Platform overview · datasheet
From the literature to reactor estimates you can check.
MESSAI turns a curated corpus of microbial-electrochemistry research into a working model of the field — semantic discovery over the papers, a causal map of the parameters, and a modelling stack that estimates reactor performance with stated uncertainty and traceable sources, and withholds an estimate when the evidence is thin.
- Domain
- MFC · MEC · MDC · MES
- Audience
- Academic MES researchers
- Snapshot
- 2026-07-06
- Architecture
- Web platform · Postgres with vector search
What it is
A research platform for bioelectrochemical reactors
Microbial electrochemical systems are reactors where bacteria oxidise organic matter and pass electrons to an electrode — producing electricity (MFC), hydrogen (MEC), desalination (MDC), or targeted chemistry (MES). The field is data-rich but fragmented across tens of thousands of papers with inconsistent units and reporting. MESSAI unifies that literature into one queryable, model-backed system so a researcher can ask what is known, design a reactor, and get a defensible performance estimate — without leaving a single surface.
The foundation
The corpus, in numbers
Live where a simple count allows; documented and dated where a figure is gated by harmonisation. Re-verify against production before external citation.
Scientific-integrity note. Extraction is imperfect and coverage is uneven — about 40% of papers still lack parameter extractions (ingest outran extraction), and dispersion is enormous (power-density CoV ≈ 1,285%). Point estimates are meaningless without their context, so every number on the platform is designed to ship with n, units, range, and a confidence flag. The binding constraint on modelability is harmonisation and verification, not raw extraction volume.
What researchers can do here
One platform, from paper to checkable estimate
Every surface reads from the same curated corpus and the same prior stack — so what you discover, analyze, and estimate all trace back to source.
A reactor design, rebuilt with rigor
Drive an interactive 3D microbial fuel cell and open a sourced dossier on every layer — its material, role, and the literature-traced fix a rigorous review caught — then compare it against reference designs.
See the case study →Parameters with real distributions
Browse canonical parameters with per-system literature distributions, hierarchical priors, and confidence — not single-number folklore.
Open the catalog →A knowledge graph of causal structure
See how parameters depend on one another through a force-directed knowledge graph — causal structure from domain consensus, with corpus co-observation marked, and provenance in one interactive view.
Explore the graph →Design a reactor in 3D
Build a bioelectrochemical reactor in the 3D lab and get live performance estimates with the interval the prior supports, an explicit note where none does, and mechanistic loss breakdowns.
Open the lab →Sweep conditions, see sensitivity
Fix your operating conditions, sweep one variable, and watch estimates move against the empirical distribution from the corpus.
Run a sweep →Surface what the literature missed
A research-scan view of physics-violating results, statistical anomalies, and Bayesian outliers worth a closer look.
Open the hunter →How it works
From a raw PDF to an estimate with a measured interval
The same pipeline feeds every surface. Each stage is auditable — you can trace any number on the platform back through calibration, canonicalization, and extraction to the paper it came from.
- 1
Corpus
19,000+ MES papers in the corpus, with full-text PDFs content-addressed and embedded for semantic retrieval.
- 2
Extraction
Two-tier LLM extraction pulls measurements with their conditions. Every value keeps its DOI, and about half keep a source snippet.
- 3
Canonicalization
Raw values are normalized to SI and mapped to canonical parameters, so numbers from different papers become comparable.
- 4
Priors & calibration
Hierarchical Bayesian priors (PyMC, log-normal) per system class, wrapped in conformal intervals with measured coverage.
- 5
Prediction
Per-physics-family predictors return every output as {value, unit, ci_low, ci_high, confidence, source}. Interval fields are filled where a calibrated interval exists.
- 6
3D lab
Design a reactor and see the prediction, the empirical evidence behind it, and the mechanistic loss decomposition side by side.
The prediction contract
Served predictions carry an interval where one is calibrated
Predictions are never single numbers. Each value ships bounds, a confidence, and a source, and is routed by physics family rather than squeezed into a three-type enum.
// every numeric output
{
value: 0.42,
unit: "W/m^2",
ci_low: 0.19,
ci_high: 0.71,
confidence: "medium",
source: "hierarchical_prior + conformal"
}
// interval coverage at the 95% target (priors v2, 2026-10-28)
coverage: 96.1% (5,269 values, 339 papers)System taxonomy
17 primary types, not three
The corpus is classified against a canonical taxonomy of seventeen primary system types (plus multi-axis subtypes and combination types). Restricting to MFC/MEC/MDC would silently coerce the rest into the wrong shape.
An honest inventory
What’s wired vs. what’s dark
Being candid about maturity is a platform value. These are shipped, user-facing surfaces versus capabilities that exist in code but have no live interface yet.
Live & wired
- Research search + grounded chat — pgvector retrieval, ~25 corpus/ML tools
- Parameters — catalog, causal DAG, knowledge graph, sweep
- 3D lab + ML predictions — intervals on served predictions where one is calibrated
- Hunter — physics violations, anomalies, outliers
- Admin — corpus stats, extraction processing
Dark (built, no UI)
- Manuscript-review engine — grounding tools complete, no surface
- On-demand figure digitization — runs nightly, not interactive
- Live Bayesian-network design recs — pre-computed, no custom endpoint
- Research-agent orchestrator — one-shot synchronous coordinator; no durable workflow
Open by default
Nine open packages (one still scaffolding)
The data and tooling that power MESSAI are released as standalone, citable packages — each with a schema, a license, and a CITATION.cff. Use them in your own analysis; they don’t depend on the platform.
MESS-Parameters
DataThe canonical MES parameter ontology — variables with literature distributions, a causal DAG, and full provenance.
CC BY 4.0MESS-Materials
DataDFT-computed electrode, membrane, and catalyst properties with Materials Project provenance and Pourbaix stability.
CC BY 4.0MESS-Microbes
DataCurated MES-relevant microorganisms — electrogens, electrotrophs, community partners, and negative controls.
MITMESS-Methods
ToolsMethodology tooling and a physics-constraint validator for experimental design, sample sizing, and QC (Python).
MITMESS-Simulations
ToolsPhysics-based models — Butler-Volmer kinetics, biofilm growth, and Nernst / Monod calculators.
MITMESS-Learning
ContentEducational calculators — sustainability, life-cycle assessment, techno-economics, and SDG alignment.
CC BY 4.0MESS-Agents
ToolsA multi-agent research orchestration framework for literature analysis and insight generation.
MITMESS-Hypotheses
ToolsResearch-gap identification and hypothesis generation with confidence scoring and contradiction detection.
MITMESS-datasets
DataA slug-keyed catalog of curated open MES datasets (Zenodo, Figshare), cross-referenced to Parameters and Materials.
CC BY 4.0New to the packages? Start with the manual or read how the parameter package is consumed downstream.
Under the hood
Four zones, one repository
An Nx monorepo deploys as four independent zones behind a single URL. Writes route exclusively through the API zone; the others read the shared Postgres + pgvector store, with Python ML services for embeddings, OCR, and Gaussian-process inference.
Research, parameters, hunter, admin, and the homepage.
The 3D reactor simulator and model catalog.
All API routes; the only zone that writes to the database.
Marketing, learning, and reference content.
Get started
Bring a research question.
Leave with the evidence, its conditions and a calibrated range where one is supported.
Search the corpus, design a reactor, and read literature-based ranges that name their sources, their conditions and where no calibrated range exists.