Choose your capabilities.

Eleven modules, 5,956 derived properties, 150+ tool API endpoints. Each module has a defined scope, published benchmarks, and clear status. Start with what you need.

🧬

Life Science

Drug properties, safety, and target selectivity — from SMILES to a decision-grade ADMET profile, multi-panel bio-target scoring, and target-based drug design in one platform.

86.0% BBB panel accuracy (7,803 scored) 0.617 CASF-2016 r ~350 mol/sec 0.989 DILI AUROC (96; scaffold exclusions)
💊

FluxMateria — ADMET

The current ADMET workflow provides permeability, distribution, metabolism and safety predictions. DILI AUROC is 0.952 / 0.989 under the two stated reference policies on the same 96 cases. The current Caco-2 alternative mode gives MAE 0.281 on 182 development-panel cases; the production profile gives 0.914 with test-reference exclusions. Full cohorts and configurations are declared in the endpoint benchmarks.

  • 8 validated endpoints: Metabolism, BBB, PPB, Solubility, DILI, hERG, Caco-2, CYP Panel
  • The current ADMET workflow provides permeability, distribution, metabolism and safety predictions. DILI AUROC is 0.952 / 0.989 under the two stated reference policies on the same 96 cases. The current Caco-2 alternative mode gives MAE 0.281 on 182 development-panel cases; the production profile gives 0.914 with test-reference exclusions. Full cohorts and configurations are declared in the endpoint benchmarks.
  • ADMET Screening + Virtual Screening + Spec Builder + Presets
  • ~350 mol/sec throughput on a consumer-grade CPU — interpretable, physics-grounded
Schedule Demo Learn More DILI Engine
🧬

FluxMateria — BioTarget

Beta

Program-aware bio-targeting: multi-panel efficacy + human off-target triage + microbiome risk + integrated ADMET. CASF-2016 validated (r = 0.617).

  • Binding affinity: Pearson r = 0.617 on CASF-2016 (269 complexes)
  • Multi-target screening across pathogen / human safety / gut panels
  • ADMET fusion: hERG / CYP / solubility / permeability / stability gating
View Demo Learn More
🔗

FluxMateria — Docking

Blind-validated pose prediction — 47.4% top-1 on PoseBusters-428 with no machine-learning training — plus affinity, kinetics and full ADMET / safety integration in one pass.

  • 47.4% top-1 on PoseBusters-428, nothing fitted to binding data
  • Per-case confidence: 66.7% correct on the most confident 40% of targets
  • ADMET / hERG / CYP / DILI safety gating on hits
Learn More View Demo
⚛

Chemistry

Molecules, reactions, and spectra. Bond lengths at 0.079 % error, bond energies at 0.289 %. Mechanisms at 99.4 % on the published 336-case set. Spectra, retrosynthesis, solution-phase properties, and advanced methods (TDDFT, QM/MM, relativistic, CBS) — all first-principles, all auditable, no machine-learning training.

453 / 906 length / energy counts 64 elements 334 / 336 mechanisms 7.5 kJ/mol barrier MAE
🧪

FluxMateria — Synthesis Planning

Route planning with first-principles barriers. 29 reaction types at 3.1% MAE. 200 specific reactions at <1% MAE. 82 reagents, 15 disconnection patterns.

  • Retrosynthetic analysis and disconnection-based route planning
  • FGI transforms, protection groups, reagent recommendations
  • <50 ms per plan, every step auditable
View Demo Learn More
📈

FluxMateria — Spectroscopy

Predict spectra before synthesis. UV-Vis 5.4% error, IR <1%, NMR 0.3–0.5 ppm MAE.

  • UV-Vis, IR, Raman, NMR predictions — validated
  • 119 UV-Vis molecules, 32 IR molecules benchmarked
  • ~25 ms per prediction, fully deterministic
View Demo Learn More
⚡

FluxMateria — Electron Transfer

Marcus theory + first-principles tunneling corrections. 26 / 26 tests passing. Through-bond decay constant matches literature ranges. 2–3× tunneling enhancement.

  • Reorganization energies, electronic coupling, rate constants
  • Normal, activationless, and inverted Marcus regimes
  • ~150 ms per pair, fully traceable outputs
Learn More Request Access
💧

FluxMateria — Solvation

Solution-phase accuracy. 0.71 logS MAE on 1,128 ESOL compounds. 45 solvents implemented, 6 benchmarked.

  • Aqueous solubility validated (ESOL benchmark passed)
  • 45 solvents implemented (protic, aprotic polar, nonpolar); 6 externally benchmarked — 2 water models plus methanol, ethanol, acetonitrile, DMSO
  • ~10 ms per molecule, fully reproducible
Learn More Request Preview Access
🌀

FluxMateria — Molecular Dynamics & Free Energy

MD simulation with trajectory viewer, plus Gibbs / Helmholtz free energy and temperature-dependent thermodynamics with AI interpretation.

