An explainable AI framework integrating machine and deep learning models for multi-species DNA functional group classification
Pratik Chakraborty, P B Shanthi · 2026
Read An explainable AI framework integrating machine and deep learning models for multi-species DNA functional group classification by Pratik Chakraborty, P B Shanthi (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-13389324.txt.
Description
Pratik Chakraborty and P B Shanthi built an explainable AI framework in 2026 that sorts DNA into functional groups across species, and shows its working. Grouping genes by function across genomes illuminates diversity, evolution, and what a sequence does. Machine learning does the sorting well, but its reasons stay hidden, which weakens trust in the biology.
The framework blends machine learning and deep learning models and trains them on human, chimpanzee, and dog sequences, plus a combined set mixing all three. Sequences are cut into short k-mers so local composition patterns can be read. The groups themselves are gene families such as transcription factors and kinases. Readers get both a classifier and an explainer: predictions for cross-species gene function, with the evidence made visible.
Catalog record
| CREATOR | Pratik Chakraborty, P B Shanthi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 99 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |