View samples Free trial run →
Live in production · 2 sample reports below

NCA and bioequivalence reporting for generics.
Every excluded subject listed with its reason. Early access.

NCA and Bioequivalence reports — the standard regulatory PK analyses, generated automatically from a CSV. Non-regulated reports, automatic verdict, PDF in your inbox.

Free trial run — NCA → See live samples

Free trial run. NCA and Bioequivalence are open now. Try it with the example, no sign-up needed (NCA · Bioequivalence); to run your own CSV, upload it directly with your email. Reports are indicative (not for regulatory submission) and your uploaded data and report are deleted within 1 hour. The NCA engine is compared against PKNCA 0.12.1 on the public reference theophylline dataset — see Algorithm Validation. The two sample reports below use synthetic demonstration datasets, labelled as such in every PDF.

Live sample · NCA report
FractaLPK Engine
Subjects without a reportable lambda-z: each excluded subject listed with adjusted R-squared and the reason for exclusion
Subjects without a reportable λz — full traceability
NCA — Population summary
Cmax, AUC0-t, AUC0-∞, λz, t½
Compared against PKNCA 0.12.1 · theophylline, n = 12
PKNCA-aligned Quality flags per subject Regulatory disclaimer
Compared against PKNCA 0.12.1 on the reference theophylline dataset — largest difference below 1e-12 % (floating-point rounding) on AUC-class parameters, 0.0 % on Cmax and Tmax (12 subjects, single oral dose).
What a report actually does
From the NCA showcase (24 synthetic subjects, declared units). The selling point isn't the plot — it's that the report refuses to report a λz it cannot defend, names the excluded subject, and gives the reason.

This is what Phoenix does not do out of the box: when the terminal slope fails the reportability criteria (adjusted R² ≥ 0.90 over ≥ 3 points), the λz-derived parameters come back N/A with a named reason — not a confident-looking number the data don't support.

Concentration-time profiles on a semi-logarithmic axis
Concentration–time (semi-log), individual profiles + population mean.
Per-subject terminal-phase lambda-z regression diagnostic panels
Per-subject λz regression diagnostics — the points used, the fit, the R².
How it works
Open engines take a free trial run directly.
Step 1
Explore the samples

Two engines, two synthetic demonstration datasets (labelled as such in every PDF). Open each one to see the verdict, models compared and diagnostic plots — exactly the report a paying client receives.

Step 2
Upload & receive

Upload your CSV, get a magic-link to the PDF when the fit completes (typically 5–10 minutes), and a copy in your inbox. No subscription, no commitment.

Live samples — open the PDFs
Each PDF is generated by the same engine that processes your uploads — same plots, same verdict logic, same honest exclusions and named non-reportable subjects.
NCA Bioequivalence
Algorithm Validation
The NCA engine is compared against PKNCA, an open-source R package for non-compartmental analysis.
NCA engine compared against PKNCA 0.12.1 on the public reference theophylline dataset (12 subjects, single oral dose). Largest difference over all subjects: below 1e-12 % (floating-point rounding) on AUC-class parameters and 0.0 % on Cmax and Tmax. Pinned versions, full method-alignment table and per-subject diff are in the report.
Scope: this validation covers the NCA engine only, on this one dataset; it does not cover the bioequivalence ANOVA (compared separately against PowerTOST, 12 synthetic subjects).
Open Algorithm Validation report (PDF) Compared against PKNCA 0.12.1 and PowerTOST 1.5.7 · see what is and is not covered
Why not just use R + PsN?
R + PsN gives you the numbers. It does not give you a deliverable that declares its own limits, marks its own non-reportable subjects, and refuses to compute what it cannot defend. That deliverable is the product.
Marks its own non-reportable subjects

When a subject's terminal slope fails the reportability criteria, its λz-derived parameters come back N/A — listed by name, with the reason, in a "Subjects without a reportable λz" section. bbr / pmtables give you tables; they don't decide what should not be reported.

Refuses to compute what it can't defend

No CL/F when you haven't declared the dose units. No [P5, P95] at n < 5. No CTD node it cannot assign. Numbers appear at the precision the data support, and not otherwise — epistemic honesty is the point, not a footnote.

Zero R, zero NONMEM

Upload a CSV, receive a PDF report + an editable Word draft (a starting template for internal review). The R stack assumes you already have a run and know how to write Quarto templates, pmtables headers and Xpose plotting code.

Minutes, not days of setup

CSV upload to PDF in your inbox: 5–10 min. Standing up an R / Quarto / PsN pipeline that produces the same self-documenting artefact takes a senior pharmacometrician days to weeks.

When FractaLPK is NOT for you: if you have an in-house pharmacometrics team already running PsN / bbr / pmtables, FractaLPK does not replace that workflow — your team's R pipeline is the right tool. FractaLPK is built for biotechs, CROs and academic groups that need a fast PK answer before opening a full regulatory analysis.