  • Molecular dynamics with interactive trajectory playback
  • Free-energy landscapes (Gibbs / Helmholtz) with AI-assisted analysis
  • Temperature-dependent thermodynamic properties
Learn More View Demo
⚖️

FluxMateria — pKa & Dispersion

Ionization-state characterization and long-range interaction coefficients. pKa with automatic ionization-site identification; C6 dispersion coefficients from polarizability.

  • pKa prediction with ionization-site identification
  • C6 dispersion coefficients derived from polarizability
  • Batch-ready, fully deterministic outputs
Learn More View Demo
🔬

Materials

From composition to properties in milliseconds: band gap, thermal conductivity, elastic modulus, formation energy across 73 elements. The universal Materials engine is the shared foundation underneath device-native specialty modules — including solar-device design, semiconductor design, catalyst discovery, battery electrochemistry, and surface / contact engineering.

73 elements 5,956 properties 6.6 % hole-mobility median error 9.3 % electron-mobility median error
📐

FluxMateria — Band Gap

Composition-only band-gap predictor with the full electronic-property bundle: alloy decomposer, dopant classifier, mobility, conductivity, band-edge alignment for heterojunctions. ~1 ms per query, no machine-learning training.

  • 0.228 eV MAE across 1,048 experimental materials · 0.338 eV on the 587 gap-bearing
  • Carrier concentration: 99.0% within factor 3, 100% type accuracy on a 197-entry Hall cohort
  • Mobility & conductivity: 100% within factor 3 vs literature across Si, III-V, II-VI, IV-VI
  • Heterojunction band offsets: ~88% Type I/II/III classification on canonical stacks
  • Novel-material mode: reproduces known-material accuracy without measured-property lookups
Learn More Benchmark
⚡

FluxMateria — Semiconductor Design

Real-time drift mobility across doping, temperature, and alloy composition. Design targets with pass/fail overlays, inverse spec search across a 34-material library, Pareto frontiers, (N, T) operating-box heatmap, and CSV export.

  • 15 agreed-reference semiconductors: median error 6.6% μh, 9.3% μe (MAPE 21.7% / 22.2%)
  • 15.9% doping-curve MAPE across 5 decades of N · 7.6% InGaAs alloy MAPE
  • Sub-millisecond evaluation · 228 automated tests
Learn More Benchmark
⚗️

FluxMateria — Catalyst Discovery

Catalyst-native scoring across eight industrial families with full cycle simulation, microkinetics, electrocatalysis (potential + pH), and constraint-driven inverse discovery. DFT-competitive barriers at microsecond speed.

  • 93.4% pairwise, 12/12 top-1 on 96-catalyst benchmark
  • 0.236 eV barrier MAE vs 12 independent DFT studies
  • 35 candidates / sec full-stack, no machine-learning training
Learn More Benchmark
🔋

FluxMateria — Battery Electrochemistry

Battery-native decision layer for cathodes and build-ready screening. Combines transport, degradation, electrolyte & coating fit, uncertainty, and prototype hand-off in one workflow.

  • 26.8 s full-stack workflow per candidate
  • 0.149 V holdout MAE vs published experimental cathode set
  • 5 / 5 scenarios pass on battery-native ranking benchmark
Learn More Benchmark
🟦

FluxMateria — Surface & Contact

Work function, contact readiness, and interface engineering. Surface-aware scoring for device stacks — metal/semiconductor junctions, Ohmic vs Schottky, heterostructure alignment.

  • Work-function prediction with surface-orientation awareness
  • Contact-type classification (Ohmic / Schottky / tunneling regime)
  • Heterostructure band-alignment diagnostics
Learn More View Demo
🗂️

Platform & Workflow

Cross-cutting tools that sit above every domain: constraint-driven inverse search, batch processing at scale, central molecule library, and a versioned project workspace with full audit trail for reproducible decisions.

Inverse search Batch pipelines Versioned runs Audit trail
📁

FluxMateria — Workspace

Projects, versioned runs, pipelines, notebooks, and comparison views. Answer “why did we pick this?” six months later.

  • Projects, Run History, Pipelines, Notebooks
  • Side-by-side candidate comparison with decision-packet export (PDF, CSV)
  • Full audit trail for reproducibility
View Demo Learn More
📋

FluxMateria — Batch Processing

Run any property across hundreds or thousands of molecules in one submission. Bond lengths, ionizations, pKa, druglikeness, NMR, materials, formation enthalpies, interactions — all batch-ready.

  • Batch pipelines for every supported property
  • Progress tracking, partial-failure tolerance, downloadable results
  • Feeds directly into the Workspace audit trail
Learn More View Demo
📚

FluxMateria — Molecule Library

Central storage for your molecules, materials, and candidate sets. Tag, version, and pull into any workflow — used by Batch Processing, Inverse Search, and every specialty module.

  • Central tagged molecule + material store
  • Version history with per-entry provenance
  • Drop-in reference for every tool in the workspace
Learn More View Demo

Not sure which modules you need?

Most pilots start with 1-2 modules. Tell us about your workflow and we'll recommend a starting point.

Request Pilot Access