Suttain / API & engine reference
The compute and data layer behind Suttain.
Every engine, method and database a Suttain result can come from, with what actually runs, what is only prepared, and how to cite it.
04
Hosted services
20
Input-file engines
15
Data sources
01 / Architecture
Four ways a result is produced
Hosted compute
Calculations that run on a connected provider and return computed results with provider attribution.
Run on Suttain
Open-source engines that Suttain runs on its own compute. Each runs the same input package you can download, and returns the engine’s output files and log.
Input preparation
Validated input files for engines you run on your own computer or cluster. Preparing files is not a calculation.
Source lookups
Live queries to public scientific databases, returned with identifiers and retrieval time.
02 / Engine reference
Engines and methods
Generated from the same registry the workflows use. Only listed methods and tasks are implemented; anything else is rejected rather than silently substituted. Select a row for its version, license, schema and citation. Engines marked “Runs on Suttain” can run on Suttain’s own compute with nothing to install; their rows also show the hardware, limits, installed version and test status.
03 / Data services
Scientific databases
- PubChem119M+ compoundsCompound identity, properties, GHS hazard classifications and safety data.Source: PubChem 2025 updateChemical Analysis · SDS Analyzer · Formula Generator · Atomistic Simulation
- ChEMBL2.9M+ compoundsBioactivity, drug and molecular target data.Source: ChEMBL 37, May 2026Drug Design · Chemical search
- ChEBIchemical ontologyCurated dictionary of biologically relevant small molecules.Chemical search
- ChemSpiderchemical structuresStructure, name and identifier cross-references.Chemical search
- RCSB PDB261k+ experimental structures3D structures of proteins and nucleic acids.Source: October 2026Drug Design · Atomistic Simulation
- UniProt150M+ protein entriesProtein sequences and functional annotation for targets.Source: October 2026Drug Design
- AlphaFold DB200M+ predicted structuresPredicted protein structures with per-residue confidence.Source: AlphaFold DBDrug Design
- Open Food Facts4.8M+ productsBarcoded food products with ingredient lists.Source: October 2026Product Scanner
- Open Beauty Facts79k+ productsBarcoded cosmetics and personal-care products with ingredient lists.Source: October 2026Product Scanner
- EPA CompToxchemical identifiers (DTXSID)Resolves EPA DSSTox identifiers so results link to the CompTox Chemicals Dashboard.Chemical Analysis
- EPA CTX APIstoxicology and exposure recordsFour EPA CTX domains: Chemical (DSSTox identity and properties), Hazard (ToxValDB evidence), Bioactivity (ToxCast screening), and Exposure (SEEM predictions and CPDat products and functional uses). Source-linked evidence, not a safety certification.Source: CTX API 1.1.1EPA CTX ExplorerOpen EPA CTX Explorer
- EPA Envirofacts (TRI)regulatory flagsToxics Release Inventory listing, carcinogen, PBT and PFAS flags.Chemical Analysis
- NIST Chemistry WebBookthermophysical dataBoiling point, melting point and phase-change data.Chemical Analysis
- BindingDBmeasured binding affinitiesMeasured protein–ligand binding data used as screening evidence.Drug Design
- openFDA · DailyMed · RxNormdrug labels and namesMedicine labels, active ingredients and drug name normalisation.Product Scanner · Regulatory checks
04 / Citations
Cite the software you used
- 01
OpenMM
Eastman et al. OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentials. J. Phys. Chem. B 128 (2024) 109–116. https://doi.org/10.1021/acs.jpcb.3c06662
- 02
GROMACS
Abraham et al. GROMACS: High performance molecular simulations through multi-level parallelism from laptops to supercomputers. SoftwareX 1–2 (2015) 19–25. https://doi.org/10.1016/j.softx.2015.06.001
- 03
AmberTools
Case et al. AmberTools. J. Chem. Inf. Model. 63 (2023) 6183–6191. https://doi.org/10.1021/acs.jcim.3c01153
- 04
MACE
Batatia et al. MACE (NeurIPS 2022). Cite the selected foundation model: MACE-MP-0, arXiv:2401.00096; MACE-OFF23, arXiv:2312.15211. Also cite ASE and the installed software versions.
