scholarly journals Predicting microbiome compositions through deep learning.

2021 ◽  
Author(s):  
Sebastian Michel-Mata ◽  
Xu-Wen Wang ◽  
Yang-Yu Liu ◽  
Marco Tulio Angulo
Keyword(s):  
Deep Learning ◽  
Microbial Communities ◽  
Synthetic Data ◽  
Soil Microbial Communities ◽  
Well Being ◽  
Training Data ◽  
Oral Microbiota ◽  
Form Complex

Microbes can form complex communities that perform critical functions in maintaining the integrity of their environment1,2 or the well-being of their hosts3-6. Successfully managing these microbial communities requires the ability to predict the community composition based on the species assemblage7. However, making such a prediction remains challenging because of our limited knowledge of the diverse physical8, biochemical9, and ecological10,11 processes governing the microbial dynamics. To overcome this challenge, here we present a deep learning framework that automatically learns the map between species assemblages and community compositions from training data. First, we systematically validate our framework using synthetic data generated by classical population dynamics models. Then, we apply it to experimental data of both in vitro and in vivo communities, including ocean and soil microbial communities12,13, Drosophila melanogaster gut microbiota14, and human gut and oral microbiota15. Our results demonstrate how deep learning can enable us to understand better and potentially manage complex microbial communities.

scholarly journals Generalizing game-changing species across microbial communities

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
Jie Deng ◽  
Marco Tulio Angulo ◽  
Serguei Saavedra
Keyword(s):  
Microbial Communities ◽  
Context Dependency ◽  
Heuristic Rules ◽  
Resident Species ◽  
Experimental Systems ◽  
Environment And Health ◽  
Structuralist Theory ◽  
Context Specific

AbstractMicrobes form multispecies communities that play essential roles in our environment and health. Not surprisingly, there is an increasing need for understanding if certain invader species will modify a given microbial community, producing either a desired or undesired change in the observed collection of resident species. However, the complex interactions that species can establish between each other and the diverse external factors underlying their dynamics have made constructing such understanding context-specific. Here we integrate tractable theoretical systems with tractable experimental systems to find general conditions under which non-resident species can change the collection of resident communities—game-changing species. We show that non-resident colonizers are more likely to be game-changers than transients, whereas game-changers are more likely to suppress than to promote resident species. Importantly, we find general heuristic rules for game-changers under controlled environments by integrating mutual invasibility theory with in vitro experimental systems, and general heuristic rules under changing environments by integrating structuralist theory with in vivo experimental systems. Despite the strong context-dependency of microbial communities, our work shows that under an appropriate integration of tractable theoretical and experimental systems, it is possible to unveil regularities that can then be potentially extended to understand the behavior of complex natural communities.

scholarly journals Molecular imaging and deep learning analysis of uMUC1 expression in response to chemotherapy in an orthotopic model of ovarian cancer

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Hongwei Zhao ◽  
Hasaan Hayat ◽  
Xiaohong Ma ◽  
Daguang Fan ◽  
Ping Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Ovarian Cancer ◽  
Deep Learning ◽  
Cancer Progression ◽  
In Vivo Imaging ◽  
Near Infrared ◽  
Response To Therapy ◽  
Response To Chemotherapy

Abstract Artificial Intelligence (AI) algorithms including deep learning have recently demonstrated remarkable progress in image-recognition tasks. Here, we utilized AI for monitoring the expression of underglycosylated mucin 1 (uMUC1) tumor antigen, a biomarker for ovarian cancer progression and response to therapy, using contrast-enhanced in vivo imaging. This was done using a dual-modal (magnetic resonance and near infrared optical imaging) uMUC1-specific probe (termed MN-EPPT) consisted of iron-oxide magnetic nanoparticles (MN) conjugated to a uMUC1-specific peptide (EPPT) and labeled with a near-infrared fluorescent dye, Cy5.5. In vitro studies performed in uMUC1-expressing human ovarian cancer cell line SKOV3/Luc and control uMUC1low ES-2 cells showed preferential uptake on the probe by the high expressor (n = 3, p < .05). A decrease in MN-EPPT uptake by SKOV3/Luc cells in vitro due to uMUC1 downregulation after docetaxel therapy was paralleled by in vivo imaging studies that showed a reduction in probe accumulation in the docetaxel treated group (n = 5, p < .05). The imaging data were analyzed using deep learning-enabled segmentation and quantification of the tumor region of interest (ROI) from raw input MRI sequences by applying AI algorithms including a blend of Convolutional Neural Networks (CNN) and Fully Connected Neural Networks. We believe that the algorithms used in this study have the potential to improve studying and monitoring cancer progression, amongst other diseases.

