octopi 1.0__py3-none-any.whl → 1.2.0__py3-none-any.whl

octopi/processing/my_metrics.py

@@ -1,26 +0,0 @@
-from monai.utils import (MetricReduction, look_up_option)
-from monai.metrics import confusion_matrix as monai_cm
-from typing import Any
-import torch, mlflow
-
-def my_log_param(params_dict, client = None, trial_run_id = None):
-
-    if client is not None and trial_run_id is not None:
-        # client.log_params(run_id=trial_run_id, params=params_dict)
-        for key, value in params_dict.items():
-            client.log_param(run_id=trial_run_id, key=key, value=value)
-    else:
-        mlflow.log_params(params_dict)
-
-
-##############################################################################################################################
-
-def my_log_metric(metric_name, val, curr_step, client = None, trial_run_id = None):
-
-    if client is not None and trial_run_id is not None:
-        client.log_metric(run_id = trial_run_id, 
-                          key = metric_name,
-                          value = val, 
-                          step = curr_step)
-    else:
-        mlflow.log_metric(metric_name, val, step = curr_step)

octopi/processing/writers.py

@@ -1,102 +0,0 @@
-# This code is adapted from the copick-utils project,
-# originally available at: https://github.com/copick/copick-utils/blob/main/src/copick_utils/writers/write.py
-# Licensed under the MIT License.
-
-# Copyright (c) 2023 The copick-utils authors
-
-from typing import Any, Dict, List
-import numpy as np
-
-def tomogram(
-    run,
-    input_volume,
-    voxel_size=10,
-    algorithm="wbp"
-):
-    """
-    Writes a volumetric tomogram into an OME-Zarr format within a Copick directory.
-
-    Parameters:
-    -----------
-    run : copick.Run
-        The current Copick run object.
-    input_volume : np.ndarray
-        The volumetric tomogram data to be written.
-    voxel_size : float, optional
-        The size of the voxels in physical units. Default is 10.
-    algorithm : str, optional
-        The tomographic reconstruction algorithm to use. Default is 'wbp'.
-
-    Returns:
-    --------
-    copick.Tomogram
-        The created or modified tomogram object.
-    """
-    
-    # Retrieve or create voxel spacing
-    voxel_spacing = run.get_voxel_spacing(voxel_size)
-    if voxel_spacing is None:
-        voxel_spacing = run.new_voxel_spacing(voxel_size=voxel_size)
-    
-    # Check if We Need to Create a New Tomogram for Given Algorithm
-    tomogram = voxel_spacing.get_tomogram(algorithm)
-    if tomogram is None:
-        tomogram = voxel_spacing.new_tomogram(tomo_type=algorithm)
-    
-    # Write the tomogram data
-    tomogram.from_numpy(input_volume)
-
-
-def segmentation(
-    run,
-    segmentation_volume,
-    user_id,
-    name="segmentation",
-    session_id="0",
-    voxel_size=10,
-    multilabel=True
-):
-    """
-    Writes a segmentation into an OME-Zarr format within a Copick directory.
-
-    Parameters:
-    -----------
-    run : copick.Run
-        The current Copick run object.
-    segmentation_volume : np.ndarray
-        The segmentation data to be written.
-    user_id : str
-        The ID of the user creating the segmentation.
-    name : str, optional
-        The name of the segmentation dataset to be created or modified. Default is 'segmentation'.
-    session_id : str, optional
-        The session ID for this segmentation. Default is '0'.
-    voxel_size : float, optional
-        The size of the voxels in physical units. Default is 10.
-    multilabel : bool, optional
-        Whether the segmentation is a multilabel segmentation. Default is True.
-
-    Returns:
-    --------
-    copick.Segmentation
-        The created or modified segmentation object.
-    """
-    
-    # Retrieve or create a segmentation
-    segmentations = run.get_segmentations(name=name, user_id=user_id, session_id=session_id)
-
-    # If no segmentation exists or no segmentation at the given voxel size, create a new one
-    if len(segmentations) == 0 or any(seg.voxel_size != voxel_size for seg in segmentations):
-        segmentation = run.new_segmentation(
-            voxel_size=voxel_size,
-            name=name,
-            session_id=session_id,
-            is_multilabel=multilabel,
-            user_id=user_id
-        )
-    else:
-        # Overwrite the current segmentation at the specified voxel size if it exists
-        segmentation = next(seg for seg in segmentations if seg.voxel_size == voxel_size)
-    
-    # Write the segmentation data
-    segmentation.from_numpy(segmentation_volume, dtype=np.uint8)

