@AxelrodSimon

Computational chemistry and machine learning @DEShawResearch | PhD at @HarvardCCB and @mit_dmse 2023 | @uoftphysics 2017 | @queensu 2016

 Manhattan, NY
Joined March 2021
  • Tweets51
  • Following143
  • Followers241
1Media
Love it. Clinical trial failures are still the biggest problem in drug discovery. Any progress here would be huge
Rohil Badkundri
@rohilbadkundriMar 30
We used AI to predict the failure of a Phase 3 trial before the results were announced. Today, we're publishing 10 more predictions for the future. Thread 🧵
6
384
Come say hi to the DESRES team! @DEShawResearch
Lucky Pattanaik@lucky_pattanaik11 Dec 2023
At #NeurIPS23 this week with @DEShawResearch ! Stop by booth 421 if you wanna say hi!
1
23
3,301
Mapping the Space of Photoswitchable Ligands and Photodruggable Proteins with Computational Modeling #machinelearning #compchem pubs.acs.org/doi/abs/10.1021…

Mapping the Space of Photoswitchable Ligands and Photodruggable Proteins with Computational Modeling

Abstract. Light-activated drugs are a promising way to localize biological activity and minimize side effects. However, their development is complicated by

pubs.acs.org
1
3
12
1,811
Great new work by @AxelrodSimon @RGBLabMIT @mit_dmse @HarvardCCB - 'Molecular #machinelearning with conformer ensembles' - iopscience.iop.org/article/1… #compchem #compbio #molecules #AI #drugdiscovery #HPC
4
32
2,758
Happy for the opportunity to present my latest work done in @RGBLabMIT at #ACSFall2023.
3
22
1,792
Simon Axelrod retweeted
DMSE at MIT@mit_dmse2 Aug 2023
Rafael Gomez-Bombarelli was one of twenty-six members of the MIT engineering faculty and researchers who received awards in recognition of their scholarship, service, and overall excellence in the past calendar quarter.
1
21
2,656
Simon Axelrod retweeted
RGB Lab @ MIT@RGBLabMIT1 Jun 2023
How to optimize the per-site activity of oxide catalysts? Check out our work, "Atom-by-Atom Design of Metal Oxide Catalysts for the Oxygen Evolution Reaction with Machine Learning," led by our new PhD graduate, Jackie, and in collaboration with @EELabMIT! arxiv.org/abs/2305.19930
3
21
2,693
Jackie’s defense brought this amazing group of young people and big bright smiles together with @RGBLabMIT @mit_dmse @MITMechE @RLEatMIT
1
3
29
3,212
Use a VAE to predict atomic coordinates from coarse-grained coordinates (backmapping) for any protein system. @SoojungYang2 @RGBLabMIT arxiv.org/abs/2303.01569
29
125
11,831
Chemically Transferable Generative Backmapping of Coarse-Grained Proteins. (arXiv:2303.01569v1 [cs.LG]) #machinelearning #compchem cutt.ly/P8Pkyvc
5
12
1,624
Simon Axelrod retweeted
RGB Lab @ MIT@RGBLabMIT26 Feb 2023
This weekend some of our group members braved the cold and enjoyed a winter hike at the Fells!❄️
3
1
27
3,318
RGB Lab @ MIT@RGBLabMIT23 Feb 2023
New preprint out! We use ligand-protein docking to evaluate the photo-druggability of different proteins, and use our #ML #compchem tools to find photo-drug candidates that are metastable, near-IR absorbing, and differentially active @AxelrodSimon arxiv.org/abs/2302.11490

Mapping the space of photoswitchable ligands and photodruggable...

