FAQ

Getting started

What does Gradiance actually do?

It accepts tabular assay data, helps you review the mapping, and runs the supported method for the selected workflow. The launch methods are unweighted linear or quadratic calibration, unweighted free-parameter 4PL dose response, and basic unweighted Michaelis-Menten. Every result keeps the uploaded data and saved result record. PNG and basic CSV results exports are available on Free; other formats depend on your account entitlement.

Do I need to write code?

No. The interface is conversational: drop the file, describe what you want in plain English, the agent handles the workflow. A Figure replay (Python) export is available to entitled accounts, but you never have to read it to use the workspace.

Which file formats can I upload?

CSV, Excel (.xlsx and .xls), and tab-separated. Multi-file uploads are supported - drop several files at once and they get treated as related datasets within the same run. See Uploading data for layout conventions and common parse errors.

Do I have to pick the assay before uploading?

No, the order is the other way around. Drop the file first; Gradiance inspects it and surfaces the most likely assays at the top of the picker (a serial-dilution shape suggests endpoint titer or dose-response, and a tidy table with named standard columns suggests a standard curve. Plate/grid layouts are Preview for this launch. You can override the suggestion or review a Preview workflow, but the supported methods require explicit mapping rather than open-ended inference.

Is my data secure?

Uploads are encrypted in transit (HTTPS/TLS) and at rest in S3. Every API endpoint that backs the workspace checks that the signed-in user owns the run before returning anything, so a leaked URL doesn't expose data to a different account. The fitted result, parameters, and exports stay attached to the run for as long as you keep the run; raw uploaded files have a shorter retention than the result record itself. We do not sell your data and we do not train models on it.

Supported and Preview assays

What assays does Gradiance fit?

The supported launch workflows in the new-run picker:

• Quantification - standard curve / sandwich ELISA and BCA / Bradford protein with explicit source roles. See Standard curves.
• Potency & dose response - IC₅₀ / EC₅₀ using an unweighted free-parameter 4PL. Cytotoxicity and neutralization remain Preview. See Dose-response.
• Gene expression (Preview) - qPCR ΔΔCt and absolute quantification. See qPCR.
• Kinetics - basic unweighted free-parameter Michaelis-Menten. Growth curves and kinetic ELISA initial-slope remain Preview. See Kinetics.
• Cell-based (Preview) - cell viability and CFU plate counts. See Cell-based assays.
• Binding & affinity (Preview) - saturation binding and competition binding. See Binding.
• Custom / freestyle (Preview) - open-ended requests are not a supported launch method.

Free accounts can submit 20 free runs per calendar month (UTC) and export PNG (with a small watermark) and basic CSV results. Required setup answers for a new run are included with that run; later refinements and follow-ups count as another run. Pro and Team plans are coming soon; final capacity and export features will be published at launch. The full pricing matrix is on the pricing page.

Western blot densitometry - coming?

It's on the picker as “Soon.” You can run it through the freestyle workflow today by including normalized band intensities; a dedicated workflow will land soon.

What's the difference between 4PL and 5PL?

4PL fits a symmetric sigmoid (top, bottom, IC₅₀, Hill). 5PL adds an asymmetry parameter so the curve can have different slopes on each side of the inflection. The dose-response workflow accepts unweighted 4PL and 5PL, plus constrained 3PL with the lower plateau fixed at zero. The 5PL relative midpoint and its propagated interval are separate from the fitted scale.

Reading results

How do I know if my fit is good?

Fits with a reported R² receive a heuristic quality tier. Review residuals, uncertainty, model assumptions, and experimental design at every tier; a high R² does not establish publication readiness. See Quality Control for the specific thresholds and flags.

The CIs on my parameter are huge. What happened?

Wide CIs mean the data don't actually identify that parameter. Most often it's an asymptote that never plateaued. Add doses past where you stopped, or constrain the parameter if you have prior information. See Understanding your results for the CI taxonomy.

Can I exclude an outlier?

Yes. Tell the agent which point: “exclude the 100 µM point” or “drop replicate 3 at the highest dose,” and it refits in place. Points whose residuals are inconsistent with the converged fit are flagged on the plot (rendered as a red ×) and surfaced in the QC panel, but no point is removed from the fit unless you ask. We prefer the explicit decision over a silent auto-drop.

