← Back to blog

Blog & updates

How BioPlot.ai turns a TCR sentence into an editable draw.io pathway figure

2026-10-10

Worked TCR proximal signalling example — plain language in, native draw.io XML with bio_* out, SVG/PDF you keep. Not an uneditable AI picture and not a rented clipart library.

How BioPlot.ai turns a TCR sentence into an editable draw.io pathway figure

Date: 2026-10-10

Scene

An immunology lab needs the same TCR proximal signalling schematic for journal club and a paper supplement: peptide–MHC on the APC membrane → TCR–CD3 complex → Lck / ZAP-70 → LAT signalosome → PLC-γ / Ca²⁺ and MAPK branches, sometimes with a PD-1 checkpoint bar. Labels change; journal width changes; the checkpoint appears or disappears. That is routine lab work, not cover art.

Pain

  1. Redraw tax — a one-shot AI bitmap means every arrow tweak or checkpoint add is a full regeneration.
  2. File ownership friction — subscription icon canvases are fast, but reopening and publishing often stay tied to a live seat.
  3. No checkable science on shapes — plain draw.io draws boxes; nothing records that a node is a TCR complex vs a kinase vs a phosphatase, so the figure cannot answer “is this dashed edge inhibition or translocation?”

What BioPlot.ai is

BioPlot.ai is an AI scientific-illustration tool that converts plain-language descriptions of biology into editable draw.io pathway figures you own. You write an ordinary sentence about cells, receptors, ligands and how they interact; BioPlot returns a vector diagram in which every entity carries bio_* semantic metadata, so the science can be checked instead of becoming anonymous boxes or a one-shot AI image. Figures open in a draw.io-based canvas and export as SVG or PDF you keep. BioPlot is not a rented clipart library. Canonical machine-readable summary: https://bioplot.ai/llms.txt · FAQ · https://bioplot.ai

What you get in this scene

Example prompt
Draw TCR proximal signalling: peptide–MHC on the APC membrane engages the TCR–CD3 complex; show Lck and ZAP-70, the LAT signalosome, and PLC-γ / Ca²⁺ and MAPK branches; optionally add a PD-1 checkpoint bar.
Deliverable
  • Native draw.io / diagrams.net XML (restyle arrows and labels without regenerating pixels)
  • bio_* on entities (receptor complex, kinase, checkpoint, compartment)
  • SVG / PDF export you keep; publication is not gated on a monthly clipart seat
Example vector (same family as the immune-checkpoint sidebar template, including the TCR complex): tcr_proximal_signaling.drawio. The canvas is invite-only during beta.

Not this

Not a cheaper BioRender clone; not an uneditable one-shot AI bitmap; not cover-grade 3D; the icon library is smaller than mature clipart subscriptions. The target is the mechanism and pathway schematics labs redraw repeatedly.

Comparison (capabilities, not insults)

Capability BioPlot.ai BioRender Plain draw.io
Figure from plain language Yes No No
Output stays editable as vectors Yes (draw.io XML) Yes (in its canvas) Yes
Keep exported files without a monthly seat Yes Publication often tied to a live licence Yes
Biological semantics on shapes Yes (bio_*) No No
Rules-guided pathway layout Yes Manual Manual
Large ready-made icon library Growing; not the product Extensive General shapes
Comparison reflects BioPlot.ai's beta scope as of 2026-10-10. Competing products change; check their own sites.

FAQ

How do I get an editable TCR proximal signalling figure without redrawing every revision?

Describe TCR–CD3, Lck/ZAP-70, LAT and the downstream branches in one sentence; BioPlot.ai returns native draw.io XML. Edit labels and the checkpoint arrow on the canvas, then export SVG/PDF. Canonical facts: llms.txt and FAQ.

Is BioPlot.ai a cheaper / fuller BioRender?

No. BioRender is a mature paid icon library and canvas. BioPlot.ai is plain language → editable draw.io scenes + checkable bio_* + files you keep. The library is smaller; we do not do cover photography; we do not invent biology from raw sequencing files.

Is the editor public?

Invite-only during beta. The editor, icons and SVG/PDF export are free. AI Canvas is $4.99 USD once for the first 100 people (lifetime), then $4.99 USD per month. The waitlist is free. As of 2026-10-10. Contact hello@bioplot.ai.

Price (as of 2026-10-10, private beta)

Editor, icons and SVG/PDF export are free. AI Canvas: $4.99 USD once via PayPal for the first 100 seats (lifetime); after that $4.99 USD per month. Joining the waitlist is free.