OSCR

VesiclePy: A machine learning vesicle analysis toolbox for volume electron microscopy.

Code ↔ Paper

4 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 4 matches
  1. [1] § Design and implementation‌‌ › Neuron type cluster analysis ↔ ves_ncls/cluster_analysis.ipynb, lines 113–126 · score 0.84 · hierarchical clustering, complete linkage, Gower distance, distance threshold, Cutting, dendrogram
  2. [2] § Design and implementation‌‌ › Morphology and spatial analysis › Vesicle morphology. ↔ ves_analysis/metadata_and_kdtree/kdTreeMeta.py, lines 97–139 · score 0.59 · kd trees, query, radius, neighbors, densities, voxels
  3. [3] § Design and implementation‌‌ › Morphology and spatial analysis › Vesicle morphology. ↔ ves_vis/scripts/conversion/dfGen.py, lines 131–211 · score 0.56 · kd trees, query, radius, neighbors, computational, voxels
  4. [4] § Design and implementation‌‌ › Large vesicle instance segmentation › Instance segmentation. ↔ ves_cls/main.py, lines 144–214 · score 0.55 · F1 score, Rand, Precision, Recall, metric, channels

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Jupyter notebook · 271 lines · 11 KB · MIT · 1 match

  1. # %%
  2. # Cluster Analysis of Vesicle Morphology
  4. # 1. Introduction
  5. # This notebook performs hierarchical cluster analysis on vesicle morphology
  6. # data to identify distinct structural groups. The dataset comprises 20 samples,
  7. # each characterized by a mix of numerical (e.g., 'TotalVol', 'NucVol') and
  8. # categorical (e.g., 'Branch' type) features.
  10. # The analysis pipeline involves:
  11. # 1. Data loading and preprocessing, including log transformation for numerical features.
  12. # 2. Calculation of a Gower distance matrix to handle the mixed data types.
  13. # 3. Application of hierarchical agglomerative clustering using the 'complete' linkage method.
  14. # 4. Determination of clusters.
  15. # 5. Visualization of the clustering results using a dendrogram and a 2D Multidimensional Scaling (MDS) plot.
  17. # This notebook aims to provide a reproducible workflow for the morphological clustering presented in the accompanying paper.
  19. # %%
  20. # 2. Setup and Dependencies
  21. !pip3 install gower
  22. import pandas as pd
  23. import numpy as np
  24. from scipy.spatial.distance import squareform
  25. import gower
  26. from scipy.cluster.hierarchy import linkage, dendrogram, fcluster
  27. import matplotlib.pyplot as plt
  28. import matplotlib.patches as mpatches
  29. import matplotlib.colors as mcolors
  30. import sys
  31. from sklearn.manifold import MDS
  33. # %%
  34. # 3. Data Loading and Definition
  36. # The dataset for vesicle morphology is defined below. It consists of 20 samples with 10 features each, plus an ID.
  38. # --- Data Definition ---
  39. data = [
  40. ['16', 124008407040, 38677401600, 'multipolar', 234517.2827, 0, 0, 1, 746, 414, 42],
  41. ['14', 155282350080, 45789296640, 'bipolar', 147096.206, 0, 0, 1, 977, 256, 100],
  42. ['13', 168469309440, 34900439040, 'multipolar', 383703.5945, 0, 0, 1, 2609, 585, 528],
  43. ['18', 130380072960, 40242923520, 'multipolar', 229978.5113, 0, 0, 1, 973, 746, 67],
  44. ['5', 173906227200, 33367234560, 'bipolar', 265659.514, 0, 0, 1, 2294, 650, 547],
  45. ['20', 208749496320, 39632885760, 'multipolar', 355348.8553, 0, 0, 1, 1848, 794, 158],
  46. ['2', 164527994880, 43507568640, 'bipolar', 120738.7693, 4, 1, 1, 1407, 200, 186],
  47. ['4', 107651973120, 35105617920, 'bipolar', 63075.63401, 4, 1, 1, 756, 140, 47],
