Machine learning to explore the psychrophilic soil microbiome
Shakira Ghazanfar, Rameesha Abid, Abeer Khan, Muhammad Yasir Akbar, Iqra Asif, Reem Nadeem, Wajya Ajmal, Adnan Ahmed Ansari · 2023
Primarily, most of the Earth&s;s biosphere is cold, and these permanently frigid conditions are home to psychrophilic archaea. Psychrophiles carry a unique genetic repertoire that enable them to adapt to cold habitats. Despite the majority and diversity of archaea in the cryosphere, only a few psychrophilic archaea have been isolated and examined due to the limitations of classical culturing techniques. However, advances in multi-omics have immensely expanded our ability to profile microbial diversity and assign gene ontology, thus unravelling molecular and physiological processes brought by microorganisms to thrive in extreme environments. With high-throughput sequencing technologies, we have a colossal amount of data at our disposal that demanded a developmental approach for extracting relevant information from enormous datasets; hence, machine learning was employed. Machine learning is a bioinformatics-based algorithmic approach that is used to investigate and identify patterns in microbial community data. Machine learning-based predictive models for the extraction of psychrophilic signatures can facilitate the understanding of the sequence–structure–function relationship responsible for adaptation in low-temperature settings and the discovery of new biomolecules for medical, agricultural and biotechnological use. However, the machine learning-predicted output models come at a price; i.e., how algorithms arrive at predicted models is unknown. Therefore, the models must be interpretable, so that machine learning can be used in more translational research for understanding microbiomes and other biological data. This chapter highlights the recent trends in machine learning applications in perceiving psychrophilic microbiomes from cold habitats as well as some of the main opportunities involved in the application of machine learning to understand microbial communities and their unique features.