Conversational bioinformatics

Research faster.
Discover more.

Upload your omics data, describe your research goals, and receive publication-ready figures, statistics, and insight — through conversation. No code required.

Request early access See how it works

MoIRA is the bioinformatics analyst on your team — one that reads your data, proposes the methods, and runs the whole analysis while you watch every step.

No code requiredFully reproducibleYou stay in control
.IDAT.FASTQ.BAM.CSV

Bring any data

Raw IDATs, FASTQs, BAMs, or a counts matrix. Drop in what came off the instrument — no preprocessing, no formatting.

Adjust for sex & batch
Sex → covariate. ✓

Just describe it

Tell MoIRA your design in plain English. It maps your samplesheet, proposes methods, and shows the plan before running.

Get real results

Publication-ready figures, statistics, and the exact R and Python scripts MoIRA wrote — all reproducible, all yours.

See it in action

See the reasoning. Trust the results.

Every analysis is planned in conversation, reviewed by you, and executed transparently from start to finish.

Run a PCA on the normalized betas, colored by Genotype.
Running PCA on the 785,432 probes that passed QC. PC1 separates your genotypes cleanly.
LIMMA · 2,148 DMPS · volcano_ko_vs_wt.png
Preprocessing pipeline
read_idat
quality_control
probe_filtering
bmiq_normalization
combat
cell_type_estimation
0 / 6 complete · 00:00 elapsed
The roadmap

One platform.
Every omic.

A unified, conversational interface for biological data — each modality shipped only after its full workflow is validated end-to-end.

DNA methylation arrays
27k · 450k · EPIC · EPICv2 · Mouse
Live
Single-cell RNA & ATAC, bulk RNA-seq
mRNA · miRNA · tRNA coverage
Next
Whole-genome & whole-exome
Validating
ChIP-seq · spatial · proteomics & more
Planned
Questions

The details matter.

Today: all major Illumina methylation arrays (27k, 450k, EPIC, EPICv2, Mouse). Next up in 2026: single-cell RNA-seq, single-cell ATAC-seq, and bulk RNA-seq — with WGS, WES, spatial, proteomics, ChIP-seq family, and more in the roadmap after that. We validate one modality at a time rather than shipping shallow support for many.
No. Raw files are the expected input for every modality — IDATs for methylation, FASTQs and BAMs for sequencing. If you've already preprocessed to a counts matrix or beta matrix, you can upload that too and MoIRA will skip to analysis.
It proposes a pipeline based on your data type, sample size, and samplesheet columns, then shows you the full plan before running. You can override any step via chat.
Your data is encrypted in transit and at rest on AWS S3. Analyses run in isolated sandboxes scoped to your account. Nothing is used for training.
Single-cell RNA, single-cell ATAC, and bulk RNA-seq are in active development for 2026. WGS and WES follow shortly after. If there's a modality you depend on, tell us — roadmap prioritization is real and customer-driven.
Yes. Every R and Python script generated for your analysis is available in the Files panel as a downloadable .py or .R file. You own the outputs.

The future of bioinformatics is conversational.

Be among the first researchers to analyze omics data through natural-language conversation.

Join the waitlist