  48. ['10', 128919244800, 46152130560, 'bipolar', 39082.73965, 0, 0, 1, 1592, 354, 172],
  49. ['7', 86131230720, 28778035200, 'unipolar', 57184.89032, 0, 0, 0, 935, 606, 11],
  50. ['19', 108731043840, 31402782720, 'unipolar', 66012.68547, 0, 1, 0, 1410, 500, 19],
  51. ['9', 138603847680, 37885255680, 'unipolar', 51708.15625, 19, 1, 0, 1035, 1490, 42],
  52. ['8', 99765473280, 33157632000, 'unipolar', 50367.52127, 10, 1, 0, 451, 316, 11],
  53. ['1', 130214338560, 37502853120, 'pseudounipolar', 68757.72662, 11, 1, 0, 1201, 439, 4],
  54. ['11', 175661045760, 51965767680, 'pseudounipolar', 52147.47713, 4, 1, 0, 794, 1298, 19],
  55. ['15', 110534277120, 31753912320, 'pseudounipolar', 71870.35016, 5, 1, 0, 1791, 911, 8],
  56. ['12', 108910295040, 36555909120, 'pseudounipolar', 73957.49723, 10, 1, 0, 1092, 943, 20],
  57. ['6', 145621862400, 37960642560, 'pseudounipolar', 78434.7676, 17, 1, 0, 808, 1548, 14],
  58. ['17', 122137896960, 41560104960, 'pseudounipolar', 44101.97098, 5, 1, 0, 1627, 842, 20],
  59. ['3', 164652687360, 41093191680, 'pseudounipolar', 62134.37108, 10, 1, 0, 652, 2156, 34]
  60. ]
  62. cols = ['ID', 'TotalVol', 'NucVol', 'Branch', 'TotalLen', 'Mic', 'Cilia', 'Handshake', 'CV', 'DCV', 'DCVH']
  63. df = pd.DataFrame(data, columns=cols)
  64. n_samples = len(df)
  66. print(f"Number of samples: {n_samples}")
  67. print("First 5 rows of the dataset:")
  68. print(df.head().to_string())
  70. # %%
  71. # 4. Data Preprocessing
  73. # This section prepares the data for clustering. It involves identifying feature
  74. # types, applying log transformations to numerical features, and ensuring
  75. # categorical features are correctly typed.
  77. num_cols = ['TotalVol', 'NucVol', 'TotalLen', 'Mic', 'Cilia', 'Handshake', 'CV', 'DCV', 'DCVH']
  78. cat_cols = ['Branch']
  79. features_for_clustering = num_cols + cat_cols
  81. df_features = df[features_for_clustering].copy() # Create a copy for feature engineering
  83. # %%
  84. # 4.1. Log Transformation of Numerical Features Numerical features are
  85. # log-transformed to help normalize their distributions and reduce the impact of
  86. # outliers or large differences in scale. For features containing zero or
  87. # negative values, inverse hyperbolic sine (IHS) transformation is used
  89. for col in ['TotalVol', 'NucVol', 'TotalLen', 'Mic', 'CV', 'DCV', 'DCVH']:
  90. if df_features[col].min() <= 0:
  91. df_features[col] = np.arcsinh(df_features[col])
  92. else:
  93. df_features[col] = np.log(df_features[col])
  95. # %%
  96. # 4.2. Set Categorical Feature Type The 'Branch' column is explicitly set to an
  97. # object data type to be treated as categorical by the Gower distance function.
  99. df_features[cat_cols] = df_features[cat_cols].astype(object)
  100. categorical_features_mask = [col in cat_cols for col in df_features.columns]
  103. # %%
  104. ## 5. Gower Distance Calculation
  106. # Gower's distance is used as it can handle mixed data types (numerical and
  107. # categorical) simultaneously, providing a suitable dissimilarity measure for
  108. # our heterogeneous vesicle features. The output is a condensed distance matrix.
  110. distance_matrix = gower.gower_matrix(df_features, cat_features=categorical_features_mask)
  111. condensed_distance_matrix = squareform(distance_matrix) # Convert to condensed form for linkage
  113. # %%
  114. ## 6. Hierarchical Clustering
