Rowan
@RowanSci
Followers
2K
Following
207
Media
121
Statuses
395
molecular design and simulation tools for scientists. (also see our literature-posting account @RowanReads.) (cover image from @owl_posting)
Joined July 2023
Our platform's changed a lot since we recorded our last "Intro to Rowan" video!
We've just refreshed our "Intro to Rowan" demo video that walks through our web-based computational chemistry platform + its features. If you're curious about what @RowanSci is or what it does, take a look!
1
2
17
We're excited to launch a bunch of new features on Rowan today! (1) ion-mobility MS prediction (2) high-throughput docking (3) pose strain estimation (4) Lyrebird, a flow-matching conformer-generation model (5) & MSA generation for co-folding. Brief summaries to follow:
1
5
18
The smartest AI agents still panic when given tools, and new ones are churning out of labs faster than anyone can test them. After 7 years at the bench, I left to build BioArena to see which models are doing real work and which ones are just doing PR. https://t.co/JpA1ePP64l
1
6
30
BoltzGen seems pretty cool and we're putting it through its paces. Impressions so far: Pros: - Grateful for AA design across diverse modalities, esp. VHH. - VHH bind via CDRs (unlike side-binders w/MBER) and don't have excessive cys residues (like original Germinal designs).
2
8
120
BoltzGen, the new protein-binder-design model from @HannesStaerk and coworkers @MITCSAIL, is now live on Rowan for all users. BoltzGen is an open-source all-atom generative model for designing protein/peptide binders to a diverse array of targets—think Boltz-2, but generative.
1
15
60
For full methodological details, literature references, and additional discussion, please refer to the full post on our newsletter! https://t.co/071JNQhWoH
rowansci.com
Rowan is a cloud-based quantum chemistry platform for submitting, viewing, analyzing, and sharing calculations on small molecules using quantum chemistry and machine-learned potentials.
0
0
1
(2) We're adding a family of ML-based microscopic pKa methods from @jonwzheng and Thomas Nevolianis to our microscopic pKa workflow. This provides users with a fast and accurate alternative to our 3D AIMNet2-based algorithm, as well as allowing for non-aqueous pKa calculations.
1
0
1
Building the infrastructure to support web-based MD was a complex + non-trivial engineering undertaking! We're happy to have this completed and anticipate adding additional MD-based workflows in the future. If you have open MD-related problems, please reach out!
1
0
1
One such filter is looking at the ligand RMSD from short MD simulations: stronger binders bind tightly, whereas weak binders move around more. This workflow is now out for all subscribing Rowan users & organizations via the "Pose Analysis MD" workflow. (Details in newsletter.)
1
0
2
(1) Last week, we released updates to increasing the rigor + validity of our SBDD workflows. But docking and co-folding are only the first step: ideally, scientists can go on to run additional filtering steps and, ultimately, free-energy methods. https://t.co/wuNtyZxRHL
New today on Rowan—a suite of updates to our structure-based drug design (SBDD) tools focused on ensuring maximum scientific rigor. Our goal is for all Rowan users to use these tools with the same safeguards as top pharma/biotech companies. Here's what we're launching today:
1
0
1
New Rowan release! Today, we're launching: (1) pose-analysis MD for deeper analysis of protein–ligand binding modes following docking/co-folding . (2) a suite of ML-based microscopic pKa models in water and non-aqueous solvents. Read on for context, details, & screenshots.
1
4
24
We just posted a high-level overview of different strategies for in silico pKa prediction, with the goal of making this somewhat complex field a bit more accessible! Check it out here: https://t.co/GbHwdarqiJ
0
1
16
the scientists yearn for cartoony images
Anyone know what program & settings was used to make these figs? I assume it isn't pymol or chimera
7
29
455
New today on Rowan—a suite of updates to our structure-based drug design (SBDD) tools focused on ensuring maximum scientific rigor. Our goal is for all Rowan users to use these tools with the same safeguards as top pharma/biotech companies. Here's what we're launching today:
1
5
20
And here's a link to the quick scientific explainer from @NobelPrize: https://t.co/PoAwAlLANc
Susumu Kitagawa, Richard Robson and Omar M. Yaghi have been awarded the 2025 #NobelPrize in Chemistry for the development of a new type of molecular architecture. In 1989, chemistry laureate Richard Robson tested utilising the inherent properties of atoms in a new way. He
0
0
3
Congrats to Omar Yaghi, Richard Robson, and Susumu Kitagawa for winning the 2025 Chemistry @NobelPrize! To celebrate, here's a video of the iconic metal–organic framework Zn-MOF-74 optimized in Rowan:
1
0
4
Although NNPs are becoming a very powerful method for chemical simulation, many reactions aren't well-defined in the gas phase. Rowan makes it easy to combine implicit-solvent models with NNPs and accurately model reactive ionic systems.
1
0
25
I think this take is correct! There's a well-known narrative in tech about the "AWS revolution" and the horizontalization of the field. Building a great software company used to require vertical integration: racking your own servers, building your own protocols and
A non-trivial number of biotechs over the past decade have died from the thousand cuts of vertical integration. If your goal is to bring one or two programs to the clinic, there is no scenario where the upfront time and cost of vertically owning your platform beats outsourcing to
1
1
25