Platform overview · datasheet
From the literature to a reactor you can predict.
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 calibrated ML stack that predicts reactor performance with honest uncertainty and traceable sources.
- Domain
- MFC · MEC · MDC · MES
- Audience
- Academic MES researchers
- Snapshot
- 2026-07-06 · local DB
- Architecture
- 4-zone · Postgres + pgvector
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 prediction
Every surface reads from the same curated corpus and the same calibrated model stack — so what you discover, analyze, and predict all trace back to source.
Search the literature, grounded
Semantic search across the corpus, plus an AI assistant that answers from retrieved papers and cites real DOIs — no fabricated sources.
Search the corpus →Parameters with real distributions
Browse canonical parameters with per-system literature distributions, hierarchical priors, and confidence — not single-number folklore.
Open the catalog →A causal DAG + knowledge graph
See how parameters depend on one another through a fitted causal graph and a force-directed knowledge graph of correlations and provenance.
Explore the DAG →Design a reactor in 3D
Build a bioelectrochemical reactor in the 3D lab and get live performance predictions with calibrated uncertainty and mechanistic loss breakdowns.
Open the lab →Sweep conditions, see sensitivity
Fix your operating conditions, sweep one variable, and watch predictions 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 a calibrated prediction
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
20k+ MES papers ingested, 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, snippet, and confidence.
- 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} — never a bare point estimate.
- 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
Every output carries its own uncertainty
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"
}
// held-out coverage at the 95% target
coverage: 97.98% (n = 940)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 — conformal intervals on every output
- 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 — stub returns 503
Open by default
Nine open packages the whole field can build on
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-Catalog
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 a calibrated answer.
Search the corpus, design a reactor, and get predictions that carry their own uncertainty and cite their own sources.