WEHI-ResearchComputing · MihinP · Mar 17, 2026 · Mar 16, 2026 · Mar 16, 2026 · Mar 16, 2026
diff --git a/Dockerfile b/Dockerfile
@@ -8,4 +8,4 @@ RUN python -m pip install --no-cache-dir --no-cache /opt/PartiNet
 
 LABEL AUTHORS Mihin Perera, Edward Yang, Julie Iskander
 LABEL MAINTAINERS Mihin Perera, Edward Yang, Julie Iskander
-LABEL VERSION v0.2.0
+LABEL VERSION v1.0.1
diff --git a/README.md b/README.md
@@ -1,4 +1,6 @@
-# PartiNet 🔬
+# PartiNet 
+
+![PartiNet RMSD](docs/static/img/partinet_RMSD.png)
 
 PartiNet is a three-stage pipeline for automated particle picking in cryo-EM micrographs, combining advanced denoising with state-of-the-art deep learning detection.
 
@@ -9,12 +11,12 @@ Use our pretrained model at [Model Weights](https://huggingface.co/MihinP/PartiN
 
 ## Features
 
-- 🧹 Heuristic denoising for improved signal-to-noise ratio
-- 🎯 Dynamic deep learning particle detection
-- ⚡ Multi-GPU support for faster processing
-- 🔄 Seamless integration with cryoSPARC and RELION workflows
-- 📊 Confidence-based particle filtering
-- 🖼️ Visual detection validation
+- Heuristic denoising for improved signal-to-noise ratio
+- Dynamic deep learning particle detection
+- Multi-GPU support for faster processing
+- Seamless integration with cryoSPARC and RELION workflows
+- Confidence-based particle filtering
+- Visual detection validation
 
 ## Prerequisites
 
@@ -49,12 +51,12 @@ docker run --gpus all -v /path/to/your/data:/data \
 
 ```
 project_directory/
-├── motion_corrected/          # 📁 Input micrographs
-├── denoised/                  # 🧹 Denoised outputs
-├── exp/                       # 🎯 Detection results
-│   ├── labels/               # 📋 Coordinates
-│   └── ...                   # 🖼️ Visualizations
-└── partinet_particles.star    # ⭐ Final output
+├── motion_corrected/          # Input micrographs
+├── denoised/                  # Denoised outputs
+├── exp/                       # Detection results
+│   ├── labels/               # Coordinates
+│   └── ...                   # Visualizations
+└── partinet_particles.star    # Final output
 ```
 
 ## Pipeline Stages
@@ -94,7 +96,8 @@ partinet star \
    - `*.png`: Visualization overlays
 
 3. **STAR File** (`partinet_particles.star`)
-   - Ready for RELION processing
+   - Ready for CryoSPARC processing
+   - Additional commands available for RELION compatible output
 
 ## Advanced Usage
 
@@ -145,3 +148,5 @@ Citation information will be added upon publication
 For issues and questions:
 - Open an [Issue](https://github.com/WEHI-ResearchComputing/PartiNet/issues)
 - Check existing [Discussions](https://github.com/WEHI-ResearchComputing/PartiNet/discussions)
+
+
diff --git a/Singularity b/Singularity
@@ -18,4 +18,4 @@ from: python:3.9.19-slim-bookworm
 %labels
   AUTHORS Mihin Perera, Edward Yang, Julie Iskander
   MAINTAINERS Mihin Perera, Edward Yang, Julie Iskander
-  VERSION v1.0.0
+  VERSION v1.0.1
diff --git a/docs/docs/getting-started.md b/docs/docs/getting-started.md
@@ -20,23 +20,23 @@ PartiNet expects and creates the following directory structure:
 
 ```
 project_directory/
-├── motion_corrected/          # 📁 Your input micrographs
+├── motion_corrected/          # Your soft-linked input micrographs
 │   ├── micrograph1.mrc
 │   ├── micrograph2.mrc
 │   └── ...
-├── denoised/                  # 🧹 Created by denoise stage
+├── denoised/                  # Created by denoise stage
 │   ├── micrograph1.mrc
 │   ├── micrograph2.mrc
 │   └── ...
-├── exp/                       # 🎯 Created by detect stage
-│   ├── labels/               # 📋 Detection coordinates
+├── exp/                       # Created by detect stage
+│   ├── labels/               # Detection coordinates (YOLO format)
 │   │   ├── micrograph1.txt
 │   │   ├── micrograph2.txt
 │   │   └── ...
-│   ├── micrograph1.png    # 🖼️ Micrographs with detections drawn
+│   ├── micrograph1.png    # Micrographs with detections drawn
 │   ├── micrograph2.
 │   └── ...
-└── partinet_particles.star   # ⭐ Final STAR file (created by star stage)
+└── partinet_particles.star   # CryoSPARC-style STAR file (created by star stage)
 ```
 