octopi-1.0.dist-info/METADATA

@@ -1,209 +0,0 @@
-Metadata-Version: 2.3
-Name: octopi
-Version: 1.0
-Summary: Model architecture exploration for cryoET particle picking
-License: MIT
-Author: Jonathan Schwartz
-Requires-Python: >=3.9,<4.0
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: copick
-Requires-Dist: ipywidgets
-Requires-Dist: kaleido
-Requires-Dist: matplotlib
-Requires-Dist: mlflow (==2.17.0)
-Requires-Dist: monai-weekly (==1.5.dev2448)
-Requires-Dist: mrcfile
-Requires-Dist: multiprocess
-Requires-Dist: nibabel
-Requires-Dist: optuna (==4.0.0)
-Requires-Dist: optuna-integration[botorch,pytorch-lightning]
-Requires-Dist: pandas
-Requires-Dist: plotly
-Requires-Dist: python-dotenv
-Requires-Dist: pytorch-lightning (==2.4.0)
-Requires-Dist: requests (>=2.25.1,<3.0.0)
-Requires-Dist: seaborn
-Requires-Dist: torch-ema
-Requires-Dist: tqdm
-Description-Content-Type: text/markdown
-
-# OCTOPI 🐙🐙🐙
-**O**bject dete**CT**ion **O**f **P**rote**I**ns. A deep learning framework for Cryo-ET 3D particle picking with autonomous model exploration capabilities.
-
-## 🚀 Introduction
-
-octopi addresses a critical bottleneck in cryo-electron tomography (cryo-ET) research: the efficient identification and extraction of proteins within complex cellular environments. As advances in cryo-ET enable the collection of thousands of tomograms, the need for automated, accurate particle picking has become increasingly urgent.
-
-Our deep learning-based pipeline streamlines the training and execution of 3D autoencoder models specifically designed for cryo-ET particle picking. Built on [copick](https://github.com/copick/copick), a storage-agnostic API, octopi seamlessly accesses tomograms and segmentations across local and remote environments. 
-
-## 🧩 Features
-
-octopi offers a modular, deep learning-driven pipeline for:
-*	Training and evaluating custom 3D U-Net models for particle segmentation.
-*	Automatically exploring model architectures using Bayesian optimization via Optuna.
-*	Performing inference for both semantic segmentation and particle localization.
-
-octopi empowers researchers to navigate the dense, intricate landscapes of cryo-ET datasets with unprecedented precision and efficiency without manual trial and error.
-
-## Getting Started
-### Installation
-
-*Octopi* is available on PyPI.
-```
-pip install octopi
-```
-
-## 📚 Usage
-
-octopi provides a clean, scriptable command-line interface. Run the following command to view all available subcommands:
-```
-octopi --help
-```
-Each subcommand supports its own --help flag for detailed usage. To see practical examples of how to interface directly with the octopi API, explore the notebooks/ folder.
-
-If you're running octopi on an HPC cluster, several SLURM-compatible submission commands are available. You can view them by running:
-```
-octopi-slurm --help
-```
-This provides utilities for submitting training, inference, and localization jobs in SLURM-based environments.
-
-### 📥 Data Import & Preprocessing
-
-To train or run inference with octopi, your tomograms must be organized inside a CoPick project. octopi supports two primary methods for data ingestion, both of which include optional Fourier cropping to reduce resolution and accelerate downstream processing.
-
-If your tomograms are already processed and stored locally in .mrc format (e.g., from Warp, IMOD, or AreTomo), you can import them into a new or existing CoPick project using:
-
-```
-octopi import-mrc-volumes \
-    --input-folder /path/to/mrc/files --config /path/to/config.json \
-    --target-tomo-type denoised --input-voxel-size --output-voxel-size 10
-```
-
-octopi also can process tomograms that are hosted on the data portal. Users can download tomograms onto their own remote machine especially if they would like to downsample the tomograms to a lower resolution for speed and memory. You can download and process the tomograms using:
-```
-octopi download-dataportal \
-    --config /path/to/config.json --datasetID 10445 --overlay-path path/to/saved/zarrs \
-    --input-voxel-size 5 --output-voxel-size 10 \
-    --dataportal-name wbp --target-tomotype wbp 
-```
-
-### 📁 Training Labels Preparation  
-
-Use `octopi create-targets` to create semantic masks for proteins of interest using annotation metadata. In this example lets generate picks segmentations for dataset 10439 from the CZ cryoET Dataportal (only need to run this step once). 
-```
-octopi create-targets \
-    --config config.json \
-    --target apoferritin --target beta-galactosidase,slabpick,1 \
-    --target ribosome,pytom,0 --target virus-like-particle,pytom,0 \
-    --seg-target membrane \
