Quickly predict pKa values
Predict the acidity of small molecules with Rowan's pKa workflow. Rowan uses AIMNet2, a machine-learned interatomic potential, to obtain fast and reasonable pKa values with minimal empiricism.
New advances in computation are making it possible to simulate chemistry with unprecedented speed and accuracy, but it's difficult to bring these breakthroughs to existing scientific teams. Rowan makes scientific software as easy to use as Uber or Venmo, while offering order-of-magnitude improvements in speed and accuracy through new machine learning-based methods.
Bring the power of modern computation to bear on your scientific problems. Design, simulate, and analyze molecules and materials through our web platform—or use our API to integrate our calculations into your workflows.
Predict the acidity of small molecules with Rowan's pKa workflow. Rowan uses AIMNet2, a machine-learned interatomic potential, to obtain fast and reasonable pKa values with minimal empiricism.
When you're doing research, you need answers in seconds, not days. AIMNet2 is an incredibly fast neural network potential that powers computational chemistry simulations in Rowan.
Quickly explore conformational space with Rowan's conformer search workflow. Rowan uses fast low-level methods to generate conformers and then scores the each structure with a more accurate final method.
Designing a new compound? Need to quickly adjust an angle? Rowan's 3D molecule editor makes it easy to draw molecules from scratch and edit existing 3D structures.
Quickly script custom workflows with Rowan's convenient Python API. Output data is returned as a developer-friendly Python dictionary, making downstream analysis simple. And the API is fully integrated with the web backend, so jobs submitted from the web can be analyzed through Python (and vice versa).
import cctk
import rowan
rowan.api_key = "rowan-sk..."
client = rowan.Client()
# load molecule by name
molecule = cctk.Molecule.new_from_name("cyclobutane")
# run calculation remotely and return result
result = client.compute(
"calculation",
input_mol=molecule,
name="opt cyclobutane",
method="aimnet2_wb97md3",
tasks=["optimize", "charge"]
)
You can see presentation-quality graphs and figures even before a job is finished. No need to teach an experimental scientist how to open a coordinate file—just generate a shareable link for any calculation and send it over.
Rowan encrypts all your data in transit and at rest.
For confidential jobs, run Rowan's Python API in delete_when_finished mode or run the Rowan AMI in your own AWS account or virtual private cloud (awaiting AWS Marketplace approval).
“
Rowan ... has the potential to democratise access to specialist quantum chemistry tools that could massively accelerate drug discovery.
”
Create an account to get started today or contact us to find a solution for your business.