 **Pipeline Flow:**

diff --git a/docs/docs/intro.md b/docs/docs/intro.md
@@ -32,17 +32,14 @@ The final stage prepares particle data for further processing and provides repor
 PartiNet is ideal for:
 - Identifying rare views
 - Picking on heterogeneous datasets
-- Reporting on particle populations
+- High speed picking
 
 ## Next Steps
 
 - **New to PartiNet?** Start with [Installation](installation.md) to get up and running
 - **Ready to begin?** Follow our [Getting Started](getting-started.md) guide for your first analysis
 - **Need specific details?** Check the individual stage documentation: [Denoise](stages/denoise.md), [Detect](stages/detect.md), [Star](stages/star.md)
 
-<!-- ## Getting Help
+## Getting Help
 
-If you encounter issues or need assistance:
-- Check the [Troubleshooting](reference/troubleshooting.md) guide
-- Review the complete [CLI Reference](reference/cli-reference.md)
-- Look at our [Examples](examples/) for common use cases -->
+If you encounter issues or need assistance please raise an issue on the GitHub
diff --git a/docs/docs/stages/denoise.md b/docs/docs/stages/denoise.md
@@ -69,16 +69,16 @@ mkdir motion_corrected
 **From CryoSPARC:**
 ```shell
 # Using symbolic links (faster, saves space)
-ln -s /path/to/cryosparc/project/job_number/motioncorrected/*_fractions_patch_aligned.mrc motion_corrected/
+ln -s /path/to/cryosparc/project/JXXX/motioncorrected/*_fractions_patch_aligned.mrc motion_corrected/
 
 # Using rsync (copies files)
-rsync /path/to/cryosparc/project/job_number/motioncorrected/*_fractions_patch_aligned.mrc motion_corrected/
+rsync /path/to/cryosparc/project/JXXX/motioncorrected/*_fractions_patch_aligned.mrc motion_corrected/
 ```
 
 **From RELION:**
 ```shell
 # Link motion-corrected micrographs
-ln -s /path/to/relion/project/MotionCorr/job_number/Micrographs/*.mrc motion_corrected/
+ln -s /path/to/relion/project/MotionCorr/jobXXX/*.mrc motion_corrected/
 ```
 