-    --tomo-alg wbp --voxel-size 10 \
-    --target-session-id 1 --target-segmentation-name remotetargets \
-    --target-user-id train-octopi
-```
-
-### 🧠 Training a single 3D U-Net model  
-Train a 3D U-Net model on the prepared datasets using the prepared target segmentations. We can use tomograms derived from multiple copick projects. 
-``` 
-octopi train-model \
-    --config experiment,config1.json \
-    --config simulation,config2.json \
-    --voxel-size 10 --tomo-alg wbp --Nclass 8 \
-    --tomo-batch-size 50 --num-epochs 100 --val-interval 10 \
-    --target-info remotetargets,train-octopi,1
-```
-Outputs will include model weights (.pth), logs, and training metrics.
-
-### 🔍 Model exploration with Optuna
-
-octopi🐙 supports automatic neural architecture search using Optuna, enabling efficient discovery of optimal 3D U-Net configurations through Bayesian optimization. This allows users to maximize segmentation accuracy without manual tuning.
-
-To launch a model exploration job:
-```
-octopi model-explore \
-    --config experiment,/mnt/dataportal/ml_challenge/config.json \
-    --config simulation,/mnt/dataportal/synthetic_ml_challenge/config.json \
-    --voxel-size 10 --tomo-alg wbp --Nclass 8 \
-    --model-save-path train_results
-```
-Each trial evaluates a different architecture and logs:
-	•	Segmentation performance metrics
-	•	Model weights and configs
-	•	Training curves and validation loss
-
-🔬 Trials are automatically tracked with MLflow and saved under the specified `--model-save-path`.
-
-#### Optuna Dashboard
-
-To quickly asses the exploration results and observe which trials results the best architectures, Optuna provides a dashboard that summarizes all the information on a dashboard. The instrucutions to access the dashboard are available here - https://optuna-dashboard.readthedocs.io/en/latest/getting-started.html, it is recommended to use either VS-Code extension or CLI. 
- 
-#### 📊 MLflow experiment tracking   
-
-To use CZI cloud MLflow tracker, add a `.env` in the root directory like below. You can get a CZI MLflow access token from [here](https://mlflow.cw.use4-prod.si.czi.technology/api/2.0/mlflow/users/access-token) (note that a new token will be generated everytime you open this site).
-```
-MLFLOW_TRACKING_USERNAME = <Your_CZ_email>
-MLFLOW_TRACKING_PASSWORD = <Your_mlflow_access_token>
-```
-
-octopi supports MLflow for logging and visualizing model training and hyperparameter search results, including:
-	•	Training loss/validation metrics over time
-	•	Model hyperparameters and architecture details
-	•	Trial comparison (e.g., best performing model)
-
-You can use either a local MLflow instance, a remote (HPC) instance, or the CZI cloud server:
-
-#### 🧪 Local MLflow Dashboard
-
-To inspect results locally: `mlflow ui` and open http://localhost:5000 in your browser.
-
-#### 🖥️ HPC Cluster MLflow Access (Remote via SSH tunnel)
-
-If running octopi on a remote cluster (e.g., Biohub Bruno), forward the MLflow port. 
-On your local machine: 
- `ssh -L 5000:localhost:5000 remote_username@remote_host` (in the case of Bruno the remote would be `login01.czbiohub.org`). 
- 
-Then on the remote terminal (login node): ` mlflow ui --host 0.0.0.0 --port 5000` to launch the MLFlow dashboard on a local borwser.
-
-#### ☁️ CZI coreweave cluser
-
-For the CZI coreweave cluser, MLflow is already hosted. Go to the CZI [mlflow server](https://mlflow.cw.use4-prod.si.czi.technology/). 
-
-🔐 A .env file is required to authenticate (see Getting Started section).
-📁 Be sure to register your project name in MLflow before launching runs.
-
-### 🔮 Segmentation
-Generate segmentation prediction masks for tomograms in a given copick project.
-```
-octopi inference \
-    --config config.json \
-    --seg-info predict,unet,1 \
-    --model-config train_results/best_model_config.yaml \
-    --model-weights train_results/best_model.pth \
-    --voxel-size 10 --tomo-alg wbp --tomo-batch-size 25
-```
-Output masks will be saved to the corresponding copick project under the `seg-info` input.
-
-### 📍 Localization
-Convert the segmentation masks into particle coordinates. 
-```
-octopi localize \
-    --config config.json \
-    --pick-session-id 1 --pick-user-id unet \
-    --seg-info predict,unet,1
-```
-
-## Contributing
-
-This project adheres to the Contributor Covenant code of conduct. By participating, you are expected to uphold this code. Please report unacceptable behavior to opensource@chanzuckerberg.com.
-
-## Reporting Security Issues
-
-Please note: If you believe you have found a security issue, please responsibly disclose by contacting us at security@chanzuckerberg.com.
-
-
-