Can I fix Top or Bottom to a known value?

Yes. “Fix bottom to 0,” “constrain top to 100,” “fix Hill to 1” all work. A pinned parameter doesn't get a CI - the constraint is treated as ground truth. See Dose-response for when constraints help versus hurt.

The agent picked the wrong columns. How do I fix it?

Just say so: “use Conc_uM as the concentration and OD450 as the response.” The agent re-runs with the corrected mapping.

Exports & reproducibility

What can I export?

• PNG (300 DPI) - figure for slides and print. Available on Free; watermarked on Free, clean exports are planned for Pro (coming soon).
• SVG - vector for editing in Illustrator or Inkscape. Pro/Team (coming soon).
• PDF report - figure, parameters, method, and provenance compiled in-browser. Pro/Team (coming soon).
• CSV - fitted values, residuals, and outlier flags. Available on Free.
• Excel - same content as CSV, multi-sheet, formatted. Pro/Team (coming soon).
• Figure replay (Python) - a saved-fit replay that redraws the saved observations, curves, parameters, and intervals. It does not rerun the AI assistant, repeat preprocessing, or re-estimate parameters from the original file. Pro/Team (coming soon).
• Audit bundle (JSON) - the full provenance record: input file hashes, fit parameters, agent steps, model versions. Useful when you need to attach a reviewable trail. Pro/Team (coming soon).

Can I re-run the analysis offline?

The exported Figure replay (Python) file is a saved-fit replay. It reads the saved observations, curves, parameters, and intervals and redraws plots in compatible coordinate groups. It does not rerun the AI assistant, repeat preprocessing, or estimate parameters again from the original input file. Follow the dependency and input instructions in the file and retain the original source data for a full analysis reproduction.

How do I cite Gradiance in a paper?

See How to cite for APA, BibTeX, RIS, and a suggested methods paragraph.

Statistical methods

What algorithms are under the hood?

Non-linear least squares via Levenberg-Marquardt (SciPy curve_fit). 95% CIs from the covariance matrix of the fitted parameters, with t-statistic correction for the degrees of freedom. Cheng-Prusoff for Ki, Spearman-Kärber for TCID₅₀, ΔΔCt for relative qPCR, and a one-way ANOVA + Tukey HSD for post-hoc multiple comparisons. See Statistical methods for the full list and the validation table.

How are confidence intervals calculated?

From the covariance matrix of the converged fit, multiplied by the t-statistic at α = 0.05 with the right degrees of freedom. For non-Gaussian parameters (e.g. log-IC₅₀), CIs are computed in the fit space and back-transformed to the reported scale.

Pricing & account

Is there a free tier?

Yes. 20 free runs per calendar month (UTC), shared across assay and Flow analysis, plus PNG and basic CSV results export with a small PNG watermark. Required setup answers for a new run are included with that run; later refinements and follow-ups count as another run. No card required. The full pricing matrix - including which assays are featured for which tier - lives on the pricing page.

How are free runs counted?

Each new analysis uses one run. Required setup answers for that run are included; later refinements and follow-ups count as another run. The allowance is 20 free runs per calendar month (UTC), shared between assay and Flow analysis.

What do paid tiers add?

Pro and Team plans are coming soon. Final capacity, export formats, and collaboration features will be published when those plans launch.

What happens to my data if I cancel?

Account access continues through the end of your billing period - exports stay enabled the whole time. After that the account drops back to Free-tier limits; saved runs remain readable, but new runs respect the Free quota. You can request immediate deletion at any time from settings or by emailing us.

Is there an API?

Team details are coming soon; no public API is available today. For now, the integration path is the exported Figure replay (Python) (when available to your account). Follow its dependency and input instructions. A copied assay run link remains private to its owner; share reviewed exports with collaborators.

Does it work offline?

The web app needs an internet connection. For exported Figure replay (Python) files, follow the dependency and input instructions included in the file; requirements vary by analysis.

Operational guides

• Troubleshooting and support reports
• Export verification and reproducibility
• AI usage and account limits

Still stuck?