CASE STUDIES

From computation to discovery.

How researchers and organizations use FluxMateria to accelerate materials discovery, screen candidates, and deliver experiment-ready results.

SOLAR DEVICE STUDIO

From 26.74% Certified to 28.51% Simulated.

How FluxMateria carried an independently demonstrated 74-µm thin-SHJ precedent into a 75-µm HBC design and produced a 28.51% research projection after charging the optical penalty. The study replays the certified reference, applies the published HBC improvement roadmap, then tests one predeclared thickness decision. Across the declared resistivity range, the candidate remains at 28.46–28.57%: a +1.39 percentage-point and +5.13% modeled relative gain over the modeled baseline. The complete screen ran in 7.47 seconds and ships with downloadable inputs, results, sources, checksums, and a laboratory validation protocol. The candidate has not been fabricated.

+5.13% modeled gain 28.46–28.57% sensitivity SOTA-class HBC 7.47-second screen Evidence packet included Lab validation pending
PUBLIC BAND-GAP BENCHMARK

0.228 eV Band-Gap MAE on 1,048 Materials, from Composition Alone

A single fixed predictor on the same 1,048-material public cohort where modern graph-neural-network ML reports ~0.31–0.33 eV MAE — matching state-of-the-art accuracy at millisecond speed, with no machine-learning training. Now extends to the full electronic-property bundle: carrier concentration (99.0% within factor 3, 100% type accuracy), mobility & conductivity (100% within factor 3), and band-edge alignment (~88% Type I/II/III). Predictions hold for novel materials the predictor has never seen.

0.228 eV MAE 1,048 materials Carrier + mobility + offsets Novel-material ab initio ~1 ms / query
DFT CROSS-CHECK

Head-to-Head with First-Principles DFT — 15 Canonical Materials

FluxMateria gives band-gap MAPE 10.3% versus 37.5% for the specified GPAW/PBE setup on the same 10 gapped materials. The current evaluated configuration, cohort and inputs are stated in the full comparison.

Beats this PBE on Eg Beats this PBE on μ ~25,000× faster
SEMICONDUCTOR DESIGN

The FluxMateria Semiconductor Atlas

4.6 million semiconductor candidate combinations, enumerated and mapped by a physics-native engine in 199 seconds on a laptop. 87.5 % match against Madelung / NSM Ioffe / Sze references, with zero parameters fit to mobility or bandgap data. Existing platforms organize computed materials — FluxMateria generates candidate universes.

4.66M candidates 199 s on a laptop 87.5 % match to literature No machine-learning training 8 compound classes
THERAPEUTIC DISCOVERY

Alzheimer's Amyloid-Pathway Discovery

A strict BACE1-centered Alzheimer's workflow that forced CNS feasibility and explicit anti-target control against AChE and KCNH2. Final result: 48 strict passes from 707 candidates, two independent BACE1-native chemotypes, and a downloadable white paper.

48 strict passes 2 chemotypes 707 enumerated 23m 28s confirmed
APPROVED-DRUG PROFILING

Iptacopan (Fabhalta®) Factor B Profile — Predicted Blind

From SMILES alone and without training on this compound: 9 of 9 ADMET endpoints match the FDA label, CYP2C8 correctly identified as primary metabolic enzyme, Factor B / Factor D selectivity at 2.5 log units, and a physics-derived binding scorer ranks a 179-compound ChEMBL Factor B panel at Pearson 0.53 with no machine-learning training.

9 / 9 ADMET match 2.5 log selectivity 0.53 physics SAR r Zero mobility / Eg fit
BATTERY MATERIALS

Better Battery Cathodes Through Interface-Aware Screening

A local battery workflow that showed why bulk-only ranking is not enough. Bulk chose LiNiO2, interface reopened LiMnPO4, battery-native scoring elevated LiMnO2, and prototype handoff selected Li4Ti5O12 as the best immediate build candidate.

26.8s local runtime 4 decision winners Build handoff included 10 cathodes screened
SOLAR MATERIALS

Solar Absorber Discovery and CdTe Replacement Challenge

A two-phase solar workflow: first, stack-aware scoring moved the winner from InP to CdTe + ZnO + Mo; then a stricter replacement challenge surfaced CuS and CuSe as novel CdTe-replacement lanes.

28.0s local runtime 51.8s replacement pass InP -> CdTe shift CuS / CuSe lanes 4/4 benchmark scenarios
POWER ELECTRONICS

Gallium-Oxide Family Screening for Next-Generation Power Devices

A staged Universal Materials Engine campaign, powered by FluxMateria's proprietary FLUX Theory physics, evaluated 10 anchor oxides, mapped 1,201,617 binary-to-quinary alloy compositions, and removed 94% through a manufacturability gate. The resulting four-candidate public shortlist recovers literature-supported (Al,Ga)2O3 and ZnGa2O4 directions while retaining LiGaO2 and under-explored NaGaO2 for experimental validation.

1.2M compositions 2.4s archived campaign 94% manufacturability gate 2 literature-supported lanes 4 public finalists
MATERIALS DISCOVERY

Novel Superconductor Family: W-Cuprate Discovery

12,800 candidates screened to 3 experiment-ready leads. A novel tungsten-cuprate composition family with predicted Tc above 160 K, synthesis protocols, and a pending patent — delivered in under 24 hours.

160+ K predicted Tc ~$21/kg Patent Pending
CACO-2 PERMEABILITY

Caco-2 Permeability: Strong Performance with Explicit Input Modes

The current Caco-2 alternative mode achieves MAE 0.281 on 182 development-panel cases; the production-profile MAE is 0.914 under its stated reference exclusions.

MAE 0.281 182 development-panel cases No ML training
ADMET SCREENING

Would FluxMateria Have Caught These Clinical Failures?

Blind retrospective screening of 34 drugs withdrawn or failed due to ADMET toxicity. 88.2% detection rate with zero false positives on 16 safe controls — in 10.5 seconds total.

88.2% detection 0% false positives 209ms / compound
MECHANISM OF ACTION

Predicting Drug MoA from Structure Alone — No ML Required

120 drug-target pairs across 12 target families. 95% accuracy on ChEMBL external validation. Agonist, antagonist, and inhibitor classification from SMILES — in 13ms per prediction.

95% ChEMBL accuracy Zero ML 13ms / prediction
REACTION MECHANISMS

56 Textbook Reactions Resolved in Under 28 Milliseconds

SN1, SN2, E1, E2, and E1CB mechanism prediction on textbook reactions from Clayden, Bruice, and March. 98.2% accuracy including condition-dependent flips — in sub-millisecond time per reaction.

98.2% accuracy 5 mechanisms <1ms / reaction
MAGNETIC MATERIALS

Beating DFT on Curie Temperature — 107 Materials, 17 Families

4.59% MAPE across 107 magnetic materials from composition alone. DFT achieves 15–30% and takes hours. FluxMateria does it in milliseconds with no machine-learning training.

4.59% MAPE Beats DFT 3–6x Milliseconds
CATALYST DESIGN

Inverse Catalyst Discovery: Rediscovery and Exclusion Search

Specify activity, selectivity, stability, and cost constraints, then force the engine off the obvious incumbent lane when needed. FluxMateria converges to the same catalyst families industry and academia already trust, then moves into credible adjacent chemistry under exclusions. The hardened public benchmark scored 1,000 full-stack API calls in 19.7 seconds.

9/9 inverse-search convergences 96 catalysts 10 reaction classes Novel discovery mode 12/12 ranking tests

Have a discovery challenge?

We work with research groups and companies to run computational discovery campaigns. Tell us what you're looking for.

Request Pilot Access →