dp-run-deep-feature-model¶
dp-run-deep-feature-model is the step that turns a prepared DeepProfiler project into raw learned feature files.
It runs the pretrained DeepProfiler model on each segmented cell and writes the per-field feature bundles that later collection steps turn into tables.
Purpose¶
Use this skill when you want:
learned single-cell morphology features
the first true biological outputs from the DeepProfiler branch
raw per-field model outputs before tabular collection
Main Outcome¶
After this skill finishes, each segmented cell has a learned morphology representation.
This is the point where the deep-feature branch starts to produce actual per-cell phenotype embeddings.
Inputs¶
This skill reads:
a project config such as
configs/project_config.demo.jsona runnable DeepProfiler project from dp-build-deep-feature-project
the DeepProfiler runtime settings from the project config
an optional output directory
In the demo setup, the model runs on two image fields and profiles four segmented cells across the five standard Cell Painting channels.
Outputs¶
The main user-facing results are:
one learned feature vector for each segmented cell
raw DeepProfiler feature files for each field
a DeepProfiler run log
Agent Demo¶
This page is based on a real local OpenClaw run against the repository demo project:
session id:
dprun-local-v3turn timestamp:
2026-05-06 20:03 UTC+8model:
vibe/gpt-5-mini
Request¶
I already built the DeepProfiler project and now want to generate the learned single-cell features for the demo cells. Please use configs/project_config.demo.json, run the deep-feature model for the prepared demo project, and then explain what was produced and what it means biologically.
Structured Trace¶
user_input:
I already built the DeepProfiler project and now want to generate the learned single-cell features for the demo cells.
planner_step_1:
intent:
Load the documented Cell Painting routing guidance and confirm which public skill runs the prepared DeepProfiler project.
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-run-deep-feature-model")
observed_result:
- the routing guidance identified `dp-run-deep-feature-model` as the public step for generating raw DeepProfiler feature files
- the skill description confirmed that this step runs the DeepProfiler model on a prepared project without collecting tables yet
planner_step_2:
intent:
Locate the prepared demo project and check that the expected DeepProfiler project files already exist.
tool_calls:
- exec("cd /root/pipeline/CellPainting-Claw && find demo/workspace/outputs -maxdepth 3 -type f | sort")
- exec("cd /root/pipeline/CellPainting-Claw && sed -n '1,220p' demo/workspace/outputs/agent_demo_dp_project/project_manifest.json")
observed_result:
- the prepared project root was confirmed at `demo/workspace/outputs/agent_demo_dp_project`
- the project already contained the expected DeepProfiler config, metadata, and checkpoint assets
planner_step_3:
intent:
Run the documented model-execution skill against the prepared demo project.
tool_calls:
- exec("cd /root/pipeline/CellPainting-Claw && /root/autodl-tmp/miniconda3_envs/lyx_env/bin/cellpainting-skills run --config /root/pipeline/CellPainting-Claw/configs/project_config.demo.json --skill dp-run-deep-feature-model --project-root /root/pipeline/CellPainting-Claw/demo/workspace/outputs/agent_demo_dp_project --output-dir /root/pipeline/CellPainting-Claw/demo/workspace/outputs/agent_demo_dp_model_run")
observed_result:
- skill_key = dp-run-deep-feature-model
- returncode = 0
- feature_dir = demo/workspace/outputs/agent_demo_dp_project/outputs/cell_painting_cnn_demo/features
- log_path = demo/workspace/outputs/logs/deepprofiler/20260506T120454Z_deepprofiler_profile.log
planner_step_4:
intent:
Inspect the produced feature files so the biological meaning can be summarized concretely.
tool_calls:
- exec("python ... load BR00000001/A01/1.npz and BR00000001/A02/1.npz, inspect array keys and feature shapes")
observed_result:
- there were 2 feature files, one for each field
- each field contained 2 single cells
- each cell was represented by a 672-dimensional learned feature vector
- total cells represented = 4
final_answer_snapshot:
The demo DeepProfiler run completed successfully and produced raw learned feature files for four segmented cells across two image fields.
Observed Result¶
A real successful run for this skill wrote:
outputs/cell_painting_cnn_demo/features/BR00000001/A01/1.npzoutputs/cell_painting_cnn_demo/features/BR00000001/A02/1.npzdemo/workspace/outputs/agent_demo_dp_model_run/pipeline_skill_manifest.jsondemo/workspace/outputs/logs/deepprofiler/20260506T120454Z_deepprofiler_profile.log
The recorded output summary showed:
2image fields4total cells2cells in wellA012cells in wellA02672learned features per cellrun
returncode = 0
Recorded Reply¶
I ran the DeepProfiler model on the prepared demo project using the stable skill `dp-run-deep-feature-model`.
Main result:
- the run completed successfully
- the prepared project now contains learned single-cell feature files for two fields
- four segmented cells were represented in total
Produced outputs:
- `outputs/cell_painting_cnn_demo/features/BR00000001/A01/1.npz`
- `outputs/cell_painting_cnn_demo/features/BR00000001/A02/1.npz`
- `demo/workspace/outputs/agent_demo_dp_model_run/pipeline_skill_manifest.json`
- `demo/workspace/outputs/logs/deepprofiler/20260506T120454Z_deepprofiler_profile.log`
What this means biologically:
- each segmented cell now has a learned single-cell morphology embedding
- each embedding is a 672-dimensional fingerprint built from the Cell Painting channels together
- these outputs can now be collected into single-cell and well-level tables in the next step