octopi-1.0.dist-info/RECORD

@@ -1,59 +0,0 @@
-octopi/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-octopi/datasets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-octopi/datasets/augment.py,sha256=k7UXQzidPANaPuLoBzer_ZHc4_vF-kKTOyZisEnAbNw,3203
-octopi/datasets/cached_datset.py,sha256=eQgKjQ9Kz4RF5rs2saFE25p-YfspA24tq3-6ugukbRA,3909
-octopi/datasets/dataset.py,sha256=9C3AuD83FMswj4MYLFn5XPqvAP1a7MQSG7UNiStg090,511
-octopi/datasets/generators.py,sha256=aqsIhipkG6bBzwpUlvP_N5m2Je5vs4Vq7gQN1z2uKPc,18874
-octopi/datasets/mixup.py,sha256=BJUAmM7ItZWFChs8glnd8RNSXR5qGW7DHscbcVc3TsU,1575
-octopi/datasets/multi_config_generator.py,sha256=SIYqz3Xps4gyWgUo02W1KbObM4ye14dIHJi25XlIIRc,10805
-octopi/entry_points/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-octopi/entry_points/common.py,sha256=lh2mPNkhMtqMoSqPPajQ-saiGXiOR-vMiFuuolJWWvI,5332
-octopi/entry_points/create_slurm_submission.py,sha256=h3pllxmPnG6QUujfop4CNE8xYNsfWrAEkavRCi9UGzg,8720
-octopi/entry_points/run_create_targets.py,sha256=IacDeL9k3sCRbeVuyn32IffjrdQe31VAbS4CxTWpHFk,11226
-octopi/entry_points/run_evaluate.py,sha256=I90kP_GOtAO7zbuEY9ptZ8Y-g1wZa41N9a2ZGbijEcs,2826
-octopi/entry_points/run_extract_mb_picks.py,sha256=iULXtjoL06SApeychQGty5lWAINeNt_1D-zGeJIXT6k,5583
-octopi/entry_points/run_extract_midpoint.py,sha256=O6GdkSD7oXIpSVqizOc6PHhv9nunz3j0RucmYQ2yryM,5742
-octopi/entry_points/run_localize.py,sha256=0TKaZD7Uk8ud2ZIlcsB9-6S6vPDlOKIdtCxe_sWnzY4,8678
-octopi/entry_points/run_optuna.py,sha256=LQXQ6W3v8MhJ9EoKbtFc84Muy3ofjzo-0SyUQaMAaMs,5743
-octopi/entry_points/run_segment_predict.py,sha256=46CfxDWxbKAZT8o2xr4JiYAwLxVpxXLwGylZU8WXgMc,5442
-octopi/entry_points/run_train.py,sha256=zdeZxtwK0fJytex9TzZBXxpQxF8b3ljpWeYdBsuOR8k,8094
-octopi/extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-octopi/extract/localize.py,sha256=jvVDl2b6cQZyuxUfLaB4WgMLY53ENCKq2K2CVw1FYUU,9515
-octopi/extract/membranebound_extract.py,sha256=VdlsiytoaKBk4wdhORJU8yRSOARFN2zvnF6PZpJkGmo,11208
-octopi/extract/midpoint_extract.py,sha256=W8sVIAweqkQcF18ie7tvvvOeBzRTBdH95FzPtjMcWjc,7033
-octopi/io.py,sha256=c9ZLhFzhoXx2XJ3GmQM-Dx2CUkCOfHj-HWOq3QQvzJU,19558
-octopi/losses.py,sha256=fs9yR80Hs-hL07WgVMkRy5N81vzP5m9XBCvzO76bIPU,3097
-octopi/main.py,sha256=03CqyB9iKCxpek1a2A-vMsIsEjWjW1Q9XbDqqDnWOW0,4866
-octopi/models/AttentionUnet.py,sha256=r185aXRtfXhN-n8FxA-Sjz18nqpxHH_2t2uadrH-Mgs,1991
-octopi/models/MedNeXt.py,sha256=9q0FsyrqTx211hCbDv0Lm2XflzXL_bGA4-76BscziGk,4875
-octopi/models/ModelTemplate.py,sha256=X80EOXwSovCjmVb7x-0_JmRjHfDfLByDdd60MrgFTyw,1084
-octopi/models/SegResNet.py,sha256=1dK8dy_7hHHKYZLsTYafl__7MxQOlWGbBqQWPGxHSXg,3609