 ### 3. Run Denoising
@@ -166,7 +166,7 @@ partinet denoise \
 
 
 ### Different Output Formats
-By default PartiNet outputs denoised images in `png` format. This is necessary for compatibility with the detection architecture. `png` is a lossless compression, however micrographs are normalised from 32 bit depth `mrc` files to 8 bit `png`. `jpg` is also available (eg for making figures) but is not recommended for use due to lossy compression.
+By default PartiNet outputs denoised images in `png` format. This is necessary for compatibility with the detection architecture. `png` is a lossless compression, however micrographs are normalised from 32 bit depth `mrc` files to 8 bit `png`. `jpg` is also available (as a legacy format) but is not recommended for use due to lossy compression.
 
 ```shell
 # JPEG format (smaller file size, lossy compression)

diff --git a/docs/docs/stages/star.md b/docs/docs/stages/star.md
@@ -81,12 +81,32 @@ Choose your confidence threshold based on:
 - Downstream processing requirements
 - Balance between particle quantity and quality
 
-## Output
+## CryoSPARC Output
 
-The command generates a STAR file containing:
+The command generates a STAR file compatible with CryoSPARC containing:
 - Particle coordinates (X, Y positions)
 - Corresponding micrograph paths
 
+## RELION output
+
+Use `--relion` and `--relion-project-dir` to generate RELION-compatible STAR outputs under `<relion_project>/partinet`:
+
+- Micrograph manifest: `<relion_project>/partinet/pick.star`
+- Per-micrograph coordinates: `<relion_project>/partinet/movies/<micrograph_basename>.star`
+
+Example:
+
+```bash
+partinet star \
+  --labels /data/partinet_picking/exp/labels \
+  --images /data/partinet_picking/denoised \
+  --output /data/partinet_picking/output.star \
+  --conf 0.2 \
+  --relion \
+  --relion-project-dir /data/relion/EMPIAR-10089 \
+  --mrc-prefix MotionCorr/job003/movies
+```
+
 
 ## Next Steps
 
@@ -96,8 +116,10 @@ After generating your STAR file, you can:
 
 :::warning
 
-PartiNet Denoise flips micrographs in the y-axis due to matrix transpose operations. If you denoised micrographs in PartiNet ensure that when you import and extract particle coordinates that you toggle `Flip in y` in CryoSPARC or similar in RELION prior to particle extraction.
+If you are using PartiNet v1.0.0, the Denoise flips micrographs in the y-axis due to matrix transpose operations. If you denoised micrographs in PartiNet ensure that when you import and extract particle coordinates that you toggle `Flip in y` in CryoSPARC prior to particle extraction. This has been fixed in v1.0.1+. You can check your version with `partinet --help`
 
 :::
 
 
+
+
diff --git a/docs/src/components/HomepageFeatures/index.tsx b/docs/src/components/HomepageFeatures/index.tsx
@@ -24,7 +24,7 @@ const FeatureList: FeatureItem[] = [
     Svg: require('@site/static/img/undraw_success_288d.svg').default,
     description: (
       <>
-        PartiNet proides improved identification of rare particle views allowing for comprehensive map reconstruction.
+        PartiNet provides improved identification of rare particle views allowing for comprehensive map reconstruction.
       </>
     ),
   },
@@ -33,7 +33,7 @@ const FeatureList: FeatureItem[] = [
     Svg: require('@site/static/img/undraw_space-exploration_dhu1.svg').default,
     description: (
       <>
-        PartiNet provides up to 10× faster inference than existing tools enabling real-time, on-the-fly picking. 
+        PartiNet provides up to 7× faster inference than existing tools enabling real-time, on-the-fly picking. 
       </>
     ),
   },

diff --git a/docs/src/pages/index.tsx b/docs/src/pages/index.tsx
@@ -5,6 +5,7 @@ import useDocusaurusContext from '@docusaurus/useDocusaurusContext';
 import Layout from '@theme/Layout';
 import HomepageFeatures from '@site/src/components/HomepageFeatures';
 import Heading from '@theme/Heading';
+import partinetRMSD from '@site/static/img/partinet_RMSD.png';
 
 import styles from './index.module.css';
 
@@ -17,6 +18,11 @@ function HomepageHeader() {
           {siteConfig.title}
         </Heading>
         <p className="hero__subtitle">{siteConfig.tagline}</p>
+        <img
+          src={partinetRMSD}
+          alt="PartiNet RMSD"
+          style={{ maxWidth: '100%', marginTop: '1rem' }}
+        />
         <div className={styles.buttons}>
           <Link
             className="button button--secondary button--lg"
@@ -33,8 +39,8 @@ export default function Home(): ReactNode {
   const {siteConfig} = useDocusaurusContext();
   return (
     <Layout
-      title={`Hello from ${siteConfig.title}`}
-      description="Description will go into a meta tag in <head />">
+      title={`PartiNet: high performance particle picking for cryo-EM`}
+      description="PartiNet is a high performance particle picking pipeline for cryo-electron microscopy (cryo-EM) that provides improved identification of rare particle views and up to 7× faster inference than existing tools.">
       <HomepageHeader />
       <main>
         <HomepageFeatures />

diff --git a/docs/static/img/partinet_RMSD.png b/docs/static/img/partinet_RMSD.png
diff --git a/partinet/__init__.py b/partinet/__init__.py
@@ -1,7 +1,7 @@
 import click
 import sys, os
 
-__version__ = "1.0.0"
+__version__ = "1.0.1"
 
 DYNAMICDET_AVAILABLE_MODELS = ["yolov7", "yolov7x", "yolov7-w6", "yolov7-e6", "yolov7-d6", "yolov7-e6e"]
 
@@ -77,12 +77,23 @@ def split(star, images, output, class_id, test_size, split_only):
 @main.command()
 @click.option("--labels", type=str, required=True, help="Path to the labels directory")
 @click.option("--images", type=str, required=True, help="Path to the images directory")
-@click.option("--output", type=str, required=True, help="Path to the output STAR file")
+@click.option("--output", type=str, required=True, help="Path to the output STAR file (CryoSPARC style)")
 @click.option("--conf", type=float, default=0.1, help="Minimum confidence threshold from predictions")
-def star(labels, images, output,conf):
+@click.option("--relion", is_flag=True, default=False, help="Also generate RELION pick.star + per-micrograph star files")
+@click.option("--relion-project-dir", type=str, default=None, help="RELION project root (creates <project>/partinet/pick.star and <project>/partinet/movies/*.star)")
+@click.option("--mrc-prefix", type=str, default="", help="Prefix path for micrograph names in RELION pick.star (e.g. MotionCorr/job003/movies)")
+def star(labels, images, output, conf, relion, relion_project_dir, mrc_prefix):
     click.echo("Generating STAR file...")
     import partinet.process_utils.star_file
-    partinet.process_utils.star_file.main(labels,images,output,conf)
+    partinet.process_utils.star_file.main(
+        labels,
+        images,
+        output,
+        conf,
+        relion=relion,
+        relion_project_dir=relion_project_dir,
+        mrc_prefix=mrc_prefix,
+    )
 
 @main.command()
 @click.option("--source", type=str, required=True, help="Path to Raw micrographs")

diff --git a/partinet/process_utils/guided_denoiser.py b/partinet/process_utils/guided_denoiser.py
@@ -167,8 +167,6 @@ def denoise(image_path: str) -> np.ndarray:
     # described in https://github.com/WEHI-ResearchComputing/PartiNet/issues/41
     image = image.astype(np.float32)
 
-    image = image.T
-    image = np.rot90(image)
     normalized_image = standard_scaler(np.array(image))
     contrast_enhanced_image = contrast_enhancement(normalized_image)
     weiner_filtered_image = wiener_filter(contrast_enhanced_image, kernel, K=30)