Chemical space visualization at scale: a survey of end-to-end pipelines and dataset-size archetypes
Maha M AlShammari, Moayad Alnammi, Moataz Ahmed · 2026
Read Chemical space visualization at scale: a survey of end-to-end pipelines and dataset-size archetypes by Maha M AlShammari, Moayad Alnammi, Moataz Ahmed (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13450572.txt.
Description
Maha M AlShammari and others took stock of how huge chem sets are drawn as maps in 2026, in a survey of fifty-six works from 2000 to 2025. As chem sets swell from thousands to billions of items, map-making must weigh chem sense with compute and memory caps. The team traced the full work flow in five steps.
The steps are: set choice, chem coding, size cut-down, grouping, and scoring. Fingerprints still rule for huge sets, since they scale well, while bits, SMILES codes, and learned codes gain use where richer cues count. Size cut-down has moved from PCA norms to tools that keep near neighbors, such as t-SNE and UMAP, with graph maps for extreme scale. Chemists gain a scale-wise guide to pick a work flow.
Catalog record
| CREATOR | Maha M AlShammari, Moayad Alnammi, Moataz Ahmed |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 110 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |