High-throughput genomic feature extraction reveals environmental adaptations of prokaryotes
Understanding the adaptations of microorganisms to their environment is key to predicting the stability and dynamics of microbial communities. To uncover molecular mechanisms of environmental response, we extracted genomic features from 13,554 prokaryotic isolates, and trained machine learning models to identify which ones are most strongly associated with the microbial salinity, temperature,…
High-throughput genomic feature extraction has uncovered environmental adaptations in prokaryotes, providing insights into molecular mechanisms of microbial response to changing conditions. Researchers extracted genomic features from 13,554 prokaryotic isolates and trained machine learning models to identify key indicators of microbial salinity, temperature, oxygen, and pH preferences.
To streamline this process, they developed FxTractor, a scalable and adjustable pipeline accessible at https://github.com/MGXlab/FxTractor. The team validated their models using experimental data from a newly discovered deep-sea extremophile belonging to the genus Limnochorda, which was not well-represented in the machine learning training sets.
The results showed strong agreement between the model predictions and the isolation conditions of this strain. The analysis revealed specific gene and non-coding RNA families associated with each environmental parameter, unveiling both known and possibly novel molecular mechanisms. For instance, the bacterial large Signaling Recognition Particle was linked to high-temperature growth (≥55°C), potentially contributing to translational pausing and structural stability under thermal stress. Additionally, the anti-hemB ncRNA was found to be associated with low-salinity environments.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