- 05
SO3LR
Kabylda, Frank, Tkatchenko et al. Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields. Cite the SO3LR release, the selected so3lr-tauri checkpoint, ASE and your installed package versions. https://so3lr.github.io/
- 06
Rowan
Rowan Scientific. Cite Rowan and the actual calculation engine, method and basis set. https://docs.rowansci.com/citations
- 07
Boltz API
Boltz-2: Passaro, Corso, Wohlwend et al. (MIT Jameel Clinic / Recursion), 2025. https://boltz.bio
- 08
Tamarind Bio
Computed with Boltz-2 on Tamarind Bio (https://www.tamarind.bio). Cite Boltz-2 and the hosting platform.
- 09
PubChem PUG-REST
Kim et al. An update on PUG-REST. Nucleic Acids Research 46 (2018) W563–W570. https://doi.org/10.1093/nar/gky294
- 10
xtb
Bannwarth, Ehlert and Grimme. GFN2-xTB. J. Chem. Theory Comput. 15 (2019) 1652–1671. https://doi.org/10.1021/acs.jctc.8b01176
- 11
RDKit
RDKit: Open-source cheminformatics. https://www.rdkit.org/ Cite the installed RDKit release.
- 12
Psi4
Smith et al. Psi4 1.4. J. Chem. Phys. 152 (2020) 184108. https://doi.org/10.1063/5.0006002
- 13
PySCF
Sun et al. Recent developments in the PySCF program package. J. Chem. Phys. 153 (2020) 024109. https://doi.org/10.1063/5.0006074
- 14
NWChem
Aprà et al. NWChem: Past, present, and future. J. Chem. Phys. 152 (2020) 184102. https://doi.org/10.1063/5.0004997
- 15
CP2K
Kühne et al. CP2K: An electronic structure and molecular dynamics software package. J. Chem. Phys. 152 (2020) 194103. https://doi.org/10.1063/5.0007045
- 16
Quantum ESPRESSO
Giannozzi et al. Advanced capabilities for materials modelling with Quantum ESPRESSO. J. Phys.: Condens. Matter 29 (2017) 465901. https://doi.org/10.1088/1361-648X/aa8f79
- 17
ABINIT
Gonze et al. The ABINIT project. Comput. Phys. Commun. 248 (2020) 107042. https://doi.org/10.1016/j.cpc.2019.107042
- 18
SIESTA
Soler et al. The SIESTA method for ab initio order-N materials simulation. J. Phys.: Condens. Matter 14 (2002) 2745. https://doi.org/10.1088/0953-8984/14/11/302
- 19
GPAW
Enkovaara et al. Electronic structure calculations with GPAW. J. Phys.: Condens. Matter 22 (2010) 253202. https://doi.org/10.1088/0953-8984/22/25/253202
- 20
Octopus
Tancogne-Dejean et al. Octopus. J. Chem. Phys. 152 (2020) 124119. https://doi.org/10.1063/1.5142502
- 21
OpenMolcas
Fdez. Galván et al. OpenMolcas. J. Chem. Theory Comput. 15 (2019) 5925–5964. https://doi.org/10.1021/acs.jctc.9b00532
- 22
BAGEL
Shiozaki. BAGEL. WIREs Comput. Mol. Sci. 8 (2018) e1331. https://doi.org/10.1002/wcms.1331
- 23
GAMESS
Schmidt et al. General atomic and molecular electronic structure system. J. Comput. Chem. 14 (1993) 1347–1363. https://doi.org/10.1002/jcc.540141112
- 24
ORCA
Neese. Software update: The ORCA program system—Version 5.0. WIREs Comput. Mol. Sci. 12 (2022) e1606. https://doi.org/10.1002/wcms.1606
Also report the installed version, method, basis set, solvent model and datasets used. For a run on Suttain, the engine version is shown with the results. Suttain and its compute provider are where a calculation ran, not a method to cite. Preparing an input file does not establish a computed result.
05 / Access
Use these engines inside Suttain
All engines and data services are available through Atomistic Simulation, Drug Design and the consumer tools. Programmatic access with personal API keys is not open at the moment.
