Tutorial 8: Using Prefab Pipelines#

Building a pipeline from scratch gives you full control, but PhenoTypic also ships prefab pipelines — pre-configured ImagePipeline subclasses tuned for common organisms and plate types. In this tutorial you will survey the available prefabs, apply one, and compare results.

What you will learn:

  1. What prefab pipelines are and when to use them

  2. Survey the available prefabs

  3. Apply a prefab pipeline

  4. Compare results from different prefabs

Imports#

[1]:

from phenotypic.data import load_synth_yeast_plate

Available Prefab Pipelines#

Each prefab is an ImagePipeline subclass with operations and measurements already configured. Choose based on your organism and plate conditions.

Prefab

Best for

Strategy

HeavyOtsuPipeline

General-purpose yeast, clean plates

Multi-stage Otsu with refinement

HeavyWatershedPipeline

Touching or clustered colonies

Watershed segmentation

RoundPeaksPipeline

Round colonies, lightweight

Peak detection

HeavyRoundPeaksPipeline

Round colonies needing refinement

Extended peak detection

FilamentousFungiPipeline

Filamentous fungi (Neurospora, etc.)

BM3D denoise + specialized detector

GridSectionPipeline

Pre-tiled grid sections

Section-level processing

Apply HeavyOtsuPipeline#

Let’s start with the most general-purpose option — HeavyOtsuPipeline. It chains Gaussian blur, CLAHE, median filtering, Sobel edge enhancement, Otsu detection, and several refinement steps (morphological opening, border removal, small-object removal, mask fill).

[2]:

from phenotypic.prefab import HeavyOtsuPipeline

plate = load_synth_yeast_plate()
heavy_otsu = HeavyOtsuPipeline()
result_otsu = heavy_otsu.apply(plate)
result_otsu.dash(overlay=True)

PNG file does not have exif data.

[3]:

print(f"HeavyOtsuPipeline detected {result_otsu.num_objects} colonies")

HeavyOtsuPipeline detected 88 colonies

Apply RoundPeaksPipeline#

Now let’s try RoundPeaksPipeline — a lighter approach that uses peak detection to find circular colonies. It is faster but may miss irregular or faint colonies.

[4]:

from phenotypic.prefab import RoundPeaksPipeline

plate2 = load_synth_yeast_plate()
round_peaks = RoundPeaksPipeline()
result_rp = round_peaks.apply(plate2)
result_rp.dash(overlay=True)

PNG file does not have exif data.

[5]:

print(f"RoundPeaksPipeline detected {result_rp.num_objects} colonies")

RoundPeaksPipeline detected 88 colonies

Compare#

Different prefabs produce different results on the same plate. The best choice depends on your colonies, your imaging conditions, and what you need to measure. A quick visual comparison and colony count helps you decide.

[6]:

print(f"HeavyOtsuPipeline:   {result_otsu.num_objects} colonies")
print(f"RoundPeaksPipeline:  {result_rp.num_objects} colonies")

HeavyOtsuPipeline:   88 colonies
RoundPeaksPipeline:  88 colonies

Prefabs Include Measurements#

Prefab pipelines come with measurements pre-configured, so you can call .apply_and_measure() directly — no need to add your own meas list.

[7]:

plate3 = load_synth_yeast_plate()
df = heavy_otsu.apply_and_measure(plate3)
print(f"{len(df)} colonies measured across {df.shape[1]} features")
df.head()

PNG file does not have exif data.

88 colonies measured across 128 features

[7]:
Shape_Area Shape_Perimeter Shape_Circularity Shape_ConvexArea Shape_MedianRadius Shape_MeanRadius Shape_MaxRadius Shape_MinFeretDiameter Shape_MaxFeretDiameter Shape_Eccentricity ... Bbox_MaxRR Bbox_MaxCC Bbox_IntensityWeightedCenterRR Bbox_IntensityWeightedCenterCC Bbox_DistWeightedCenterRR Bbox_DistWeightedCenterCC Grid_RowNum Grid_ColNum Grid_RowMajorIdx Grid_ColMajorIdx
0 2746.0 192.752309 0.928777 184.931454 8.944272 10.073936 28.861739 57.000000 59.908263 0.197044 ... 96 705 65.577126 675.117063 65.687209 675.177970 0 9 9 72
1 2804.0 194.994949 0.926704 186.843865 8.944272 10.152089 29.274562 58.689863 60.539243 0.140064 ... 98 153 67.158223 122.557819 67.191776 122.542560 0 1 1 8
2 2181.0 172.267027 0.923552 164.531689 8.000000 9.026047 25.632011 51.000000 53.009433 0.183600 ... 91 275 63.812682 248.465178 63.866256 248.428227 0 3 3 24
3 2313.0 177.681241 0.920666 169.588697 8.062258 9.262891 26.627054 53.000000 54.644304 0.184090 ... 92 583 64.928982 554.744857 64.973582 554.700651 0 7 7 56
4 2675.0 191.338095 0.918186 182.718280 8.944272 9.929177 28.284271 57.000000 58.830264 0.108238 ... 97 90 66.665330 60.434904 66.841375 60.565583 0 0 0 0

5 rows × 128 columns

Summary#

Prefab pipelines are the fastest path from plate image to results:

  • ``HeavyOtsuPipeline`` — robust general-purpose detection with refinement

  • ``RoundPeaksPipeline`` — lightweight peak-based detection for round colonies

  • ``HeavyWatershedPipeline`` — for touching or clustered colonies

  • ``FilamentousFungiPipeline`` — specialized for branching fungal morphology

  • All prefabs support .apply(), .apply_and_measure(), .to_json(), etc.

Choose based on your organism, plate conditions, and desired accuracy. When a prefab is close but not quite right, use it as a starting point and customize the parameters.

Next up: Tutorial 9: Diagnosing Image Quality — assess plate quality before choosing a pipeline.