Light-activated drugs are a promising way to localize biological activity and minimize side effects. However, their development is complicated by the numerous photophysical and biological...

arxiv.org
8
465
Twitterverse - what does everyone think of this? Where does the gap between ML model performance and real world clinical trial improvements come from?
Simon Axelrod@AxelrodSimon12 Feb 2023
Replying to @wpwalters
Do you see a role for AI in reducing clinical trial failures? Models routinely get great scores on ClinTox, but afaik the clinical trial failure rate is still 90%. Are these models overfit and useless? Or are they great but ignored? Or something else?
4
3
7
4,984
Thermal half-lives of azobenzene derivatives: virtual screening based on intersystem crossing using a machine learning potential. NEW #ASAP by @AxelrodSimon, Eugene Shakhnovich, and @RGBLabMIT Read it here: go.acs.org/3NW
2
7
2,360
We use differentiable simulations to train machine learned interatomic potentials from radial distribution functions, opening a new avenue to derive force fields from experimental data. @RGBLabMIT @JDietschreit aippub.org/3Y46eRg
6
19
2,169
#compchem Good read: Learning pair potentials using differentiable simulations doi.org/10.1063/5.0126475
9
50
5,349
Check out our new article in @ACSCentSci! Thermal half-lives of azobenzene derivatives: virtual screening based on intersystem crossing using a machine learning potential. Work done with Eugene Shakhnovich and @RGBLabMIT. #compchem #physics #drugdiscovery pubs.acs.org/doi/full/10.102…

Thermal Half-Lives of Azobenzene Derivatives: Virtual Screening Based on Intersystem Crossing Using...

Abstract. Molecular photoswitches are the foundation of light-activated drugs. A key photoswitch is azobenzene, which exhibits trans–cis isomerism in respo

pubs.acs.org
1
4
18
2,133
Simon Axelrod retweeted
RGB Lab @ MIT@RGBLabMIT25 Jan 2023
Just out in ACS Central Science! We made an automated workflow for predicting the thermal half-lives of azobenzene derivatives. TL;DR isomerization involves intersystem crossing, multi-reference effects are critical, and ML gives fast and accurate results! pubs.acs.org/doi/full/10.102…

Thermal Half-Lives of Azobenzene Derivatives: Virtual Screening Based on Intersystem Crossing Using...

Abstract. Molecular photoswitches are the foundation of light-activated drugs. A key photoswitch is azobenzene, which exhibits trans–cis isomerism in respo

pubs.acs.org
1
7
22
3,213
Simon Axelrod retweeted
Jiayu Peng@peng_jiayu19 Jan 2023
Our recent work "Design principles for transition metal nitride stability and ammonia generation in acid" is featured #OnTheCover of @Joule_CP. Check out the paper using this free link (valid before 2/7/2023): authors.elsevier.com/a/1gHD0… @EELabMIT @mit_romangroup #Energy #ChemTwitter
On the cover: The dissolution of transition metal nitrides in acid to form ammonia has led to catalyst degradation (e.g., in developing hydrogen fuel cells) or false positives (e.g., in designing catalysts for ammonia synthesis). This cover image shows the decomposition of nitrides and the generation of ammonia in acid. In this issue, Peng et al. develop new stability design principles of transition metal nitrides in acid based on their electronic structure (highlighted in the image). These physical principles not only provide a fundamental understanding of nitride dissolution in acid but also offer a blueprint to optimize metal nitrides for diverse acidic clean energy applications to electrify and decarbonize the production and utilization of chemicals and fuels.

ALT On the cover: The dissolution of transition metal nitrides in acid to form ammonia has led to catalyst degradation (e.g., in developing hydrogen fuel cells) or false positives (e.g., in designing catalysts for ammonia synthesis). This cover image shows the decomposition of nitrides and the generation of ammonia in acid. In this issue, Peng et al. develop new stability design principles of transition metal nitrides in acid based on their electronic structure (highlighted in the image). These physical principles not only provide a fundamental understanding of nitride dissolution in acid but also offer a blueprint to optimize metal nitrides for diverse acidic clean energy applications to electrify and decarbonize the production and utilization of chemicals and fuels.

4
6
59
7,398
How to validate machine-learned interatomic potentials arxiv.org/abs/2211.12484 #compchem

How to validate machine-learned interatomic potentials

Machine learning (ML) approaches enable large-scale atomistic simulations with near-quantum-mechanical accuracy. With the growing availability of these methods there arises a need for careful...

arxiv.org
5
13
Load more