12 Derived Features
Derived features combine existing features, including features from different channels. For example, the normalized optical redox ratio uses the intensity_sum from two channels: NAD(P)H / (NAD(P)H + FAD).
12.1 Build Derived Features
Select Derived features near the bottom of the Configuration page to open the builder.
Any derived features already defined for the current profile are listed at the top, each showing its name, its expanded formula, and a 🗑️ button to delete it. Below the list, a new feature is composed from:
- a
Template(a common formula, orCustom…to write your own), - a
Name(e.g. redox_ratio) — the output column becomesDerived: <Name>, and - the operands that fill the formula.
Operands are available from all channels. If none are listed, select feature extractors for your channels first, then return to the builder.
Each operand dropdown lists categorized features first, followed by bookkeeping columns without an extractor prefix: amp1, offset, reduced_chi_square, centroid coordinates, and the a2 / a3 fit remainders. These are per-cell numbers and can be used like any other operand.
For example, background-corrected intensity is Intensity texture_<channel>: intensity_sum minus <channel>_offset times the number of time bins. Enter the bin count as a number in Custom… mode, e.g. A - B*256.
A pixel-prefitted (SPCImage) channel does no fit of its own, so it contributes only its a2 / a3 remainder — no amp, offset or reduced_chi_square.
When the preview is valid, click ➕ Add derived feature. Each extraction profile keeps its own definitions; adding or deleting them saves the change immediately.
12.1.1 Templates
The Template dropdown offers four ready-made formulas: normalized A / (A + B), ratio A / B, difference A - B, and sum A + B. Each fills in the formula and provides searchable dropdowns for operands A and B.
Pick both features and give the result a Name, then check the live preview. The fifth option, Custom…, opens the formula editor described next.
12.1.2 Custom Formulas
Custom… mode lets you compose an arbitrary formula. First pick the operands from the Operands (each becomes A, B, C… in the order picked) multiselect — the features you choose are aliased A, B, C, … in pick order, and a caption echoes the mapping (e.g. A = Intensity texture_fad: intensity_sum, B = …). Then build the formula in the Formula box, typing directly or using the append buttons for the operators (+ - * / ( )) and for each alias.
The formula language supports:
- the four arithmetic operators
+,-,*,/, - a leading sign (unary
+/-), - numeric constants, and
- parentheses for grouping.
Division by zero yields NaN rather than raising an error or producing infinity. Anything outside this language — function calls, exponentiation (**), modulo (%), comparisons, or a bare operand with no operator — is rejected.
12.2 Compute Derived Features
Derived features are computed during Numerical Feature Extraction, after all FOV results have been concatenated. The definitions from the active extraction profile are recorded in the automatically saved FOV metadata alongside the extraction settings. Each definition adds one Derived: <name> column to the output dataset.
If any cell has NaN in a derived column, for example after division by zero or use of a NaN operand, a single dataset-wide warning reports the affected cell count for that feature. These cells remain in the output.
12.3 Derived Feature In Data Analysis
On the Data Analysis page, all derived features are collected into one Derived Features group in the numerical selection widgets, alongside the per channel-extractor groups. A derived feature is labeled by its plain name (e.g. redox_ratio); unlike extracted lifetime or intensity features, it carries no unit or symbol, since its meaning is entirely user-defined.
