Sign in

Pablo Arantes

@pabloarantes.bsky.social
879 followers 1.4K following 49 posts

#compchem Research Scientist at Vita Nova Institute- Work interests mostly related to the simulation of biomolecular systems - Lead developer of the Making It Rain, Cloud-Bind and ParametrizANI projects. pablo-arantes.github.io

PostsRepliesMedia
Pablo Arantes @pabloarantes.bsky.social · 25/05/2026
📄 Paper (JCIM 2025): pubs.acs.org/doi/abs/10.1021/acs.jcim.5c01957 Feedback & contributions welcome! 🙏 #CompChem #MolecularDynamics #Python #OpenSource #DrugDiscovery 🧵 4/4
pubs.acs.org
ParametrizANI: Fast and Accessible Dihedral Parametrization for Small Molecules
In molecular studies, the accurate parametrization of small molecules stands as an essential yet growing demand. Addressing this, we introduce ParametrizANI, a tool crafted explicitly for establishing...
092
Pablo Arantes @pabloarantes.bsky.social · 25/05/2026
💻 Quick code demo: 🧵 3/4
110
Pablo Arantes @pabloarantes.bsky.social · 25/05/2026
✨ What's new vs. the Colab notebooks: • Clean pip-installable API • GAFF2 + OpenFF support • Multi-format export (AMBER, GROMACS, OpenMM) • 7 ANI models + MACE, AIMNet2, xTB • Optional Psi4 RESP charges • Built-in RMSE/MAE/R² validation 🧵 2/4
100
Pablo Arantes @pabloarantes.bsky.social · 25/05/2026
🚀 ParametrizANI is now a Python package! From SMILES to AMBER/GROMACS/OpenMM force field parameters in one script, powered by neural network potentials (TorchANI, MACE-OFF, AIMNet2, xTB). DFT-level accuracy, CPU-only. 📦 github.com/pablo-arantes/ParametrizANI 📚 parametrizani.readthedocs.io 🧵1/4
github.com
GitHub - pablo-arantes/ParametrizANI: Free Parametrization for Small Molecules
Free Parametrization for Small Molecules. Contribute to pablo-arantes/ParametrizANI development by creating an account on GitHub.
262
Reposted by Pablo Arantes
jproney @jproney.bsky.social · 10/12/2025
I'm super excited to announce the first preprint of my PhD, together with Chenxi Ou and @sokrypton.org! ML has revolutionized protein modeling, but crucial challenges remain. For example, we can't reliably predict complicated protein structures without MSAs, which limits what we can design.
2326
Pablo Arantes @pabloarantes.bsky.social · 19/11/2025
🎉 New publication in JCIM at @pubs.acs.org! We present eRMSF, a Python package for ensemble-based RMSF analysis of biomolecular systems, supporting MD, PDB, and ML ensembles. Proud to collaborate with Rodrigo Ligabue-Braun and @conradopedebos.bsky.social pubs.acs.org/doi/10.1021/...
pubs.acs.org
eRMSF: A Python Package for Ensemble-Based RMSF Analysis of Biomolecular Systems
Understanding molecular flexibility and dynamics across different structural ensembles is essential for interpreting the behavior of complex biological systems. Here, we introduce eRMSF, a fast and user-friendly Python package built with MDAKit from MDAnalysis, designed to perform ensemble-based root mean square fluctuation (RMSF) analyses. Unlike traditional approaches limited to molecular dynamics trajectories, eRMSF extends flexibility analysis to ensembles generated by different methods, such as MD simulations, BioEmu (a deep learning tool for equilibrium ensemble prediction), subsampled AlphaFold2 (AlphaFold ensemble generation), and other computational or experimental sources. By enabling RMSF calculations across heterogeneous ensembles, eRMSF provides a unified framework to evaluate residue or atomic fluctuations in both simulated and predicted structures. Users can easily customize atom, residue, or region selections, tailoring analyses to specific research questions. This approach delivers high-resolution insights into localized motions, complements global stability assessments, and reveals dynamic regions often overlooked by single-method analyses. The repository for eRMSF is available at https://github.com/pablo-arantes/ermsfkit.
