The AI-native workspace for biology

DNA Dojo turns papers into structured experimental intelligence: citation-backed answers, methods cards, entity memory, and reusable context for life-science projects.

Evidence-bound answers
Methods extraction
Project memory
Paper intelligence run
Evidence locked
Paper Card

MAPK rebound after KRAS inhibition

Extracts models, perturbations, controls, readouts, limitations, and source-backed follow-up questions.

KRAS G12C
phospho-ERK
vehicle control
Citation graph

Answers route through embedded chunks and return citations before they become saved project memory.

Methods p.4Results p.7

DNA Dojo Paper is the first active module

The first release focuses on a narrow but high-value loop: private PDF upload, text extraction, chunk embeddings, structured Paper Card generation, Methods Card extraction, citation-backed Q&A, and saved research cards.

Parse PDFs into page-aware chunks for traceable retrieval.
Extract experimental model systems, perturbations, assays, controls, and readouts.
Generate answers only from retrieved paper evidence, with citation labels.
KRAS inhibitor resistance
3 papers · 12 questions · 8 saved cards
Evidence ready
Paper Card

Adaptive resistance after pathway inhibition, core finding, limitations, and next questions.

Methods Card

Cell line, animal model, perturbation, assay, control group, variable, and readout extraction.

Citation Q&A

Each answer is generated from retrieved chunks and saved with citation metadata.

Project memory

Save paper summaries, methods, and answers as reusable research cards.

Designed around biological evidence, not generic chat

DNA Dojo treats papers as experimental records. The interface privileges methods, controls, model systems, entities, and citations so researchers can evaluate evidence quickly.

Paper-grounded synthesis

Research questions, claims, methods, entities, caveats, and suggested follow-ups stay tied to source chunks.

Experimental method extraction

Model systems, perturbations, assays, controls, readouts, and protocol notes are normalized into reusable cards.

Biology memory layer

Saved cards turn papers and answers into project memory for genes, pathways, compounds, and assays.

A workspace that can grow beyond papers

Paper is live first. Molecule, sequence, tutoring, experiment, and discovery modules are intentionally reserved so future tools can share one project memory layer.

Paper

Active in V1

Read, query, and card biology papers with citations.

Molecule

Reserved

Track compounds, targets, mechanisms, and assay evidence.

DNA / Protein

Reserved

Annotate sequences and connect variants to literature.

Tutor

Reserved

Turn project context into guided explanations and checks.

Experiment

Reserved

Draft experiment plans from methods and constraints.

Discovery

Reserved

Surface hypotheses, gaps, and next papers to read.

Built for the loop researchers actually run

Upload a paper, extract the evidence, ask follow-up questions, then save the useful pieces back into the project.

1

Ingest

Private PDFs, metadata, and project scope are captured together.

2

Extract

Methods, entities, controls, and limitations are structured into reusable cards.

3

Ask

Questions return citation-backed answers that can be saved to project memory.