Explore the vast range of titles available.

Background: The number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction – a process called ‘end-to-end learning’ – has led to state-of-the-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN. Results: By using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension. Conclusion: Our study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.

Spaceflight has several detrimental effects on human and rodent health. For example, liver dysfunction is a common phenotype observed in space-flown rodents, and this dysfunction is partially reflected in transcriptomic changes. Studies linking transcriptomics with liver dysfunction rely on tools which exploit correlation, but these tools make no attempt to disambiguate true correlations from spurious ones. In this work, we use a machine learning ensemble of causal inference methods called the Causal Research and Inference Search Platform (CRISP) which was developed to predict causal features of a binary response variable from high-dimensional input. We used CRISP to identify genes robustly correlated with a lipid density phenotype using transcriptomic and histological data from the NASA Open Science Data Repository (OSDR). Our approach identified genes and molecular targets not predicted by previous traditional differential gene expression analyses. These genes are likely to play a pivotal role in the liver dysfunction observed in space-flown rodents, and this work opens the door to identifying novel countermeasures for space travel.

Heterotrophic microbial communities use extracellular enzymes to initialize degradation of high molecular weight organic matter in the ocean. The potential of microbial communities to access organic matter, and the resultant rates of hydrolysis, affect the efficiency of the biological pump as well as the rate and location of organic carbon cycling in surface and deep waters. In order to investigate spatial- and depth-related patterns in microbial enzymatic capacities in the ocean, we measured hydrolysis rates of six high-molecular-weight polysaccharides and two low-molecular-weight substrate proxies at sites spanning 38°S to 10°N in the Atlantic Ocean, and at six depths ranging from surface to bottom water. In surface to upper mesopelagic waters, the spectrum of substrates hydrolyzed followed distinct patterns, with hydrolytic assemblages more similar vertically within a single station than at similar depths across multiple stations. Additionally, the proportion of total hydrolysis occurring above the pycnocline, and the spectrum of substrates hydrolyzed in mesopelagic and deep waters, was positively related to the strength of stratification at a site, while other physichochemical parameters were generally poor predictors of the measured hydrolysis rates. Spatial as well as depth-driven constraints on heterotrophic hydrolytic capacities result in broad variations in potential carbon-degrading activity in the ocean. The spectrum of enzymatic capabilities and rates of hydrolysis in the ocean, and the proportion of organic carbon hydrolyzed above the permanent thermocline, may influence the efficiency of the biological pump and net carbon export across distinct latitudinal and depth regions.

The forthcoming human deep space exploration missions necessitate a thorough understanding of the impact of spaceflight conditions on human physiological systems. The NASA Open Science Data Repository (OSDR; ) serves as a valuable resource, housing data derived from model organisms and human experiments conducted in spaceflight and terrestrial microgravity analogues. Machine Learning applications could maximize the use of existing data to understand and ultimately counteract physiological abnormalities during long-term missions. In our present study, we identified enriched terms and pathways associated with significantly dysregulated genes within each species and across orthologous counterparts. We also generated AI-ready merged meta-datasets comprised of musculoskeletal tissues from Mus musculus and Homo sapiens organisms. We then applied a series of supervised Machine Learning models to classify genes that were significantly over-expressed and under-expressed. Subsequently, we explored the utility of Transfer Learning in this domain by pretraining a model on the larger Mus musculus merged dataset and then refining it on the smaller Homo sapiens dataset. This approach showcases the potential of Transfer Learning in providing an insight into the effective transfer of information from model organisms to humans, offering a robust framework for advancing research in space biology and developing countermeasures for long-duration space exploration.

The adverse effects of microgravity exposure on mammalian physiology during spaceflight necessitate a deep understanding of the underlying mechanisms to develop effective countermeasures. One such concern is muscle atrophy, which is partly attributed to the dysregulation of calcium levels due to abnormalities in SERCA pump functioning. To identify potential biomarkers for this condition, multi-omics data and physiological data available on the NASA Open Science Data Repository (osdr.nasa.gov) were used, and machine learning methods were employed. Specifically, we used multi-omics (transcriptomic, proteomic, and DNA methylation) data and calcium reuptake data collected from C57BL/6 J mouse soleus and tibialis anterior tissues during several 30+ day-long missions on the international space station. The QLattice symbolic regression algorithm was introduced to generate highly explainable models that predict either experimental conditions or calcium reuptake levels based on multi-omics features. The list of candidate models established by QLattice was used to identify key features contributing to the predictive capability of these models, with Acyp1 and Rps7 proteins found to be the most predictive biomarkers related to the resilience of the tibialis anterior muscle in space. These findings could serve as targets for future interventions aiming to reduce the extent of muscle atrophy during space travel.

Warm core, anticyclonic rings that spin off from the Gulf Stream circulate through the region directly offshore of the Mid-Atlantic Bight. If a warm core ring reaches the continental shelf break, its warm, highly saline water may subduct under cooler, fresher continental shelf surface water, resulting in subsurface waters at the shelf break and over the upper continental slope with high temperatures and salinities and distinct physical and chemical properties characteristic of Gulf Stream water. Such intruding water may also have microbial communities with distinct functional capacities, which may in turn affect the rate and nature of carbon cycling in this coastal/shelf environment. However, the functional capabilities of microbial communities within ring intrusion waters relative to surrounding continental shelf waters are largely unexplored. We investigated microbial community capacity to initiate organic matter remineralization by measuring hydrolysis of a suite of polysaccharide, peptide, and glucose substrates along a transect oriented across the Mid-Atlantic Bight shelf, shelf break, and upper slope. At the outermost sampling site, warm and salty water derived from a Gulf Stream warm core ring was present in the lower portion of the water column. This water exhibited hydrolytic capacities distinct from other sampling sites, and exhibited lower heterotrophic bacterial productivity overall. Warm core rings adjacent to the Mid-Atlantic Bight shelf have increased in frequency and duration in recent years. As the influence of warm core rings on the continental shelf and slope increases in the future, the rate and nature of organic matter remineralization on the continental shelf may also shift.