2166
Pablo Arantes @pabloarantes.bsky.social · 12/10/2025
WOW!!! Fantastic news, Fiona! 🎉 Wishing you all the best, can’t wait to hear more about your new group!
000
Pablo Arantes @pabloarantes.bsky.social · 09/10/2025
🧠💥 ParametrizANI found a home! Our paper is now published in JCIM! Making ML-based force field parametrization open and easy for everyone. With TorchANI, @rdkit.bsky.social & @openmm.org 🔗 pubs.acs.org/doi/abs/10.1... @acs.org @giuliapalermo.bsky.social
030
Pablo Arantes @pabloarantes.bsky.social · 07/10/2025
Your protein moves, but when exactly? ⏱️ Meet eRMSF, our new Python tool that tracks fluctuations over time! Traditional RMSF shows “how much.” eRMSF shows “when.” 🔥 Preprint 🔗 doi.org/10.26434/che... GitHub github.com/pablo-arante... Try it on Colab → colab.research.google.com/github/pablo...
041
Reposted by Pablo Arantes
Martin Pacesa @martinpacesa.bsky.social · 27/08/2025
Exciting to see our protein binder design pipeline BindCraft published in its final form in @Nature ! This has been an amazing collaborative effort with Lennart, Christian, @sokrypton.org, Bruno and many other amazing lab members and collaborators. www.nature.com/articles/s41...
14305109
Pablo Arantes @pabloarantes.bsky.social · 21/08/2025
Thank you, @olexandr.bsky.social! Yes, AIMNet2 is included in the notebook. Users can choose between several models: TorchANI, AIMNet2, and MACE-OFF. 😉
020
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
Thank you my friend! 🥰
000
Reposted by Pablo Arantes
Marcelo D. Polêto @mdpoleto.bsky.social · 20/08/2025
When Pablo told me about this idea, I could see an immediate impact on drug discovery endeavors. People can easily refine parameters of multiple dihedral torsion for hundreds of molecules and employ those in FEP simulations. 10/10 recommend 👍
141
Reposted by Pablo Arantes
Giulia Palermo @giuliapalermo.bsky.social · 20/08/2025
New from our lab! 🚀 ParametrizANI - a #NeuralNetworks tool for molecular parametrization. Predicts potential energy surfaces with near-DFT/CC accuracy, at a fraction of the computational cost! #AI #QuantumChemistry #CompChem #ML 🤖 chemrxiv.org/engage/chemr... Try it: github.com/palermolab/P...
github.com
GitHub - palermolab/ParametrizANI: ParametrizANI - Fast, Accurate and Free Dihedral Parametrization in the Cloud with TorchANI
ParametrizANI - Fast, Accurate and Free Dihedral Parametrization in the Cloud with TorchANI - palermolab/ParametrizANI
3379
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
Huge thanks to our co-authors Souvik Sinha & @giuliapalermo.bsky.social ! And deep gratitude to the @openmm.org, TorchANI team, Rotational Profiler developers, the "Making it Rain" team (@conradopedebos.bsky.social , @mdpoleto.bsky.social and Rodrigo Ligabue Braun) for their inspiration! 8/8
media.tenor.com
a man with long hair and a beard is smiling and saying thank you .
ALT: a man with long hair and a beard is smiling and saying thank you .
020
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
Ready to try it? ✨ All our Colab notebooks are freely & publicly available on @github.com! Dive in to enhance your molecular studies. We're committed to fostering deeper insights & improved methodologies in the scientific community. Find ParametrizANI here: 7/8 github.com/palermolab/P...