piCRISPR: Physically Informed Features Improve Deep Learning Models for CRISPR/Cas9 Off-Target Cleavage Prediction

2021 ◽  
Author(s):  
Florian Störtz ◽  
Jeffrey Mak ◽  
Peter Minary
Keyword(s):  
Deep Learning ◽  
Gene Editing ◽  
Target Prediction ◽  
Model Space ◽  
Chromatin Accessibility ◽  
Sequence Context ◽  
Prediction Algorithms ◽  
Cleavage Assay

CRISPR/Cas programmable nuclease systems have become ubiquitous in the field of gene editing. With progressing development, applications in in vivo therapeutic gene editing are increasingly within reach, yet limited by possible adverse side effects from unwanted edits. Recent years have thus seen continuous development of off-target prediction algorithms trained on in vitro cleavage assay data gained from immortalised cell lines. Here, we implement novel deep learning algorithms and feature encodings for off-target prediction and systematically sample the resulting model space in order to find optimal models and inform future modelling efforts. We lay emphasis on physically informed features, hence terming our approach piCRISPR, which we gain on the large, diverse crisprSQL off-target cleavage dataset. We find that our best-performing model highlights the importance of sequence context and chromatin accessibility for cleavage prediction and outperforms state-of-the-art prediction algorithms in terms of area under precision-recall curve.

Platelet-agglutinating protein P37 from a thrombotic thrombocytopenic purpura plasma forms a complex with human immunoglobulin G

Blood ◽  
1988 ◽  
Vol 71 (2) ◽  
pp. 299-304 ◽  
Author(s):  
FA Siddiqui ◽  
EC Lian
Keyword(s):  
Complex Formation ◽  
Thrombotic Thrombocytopenic Purpura ◽  
Fluid Phase ◽  
Enzyme Linked Immunosorbent Assay ◽  
Thrombocytopenic Purpura ◽  
Form Complex ◽  
Specific Igg ◽  
Sepharose 4B

Abstract We have previously reported the purification of a 37-kd platelet- agglutinating protein (PAP p37) from the plasma of a patient with thrombotic thrombocytopenic purpura (TTP) that was shown to be present in a subset of TTP patients. The platelet agglutination induced by PAP p37 has been shown to be inhibited by IgG from normal human adults and the same TTP patient after recovery. To elucidate the mechanism of inhibition of IgG, the interaction between PAP p37 and IgG was studied. The complex formation was demonstrated by the binding of fluid-phase IgG from normal adults and the same TTP patient after recovery to adsorbed PAP by using an enzyme-linked immunosorbent assay. The binding was specific, concentration dependent, and saturable. IgG purified from a 5-month-old baby and the same TTP patient during active disease did not form complex with PAP p37. The IgG covalently cross-linked to Sepharose 4B bound 125I-PAP p37 but not 125I-fibrinogen. Sucrose density gradient ultracentrifugation of a mixture of 125I-PAP p37 and IgG also revealed the fluid-phase complex formation with a sedimentation value of 19S. Complexes of molecular weight ranging from 180,000 to over 350,000 daltons were also detected by molecular sieve chromatography. The IgG that was bound to PAP p37 conjugated to Sepharose 4B inhibited the agglutination of washed platelets induced by TTP plasma containing PAP p37, whereas the IgG that was not bound to PAP p37 did not have a significant inhibitory effect. The complex formation between PAP p37 and specific IgG is likely to account for the in vitro inhibition of TTP plasma-induced agglutination and, at least partly, the in vivo successful treatment with specific IgG-containing normal plasma.

scholarly journals Soil Microbial Biogeography in a Changing World: Recent Advances and Future Perspectives

mSystems ◽  
2020 ◽  
Vol 5 (2) ◽  
Author(s):  
Haiyan Chu ◽  
Gui-Feng Gao ◽  
Yuying Ma ◽  
Kunkun Fan ◽  
Manuel Delgado-Baquerizo
Keyword(s):  
Microbial Communities ◽  
Soil Microbial Communities ◽  
Well Being ◽  
Ecosystem Functions ◽  
Soil Microbial ◽  
Microbial Biogeography ◽  
Recent Advances ◽  
Technological Advances ◽  
Global Change Scenarios ◽  
Changing World

