advancements in alchemiscale v0.6
In February of this year we released alchemiscale v0.
Earlier this year we released alchemiscale v0.6.0, and followed this up with v0.6.1 and v0.6.2. We wanted to take a moment to highlight these releases, and the improvements they bring for users!
Read our full post here: alchemiscale.org/advancements...
#compchem #drugdiscovery #alchemistry
03.06.2025 20:30 β π 2 π 1 π¬ 0 π 0
Eager to apply alchemiscale and @openfree.energy to your problems, but not sure where to start? Don't hesitate to reach out!
#compchem #alchemistry #opensource #openscience
27.05.2025 23:27 β π 4 π 0 π¬ 0 π 0
This poster illustrates the substantial flexibility of the open source @openfree.energy ecosystem, enabling unconventional approaches for applying free energy methods. As this ecosystem continues to evolve, I'm excited to see what users do with the advancements we make!
27.05.2025 23:27 β π 0 π 1 π¬ 1 π 0
With alchemiscale as the coordinator and Folding@Home as a "planetary scale" engine of citizen-science compute, we are able to increase our calculation throughput by at least 3x over conventional compute alone, and with equal accuracy!
27.05.2025 23:27 β π 0 π 0 π¬ 1 π 0
Proud to have shared some of our recent work at the 2025 Workshop on Free Energy Methods in Boston!
Our poster detailed the engineering approach we took to enable large-scale computation of alchemical binding free energies via alchemiscale (alchemiscale.org) and Folding@Home (foldingathome.org).
27.05.2025 23:27 β π 6 π 0 π¬ 1 π 0
If they suspend Habeas Corpus, it won't just be for "migrants" or "illegals" or "criminals." If they suspend Habeas Corpus it will be for you and me and whomever this regime decides is unfit, undesirable, and a threat or a problem. This is how it works. This is how it's always worked.
11.05.2025 16:53 β π 9482 π 3095 π¬ 194 π 126
En route to Boston for the 2025 Workshop on Free Energy Methods in Drug Design!
Looking for ways to better scale the free energy calculations that support your active drug discovery programs? Hit me up here or find me there!
#drugdesign #drugdiscovery #compchem #alchemistry
05.05.2025 20:36 β π 3 π 0 π¬ 0 π 0
Achira support for Datryllic's efforts in 2025
In February, we published the alchemiscale projectβs 2025 roadmap, detailing our objectives for the year, our available resources, and the path we intend to take to leverage these resources in service...
Excited to announce that Achira (achira.ai) is supporting Datryllic in advancing alchemiscale in 2025!
Details here: alchemiscale.org/advancements...
Looking to scale free energy calculations for your applications? Donβt hesitate to reach out!
#drugdiscovery #alchemistry #opensource #compchem
21.04.2025 17:58 β π 3 π 0 π¬ 0 π 0
Yup. The US is really cutting off its nose to spite its face here, and abdicating its own position as a global leader in scientific advancement.
It's beyond stupid.
19.03.2025 01:39 β π 2 π 0 π¬ 0 π 0
Figure 1 from arXiv preprint https://doi.org/10.1101/2025.01.06.631610
Fig. 1 Espaloma is an end-to-end differentiable molecular mechanics parameter assignment scheme for arbitrary organic molecules. Espaloma (extensible surrogate potential optimized by message-passing) is a modular approach for directly computing molecular mechanics force field parameters FFF from a chemical graph G such as a small molecule or biopolymer via a process that is fully differentiable in the model parameters FNN. In Stage 1, a graph neural network is used to generate continuous latent atom embeddings describing local chemical environments from the chemical graph. In Stage 2, these atom embeddings are transformed into feature vectors that preserve appropriate symmetries for atom, bond, angle, and proper/improper torsion inference via Janossy pooling.54 In Stage 3, molecular mechanics parameters are directly predicted from these feature vectors using feed-forward neural networks. This parameter assignment process is performed once per molecular species, allowing the potential energy to be rapidly computed using standard molecular mechanics or molecular dynamics frameworks thereafter. The collection of parameters FNN describing the espaloma model can be considered as the equivalent complete specification of a traditional molecular mechanics force field such as GAFF38,39/AM1-BCC55,56 in that it encodes the equivalent of traditional typing rules, parameter assignment tables, and even partial charge models. Reproduced from ref. 49 with permission from the Royal Society of Chemistry.
Everything is chaos, but I wanted to share some awesome recent science from the lab that hints at where the future of biomolecular simulation is headed:
Foundation simulation models that can be fine-tuned to experimental free energy data to produce systematically more accurate predictions.
19.02.2025 19:30 β π 107 π 30 π¬ 3 π 1
Guess I'll start using the great American high speed rail...
17.02.2025 17:14 β π 1 π 0 π¬ 0 π 0
"But the price of eggs!" is the new "But her emails!" π«
12.02.2025 15:42 β π 3 π 0 π¬ 0 π 0
alchemiscale roadmap 2025
Itβs 2025, and this month the project now known as alchemiscale celebrates its 3rd anniversary since kicking off in 2022.
This month the alchemiscale project celebrates its 3rd anniversary since kicking off in 2022! We've come a long way, and there is much we look forward to improving this year.