github.com
GitHub - palermolab/ParametrizANI: ParametrizANI - Fast, Accurate and Free Dihedral Parametrization in the Cloud with TorchANI
ParametrizANI - Fast, Accurate and Free Dihedral Parametrization in the Cloud with TorchANI - palermolab/ParametrizANI
100
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
A game-changer! ParametrizANI is perfect for drug discovery, helping evaluate candidates with high accuracy & speed. It's also an excellent resource for education, offering hands-on experience without complex setups, & allows professional customization. #DrugDiscovery 6/8
media.tenor.com
a man with his mouth open and the words lightbulb moment written on the bottom
ALT: a man with his mouth open and the words lightbulb moment written on the bottom
100
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
Our user-friendly Jupyter notebooks provide a complete workflow for dihedral parametrization, from SMILES strings to optimized force field parameters. We support both GAFF & @openforcefield.org force fields, ensuring compatibility for your simulations. #ForceFields 5/8
210
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
Accessibility is key! ParametrizANI runs on @googlecolab.bsky.social, a "click-and-go" experience with free access to CPUs. No heavy parallel processing needed! We've parametrized molecules in less than 5 minutes on CPU. A big step for accurate, efficient small molecule parametrization! 4/8
media.tenor.com
a cartoon character named spongebob is holding a box with the words " the cloud " written on it
ALT: a cartoon character named spongebob is holding a box with the words " the cloud " written on it
100
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
A core component: our Python version of the Rotational Profiler code. This analytical algorithm efficiently computes classical torsional dihedral parameters by fitting empirical energy profiles to a reference curve. #ComputationalChemistry #Algorithms #ForceFields 3/8
media.tenor.com
a man says " my algorithm is insane " while wearing a baseball cap
ALT: a man says " my algorithm is insane " while wearing a baseball cap
100
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
How? ParametrizANI uses the robust PyTorch-based TorchANI program & ANI deep learning models (ANI-1x, ANI-2x). This predicts potential energy surfaces with near-DFT or coupled-cluster accuracy, at a fraction of the computational cost! #DeepLearning #TorchANI #AIforScience 2/8
media.tenor.com
a woman says yes that is painfully accurate in front of a crowd of people
ALT: a woman says yes that is painfully accurate in front of a crowd of people
110
Pablo Arantes @pabloarantes.bsky.social · 20/08/2025
Exciting news for molecular research! Introducing ParametrizANI: a fast, accurate, & free tool for small molecule parametrization! We're democratizing research, enabling teams of all sizes to perform dihedral parametrization with DFT-level accuracy. 1/8 doi.org/10.26434/che...
doi.org
ParametrizANI: Fast, Accurate, and Free Parametrization for Small Molecules
In molecular studies, the accurate parametrization of small molecules stands as an essential yet growing demand. Addressing this, we introduce ParametrizANI, a tool crafted explicitly for establishing...
193
Reposted by Pablo Arantes
Martin Pacesa @martinpacesa.bsky.social · 30/06/2025
We have written up a tutorial on how to run BindCraft, how to prepare your input PDB, how to select hotspots, and various other tips and tricks to get the most out of binder design! github.com/martinpacesa...
413755
Reposted by Pablo Arantes
Stand Up for Science! @standupforscience.net · 09/06/2025
🚨BREAKING: 300+ NIH employees call out the harm of censorship & politicized science in scathing email to Bhattacharya, demanding an end to political interference, a lift on funding freezes, & rehiring of fired staff whose work saves lives. This is historic - insiders are blowing the whistle. 🧵(1/5)
Front-page-style graphic titled “BREAKING NEWS” with photos of RFK Jr. and Dr. Bhattacharya in front of a government hearing chamber. Text reads: “NIH Scientists Sound the Alarm as Health Research Faces Historic Threat” and “NIH Employees Send Trump Cronies Scathing Wake-Up Call.”
4043101388
Pablo Arantes @pabloarantes.bsky.social · 09/06/2025
Tem vaga ainda?
000
Reposted by Pablo Arantes
Yehlin Cho @yehlincho.bsky.social · 03/06/2025
🚀 Excited to release BoltzDesign1! ✨ Now with LogMD-based trajectory visualization. 🔗 Demo: rcsb.ai/ff9c2b1ee8 Feedback & collabs welcome! 🙌 🔗: GitHub: github.com/yehlincho/Bo... 🔗: Colab: colab.research.google.com/github/yehli... @sokrypton.org @martinpacesa.bsky.social
15417
Pablo Arantes @pabloarantes.bsky.social · 08/04/2025
This is the kind of message that makes it all worth it. When someone takes a moment to say thank you, it reminds me why we keep pushing forward—sharing tools, writing posts, and trying to make science more open and accessible. Grateful for the kind words!