Human exploration of deep space will involve missions of substantial distance and duration. To effectively mitigate health hazards, paradigm shifts in astronaut health systems are necessary to enable Earth-independent healthcare, rather than Earth-reliant. Here we present a summary of decadal recommendations from a workshop organized by NASA on artificial intelligence, machine learning and modelling applications that offer key solutions toward these space health challenges. The workshop recommended various biomonitoring approaches, biomarker science, spacecraft/habitat hardware, intelligent software and streamlined data management tools in need of development and integration to enable humanity to thrive in deep space. Participants recommended that these components culminate in a maximally automated, autonomous and intelligent Precision Space Health system, to monitor, aggregate and assess biomedical statuses. Deep-space exploration missions require new technologies that can support astronaut health systems as well as biological monitoring and research systems that can function independently from Earth-based mission control centres. A NASA workshop explored how artificial intelligence advances could help address these challenges and, in this first of two Review articles based on the findings from the workshop, a vision for autonomous biomonitoring and precision space health is discussed.

Space biology research aims to understand fundamental spaceflight effects on organisms, develop foundational knowledge to support deep space exploration and, ultimately, bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals and humans for sustained multi-planetary life. To advance these aims, the field leverages experiments, platforms, data and model organisms from both spaceborne and ground-analogue studies. As research is extended beyond low Earth orbit, experiments and platforms must be maximally automated, light, agile and intelligent to accelerate knowledge discovery. Here we present a summary of decadal recommendations from a workshop organized by the National Aeronautics and Space Administration on artificial intelligence, machine learning and modelling applications that offer solutions to these space biology challenges. The integration of artificial intelligence into the field of space biology will deepen the biological understanding of spaceflight effects, facilitate predictive modelling and analytics, support maximally automated and reproducible experiments, and efficiently manage spaceborne data and metadata, ultimately to enable life to thrive in deep space. Deep space exploration missions will require new technologies that can support astronaut health systems, as well as biological monitoring and research systems that can function independently from Earth-based mission control centres. A NASA workshop explored how artificial intelligence advances could help address these challenges and, in this second of two Review articles based on the findings from the workshop, the intersection between artificial intelligence and space biology is discussed.

Oceanic bacterial communities process a major fraction of marine organic carbon. A substantial portion of this carbon transformation occurs in the mesopelagic zone, and a further fraction fuels bacteria in the bathypelagic zone. However, the capabilities and limitations of the diverse microbial communities at these depths to degrade high-molecular-weight (HMW) organic matter are not well constrained. Here, we compared the responses of distinct microbial communities from North Atlantic epipelagic (0–200 m), mesopelagic (200–1000 m), and bathypelagic (1000–4000 m) waters at two open-ocean stations to the same input of diatom-derived HMW particulate and dissolved organic matter. Microbial community composition and functional responses to the input of HMW organic matter – as measured by polysaccharide hydrolase, glucosidase, and peptidase activities – were very similar between the stations, which were separated by 1370 km but showed distinct patterns with depth. Changes in microbial community composition coincided with changes in enzymatic activities: as bacterial community composition changed in response to the addition of HMW organic matter, the rate and spectrum of enzymatic activities increased. In epipelagic mesocosms, the spectrum of peptidase activities became especially broad and glucosidase activities were very high, a pattern not seen at other depths, which, in contrast, were dominated by leucine aminopeptidase and had much lower peptidase and glucosidase rates in general. The spectrum of polysaccharide hydrolase activities was enhanced particularly in epipelagic and mesopelagic mesocosms, with fewer enhancements in rates or spectrum in bathypelagic waters. The timing and magnitude of these distinct functional responses to the same HMW organic matter varied with depth. Our results highlight the importance of residence times at specific depths in determining the nature and quantity of organic matter reaching the deep sea.

SAR86 is an abundant and ubiquitous heterotroph in the surface ocean that plays a central role in the function of marine ecosystems. We hypothesized that despite its ubiquity, different SAR86 subgroups may be endemic to specific ocean regions and functionally specialized for unique marine environments. However, the global biogeographical distributions of SAR86 genes, and the manner in which these distributions correlate with marine environments, have not been investigated. We quantified SAR86 gene content across globally distributed metagenomic samples and modeled these gene distributions as a function of 51 environmental variables. We identified five distinct clusters of genes within the SAR86 pangenome, each with a unique geographic distribution associated with specific environmental characteristics. Gene clusters are characterized by the strong taxonomic enrichment of distinct SAR86 genomes and partial assemblies, as well as differential enrichment of certain functional groups, suggesting differing functional and ecological roles of SAR86 ecotypes. We then leveraged our models and high-resolution, remote sensing-derived environmental data to predict the distributions of SAR86 gene clusters across the world’s oceans, creating global maps of SAR86 ecotype distributions. Our results reveal that SAR86 exhibits previously unknown, complex biogeography, and provide a framework for exploring geographic distributions of genetic diversity from other microbial clades.