  116. # Hierarchical agglomerative clustering is performed on the Gower distance matrix.
  117. # - **Linkage Method:** 'complete' linkage is used, which considers the maximum distance between elements of each cluster when merging.
  118. # - **Cluster Assignment:** Clusters are formed by cutting the dendrogram at a specified distance threshold (0.4).
  120. # Perform hierarchical/agglomerative clustering
  121. linked = linkage(condensed_distance_matrix, method='complete')
  123. # Assign clusters based on the distance threshold
  124. distance_threshold = 0.4
  125. clusters = fcluster(linked, t=distance_threshold, criterion='distance')
  126. df['predicted_cluster'] = clusters
  128. # %%
  129. ### 6.1. Cluster Assignment Results
  130. # The predicted cluster for each sample ID and the overall cluster sizes at the chosen distance threshold are printed below.
  132. output_df = df[['ID', 'predicted_cluster']].rename(columns={'predicted_cluster': 'Predicted Cluster'})
  133. output_df_sorted = output_df.sort_values(by='Predicted Cluster')
  135. print(f"\nPredicted Clusters (Sorted by Cluster Number, distance <= {distance_threshold})")
  136. print(output_df_sorted.to_string(index=False))
  138. num_clusters_found = len(output_df_sorted['Predicted Cluster'].unique())
  139. print(f"\nNumber of clusters found at distance {distance_threshold}: {num_clusters_found}")
  141. print("\nCluster Sizes:")
  142. print(output_df_sorted['Predicted Cluster'].value_counts().sort_index())
  144. # %%
  145. # ## 7. Visualization
  147. # The clustering results are visualized using a dendrogram and a 2D MDS plot.
  149. # 7.1. Dendrogram The dendrogram visually represents the hierarchical
  150. # clustering. Branches are colored according to the clusters formed at the
  151. # distance threshold of 0.4. The helper functions `get_one_leaf` and
  152. # `get_link_color_simple` are defined for this custom coloring.
  154. cluster_labels = sorted(output_df_sorted['Predicted Cluster'].unique())
  155. # Define a color palette for the clusters
  156. hex_colors = ['#64D9C9', '#485A96', '#B7C72C', '#DB6E96']
  157. color_map = {label: hex_colors[i % len(hex_colors)] for i, label in enumerate(cluster_labels)}
  158. default_link_color = '#808080' # Gray for links above threshold or unassigned
  160. memo_leaf = {} # Memoization for get_one_leaf
  162. def get_one_leaf(node_id):
  163. """
  164. Helper function to get a representative leaf index from a cluster node.
  165. Used for consistent coloring of dendrogram branches within the same final cluster.
  166. """
  167. if node_id in memo_leaf:
  168. return memo_leaf[node_id]
  169. if node_id < n_samples: # Leaf node
  170. memo_leaf[node_id] = node_id
  171. return node_id
  172. else: # Internal node
  173. link_idx = int(node_id - n_samples)
  174. child1_id = int(linked[link_idx, 0]) # Get one of the children
  175. leaf_idx = get_one_leaf(child1_id)
  176. memo_leaf[node_id] = leaf_idx
  177. return leaf_idx
  179. def get_link_color_simple(cluster_id):
  180. """
  181. Determines the color for a dendrogram link based on whether the merged cluster
  182. is below the predefined distance_threshold.
  183. """
  184. link_idx = int(cluster_id - n_samples) # Convert cluster_id to index in 'linked' array
  185. # Basic check for validity, though dendrogram usually passes valid IDs
  186. if link_idx < 0 or link_idx >= linked.shape[0]:
  187. return default_link_color
  189. merge_distance = linked[link_idx, 2] # The distance at which this merge occurred
