Foundation models,for neuroscience data.
Neuron Lab pairs classical, reproducible pipelines with Neuron-FM — cell, signal and connectome foundation models — running on your data with real math on the server.
31 analysis modules, real math, tested end-to-end.
15 computational neuroscience and 16 neurobioinformatics modules, plus 3 Neuron-FM foundation models and 7 live nf-core genomics pipelines — every one runs a genuine algorithm on the server and renders a structured result viewer.
Differential expression
Welch's t, limma-style empirical-Bayes moderation, BH-FDR — volcano + top-genes table.
PCA & clustering
Covariance-eigendecomposition PCA with scree, projections and explained variance.
Spike-train stats
Firing rate, ISI, CV, jittered cross-correlograms and population dynamics.
LFP / EEG spectra
Welch and multitaper PSD, band power, spectral entropy, Hjorth parameters.
HH / LIF neurons
RK4 integration of Hodgkin–Huxley, LIF, AdEx, Izhikevich with spike detection.
GWAS association
Case/control scans with genomic control λ, BH q-values and Manhattan plots.
Group comparisons
Welch ANOVA, Kruskal–Wallis, Games-Howell post-hoc, Hedges' g with 95% CI.
Robust & resampling
Huber M-estimator regression, permutation tests and percentile bootstrap CIs.
31 launchable modules
15 computational neuroscience + 16 neurobioinformatics modules, one launcher and one result viewer.
Recently shipped in Neuron Lab.
Disease workflows
Ready-made, phased protocols for Alzheimer's, Parkinson's, MS, ALS, TBI and more — every step launches the right pipeline, workflow or module.
Neuro toolkit suites (4)
MNE-Python, EEGLAB, Brainstorm and FSL-style suites for brain mapping and signal processing — preselect a module and run.
Pipeline Advanced Options
Tune aligners, QC strictness and per-pipeline parameters from the backend schema, with Default / Strict QC / Fast / Publication presets.
Single-cell analysis catalog
scRNA, scATAC, single-cell methylation, CUT&Tag and 10x Multiome grouped in the runner — plus a Single-Cell pipeline section.
BioAgent orchestration
Describe your question in plain English; the agent plans, QCs, runs the right modules and interprets the output.
Deep analysis (Level 2)
Second-stage modules for ATAC, ChIP, methyl, CUT&RUN and variant runs — differential accessibility, DMRs, TMB and drivers.
Downstream from pipelines
Launch DESeq2, PCA and clustering straight off a completed RNA-seq or scRNA-seq run, with custom references.
Direct cloud uploads
FASTQ, BAM, VCF and matrices upload straight to cloud storage via signed URLs with progress and resume — no size ceiling from the app.
Notebooks
Python (Pyodide) and R (WebR) notebooks in the browser — your datasets load as a DataFrame, plots export as PNG.
Credits & workspaces
Token wallet with a shared exhaustion rule, organisation workspaces, shareable read-only results.
nf-core RNA-seq, scRNA-seq, ATAC-seq, CUT&RUN, DNA, ChIP-seq & methylation.
Raw FASTQ to biology on dedicated cloud compute — pay per sample, no cluster to maintain. 7 nf-core pipelines are live: RNA-seq, ATAC-seq, ChIP-seq, CUT&RUN, Bisulfite-seq, Variant Calling (Sarek), scRNA-seq. Upload your own reference or use a pre-loaded genome, then send results straight into the analysis modules.
Samplesheet in
Point Neuron Lab at an nf-core samplesheet — paired or single-end FASTQ.
Salmon or STAR
Pick the aligner and read-depth tier; the exact price is shown before launch.
Counts + MultiQC out
Track live run status, then download counts, QC and the full MultiQC report.
Foundation models, integrated end-to-end.
Cell, signal and connectome FMs share the same launcher, storage, RLS and result viewer as every classical analysis — swap the backbone, keep the pipeline.
Cell Atlas FM
PCA embedding · scGPT / Geneformer-class in production
Embed cells, then annotate cell types zero-shot or cluster them — accuracy on held-out cells.
Neural Signal FM
spectral + PCA · LaBraM / CBraMod-class in production
Embed neural-signal windows and classify dynamical state — regular / bursting / irregular.
Connectome FM
spectral node embedding · graph pretraining in production
Embed connectome nodes and detect communities; ARI vs planted modules.
Built for research that has to be reproducible.
Every dataset and analysis is owned by a user, protected by row-level security, and versioned by parameters — so a result from today can be replayed tomorrow.
Per-user isolation
Row-level security scopes every dataset, analysis, and result to its owner.
Dataset storage
Signed uploads, private storage, grouped by project.
Rich viewers
Metrics grids, sortable tables, volcano/scatter/line charts, downloads.
Reproducible
Typed parameters, deterministic runs, versioned modules.
Compliance as Architecture
Enforced at the infrastructure level, your data stays in your jurisdiction, always.
Ready to run your first analysis?
Create an account, upload a dataset, and launch a real pipeline in minutes.