Pablo Arantes
@pabloarantes.bsky.social
#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.
https://pablo-arantes.github.io/
https://pablo-arantes.github.io/
WOW!!! Fantastic news, Fiona! 🎉 Wishing you all the best, can’t wait to hear more about your new group!
October 12, 2025 at 2:31 AM
WOW!!! Fantastic news, Fiona! 🎉 Wishing you all the best, can’t wait to hear more about your new group!
Thank you, @olexandr.bsky.social! Yes, AIMNet2 is included in the notebook. Users can choose between several models: TorchANI, AIMNet2, and MACE-OFF. 😉
August 21, 2025 at 10:54 AM
Thank you, @olexandr.bsky.social! Yes, AIMNet2 is included in the notebook. Users can choose between several models: TorchANI, AIMNet2, and MACE-OFF. 😉
Thank you my friend! 🥰
August 20, 2025 at 8:43 PM
Thank you my friend! 🥰
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
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 .
media.tenor.com
August 20, 2025 at 1:34 PM
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
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 - 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
github.com
August 20, 2025 at 1:34 PM
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...
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
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
media.tenor.com
August 20, 2025 at 1:34 PM
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
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
August 20, 2025 at 1:34 PM
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
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
@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
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
media.tenor.com
August 20, 2025 at 1:34 PM
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
@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
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
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
media.tenor.com
August 20, 2025 at 1:34 PM
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
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
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
media.tenor.com
August 20, 2025 at 1:34 PM
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
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...
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...
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...
doi.org
March 24, 2025 at 12:34 PM
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...
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...
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.
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.
March 24, 2025 at 12:34 PM
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.
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.