0123
Pablo Arantes @pabloarantes.bsky.social · 02/04/2025
Our latest paper just dropped in PNAS! 🎉 Turns out, CRISPR-associated transposons don’t just jump—they dance their way through DNA! 🕺🔬 Exciting times for genome engineering! 🧬 Read more in PNAS: www.pnas.org/doi/10.1073/... #CRISPR #GeneEditing #PNAS #MDsimulations #CompChem
lnkd.in
LinkedIn
This link will take you to a page that’s not on LinkedIn
061
Pablo Arantes @pabloarantes.bsky.social · 02/04/2025
I have included side-chain reconstruction using HPacker in the BioEmu Notebook. Thank you to @martinsteinegger.bsky.social whose notebook provided inspiration for incorporating the cell to add side-chain reconstruction. 🔗 Try it on Google Colab: colab.research.google.com/github/pablo...
161
Pablo Arantes @pabloarantes.bsky.social · 24/03/2025
And what do you think would be faster to run it on a local machine with RTX 4090 or keep on the colab with the A100? I don't have access to RTX 4090 and I'm only using A100 on Google Colab, so I suggested to check the original paper: doi.org/10.1101/2024...
doi.org
Scalable emulation of protein equilibrium ensembles with generative deep learning
Following the sequence and structure revolutions, predicting the dynamical mechanisms of proteins that implement biological function remains an outstanding scientific challenge. Several experimental t...
010
Pablo Arantes @pabloarantes.bsky.social · 24/03/2025
However, do you think it would be better to do 5000 sample compared to 1000 sample? I ran some tests and compared an ensemble of 1000 samples with each containing 5000 frames. I did not observe any differences between them except for the number of frames.
110
Pablo Arantes @pabloarantes.bsky.social · 24/03/2025
Regarding your ideas, I loved the idea to compare an ensemble of WT and mutated protein using BioEmu, I'm working on a notebook to do that.
210
Pablo Arantes @pabloarantes.bsky.social · 24/03/2025
Hi Tareq, Thank you for all information regarding BioEmu. As I clearly described on my firt post, I did not develop the BioEmu, I just performed the implementation using Google Colab.
210
Pablo Arantes @pabloarantes.bsky.social · 21/03/2025
This code only supports sampling structures of monomers. You can try to sample multimers using two sequences you want to predict and connect them with a long linker, but in their experiments, this has not worked well.
020
Pablo Arantes @pabloarantes.bsky.social · 20/03/2025
I’ve just updated the BioEmu notebook to include the powerful LogMD. Now, you can generate equilibrium ensembles and explore the full ensemble directly in the notebook. A huge thanks to Alexander Mathiasen for the support! 🙌 🔗 Try it on Google Colab: lnkd.in/gcuqd-fT
35117
Pablo Arantes @pabloarantes.bsky.social · 01/03/2025
🔗 Try it on Google Colab: colab.research.google.com/github/pablo... 🔗 BioEmu GitHub Repo: github.com/microsoft/bi... 🔗 Making it Rain Repo: pablo-arantes.github.io/making-it-ra... #MolecularDynamics #AIforScience #CloudComputing #ComputationalChemistry #ProteinFolding #DeepLearning #MakingItRain
colab.research.google.com
Google Colab
071
Pablo Arantes @pabloarantes.bsky.social · 01/03/2025
🎓 BioEmu is based on the paper: 📄 Scalable emulation of protein equilibrium ensembles with generative deep learning 👨‍🔬 Authors: SarahLewis & @franknoe.bsky.social (corresponding), et al. 📌 Read it here: doi.org/10.1101/2024...
doi.org
Scalable emulation of protein equilibrium ensembles with generative deep learning
Following the sequence and structure revolutions, predicting the dynamical mechanisms of proteins that implement biological function remains an outstanding scientific challenge. Several experimental t...
173
Pablo Arantes @pabloarantes.bsky.social · 01/03/2025
🔥 To make it even easier to use, I’ve added a new notebook to the Making it Rain repo, bringing BioEmu to Google Colab. Now, you can generate equilibrium ensembles without expensive hardware or setup hassles! 🧬💻
media.tenor.com
a cartoon character named spongebob is holding a box with the words " the cloud " written on it
ALT: a cartoon character named spongebob is holding a box with the words " the cloud " written on it
110
Pablo Arantes @pabloarantes.bsky.social · 01/03/2025
Meet BioEmu, a generative AI model for scalable emulation of protein equilibrium ensembles—predicting structural distributions from just an amino acid sequence! Developed by Microsoft Research & Freie Universität Berlin, this model is reshaping biomolecular modeling. Picture from BioEmu repository.
