Xin@QuantumChem
@xinquantum.bsky.social
When it comes to real production level chemistry code, both Gemini 3 Pro and Claude Opus became clumsy. It took them around 40 minutes and multiple rounds of conversation just to finish the project. They’re clearly not great with RDKit or chemistry APIs.
#CompChemsky #compchem #Chemistry
#CompChemsky #compchem #Chemistry
November 28, 2025 at 7:03 PM
When it comes to real production level chemistry code, both Gemini 3 Pro and Claude Opus became clumsy. It took them around 40 minutes and multiple rounds of conversation just to finish the project. They’re clearly not great with RDKit or chemistry APIs.
#CompChemsky #compchem #Chemistry
#CompChemsky #compchem #Chemistry
In one sentence: Orb-v3 is accurate in describing F-Li-Be Molten Salt *without fine-tuning*.
AIMD results came from: doi.org/10.1103/PRXE...
They also compared with Neutron Diffraction. @myzzzz.bsky.social will benchmark the S(Q) with experimental data.
#compchemsky #compchem
AIMD results came from: doi.org/10.1103/PRXE...
They also compared with Neutron Diffraction. @myzzzz.bsky.social will benchmark the S(Q) with experimental data.
#compchemsky #compchem
November 23, 2025 at 10:25 PM
In one sentence: Orb-v3 is accurate in describing F-Li-Be Molten Salt *without fine-tuning*.
AIMD results came from: doi.org/10.1103/PRXE...
They also compared with Neutron Diffraction. @myzzzz.bsky.social will benchmark the S(Q) with experimental data.
#compchemsky #compchem
AIMD results came from: doi.org/10.1103/PRXE...
They also compared with Neutron Diffraction. @myzzzz.bsky.social will benchmark the S(Q) with experimental data.
#compchemsky #compchem
Wetlab is a different world. A wetlab biologist just told me she uses a visualization website where you input a protein sequence and click, the 3D structures show instantly. The visualization thing is called AlphaFold. #Biology #AlphaFold #compchemsky
November 16, 2025 at 6:14 PM
Wetlab is a different world. A wetlab biologist just told me she uses a visualization website where you input a protein sequence and click, the 3D structures show instantly. The visualization thing is called AlphaFold. #Biology #AlphaFold #compchemsky
Yesterday I posted an incorrect comparison. I accidentally copied the TS3 structure into TS1 for UMA and Orb-V3, so the MLIP results for TS1 were wrong. Really sorry about that misleading! In the next post I will share IRC of DFT calculation and wB97M-V/def2-TZVPD results.
#compchem #compchemsky
#compchem #compchemsky
November 2, 2025 at 7:49 PM
Yesterday I posted an incorrect comparison. I accidentally copied the TS3 structure into TS1 for UMA and Orb-V3, so the MLIP results for TS1 were wrong. Really sorry about that misleading! In the next post I will share IRC of DFT calculation and wB97M-V/def2-TZVPD results.
#compchem #compchemsky
#compchem #compchemsky
Sorry this post is incorrect. I accidentally copied the TS3 structure into TS1. The corrected results should be:
November 2, 2025 at 7:42 PM
Sorry this post is incorrect. I accidentally copied the TS3 structure into TS1. The corrected results should be:
THIS POST is wrong: I wrongly copied the TS3 structure into TS1 in this post. The corrected results profile should be
November 2, 2025 at 7:40 PM
THIS POST is wrong: I wrongly copied the TS3 structure into TS1 in this post. The corrected results profile should be
Oh, sorry, I made a mistake. I copied the TS3 structure into TS1. The corrected figure should be. As for wB97M-V/def2-TZVPD, its relative energy of TS1 is very close to M06-2X/def2-TZVPP (within <0.1 kcal/mol). I will share the notebook, IRC and data very soon.
November 2, 2025 at 7:38 PM
Oh, sorry, I made a mistake. I copied the TS3 structure into TS1. The corrected figure should be. As for wB97M-V/def2-TZVPD, its relative energy of TS1 is very close to M06-2X/def2-TZVPP (within <0.1 kcal/mol). I will share the notebook, IRC and data very soon.
A failure case for deep-learning potential: the TS1 geometry is so weird that UMA and Orb-v3 underestimate the barrier by ~15 kcal/mol, likely because it far from the training set. Handling chemical reactions is extremely hard for general deep learning models.
#compchem #compchemsky
#compchem #compchemsky
November 2, 2025 at 1:40 AM
A failure case for deep-learning potential: the TS1 geometry is so weird that UMA and Orb-v3 underestimate the barrier by ~15 kcal/mol, likely because it far from the training set. Handling chemical reactions is extremely hard for general deep learning models.
#compchem #compchemsky
#compchem #compchemsky
UMA (small model) is very close to DFT M06-2X. Maybe I can deploy nanoreactors using UMA model for coarse reaction space sampling. This is a reactive trajectory of a compound with 24 Carbon atoms.
#CompChem #ChemChemSky
#CompChem #ChemChemSky
October 22, 2025 at 7:18 PM
UMA (small model) is very close to DFT M06-2X. Maybe I can deploy nanoreactors using UMA model for coarse reaction space sampling. This is a reactive trajectory of a compound with 24 Carbon atoms.
