dp-summarize-deep-features¶
dp-summarize-deep-features is the step that turns DeepProfiler feature tables into a compact result bundle for human review.
It gives a first-pass view of whether the learned features separate the samples at all.
Purpose¶
Use this skill when you want:
a compact summary of the deep-feature result instead of only parquet tables
a quick check that the learned features separate the demo wells at all
a simple figure for first-pass inspection
Main Outcome¶
After this skill finishes, the deep-feature branch has a readable summary instead of only high-dimensional tables.
This is a first-pass review step, not a final biological conclusion step.
Inputs¶
This skill reads:
a project config such as
configs/project_config.demo.jsonthe single-cell and well-level deep-feature tables from dp-collect-deep-features
an optional output directory
In the demo setup, the summary is based on four cells, two wells, and 672 learned feature columns.
Outputs¶
profile_summary.jsonA compact machine-readable summary of the deep-feature result.well_metadata_summary.csvA per-well summary of the retained metadata.top_variable_features.csvThe learned features that varied the most across wells.pca_coordinates.csvPCA coordinates for each well.pca_plot.pngA quick PCA figure.pipeline_skill_manifest.jsonThe run record for this skill invocation.
Agent Demo¶
This page is based on the recorded DeepProfiler summary outputs already produced for the repository demo:
demo record:
demo_record_2026_04_25_gpu_finalsource summary bundle:
08_dp_summary
Request¶
I already have the deep-feature tables and want a quick summary of what the demo wells look like in learned-feature space.
Structured Trace¶
user_input:
I already have the deep-feature tables and want a quick summary of what the demo wells look like in learned-feature space.
planner_step_1:
intent:
Select the public DeepProfiler summary step that turns the collected feature tables into a readable result bundle.
tool_calls:
- read("integrations/openclaw/autodl/workspace/skills/cellpaint-pipeline/SKILL.md")
- exec("cd /root/pipeline/CellPainting-Claw && /root/autodl-tmp/miniconda3_envs/lyx_env/bin/cellpainting-skills describe --skill dp-summarize-deep-features")
observed_result:
- the routing guidance identified `dp-summarize-deep-features` as the public step for summarizing the collected deep-feature tables
- the skill description confirmed that this step writes `profile_summary.json`, `top_variable_features.csv`, `pca_coordinates.csv`, and `pca_plot.png`
planner_step_2:
intent:
Inspect the completed summary bundle from the recorded demo run.
tool_calls:
- read("demo/workspace/outputs/demo_record_2026_04_25_gpu_final/08_dp_summary/profile_summary.json")
- exec("find /root/pipeline/CellPainting-Claw/demo/workspace/outputs/demo_record_2026_04_25_gpu_final/08_dp_summary -maxdepth 2 -type f | sort")
observed_result:
- cell_count = 4
- well_count = 2
- feature_count = 672
- top_feature_count = 50
- pca_explained_variance_ratio = [1.0, 1.6090012673630894e-33]
final_answer_snapshot:
The demo deep-feature summary shows a simple two-well separation along one dominant PCA axis, which is useful as a sanity check but too small for a biological claim.
Representative Figure¶
This figure comes from the recorded deep-feature summary bundle for the repository demo.

Caption: PCA plot from dp-summarize-deep-features for the demo DeepProfiler run. With only two wells and four cells, this figure is useful as a sanity check, not as a phenotype conclusion.
Observed Result¶
A real recorded run for this skill wrote:
profile_summary.jsonwell_metadata_summary.csvtop_variable_features.csvpca_coordinates.csvpca_plot.pngpipeline_skill_manifest.json
The recorded output summary showed:
4cells2wells672learned feature columns50reported top variable featuresPC1 = 1.0PC2 = 1.6090012673630894e-33
Recorded Reply¶
This summary bundle is the first compact view of the learned DeepProfiler result.
Main result:
- the demo wells separate along one dominant learned-feature axis
- the summary reports the most variable learned features and a simple PCA view
What this means biologically:
- the model captured a measurable difference between the two demo wells in morphology-embedding space
- the individual learned features are not directly human-interpretable in the same way as classical measurements such as area or intensity
- with only two wells and four cells, this result should be treated as a demo-scale first pass rather than a phenotype claim