afMLevel: paired raw and levelled atomic force microscopy height images with foreground masks
- Provider
- Heath AFM Lab
- License
- CC-BY-4.0 (source)
- Size
- 6,499 files
- Format
- TIFF, CSV (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/Heath-AFM-Lab/afMLevel-data)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Structural Biology
- Source
- https://github.com/mayatek1/afMLevel
About this dataset
Training and test data for afMLevel, a deep learning tool from the Heath AFM lab that levels atomic force microscopy (AFM) topography images by automated background estimation or foreground masking. Each sample pairs a raw AFM height image with a reference image levelled by hand in NanoLocz, plus a binary foreground mask. There are 2,165 images (2,001 train, 164 test), 32-bit float single-channel TIFFs in nanometres, from 128 x 128 to 1024 x 1024 pixels, released before augmentation; masks are CSV files. Layout: train/ and test/ each with Image/, Levelled/ and Mask/ folders paired by index, plus per-image provenance tables (training_data_sources.csv, test_data_sources.csv). Read the TIFFs with tifffile rather than PIL to keep float height values. About 3 GB. Useful for AFM image processing, background subtraction and U-Net segmentation of biomolecular AFM. The card states the dataset is released under CC BY 4.0, with contributing authors of unpublished data agreeing to that license; cite the afMLevel paper and github.com/mayatek1/afMLevel.
How to load this dataset in Python
import pandas as pd
df = pd.read_csv("hf://datasets/Heath-AFM-Lab/afMLevel-data/test/Mask/test_mask_000.csv")
df.head()Data structure
File types in sampled files: TIFF, CSV
Files
Example file: test/Mask/test_mask_000.csv
Analyze this dataset without downloading it
On Scigantic, afMLevel: paired raw and levelled atomic force microscopy height images with foreground masks opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Structural Biology datasets
- CryoET Data Portal 10004: C. elegans Serial Lift-Out Tomograms of Whole Worms
- Disclosing Pathogenic Variant Effects on the Structural Dynamics of the VAPB MSP Domain Causing Familial ALS
- CATH v4.4.0 protein domain classification with an S35-aware train/test split
- Processed data and analysis results for 104 RBPs
- Structural analyses define the molecular basis of clusterin chaperone function
- CryoET Data Portal 10444: Affinity-Captured Lysosomes (GFP-LAMP1) from HEK293T Cells
- POPSICLE: cryoET segmentation and particle-picking benchmark
- A Conserved Inhibitory Interdomain Interaction Regulates DNA-binding Activities of Hybrid Two-component Systems in Bacteroides