rowan

Rowan: Cloud-Native Molecular-Modeling and Drug-Design Workflows

Overview

Rowan is a cloud-native workflow platform for molecular simulation, medicinal chemistry, and structure-based design. Its Python API exposes a unified interface for small-molecule modeling, property prediction, docking, molecular dynamics, and AI structure workflows.

Use Rowan when you want to run medicinal-chemistry or molecular-design workflows programmatically without maintaining local HPC infrastructure, GPU provisioning, or a collection of separate modeling tools. Rowan handles all infrastructure, result management, and computation scaling.

When to use Rowan

Rowan is a good fit for:

• Quantum chemistry, semiempirical methods, or neural network potentials
• Batch property prediction (pKa, descriptors, permeability, solubility)
• Conformer and tautomer ensemble generation
• Docking workflows (single-ligand, analogue series, pose refinement)
• Protein-ligand cofolding and MSA generation
• Multi-step chemistry pipelines (e.g., tautomer search → docking → pose analysis)
• Batch medicinal-chemistry campaigns where you need consistent, scalable infrastructure

Rowan is not the right fit for:

• Simple molecular I/O (use RDKit directly)
• Post-HF ab initio quantum chemistry or relativistic calculations

Access and pricing model

Rowan uses a credit-based usage model. All users, including free-tier users, can create API keys and use the Python API.

Free-tier access

• Access to all Rowan core workflows
• 20 credits per week
• 500 signup credits

Pricing and credit consumption

Credits are consumed according to compute type:

• CPU: 1 credit per minute
• GPU: 3 credits per minute
• H100/H200 GPU: 7 credits per minute

Purchased credits are priced per credit and remain valid for up to one year from purchase.

Typical cost estimates

| Workflow | Typical Runtime | Estimated Credits | Notes | |----------|----------------|-------------------|-------| | Descriptors | <1 min | 0.5–2 | Lightweight, good for triage | | pKa (single transition) | 2–5 min | 2–5 | Depends on molecule size | | MacropKa (pH 0–14) | 5–15 min | 5–15 | Broader sampling, higher cost | | Conformer search | 3–10 min | 3–10 | Ensemble quality matters | | Tautomer search | 2–5 min | 2–5 | Heterocyclic systems | | Docking (single ligand) | 5–20 min | 5–20 | Depends on pocket size, refinement | | Analogue docking series (10–50 ligands) | 30–120 min | 30–100+ | Shared reference frame | | MSA generation | 5–30 min | 5–30 | Sequence length dependent | | Protein-ligand cofolding | 15–60 min | 20–50+ | AI structure prediction, GPU-heavy |

Quick start

uv pip install rowan-python

import rowan
rowan.api_key = "your_api_key_here"  # or set ROWAN_API_KEY env var

# Submit a descriptors workflow — completes in under a minute
wf = rowan.submit_descriptors_workflow("CC(=O)Oc1ccccc1C(=O)O", name="aspirin")
result = wf.result()

print(result.descriptors['MW'])    # 180.16
print(result.descriptors['SLogP']) # 1.19
print(result.descriptors['TPSA'])  # 59.44

If that prints without error, you're set up correctly.

Installation

uv pip install rowan-python
# or: pip install rowan-python

User and webhook management

Authentication

Set an API key via environment variable (recommended):

export ROWAN_API_KEY="your_api_key_here"

Or set directly in Python:

import rowan
rowan.api_key = "your_api_key_here"

Verify authentication:

import rowan
user = rowan.whoami()  # Returns user info if authenticated
print(f"User: {user.email}")
print(f"Credits available: {user.credits_available_string}")

Webhook secret management

For webhook signature verification, manage secrets through your user account:

import rowan

# Get your current webhook secret (returns None if none exists)
secret = rowan.get_webhook_secret()
if secret is None:
    secret = rowan.create_webhook_secret()
print(f"Secret key: {secret.secret}")

# Rotate your secret (invalidates old, creates new)
# Use this periodically for security
new_secret = rowan.rotate_webhook_secret()
print(f"New secret created (old secret disabled): {new_secret.secret}")

# Verify incoming webhook signatures
is_valid = rowan.verify_webhook_secret(
    request_body=b"...",           # Raw request body (bytes)
    signature="X-Rowan-Signature", # From request header
    secret=secret.secret
)

Molecule input formats

Rowan accepts molecules in the following formats:

• SMILES (preferred): "CCO", "c1ccccc1O"
• SMARTS patterns (for some workflows): subset of SMARTS for substructure matching
• InChI (if supported in your API version): "InChI=1S/C2H6O/c1-2-3/h3H,2H2,1H3"

The API will validate input and raise a rowan.ValidationError if a molecule cannot be parsed. Always use canonicalized SMILES for reproducibility.

Tip: Use RDKit to validate SMILES before submission:

from rdkit import Chem
smiles = "CCO"
mol = Chem.MolFromSmiles(smiles)
if mol is None:
    raise ValueError(f"Invalid SMILES: {smiles}")

Core usage pattern

Most Rowan tasks follow the same three-step pattern:

1. Submit a workflow
2. Wait for completion (with optional streaming)
3. Retrieve typed results with convenience properties

import rowan

# 1. Submit — use the specific workflow function (not the generic submit_workflow)
workflow = rowan.submit_descriptors_workflow(
    "CC(=O)Oc1ccccc1C(=O)O",
    name="aspirin descriptors",
)

# 2. & 3. Wait and retrieve
result = workflow.result()  # Blocks until done (default: wait=True, poll_interval=5)
print(result.data)              # Raw dict
print(result.descriptors['MW']) # 180.16 — use result.descriptors dict, not result.molecular_weight

For long-running workflows, use streaming:

for partial in workflow.stream_result(poll_interval=5):
    print(f"Progress: {partial.complete}%")
    print(partial.data)

result() vs. stream_result()

| Pattern | Use When | Duration | |---------|----------|----------| | result() | You can wait for the full result | <5 min typical | | stream_result() | You want progress feedback or need early partial results | >5 min, or interactive use |

Guideline: Use result() for descriptors, pKa. Use stream_result() for conformer search, docking, cofolding.

Working with results

Rowan's API includes typed workflow result objects with convenience properties.

Using typed properties and .data

Results have two access patterns:

1. Convenience properties (recommended first): result.descriptors, result.best_pose, result.conformer_energies
2. Raw fallback: result.data — raw dictionary from the API

Example:

result = rowan.submit_descriptors_workflow(
    "CCO",
    name="ethanol",
).result()

# Convenience property (returns dict of all descriptors):
print(result.descriptors['MW'])   # 46.042
print(result.descriptors['SLogP'])  # -0.001
print(result.descriptors['TPSA'])   # 57.96

# Raw data fallback (descriptors are nested under 'descriptors' key):
print(result.data['descriptors'])
# {'MW': 46.042, 'SLogP': -0.001, 'TPSA': 57.96, 'nHBDon': 1.0, 'nHBAcc': 1.0, ...}

Note: DescriptorsResult does not have a molecular_weight property. Descriptor keys use short names (MW, SLogP, nHBDon) not verbose names.

Cache invalidation

Some result properties are lazily loaded (e.g., conformer geometries, protein structures). To refresh:

result.clear_cache()
new_structures = result.conformer_molecules  # Refetched

Projects, folders, and organization

For nontrivial campaigns, use projects and folders to keep work organized.

Projects

import rowan

# Create a project
project = rowan.create_project(name="CDK2 lead optimization")
rowan.set_project("CDK2 lead optimization")

# All subsequent workflows go into this project
wf = rowan.submit_descri