Read about where we're going in 2025: alchemiscale.org/roadmaps/alc...
#compchem #opensource #alchemistry #drugdiscovery
12.02.2025 01:04 β π 6 π 0 π¬ 0 π 0
Ah yes, the DEI boogeyman strikes again. π
30.01.2025 19:07 β π 0 π 0 π¬ 0 π 0
Datryllic efforts for ASAP Discovery in 2025
In October, we offered a detailed perspective on what we considered to be the alchemiscale projectβs most attractive advancement opportunities in 2025.
Very pleased to announce that ASAP Discovery (asapdiscovery.org) is supporting Datryllic in advancing alchemiscale in 2025!
More details here: alchemiscale.org/advancements...
Looking to advance alchemiscale further? Donβt hesitate to reach out!
#drugdiscovery #alchemistry #opensource #compchem
24.01.2025 19:06 β π 4 π 0 π¬ 0 π 0
Ask Poland about how entitled Germany felt to its land less than a century ago. Lebensraum and all that.
08.01.2025 22:47 β π 0 π 0 π¬ 0 π 0
Ego-driven policy, blatant oligarchy, and ecological disaster we may never recover from.
08.01.2025 22:44 β π 0 π 0 π¬ 0 π 0
It had me at space elevator. π
01.01.2025 00:31 β π 0 π 0 π¬ 0 π 0
Tis the season for making space to realign the spirit with the mind and body.
To rekindle the enthusiasm that set you down the path you're on, and to consider the possibilities beyond it.
To take stock of what you have learned, and what you likely need to.
To be ready to make a positive impact.
30.12.2024 00:00 β π 3 π 0 π¬ 0 π 0
π¦ Weβre excited to announce our first competition in partnership with @asapdiscovery.bsky.social and @omsf.io!
Test your skills across three sub-challenges revolving around SARS-CoV-2 and MERS-CoV Mproπ§΅
Full details: polarishub.io/competitions
Blog: polarishub.io/blog/antivir...
03.12.2024 15:13 β π 43 π 16 π¬ 1 π 8
The OMSF (@omsf.bsky.social) OpenADMET project is hiring a Science Lead for ML models of molecular property prediction, as well as a Senior Scientist for data curation and pipeline integration! Help build the future of open source ADMET prediction and ML model enablement!
openadmet.org/jobs/
16.11.2024 01:42 β π 22 π 12 π¬ 0 π 0
We are now on Bluesky! OMSF supports the ever-growing ecosystem of open source molecular software. We love all things #opensource, #science, and #software - if you do too, follow us!
28.09.2023 19:27 β π 17 π 6 π¬ 0 π 2
@katyhuff.bsky.social howdy stranger! Great to see you here!
14.11.2024 05:44 β π 3 π 0 π¬ 1 π 0
To all the newcomers to @bsky.app , welcome! Let's make this a better place than, well, you already know. π
12.11.2024 23:25 β π 3 π 0 π¬ 0 π 0
Do you use alchemiscale in production? Or would you like to?
We recently shared a perspective on the progress of the project, where we're currently focused, and the opportunities we see for advancement in 2025:
alchemiscale.org/opportunitie...
Let us know what you think! #drugdiscovery #oss
30.10.2024 01:47 β π 2 π 2 π¬ 0 π 0
Gave an invited talk a few weeks back at Memorial Sloan Kettering Cancer Center on alchemiscale (github.com/openforcefie...), and how we're working to scale out alchemical free energy calculations to support open data antiviral discovery for ASAP Discovery (asapdiscovery.org) via Folding@Home.
14.02.2024 02:16 β π 3 π 0 π¬ 0 π 0
Achira is building atomistic foundation simulation models to power the future of drug discovery.
http://achira.ai
Optimistic Nihilist haphazardly trying to leave the world a slightly better place than I found it.
Protein and coffee lover, father of two, professor of biophysics and sudo scientist at the LinderstrΓΈm-Lang Centre for Protein Science, University of Copenhagen π©π°
Industrializing scientific discovery to radically improve lives.
Powered by @recursionpharma.bsky.social
PhD student @MIT β’ Research on Generative Models for Biophysics and Drug Discovery
biology + computers + a leavening of snark | π¨βπ¨βπ§βπ§π³οΈβπ| nanomedicine | cancer genomics 𧬠| ML | biomaterials | #compchem #matsky #chemsky #ai4science #materialsinformatics #md | startups | @Cal π» @Stanford @UniversityOfOxford @OxfordNano (swimsf on the Bad Place)
Schmidt AI in Science Postdoctoral Fellow at U. Chicago
theoretical & computational soft matter, biophysics, machine learning
jordanshivers.github.io
Entrepreneur
Costplusdrugs.com
𧬠Structural Bioinformatics | π AI/ML for Drug Discovery | Geometric DL
π¬ @iocbprague.bsky.social, prev. PhD @cusbg.bsky.social @mff.unikarlova.cuni.cz
I use robots and biophysics to study cancer therapies in the Chodera Lab at Memorial Sloan Kettering Cancer Center. Views are my own.
Assistant Professor at UMich with a focus on computational pharmacology (he/him)
The Queen of a Kingβs town.