ABSTRACT Soil microbial communities are fundamental to maintaining key soil processes associated with litter decomposition, nutrient cycling, and plant productivity and are thus integral to human well-being. Recent technological advances have exponentially increased our knowledge concerning the global ecological distributions of microbial communities across space and time and have provided evidence for their contribution to ecosystem functions. However, major knowledge gaps in soil biogeography remain to be addressed over the coming years as technology and research questions continue to evolve. In this minireview, we state recent advances and future directions in the study of soil microbial biogeography and discuss the need for a clearer concept of microbial species, projections of soil microbial distributions toward future global change scenarios, and the importance of embracing culture and isolation approaches to determine microbial functional profiles. This knowledge will be critical to better predict ecosystem functions in a changing world.

scholarly journals Effect of Ligilactobacillus salivarius and Other Natural Components against Anaerobic Periodontal Bacteria

Molecules ◽  
2020 ◽  
Vol 25 (19) ◽  
pp. 4519
Author(s):  
Marzena Kucia ◽  
Ewa Wietrak ◽  
Mateusz Szymczak ◽  
Paweł Kowalczyk
Keyword(s):  
Alveolar Bone ◽  
Anaerobic Bacteria ◽  
Drug Susceptibility ◽  
Diffusion Method ◽  
In Vitro Tests ◽  
Growth Media ◽  
Oral Microbiota ◽  
Disk Diffusion Method

In this present study, the bacteriostatic effect of Salistat SGL03 and the Lactobacillus salivarius strain contained in it was investigated in adults in in vivo and in vitro tests on selected red complex bacteria living in the subgingival plaque, inducing a disease called periodontitis, i.e., chronic periodontitis. Untreated periodontitis can lead to the destruction of the gums, root cementum, periodontium, and alveolar bone. Anaerobic bacteria, called periopathogens or periodontopathogens, play a key role in the etiopathogenesis of periodontitis. The most important periopathogens of the oral microbiota are: Porphyromonas gingivalis, Tannerella forsythia, Treponema denticola and others. Our hypothesis was verified by taking swabs of scrapings from the surface of the teeth of female hygienists (volunteers) on full and selective growth media for L. salivarius. The sizes of the zones of growth inhibition of periopathogens on the media were measured before (in vitro) and after consumption (in vivo) of Salistat SGL03, based on the disk diffusion method, which is one of the methods of testing antibiotic resistance and drug susceptibility of pathogenic microorganisms. Additionally, each of the periopathogens analyzed by the reduction inoculation method, was treated with L. salivarius contained in the SGL03 preparation and incubated together in Petri dishes. The bacteriostatic activity of SGL03 preparation in selected periopathogens was also analyzed using the minimum inhibition concentration (MIC) and minimum bactericidal concentration (MBC) tests. The obtained results suggest the possibility of using the Salistat SGL03 dietary supplement in the prophylaxis and support of the treatment of periodontitis—already treated as a civilization disease.

scholarly journals Publisher Correction: Research on oral microbiota of monozygotic twins with discordant caries experience - in vitro and in vivo study

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Hongle Wu ◽  
Benhua Zeng ◽  
Bolei Li ◽  
Biao Ren ◽  
Jianhua Zhao ◽  
...  
Keyword(s):  
Monozygotic Twins ◽  
In Vivo Study ◽  
Caries Experience ◽  
Oral Microbiota

scholarly journals Bolt-Loosening Monitoring Framework Using an Image-Based Deep Learning and Graphical Model

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3382 ◽  
Author(s):  
Hai Chien Pham ◽  
Quoc-Bao Ta ◽  
Jeong-Tae Kim ◽  
Duc-Duy Ho ◽  
Xuan-Linh Tran ◽  
...  
Keyword(s):  
Deep Learning ◽  
Graphical Model ◽  
Synthetic Data ◽  
Learning Model ◽  
Training Data ◽  
Bolted Joint ◽  
Bolt Loosening ◽  
Truss Bridge ◽  
Deep Learning Model ◽  
Real Scale

