Causal language model for binary classification of microalgal vs. contaminant protein sequences, built on
nanoGPT. algaGPT distinguishes algal proteins from bacterial, archaeal, and fungal contaminants in metagenomic assemblies without requiring sequence homology.
1# See Nelson et al. (2025) for full inference pipeline
2# Batch inference: https://github.com/SarahD4/dark-whiteGPLM/blob/main/batch_inference.py
algaGPT served as the primary proteome extraction tool in the ELF-NET study, purifying algal protein sequences from 2,044 TARA Oceans metagenome assemblies to yield 221.9 million sequences for downstream domain-environment coupling analysis.
David R. Nelson, Ashish Kumar Jaiswal, Noha Samir Ismail, Alexandra Mystikou, Kourosh Salehi-Ashtiani
1@article{nelson2025la4sr,
2 title = {Pan-microalgal dark proteome mapping via interpretable deep learning and synthetic chimeras},
3 author = {Nelson, David R. and Jaiswal, Ashish Kumar and Ismail, Noha Samir and Mystikou, Alexandra and Salehi-Ashtiani, Kourosh},
4 journal = {Patterns},
5 volume = {6},
6 pages = {101373},
7 year = {2025},
8 doi = {10.1016/j.patter.2025.101373}
9}
1@article{nelson2026elfnet,
2 title = {Coupling of oceanographic state to the dark proteome: a foundation for genome-informed marine productivity modeling},
3 author = {Nelson, David Roy and Plouviez, Maxence and Daakour, Sarah and Jaiswal, Ashish and Fu, Weiqi and Amin, Shady A. and Salehi-Ashtiani, Kourosh},
4 journal = {Forthcoming},
5 year = {2026}
6}
Kourosh Salehi-Ashtiani --
ksa3@nyu.edu