  191. if merge_distance > distance_threshold:
  192. return default_link_color # Color gray if merge is above threshold
  193. else:
  194. # If below threshold, color according to the final cluster of one of its leaves
  195. leaf_index = get_one_leaf(cluster_id)
  196. final_cluster_label = clusters[leaf_index] # 'clusters' is from fcluster
  197. return color_map.get(final_cluster_label, default_link_color)
  199. # Plot the dendrogram
  200. plt.figure(figsize=(15, 10))
  201. memo_leaf.clear() # Clear memoization cache before use
  203. dendrogram_result = dendrogram(
  204. linked,
  205. orientation='top',
  206. labels=df['ID'].values,
  207. distance_sort='descending', # Show larger clusters forming first on one side
  208. show_leaf_counts=True,
  209. link_color_func=lambda k: get_link_color_simple(k),
  210. above_threshold_color=default_link_color # Color for links above the threshold
  211. )
  213. # Add plot enhancements
  214. plt.title(f'Hierarchical Clustering Dendrogram (Threshold = {distance_threshold})', fontsize=16)
  215. plt.xlabel('Sample ID', fontsize=14)
  216. plt.ylabel('Distance (Gower)', fontsize=14)
  217. plt.xticks(fontsize=10, rotation=90)
  218. plt.yticks(fontsize=10)
  220. # Optional: Save the figure for your paper
  221. # plt.savefig("dendrogram_for_paper.png", dpi=300, bbox_inches='tight')
  222. plt.show()
  224. # %%
  225. # Perform MDS
  226. mds = MDS(n_components=2, dissimilarity='precomputed', random_state=42, normalized_stress=False)
  227. mds_coords = mds.fit_transform(distance_matrix) # Use the full Gower distance matrix
  229. # Create DataFrame for MDS results
  230. mds_df = pd.DataFrame(mds_coords, columns=['MDS1', 'MDS2'], index=df.index)
  231. mds_df['predicted_cluster'] = df['predicted_cluster'] # Add cluster assignments from previous step
  232. mds_df['ID'] = df['ID'] # Add IDs for labeling
  234. # Plot MDS results
  235. fig, ax = plt.subplots(figsize=(9, 6))
  237. # Define colors and transparency
  238. face_alpha = 0.75
  239. edge_alpha = 0.6
  240. edge_base_color = 'black'
  242. # Map predicted clusters to colors
  243. cluster_colors_mapped = mds_df['predicted_cluster'].map(color_map).fillna(default_link_color)
  244. face_colors_rgba = [mcolors.to_rgba(hex_color, alpha=face_alpha) for hex_color in cluster_colors_mapped]
  245. edge_color_rgba = mcolors.to_rgba(edge_base_color, alpha=edge_alpha)
  247. # Scatter plot
  248. ax.scatter(mds_df['MDS1'], mds_df['MDS2'], c=face_colors_rgba, s=200, edgecolors=edge_color_rgba, linewidths=1)
  249. ax.tick_params(axis='both', which='major', labelsize=10)
  251. # Annotate points with IDs
  252. for i, txt in enumerate(mds_df['ID']):
  253. ax.text(mds_df['MDS1'].iloc[i] + 0.01, mds_df['MDS2'].iloc[i] + 0.01, txt, fontsize=10) # Adjust offset as needed
  255. # Add plot enhancements
  256. ax.set_title('MDS Plot of Vesicle Samples by Cluster', fontsize=16)
  257. ax.set_xlabel('MDS Dimension 1', fontsize=14)
  258. ax.set_ylabel('MDS Dimension 2', fontsize=14)
  260. # Customize spines
  261. axis_thickness = 1.5
  262. ax.spines['left'].set_linewidth(axis_thickness)
  263. ax.spines['bottom'].set_linewidth(axis_thickness)
  264. ax.spines['top'].set_visible(False)
  265. ax.spines['right'].set_visible(False)
  267. fig.tight_layout()
  269. # Optional: Save the figure for your paper
  270. # plt.savefig("mds_plot_for_paper.png", dpi=300, bbox_inches='tight')
  271. plt.show()

