3 simulations per simulation condition with statistical analysis?" From @commsbio.bsky.social's "Reliability and reproducibility checklist for molecular dynamics simulations" (doi.org/10.1038/s420...) IMO the number 3 is meaningless and could equally well be 1 or 1000
2195
Reposted by Kyle Tretina
Frank Noe @franknoe.bsky.social · 06/12/2024
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science. www.biorxiv.org/content/10.1...
21441147
Kyle Tretina @allthingsapx.bsky.social · 06/12/2024
DiffDock was the first time a traditional drug discovery simulation task was represented as a generative AI task AFAIK. Recent DiffDock versions + other DL models are advancing rapidly + solving real problems for researchers. Let's have a balanced conversation about it. arxiv.org/abs/2412.02889
arxiv.org
Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows
The diffusion learning method, DiffDock, for docking small-molecule ligands into protein binding sites was recently introduced. Results included comparisons to more conventional docking approaches, wi...
120
Reposted by Kyle Tretina
Martin Pacesa @martinpacesa.bsky.social · 30/11/2024
#CASP16 results are in! Template-based VFold seems to be lead method for nucleic acid structure prediction! AlphaFold2 and 3 still seem to be best methods for protein monomer and complex prediction.
28623
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it!
000
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it.
000
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it.
100
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it.
100
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to your starter packs. I'd appreciate it. Nice to meet you!
000
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it.
000
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it.
000
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it.
000
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it.
000
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack. I'd appreciate it.
110
Kyle Tretina @allthingsapx.bsky.social · 03/12/2024
Please add me to this starter pack as well. I'd appreciate it.
100
Kyle Tretina @allthingsapx.bsky.social · 19/11/2024
If you're building AI models for drug discovery, you should check out the newly open-source #BioNeMo Framework: code: github.com/NVIDIA/bione... paper: arxiv.org/abs/2411.10548 docs: docs.nvidia.com/bionemo-fram... explainer: t.co/7MOamSChGN
github.com
GitHub - NVIDIA/bionemo-framework: BioNeMo Framework: For building and adapting AI models in drug discovery at scale
BioNeMo Framework: For building and adapting AI models in drug discovery at scale - NVIDIA/bionemo-framework
094
Kyle Tretina @allthingsapx.bsky.social · 16/11/2024
Friends, Real-time, accurate protein structure prediction has never felt so imminent. Code: github.com/soedinglab/m... Publication: www.biorxiv.org/content/10.1... Blog: developer.nvidia.com/blog/boost-a... Press: blogs.nvidia.com/blog/japan-s...
030
Reposted by Kyle Tretina
Anshul Kundaje @anshulkundaje.bsky.social · 14/11/2024
developer.nvidia.com/blog/boost-a... Boost Alphafold2 Protein Structure Prediction with GPU-Accelerated MMseqs2 Nice improvements in speed
developer.nvidia.com
Boost Alphafold2 Protein Structure Prediction with GPU-Accelerated MMseqs2 | NVIDIA Technical Blog
The ability to compare the sequences of multiple related proteins is a foundational task for many life science researchers. This is often done in the form of a multiple sequence alignment (MSA)…
35315
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Now available – DiffDock 2.0 NIM This latest #NVIDIANIM update offers computational chemists and researchers a significant boost with 16% improved accuracy in identifying potential protein-small molecule interactions with Test for free: build.nvidia.com/mit/diffdock...
build.nvidia.com
diffdock model by mit | NVIDIA NIM
Predicts the 3D structure of how a molecule interacts with a protein.
000
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Now available – an updated RFdiffusion NIM This #NVIDIANIM enables researchers to efficiently design protein therapeutic candidates 1.9x faster due to accelerations in the inference engine, making their preclinical research smarter and less expensive. Test for free: build.nvidia.com/ipd/rfdiffus...
build.nvidia.com
rfdiffusion model by ipd | NVIDIA NIM
A generative model of protein backbones for protein binder design.
000
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Cheers to some exceptional researchers Christian Dallago, Alejandro Chacon, Bertil Schmidt, Milot Mirdita, Martin Steinegger and Felix Kallenborn and others! Read more details in the blog at the top of this thread, and the preprint will be on BioRxiv soon. 6/
000
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Since many other AI models and workflows could benefit from the acceleration, I'm excited to see what it accelerates next! 5/
100
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Since many protein structure prediction models depend on algorithms like #MMseqs2GPU, it was integrated into AlphaFold2 (ColabFold) and saw a 22x speedup in end-to-end prediction times. 4/🧵
100
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
This acceleration is a game-changer for drug discovery. It enables scientists to perform many workflows faster, including those for target ID, protein function studies, lead optimization, drug resistance, precision medicine, vaccine design research, and many others. 3/🧵
100
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Imagine unlocking biological insights in minutes, not hours. #MMseqs2GPU means researchers can search for homologous sequences >170x to 720x faster. 2/🧵
100
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Accelerated computing is powering a new era in protein structure prediction, now with speed-of-light multiple sequence alignments. #MMseqs2GPU now makes #AlphaFold2 predictions faster and more efficient than ever. 1/🧵 developer.nvidia.com/blog/boost-a...
developer.nvidia.com
Boost Alphafold2 Protein Structure Prediction with GPU-Accelerated MMseqs2 | NVIDIA Technical Blog
The ability to compare the sequences of multiple related proteins is a foundational task for many life science researchers. This is often done in the form of a multiple sequence alignment (MSA)…
100
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Accelerated computing is revolutionizing protein structure prediction, starting with lightning-fast multiple sequence alignments. Read more about #AlphaFold and #MMseqs2GPU: developer.nvidia.com/blog/boost-a...
developer.nvidia.com
Boost Alphafold2 Protein Structure Prediction with GPU-Accelerated MMseqs2 | NVIDIA Technical Blog
The ability to compare the sequences of multiple related proteins is a foundational task for many life science researchers. This is often done in the form of a multiple sequence alignment (MSA)…
120
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Have you seen the innovation coming out of Japan recently? 👀 blogs.nvidia.com/blog/japan-s...
blogs.nvidia.com
Japan Develops Next-Generation Drug Design, Healthcare Robotics and Digital Health Platforms
Japan is pursuing sovereign AI initiatives supporting nearly every aspect of healthcare. They're highlighted at the NVIDIA AI Summit Japan.
000
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
Analyzing extensive scientific literature and real-world evidence, Muse delivers comprehensive research and identifies optimal patient profiles and recruitment strategies, including materials tailored for diverse populations. formation.bio/blog/introdu...
formation.bio
Introducing Muse
Formation Bio collaborates with Sanofi and OpenAI to Introduce Muse, a first of its kind AI tool to accelerate patient recruitment in drug development.
120
Kyle Tretina @allthingsapx.bsky.social · 13/11/2024
I can't help but think TDC-2 is a peek into the future of therapeutic AI, where multimodal data integration and single-cell precision drive discovery. biorxiv.org/content/10.1...
biorxiv.org
010