assay prioritization · model auditing

Stop guessing which mutations matter

Upload your CSV. Get a ranked dashboard across three kinetic channels. Compare scoring methods side by side. Know exactly which mutations to run in the lab next.

Try MutaRank Now → Learn More

Three channels. One triage layer.

Every mutation is scored across three independent effect channels, not collapsed into a single misleading number.

CH-1

Productive-Fold Slowdown

Detects mutations that impede the folding pathway. The protein may eventually fold, but the kinetic cost matters for throughput and yield.

CH-2

Native-State Destabilization

Quantifies thermodynamic instability in the folded state. Catches mutations that weaken the native structure without necessarily blocking folding.

CH-3

Unfolding Acceleration

Flags mutations that increase the rate of unfolding. A protein that folds fine but unfolds too fast is functionally compromised.

mutarank — batch_042.csv — 847 mutations
Mutation Rank Fold Slow Destab Unfold Acc Flag
G148R #1 0.91 0.76 0.97 seq-only
A203V #2 0.72 0.91 0.48 ok
L57P #3 0.95 0.38 0.64 seq-only
D312N #4 0.44 0.69 0.81 ok

Built for the bench, not the boardroom

csv

Batch CSV Upload

Drop in hundreds of mutations with optional protein metadata. Validated on ingest, ranked on output.

pdf

Downloadable Reports

Export ranked results as PDF or CSV. Share with collaborators or attach to grant applications.

f(x)

Editable Scoring Logic

Every formula is modular and exposed. Update weights, swap methods, audit the math. No black boxes.

!?

Insufficiency Flags

Rows where sequence-only scoring may be unreliable are flagged automatically. Know when to reach for structural data.

src

Exportable Source

The entire scoring engine is exportable to GitHub. Reproduce, fork, extend. Full scientific transparency.

Future Integrations

Designed for ESM, ProteinMPNN, AlphaFold/ColabFold, UniProt, and PDB inputs. The architecture is ready.

Four receivers. One comparison panel.

See how different scoring approaches rank the same mutation. Side by side. No switching tools.

Local

Sequence-neighbor context around the mutation site

Structure-Aware

3D spatial relationships and contact networks

Evolutionary

Conservation and covariation from MSA data

PLM

Protein language model embeddings and predictions

The triage layer that mutation tools never built

MutaRank doesn't predict universal folding. It tells you where to look next, and which of your models to trust.

Start Triaging →