cluster_analysis.ipynb at commit d5d65fa, under MIT · at the source

Overview

Authors: Jason Ken Adhinarta1, Yutian Fan1, Adam Gohain1, Michael Lin1, Paige Nurkin2, Richard Ren2, Micaela Roth1, Shulin Zhang2, Ayal Yakobe2, Rafael Yuste2, Donglai Wei1
ORCID iDs: Jason Ken Adhinarta, Adam Gohain, Paige Nurkin, Micaela Roth, Donglai Wei
  1. Computer Science Department, Boston College, Chestnut Hill, Massachusetts, United States of America
  2. NeuroTechnology Center, Columbia University, New York, New York‌‌, United States of America
Institutions: Boston College (United States); Columbia University (United States)
Journal: PLoS computational biology, volume 22, issue 5, article e1013499
Dates: received 6 September 2025; accepted 14 April 2026; published online 14 May 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1371/journal.pcbi.1013499 · PMID 42133697 · PMCID PMC13211309 · OpenAlex W4414239643
Open access: gold, a free copy (OpenAlex)
Preprint: doi:10.1101/2025.09.08.674799
Status: code verified
Categories: histology / microscopy (modality), human (organism), methods / tools (subfield)
Methods: Smoothing, state filtering, decompositions, Machine learning, Statistics, fMRI & imaging
MeSH: Machine Learning*, Synaptic Vesicles*, Volume Electron Microscopy*, Animals, Computational Biology, Humans, Image Processing, Computer-Assisted, Imaging, Three-Dimensional, Neurons, Software (* major topic)
Journal subjects: Software, Biology and Life Sciences, Cell Biology, Cellular Structures and Organelles, Vesicles, Cellular Types, Animal Cells, Neurons, Neuroscience, Cellular Neuroscience, Neuronal Morphology, Research and Analysis Methods, Microscopy, Electron Microscopy, Computer and Information Sciences, Data Management, Data Visualization, Cognitive Science, Cognitive Psychology, Perception, Sensory Perception, Vision, Psychology, Social Sciences, Linguistics, Linguistic Morphology, Geoinformatics, Spatial Analysis, Earth Sciences, Geography
Topic: Extracellular vesicles in disease (Molecular Biology, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: NSF (CRCNS 1822550, 2203119, 2239688); DOD (ONR N000142012828)
Citations: not cited yet (Europe PMC); 30 references in the paper

Abstract

Vesicles are critical components of neurons that package neurotransmitters and neuropeptides for their release, in order to communicate with other neurons and cells. However, due to their small size, the reconstruction of the full vesicle endowment across an entire neuronal morphology remains challenging. To achieve this, we have used, as a tool to identify and visualize vesicles, Volume Electron Microscopy (vEM), a method that has the nanoscale resolution to detect individual vesicle boundaries, content, and 3D locations. However, the large volume of vEM datasets poses a challenge in the segmentation, classification, and spatial analysis of tens of thousands of vesicles and their target cell in 3D. Here we report the development of VesiclePy, an integrated pipeline for automated segmentation, classification, proofreading, and spatial analysis of vesicles, relative to neuron masks in large-volume electron microscopy data. Our package integrates the efficiency of deep learning and the accuracy of human proofreading and provides a streamlined package in chunked processing and accurate indexing, localization, and visualization of single vesicle resolution in large vEM data. We demonstrate the viability of VesiclePy using high-pressure frozen serial EM data of Hydra vulgaris and quantify the performance of the package using ground truth manual annotations. We show that VesiclePy can process a multiterabyte serial EM dataset, efficiently annotate 53,851 vesicles from 20 complete neurons, and classify vesicles into 5 types. Each vesicle has a unique ID and 3D location for further spatial analysis in relation to neuron or non-neuronal targets nearby. Finally, by combining vesicle data and morphological information of each neuron, we can quantitatively cluster neurons into subtypes. VesiclePy is available at https://github.com/PytorchConnectomics/VesiclePy under an MIT license.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repositories