In this study, we investigate a novel idea of using synthetic images of bolts which are generated from a graphical model to train a deep learning model for loosened bolt detection. Firstly, a framework for bolt-loosening detection using image-based deep learning and computer graphics is proposed. Next, the feasibility of the proposed framework is demonstrated through the bolt-loosening monitoring of a lab-scaled bolted joint model. For practicality, the proposed idea is evaluated on the real-scale bolted connections of a historical truss bridge in Danang, Vietnam. The results show that the deep learning model trained by the synthesized images can achieve accurate bolt recognitions and looseness detections. The proposed methodology could help to reduce the time and cost associated with the collection of high-quality training data and further accelerate the applicability of vision-based deep learning models trained on synthetic data in practice.

scholarly journals Multiple sclerosis-associated changes in the composition and immune functions of spore-forming bacteria

2018 ◽  
Author(s):  
Egle Cekanaviciute ◽  
Anne-Katrin Pröbstel ◽  
Anna Thomann ◽  
Tessel F. Runia ◽  
Patrizia Casaccia ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
T Lymphocytes ◽  
Microbial Communities ◽  
Immune Functions ◽  
Simple Description ◽  
Regulatory T Lymphocytes ◽  
Select Group ◽  
Spore Forming Bacteria

AbstractMultiple sclerosis (MS) is an autoimmune disease of the central nervous system characterized by adaptive and innate immune system dysregulation. Recent work has revealed moderate alteration of gut microbial communities in subjects with MS and in experimental, induced models. However, a mechanistic understanding linking the observed changes in the microbiota and the presence of the disease is still missing. Chloroform-resistant, spore-forming bacteria have been shown to exhibit immunomodulatory properties in vitro and in vivo, but they have not yet been characterized in the context of human disease. This study addresses the community composition and immune function of this bacterial fraction in MS. We identify MS-associated spore-forming taxa and show that their presence correlates with impaired differentiation of IL-10 secreting, regulatory T lymphocytes in-vitro. Colonization of antibiotic-treated mice with spore-forming bacteria allowed us to identify some bacterial taxa favoring IL-10+ lymphocyte differentiation and others inducing differentiation of pro-inflammatory, IFNγ+ T lymphocytes. However, when fed into antibiotic-treated mice, both MS and control derived spore-forming bacteria were able to induce immunoregulatory responses.Our analysis also identified Akkermansia muciniphila as a key organism that may interact either directly or indirectly with spore-forming bacteria to exacerbate the inflammatory effects of MS-associated gut microbiota. Thus, changes in the spore-forming fraction may influence T lymphocyte-mediated inflammation in MS. This experimental approach of isolating a subset of microbiota based on its functional characteristics may be useful to investigate other microbial fractions at greater depth.ImportanceDespite the rapid emergence of microbiome related studies in human diseases, few go beyond a simple description of relative taxa levels in a select group of patients. Our study integrates computational analysis with in vitro and in vivo exploration of inflammatory properties of both complete microbial communities and individual taxa, revealing novel functional associations. We specifically show that while small differences exist between the microbiomes of MS patients and healthy subjects, these differences are exacerbated in the chloroform resistant fraction. We further demonstrate that, when purified from MS patients, this fraction is associated with impaired immunomodulatory responses in vitro.

scholarly journals In vitro selection of a microbial consortium predictive of synergistic functioning along multiple ecosystem scales

2020 ◽  
Author(s):  
Peter Baas ◽  
Colin Bell ◽  
Lauren Mancini ◽  
Melanie Lee ◽  
Matthew D. Wallenstein ◽  
...  
Keyword(s):  
Plant Growth ◽  
In Vitro Selection ◽  
Bacterial Species ◽  
Microbial Consortia ◽  
Ecosystem Functions ◽  
Emergent Properties ◽  
Form Complex ◽  
Soil P

AbstractSoil microbes form complex interactive networks throughout the soil and plant rhizosphere. These interactions can result in emergent properties for consortia that are not predictable from the phenotypes of constituents in isolation. We used a four-species consortium to assess the capacity of individual microbial species versus different consortia permutations of the four species to contribute to increased P-solubilization using soil incubations and plant growth experiments. We found that as different combinations of bacterial species were assembled into differing consortia, they demonstrated differing abilities to stimulate soil P cycling and plant growth. The combination of all four microbes in the consortia were much more effective at solubilizing P and stimulating plant growth than any of the individual bacterial species alone. This suggests that in vivo functionally synergistic soil microbial consortia can be adept at performing specific ecosystem functions in situ. Improving our understanding of the mechanisms that facilitate synergistic functioning examined in this study is important for maximizing future food production and agroecosystem sustainability.

Sign in / Sign up

Export Citation Format

Share Document