Applications of Machine Learning in Chemical and Biological Oceanography.

Machine learning (ML) refers to computer algorithms that predict a meaningful output or categorize complex systems based on a large amount of data. ML is applied in various areas including natural science, engineering, space exploration, and even gaming development. This review focuses on the use of machine learning in the field of chemical and biological oceanography. In the prediction of global fixed nitrogen levels, partial carbon dioxide pressure, and other chemical properties, the application of ML is a promising tool. Machine learning is also utilized in the field of biological oceanography to detect planktonic forms from various images (i.e., microscopy, FlowCAM, and video recorders), spectrometers, and other signal processing techniques. Moreover, ML successfully classified the mammals using their acoustics, detecting endangered mammalian and fish species in a specific environment. Most importantly, using environmental data, the ML proved to be an effective method for predicting hypoxic conditions and harmful algal bloom events, an essential measurement in terms of environmental monitoring. Furthermore, machine learning was used to construct a number of databases for various species that will be useful to other researchers, and the creation of new algorithms will help the marine research community better comprehend the chemistry and biology of the ocean.

Meta-analysis cum machine learning approaches address the structure and biogeochemical potential of marine copepod associated bacteriobiomes.

Copepods are the dominant members of the zooplankton community and the most abundant form of life. It is imperative to obtain insights into the copepod-associated bacteriobiomes (CAB) in order to identify specific bacterial taxa associated within a copepod, and to understand how they vary between different copepods. Analysing the potential genes within the CAB may reveal their intrinsic role in biogeochemical cycles. For this, machine-learning models and PICRUSt2 analysis were deployed to analyse 16S rDNA gene sequences (approximately 16 million reads) of CAB belonging to five different copepod genera viz., Acartia spp., Calanus spp., Centropages sp., Pleuromamma spp., and Temora spp.. Overall, we predict 50 sub-OTUs (s-OTUs) (gradient boosting classifiers) to be important in five copepod genera. Among these, 15 s-OTUs were predicted to be important in Calanus spp. and 20 s-OTUs as important in Pleuromamma spp.. Four bacterial s-OTUs Acinetobacter johnsonii, Phaeobacter, Vibrio shilonii and Piscirickettsiaceae were identified as important s-OTUs in Calanus spp., and the s-OTUs Marinobacter, Alteromonas, Desulfovibrio, Limnobacter, Sphingomonas, Methyloversatilis, Enhydrobacter and Coriobacteriaceae were predicted as important s-OTUs in Pleuromamma spp., for the first time. Our meta-analysis revealed that the CAB of Pleuromamma spp. had a high proportion of potential genes responsible for methanogenesis and nitrogen fixation, whereas the CAB of Temora spp. had a high proportion of potential genes involved in assimilatory sulphate reduction, and cyanocobalamin synthesis. The CAB of Pleuromamma spp. and Temora spp. have potential genes accountable for iron transport.

Bioconversion of chitin and concomitant production of chitinase and N-acetylglucosamine by novel Achromobacter xylosoxidans isolated from shrimp waste disposal area.

Marine pollution is a significant issue in recent decades, with the increase in industries and their waste harming the environment and ecosystems. Notably, the rise in shellfish industries contributes to tons of shellfish waste composed of up to 58% chitin. Chitin, the second most ample polymer next to cellulose, is insoluble and resistant to degradation. It requires chemical-based treatment or enzymatic hydrolysis to cleave the chitin polymers. The chemical-based treatment can lead to environmental pollution, so to solve this problem, enzymatic hydrolysis is the best option. Moreover, the resulting biopolymer by-products can be used to boost the fish immune system and also as drug delivery agents. Many marine microbial strains have chitinase producing ability. Nevertheless, we still lack an economical and highly stable chitinase enzyme for use in the industrial sector. So we isolate a novel marine bacterial strain Achromobacter xylosoxidans from the shrimp waste disposal site using chitin minimal medium. Placket-Burman and central composite design statistical models for culture condition optimisation predicted a 464.2 U/ml of chitinase production. The culture conditions were optimised for maximum chitinase production recording up to 467 U/ml. This chitinase from the A. xylosoxidans was 100% active at an optimum temperature of 45 °C (withstand up to 55 °C) and pH 8 with 80% stability. The HPLC analysis of chitinase degraded shellfish waste reveals a major amino acid profile composition-arginine, lysine, aspartic acid, alanine, threonine and low levels of isoleucine and methionine. These chitinase degraded products and by-products can be used as supplements in the aquaculture industry.

Metagenomic 16S rDNA amplicon data of microbial diversity and its predicted metabolic functions in the Southern Ocean (Antarctic).

Antarctica holds about 70% of all the freshwater on the planet in the form of ice. The seawater, it chills, affect the currents and temperature everywhere. Global warming risks the melting of the icecaps as it has already increased the ocean temperature by 1 °C to the West Antarctic peninsula since 1955. A better understanding of the microbial community in this extreme environment of utmost importance is of interest to the scientific community. Herein, we document our metagenomics analysis of the microbial diversity and abundance in the Southern Ocean [Lat 55″ 33' 396 S; Lon 55″ 31' 448 E] using Next Generation Sequencing (NGS), QIIME 1.9.1, Silvangs and a naïve Bayesian classifier. Such metagenomics data hold the potential to aid predictive analysis, which is critical to our understanding of the dynamics of the microbial communities and their role in the Southern Ocean at present and in the future.

Metagenomic data of vertical distribution and abundance of bacterial diversity in the hypersaline sediments of Mad Boon-mangrove ecosystem, Bay of Bengal.

Bacterial diversity studies in hypersaline soil often yield novel organisms and contribute to our understanding of this extreme environment. Soil from Mad Boon is previously uncharacterized, with dense mangrove forest in one side and hypersaline soil in another side of backwater located in Southeast coast of Tamil Nadu, India. We surveyed to characterize the structure and diversity of the bacterial community. Samples were collected in a partially vegetated upland, exposed backwater sedimentation and water-logged location. In this study, we investigate the bacterial community structure using pyrosequence analysis of the V5- V9 gene region. After quality checks a total of 3919, 7298 and 7399 reads were obtained. About 42 phyla were observed, among them Proteobacteria were dominant phylum followed by Acidobacteria, Firmicutes and Chloroflexi. Classes including Deltaproteobacteria and Gammaproteobacteriawere observed. All sequences generated in this study were submitted to NCBI SRA under the accession numbers SRR627695, SRR63011 and SRR631012.

Pyrosequencing-Based Seasonal Observation of Prokaryotic Diversity in Pneumatophore-Associated Soil of Avicennia marina.

Pneumatophores are aerial roots developing from the main roots of mangrove plants away from the gravity. The below ground pneumatophore-associated soil prokaryotic community of Avicennia marina was studied by amplicon pyrosequencing (39,378 reads) during monsoon and summer seasons. Apart from the most dominant phylum Proteobacteria in both seasons, the second most were Acidobacteria (summer) and Cyanobacteria/Chloroplast (monsoon). Similarly, Acidobacteria_Gp10 and Cyanobacteria were the second most abundant at class level during summer and monsoon, respectively. Archaeal phylum Thaumarchaeota was the most abundant followed by Crenarchaeota and Euryarchaeota. The classes detected in our study were Thermoprotei, Halobacteria, and Methanomicrobia. The highest richness and diversity were observed during summer for bacteria, whereas the same phenomena for archaea in monsoon at 97% sequence similarity. To the best of our knowledge, this is the first attempt to catalog the prokaryotic diversity of pnueumatophore-associated soil.