Its files are read in the Code ↔ Paper reader above, with 4 matches between paragraphs and lines of code.

pytorchconnectomics/vesiclepy

License: MIT
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: d5d65fa104a4e3e7496606bdd455b8539b274bbf, 31 July 2025
Languages: Python (56), JavaScript (8), Jupyter (1)
Size: 3,429 files, 65 scripts
Software Heritage: not archived
Found in: “Data Availability”
Holds: README, license file, environment (requirements.txt)
Not found: CITATION.cff, tests, continuous integration, documentation
Tools: NumPy (47 files), h5py (29 files), SciPy (17 files), Matplotlib (13 files), pandas (7 files), PyTorch (7 files), Pillow (6 files), imageio (5 files), scikit-image (5 files), OpenCV (2 files), scikit-learn (2 files), Plotly (1 file), Pyro (1 file), UMAP (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
67 files
At the source: github.com/PytorchConnectomics/VesiclePy/tree/main/ves_seg/sample

Zenodo 16644943

License: CC-BY-4.0
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Size: 1 file
Software Heritage: not checked
Found in: “Data Availability”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Availability: 1 check, the latest on 28 September 2026: the link answers (HTTP 200)
  • 28 September 2026: the link answers (HTTP 200)
At the source: doi.org/10.5281/zenodo.16644943

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 65 scripts, each with its path and the digest of its content;
  • 4 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data Availability

VesiclePy is freely available under the MIT license on GitHub (https://github.com/PytorchConnectomics/VesiclePy) with an archive on Zenodo (https://doi.org/10.5281/zenodo.16644943). A sample of testing data can be found in the GitHub repository (https://github.com/PytorchConnectomics/VesiclePy/tree/main/ves_seg/sample).

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 2, 28 September 2026

  • Authors: added Jason Ken Adhinarta (0000-0002-6247-7475); removed Jason Ken Adhinarta

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 11 authors, 10 MeSH terms, 2 funders, 24 references.

Cite

This paper

Adhinarta, J. K., Fan, Y., Gohain, A., Lin, M., Nurkin, P., Ren, R., Roth, M., Zhang, S., Yakobe, A., Yuste, R., & Wei, D. (2026). VesiclePy: A machine learning vesicle analysis toolbox for volume electron microscopy. PLoS computational biology, 22(5), e1013499. https://doi.org/10.1371/journal.pcbi.1013499

BibTeX

@article{adhinarta2026vesiclepy,
author = {Adhinarta, Jason Ken and Fan, Yutian and Gohain, Adam and Lin, Michael and Nurkin, Paige and Ren, Richard and Roth, Micaela and Zhang, Shulin and Yakobe, Ayal and Yuste, Rafael and Wei, Donglai},
title = {{VesiclePy: A machine learning vesicle analysis toolbox for volume electron microscopy}},
journal = {PLoS computational biology},
year = {2026},
month = may,
volume = {22},
number = {5},
pages = {e1013499},
publisher = {PLOS},
issn = {1553-734X},
doi = {10.1371/journal.pcbi.1013499},
url = {https://doi.org/10.1371/journal.pcbi.1013499},
pmid = {42133697},
pmcid = {PMC13211309}
}

RIS

TY - JOUR
AU - Adhinarta, Jason Ken
AU - Fan, Yutian
AU - Gohain, Adam
AU - Lin, Michael
AU - Nurkin, Paige
AU - Ren, Richard
AU - Roth, Micaela
AU - Zhang, Shulin
AU - Yakobe, Ayal
AU - Yuste, Rafael
AU - Wei, Donglai
TI - VesiclePy: A machine learning vesicle analysis toolbox for volume electron microscopy
T2 - PLoS computational biology
J2 - PLoS Comput Biol
PY - 2026
DA - 2026/05/14
VL - 22
IS - 5
SP - e1013499
SN - 1553-734X
PB - PLOS
DO - 10.1371/journal.pcbi.1013499
UR - https://doi.org/10.1371/journal.pcbi.1013499
LA - en
ER -