100
Pablo Arantes @pabloarantes.bsky.social · 01/03/2025
🚀 Making it Rain ☁️💦 just got an AI-powered upgrade! 🚀 First, we made MD simulations rain down from the cloud. Now, we’re bringing deep learning into the mix! 🌩️🤖
media.tenor.com
a robot says hey guys in a purple light
ALT: a robot says hey guys in a purple light
263
Pablo Arantes @pabloarantes.bsky.social · 19/02/2025
Just a small lesson for our dear American friends…😉
040
Reposted by Pablo Arantes
Prof. Anthea Butler @antheabutler.bsky.social · 19/02/2025
How completely jealous am I of Brazil right now
nytimes.com
Brazil Charges Bolsonaro With Attempting a Coup (Gift Article)
Brazil’s attorney general charged the former president Jair Bolsonaro with trying to overturn the 2022 elections.
16695131170
Reposted by Pablo Arantes
Rafael C. Bernardi @rcbernardi.bsky.social · 17/02/2025
🚀 First Bluesky Post! 🎉 VMD 2.0 Alpha is here! Released today at BPS 2025, this is the biggest update in 30 years—new UI, real-time ray tracing, fast surfaces, UHD & touchscreen support. Monthly updates coming in 2025! Try it now! #VMD #BPS2025 #MolecularVisualization www.ks.uiuc.edu/Research/vmd...
311442
Reposted by Pablo Arantes
Roland Dunbrack 🏳️‍🌈 @rolanddunbrack.bsky.social · 16/02/2025
The d0 is key to eliminating the dependence of the TM score on alignment/structure length. It's easier for two short proteins to be randomly similar than it is for two very large proteins. A bit Bayesian: short proteins require better evidence for similarity than large ones. Better p(data | model)
Figure from Zhang and Skolnigk paper on how d0 makes TM score length-independent for random unrelated protein pairs of same length.The value of d0 as a function of length. It's a cube root.
161
Reposted by Pablo Arantes
Andrew White 🐦‍⬛ @andrew.diffuse.one · 14/02/2025
Molecular dynamics requires a lot of expert knowledge to set-up and analyze simulations. We set out to automate it with LLM agents: MDCrow!
1246
Reposted by Pablo Arantes
Giulia Palermo @giuliapalermo.bsky.social · 08/02/2025
Do you want to know why #ABE 8e is the most efficient adenine base editor? Read our paper with the amazing Audrey Lapinaite! @narjournal.bsky.social The dimerization of TadA8e and its exclusive interactions with #CRISPR Cas9 boost #BaseEditing efficiency! academic.oup.com/nar/article/...
academic.oup.com
Dimerization of the deaminase domain and locking interactions with Cas9 boost base editing efficiency in ABE8e
Abstract. CRISPR-based DNA adenine base editors (ABEs) hold remarkable promises to address human genetic diseases caused by point mutations. ABEs were deve
0102
Reposted by Pablo Arantes
Flavia Ward 🌼🌱 @flaviaward.bsky.social · 27/01/2025
Bom dia! “Tú no puedes comprar al viento Tú no puedes comprar al sol Tú no puedes comprar la lluvia Tú no puedes comprar el calor”
211213
Reposted by Pablo Arantes
Alex Huffman @alexhuffman.bsky.social · 23/01/2025
Have any academic researchers started hearing about cuts/holds on federal grants from other federal agencies outside of NIH? I got a concerning message today about a grant hold, and it seems to be the same politics. Not surprising, but further worrying ... 😨
71111
Reposted by Pablo Arantes
Alejandra Caraballo @esqueer.net · 21/01/2025
Nazis: "that's a nazi salute" Historians: "that's a nazi salute" Average person: "that's a nazi salute" The Media: "Elon Musk makes odd gesture throwing his heart to the crowd."
7984857012512
Pablo Arantes @pabloarantes.bsky.social · 21/01/2025
It’s Nazi gestures, Nazi aesthetics, Nazi rhetoric, Nazi symbols. But they’re not Nazis, okay?
030