Maciej Majewski

49 posts

Maciej Majewski

Maciej Majewski

@MacMaje

PhD in comp. chem. Currently @sanofi. Previously in @acellera, @gdefabritiis, @XavierBarril and @JemielityLab labs He/him

Barcelona Katılım Mart 2021
190 Takip Edilen97 Takipçiler
Sabitlenmiş Tweet
Maciej Majewski
Maciej Majewski@MacMaje·
I’m happy to share our recent preprint on using neural network potentials (NNPs) for coarse-grained molecular dynamics (CGMD) simulations of proteins. Here's a summary of our findings: 🧵1/8 arxiv.org/abs/2212.07492
English
2
18
105
11.4K
Maciej Majewski retweetledi
Cecilia Clementi
Cecilia Clementi@CecClementi·
Our development of machine-learned transferable coarse-grained models in now on Nat Chem! doi.org/10.1038/s41557… I am so proud of my group for this work! Particularly first authors Nick Charron, Klara Bonneau, @sayeg84, Andrea Guljas.
English
3
40
127
9.6K
Maciej Majewski retweetledi
Christian Dallago
Christian Dallago@sacdallago·
@HeinzingerM and I are seeking talented postdocs to support for the Marie Skłodowska-Curie Fellowship! Join our international AI+biology team, collaborate on protein design, and access top labs in the US & EU. Interested? Apply by July 15! Details: machine.learning.bio/news/msca
English
0
4
8
320
Maciej Majewski retweetledi
Christian Dallago
Christian Dallago@sacdallago·
GPUs are *fast* at aligning protein sequences (and profiles!). 178x faster than JackHMMER! In ColabFold, 23x faster end-to-end compared to AlphaFold2 reaching the same accuracy! You get immediate speedups for all methods leveraging MSAs, from DCA, to PoET, and even AlphaFold3!
Christian Dallago tweet media
English
4
26
161
18.1K
Maciej Majewski retweetledi
Christian Dallago
Christian Dallago@sacdallago·
ml4lms.bio will be next friday. We haveso many quality submissions -- come meet the authors! Likewise, we have a fantastic lineup, prizes, food,... Everything to set you up for the next exciting paper! Also, sign up for the social ASAP: lu.ma/rojc95k1
English
0
11
34
3.1K
Maciej Majewski retweetledi
Christian Dallago
Christian Dallago@sacdallago·
🏳️🏳️🏳️🏳️🏳️🏳️ OK, ok; my bad! ml4lms.bio submission deadline extended to May 23rd. Remember: it's **UP TO** 5 pages. Subit any below that and you're fine! Just make it sensible, topical & exciting.
English
0
9
29
9.1K
Maciej Majewski retweetledi
Acellera
Acellera@acellera·
Excited to share our latest review article on advancing the frontier of #DrugDiscovery through #MachineLearning! We delve into ML algorithms for predicting molecular properties of small molecules, a key step towards computable drug discovery. 🧪🖥️ 🔗 doi.org/10.1016/j.aich…
English
0
2
14
1.1K
Maciej Majewski retweetledi
Cecilia Clementi
Cecilia Clementi@CecClementi·
I am excited to present this work, result of a 4-year big collaborative project: arxiv.org/abs/2310.18278 #MachineLearning a transferable bottom-up protein force field, trained on force data from over all-atom MD simulations, using physical priors and graph neural networks.🧵⬇️
English
1
49
216
23.7K
Maciej Majewski
Maciej Majewski@MacMaje·
Happy to share that my latest paper was published in @NatureComms ! 🥳 #MolecularDynamics #MachineLearning #CoarseGraining #MD #ML #NNP #NatureComms #BiotechNatureComms
Nature Communications@NatureComms

MacMaje @gdefabritiis @FrankNoeBerlin @CecClementi @acellera construct coarse-grained molecular potentials using artificial neural networks, accelerating protein dynamics simulations while preserving their thermodynamics. #BiotechNatureComms nature.com/articles/s4146…

English
0
1
8
426
Maciej Majewski retweetledi
Diego del Alamo
Diego del Alamo@DdelAlamo·
"Top-down machine learning of coarse-grained protein force-fields" General-purpose neural network potentials trained on 15,000 proteins are compared to protein-specific potentials arxiv.org/abs/2306.11375
Diego del Alamo tweet media
English
1
55
215
21.9K
Maciej Majewski retweetledi
Carles Navarro
Carles Navarro@11krls·
1/🧵 Happy to share my first preprint! "Top-down machine learning of coarse-grained protein force-fields" We've trained a general and protein specific coarse-grained neural network potentials (NNPs) using only protein structures and short molecular dynamic trajectories.
Carles Navarro tweet media
English
1
24
121
9.9K