#CompChem #ChemChemSky
#CompChem #ChemChemSky
I'd like to name it as "QM/MM".
August 13, 2025 at 8:14 PM
I'd like to name it as "QM/MM".
Cunning ChatGPT bypassing 3D depth analysis, and calling the rdkit function to generate the coordinate of an Ibuprofen. Grok3 just failed this test and misrecognized it as glucose, as expected.
July 27, 2025 at 8:04 PM
Cunning ChatGPT bypassing 3D depth analysis, and calling the rdkit function to generate the coordinate of an Ibuprofen. Grok3 just failed this test and misrecognized it as glucose, as expected.
Boltz2 can be run on a $430 RTX5060 Ti (16G) card, although it's much slower than ~$30,000 H100 (RTX 5060 Ti: 1min 47s, H100: 18s), but it doesn't matter, because the cold-start time is about 1 minute for both cards.
#CompChemSky #CompChem #GPU
#CompChemSky #CompChem #GPU
July 23, 2025 at 8:58 PM
Boltz2 can be run on a $430 RTX5060 Ti (16G) card, although it's much slower than ~$30,000 H100 (RTX 5060 Ti: 1min 47s, H100: 18s), but it doesn't matter, because the cold-start time is about 1 minute for both cards.
#CompChemSky #CompChem #GPU
#CompChemSky #CompChem #GPU
Kvass and Khinkali
July 14, 2025 at 12:38 AM
Kvass and Khinkali
This is creepy, but lots of fun. Gemini Veo has a perception of spatial depth and can rotate the molecules.
Inspired by www.youtube.com/watch?v=mDyt...
#compchem #compchemsky
Inspired by www.youtube.com/watch?v=mDyt...
#compchem #compchemsky
July 12, 2025 at 6:06 PM
This is creepy, but lots of fun. Gemini Veo has a perception of spatial depth and can rotate the molecules.
Inspired by www.youtube.com/watch?v=mDyt...
#compchem #compchemsky
Inspired by www.youtube.com/watch?v=mDyt...
#compchem #compchemsky
UMA (uma-sm) combined with NEB successfully locates the transition state and path for a Ni-catalyzed reaction. UMA prediction lies between two DFT functional, and the transition state closely matches the result from a literature: www.nature.com/articles/nat...
#compchemsky #chemsky #compchem
#compchemsky #chemsky #compchem
July 4, 2025 at 12:14 AM
UMA (uma-sm) combined with NEB successfully locates the transition state and path for a Ni-catalyzed reaction. UMA prediction lies between two DFT functional, and the transition state closely matches the result from a literature: www.nature.com/articles/nat...
#compchemsky #chemsky #compchem
#compchemsky #chemsky #compchem
The relationship between Ki and IC₅₀ is described by the Cheng–Prusoff equation. And William L. Jorgensen et al. did an effective calculation for predicting potency in his paper during pandemic.
pubs.acs.org/doi/10.1021/...
pubs.acs.org/doi/10.1021/...
June 27, 2025 at 3:28 AM
The relationship between Ki and IC₅₀ is described by the Cheng–Prusoff equation. And William L. Jorgensen et al. did an effective calculation for predicting potency in his paper during pandemic.
pubs.acs.org/doi/10.1021/...
pubs.acs.org/doi/10.1021/...
June 26, 2025 at 4:30 AM
Surprisingly, the UMA (by meta) model captures the bond-breaking process in the carbon nanotube stretching test, similar to GFN2-xTB. I hadn't expected deep learning models to extrapolate over bond lengths.
#compchemsky #chemsky
#compchemsky #chemsky
June 4, 2025 at 3:52 PM
Surprisingly, the UMA (by meta) model captures the bond-breaking process in the carbon nanotube stretching test, similar to GFN2-xTB. I hadn't expected deep learning models to extrapolate over bond lengths.
#compchemsky #chemsky
#compchemsky #chemsky
Seeking Image-to-SMILES conversion for local tiny device deployment. Deep learning offers accuracy but is too heavy. Are there lightweight alternatives without deep learning? Mathpix (SaaS) appears best, but closed-source and need internet.
January 10, 2025 at 2:40 PM
Seeking Image-to-SMILES conversion for local tiny device deployment. Deep learning offers accuracy but is too heavy. Are there lightweight alternatives without deep learning? Mathpix (SaaS) appears best, but closed-source and need internet.
Red Dead Redemption 2
January 3, 2025 at 6:37 PM
Red Dead Redemption 2
Stretching of a carbon nanotube, a DFTB simulation. Do you know why I placed a nitrogen atom at the center?
#CompChem #CompChemSky #Science #Chemistry
#CompChem #CompChemSky #Science #Chemistry
December 21, 2024 at 8:05 PM
Stretching of a carbon nanotube, a DFTB simulation. Do you know why I placed a nitrogen atom at the center?
#CompChem #CompChemSky #Science #Chemistry
#CompChem #CompChemSky #Science #Chemistry