CSL-JSON

{
"id": "10.1371/journal.pcbi.1013499",
"type": "article-journal",
"title": "VesiclePy: A machine learning vesicle analysis toolbox for volume electron microscopy",
"container-title": "PLoS computational biology",
"author": [
{
"family": "Adhinarta",
"given": "Jason Ken"
},
{
"family": "Fan",
"given": "Yutian"
},
{
"family": "Gohain",
"given": "Adam"
},
{
"family": "Lin",
"given": "Michael"
},
{
"family": "Nurkin",
"given": "Paige"
},
{
"family": "Ren",
"given": "Richard"
},
{
"family": "Roth",
"given": "Micaela"
},
{
"family": "Zhang",
"given": "Shulin"
},
{
"family": "Yakobe",
"given": "Ayal"
},
{
"family": "Yuste",
"given": "Rafael"
},
{
"family": "Wei",
"given": "Donglai"
}
],
"container-title-short": "PLoS Comput Biol",
"volume": "22",
"issue": "5",
"page": "e1013499",
"DOI": "10.1371/journal.pcbi.1013499",
"PMID": "42133697",
"PMCID": "PMC13211309",
"ISSN": "1553-734X",
"publisher": "PLOS",
"URL": "https://doi.org/10.1371/journal.pcbi.1013499",
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
14
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1016/j.xcrm.2026.102766 [code]
A longitudinal single-cell and spatial multiomic atlas of pediatric high-grade glioma.
Journal: Cell reports. Medicine
In common: imageio, UMAP, Plotly, 9 other tools, 1 reference
[2] doi:10.3389/fnsys.2026.1822122 [code]
Convergence-divergence circuits for multimodal integration of innate and learned opponent valences.
Journal: Frontiers in systems neuroscience
In common: UMAP, Plotly, scikit-image, 8 other tools, 3 references
[3] doi:10.1038/s41598-026-57519-w [code]
Automated segmentation of neurons and spinal cord structures in immunofluorescence images using SpineDL.
Journal: Scientific reports
In common: imageio, Plotly, OpenCV, 9 other tools, histology / microscopy, methods / tools, 1 reference
[4] doi:10.1038/s41593-026-02388-9 [code]
Hippocampal CA3 connectomics reveals a gradient of mossy fiber inputs and selective feedforward inhibition onto pyramidal cells.
Journal: Nature neuroscience
In common: imageio, Plotly, OpenCV, 7 other tools, histology / microscopy, 3 references
[5] doi:10.1371/journal.pcbi.1014263 [code]
MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery.
Journal: PLoS computational biology
In common: imageio, UMAP, OpenCV, 9 other tools
[6] doi:10.1038/s41467-026-72057-9 [code]
Sex-specific behavioral feedback modulates sensorimotor processing and drives flexible social behavior.
Journal: Nature communications
In common: UMAP, OpenCV, scikit-image, 8 other tools, 2 references
[7] doi:10.3389/fendo.2026.1828487 [code]
Castration-induced nigrostriatal deficits are linked to reduced TrkB and loss of mature spines in the dorsal striatum.
Journal: Frontiers in endocrinology
In common: imageio, UMAP, Plotly, 8 other tools, histology / microscopy
[8] doi:10.1016/j.isci.2026.116825 [code]
Social hierarchy shapes behavioral and transcriptional responses to chronic stress and ketamine in male mice.
Journal: iScience
In common: UMAP, Plotly, OpenCV, 9 other tools
[9] doi:10.1016/j.crmeth.2026.101429 [code]
DRIFT-EM enables direct wafer retrieval of ultrathin serial sections for large-volume electron microscopy.
Journal: Cell reports methods
In common: OpenCV, scikit-image, Pillow, 4 other tools, histology / microscopy, methods / tools, 4 references
[10] doi:10.1038/s41597-026-07248-6 [code]
A large-scale fMRI dataset for vision-language semantic association.
Journal: Scientific data
In common: imageio, OpenCV, scikit-image, 8 other tools, methods / tools

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.