QUAM-AFM Lite: Simulated AFM Images for 1,755 Organic Molecules

421,200 simulated Atomic Force Microscopy images for 1,755 organic molecules, each with 24 3D image stacks at 256x256 pixel resolution. This dataset was created by Quasar Science Resources S.L. and the Universidad Autónoma de Madrid's SPMTH group, with a last update recorded on 2024-05 05. It includes molecular depictions, IUPAC names, formulas, coordinates, and atom height maps.

Use Cases

• Training computer vision models for molecular structure recognition based on simulated AFM image stacks.
• Analyzing the effect of AFM operational parameters like cantilever amplitude on image features.
• Developing tools for on-surface synthesis research using the provided molecular coordinates and height maps.
• Benchmarking multimodal learning approaches that combine chemical formulas and image data.

Strengths

• Contains 421,200 high-resolution (256x256) simulated images.
• Covers 1,755 molecules selected for relevant bonding structures and chemical species.
• Includes multimodal data per molecule: images, IUPAC name, formula, coordinates, and height maps.
• Provides a dedicated GUI for searching structures by CID, name, or formula.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is simulated, which may not fully capture experimental noise and artifacts.

Provenance

Source

Quasar Science Resources S.L. and Universidad Autónoma de Madrid's Scanning Probe Microscopy Theory & Nanomechanics Research Group.

Collection Method

Simulated from a selection of molecules, funded by the Comunidad de Madrid Industrial Doctorate Programme 2017.

Time Range

null

Freshness

Last updated 2024-05-05 04:45:43; freshness should be verified.

Geography

null