-octopi/models/Unet.py,sha256=7RGT_nl7ogsNlS3Y3Qexe305Ym9NlK9CV0y45g2DEU4,2171
-octopi/models/UnetPlusPlus.py,sha256=fnV-SvJV8B432KJXQAtdwLy8Va6DJ4fRB_7a1mZiqTU,1529
-octopi/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-octopi/models/common.py,sha256=kXE0GcQSdfbiP0PDaJBkAJClBqTqCamP-2bHkbe0uBg,2307
-octopi/processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-octopi/processing/create_targets_from_picks.py,sha256=D7JlPIaq3ClzCKvK-Z8F-eUpUbUd7zGysJ2Z0AYQzzE,4010
-octopi/processing/downsample.py,sha256=zlZAgrKiPEltFZCLYgcAcVVtoKb_qMzV_eUv1UaBy4k,5498
-octopi/processing/evaluate.py,sha256=0w1iqmD8EXRdce-ctSoEJu5lAwYk1CjL4Qd_dpZt7Yw,13364
-octopi/processing/importers.py,sha256=TBgPlleGGOW8tJJLArrAFWxzvxH1qE-id_PTLRscgEs,8876
-octopi/processing/my_metrics.py,sha256=7ZhCEiSYkqbSpoTntAkCrr7y83u6-jI8k8d3P9TlrQA,1040
-octopi/processing/segmentation_from_picks.py,sha256=jah1gAXEn09LIok1Cb8IeVN-fT3jktcVPfjbOFHkgg0,7089
-octopi/processing/writers.py,sha256=YB6-0mwJ9sc_eJ3G_WItcqlBjFOpggyNhoRswKOZA6Q,3301
-octopi/pytorch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-octopi/pytorch/hyper_search.py,sha256=xCJ_8qYaK80UMb2JrBvU31tEZ8-L7MBGBE9pb63-8a0,9431
-octopi/pytorch/model_search_submitter.py,sha256=2sgOrrQFdvvSrnfVgpt0uQmZ0H1MjudNyaDvLXSBSKY,11162
-octopi/pytorch/segmentation.py,sha256=hS9mUBAmHqTk7zB0lyCHerzir5IvTbXtOA7lRIOJk7w,13689
-octopi/pytorch/trainer.py,sha256=wP384rmpuXna1Ou3wksPXHGe2n3bZNfIUZWynbzLHGU,17549
-octopi/pytorch_lightning/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-octopi/pytorch_lightning/optuna_pl_ddp.py,sha256=ynD5i81IP-awr6OD9GDurjrQK-5Kc079qPaukphTHnA,11924
-octopi/pytorch_lightning/train_pl.py,sha256=igOHzU_mUdZRQGhoOGW5vmxJcHFcw5fAPHfVCIZ0eG4,10220
-octopi/stopping_criteria.py,sha256=Fib1fiFqPQPLDxZQNUTgQInY8RWGNBzXkpqF_WJ2PSo,6112
-octopi/submit_slurm.py,sha256=cRbJTESbPFCt6Cq4Hat2uPOQKFYMPcQxuNs0jc1ygUA,1945
-octopi/utils.py,sha256=iezl5ui2E_Qs00_HS4uPPh008pdyY6IXI9euLfkUq4s,9008
-octopi/visualization_tools.py,sha256=80Kj8yX09LEXJe3QqeithhlwEdoz9wOYRk7T1RFRmw4,7368
-octopi-1.0.dist-info/LICENSE,sha256=zYaYdrEn2O4KTO8sLySIhHOKerzA69toCj2ywuvHT7Q,1816
-octopi-1.0.dist-info/METADATA,sha256=lOJwRTgwySLUtMLeaaTegM20fCxZMqtu73tVyMXhqS4,9483
-octopi-1.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-octopi-1.0.dist-info/entry_points.txt,sha256=FnDGURPvbr2Hl7n0LPN-5jHtvrKA87MNvhCFO-BwAfg,87
-octopi-1.0.dist-info/RECORD,,

octopi-1.0.dist-info/entry_points.txt

@@ -1,4 +0,0 @@
-[console_scripts]
-octopi=octopi.main:cli_main
-octopi-slurm=octopi.main:cli_slurm_main
-