Distinction of Lymphoma from Sarcoidosis on 18F-FDG PET/CT: Evaluation of Radiomics-Feature-Guided Machine Learning Versus Human Reader Performance

Sarcoidosis and lymphoma often share common features on ¹⁸F-FDG PET/CT, such as intense hypermetabolic lesions in lymph nodes and multiple organs. We aimed at developing and validating radiomics signatures to differentiate sarcoidosis from Hodgkin lymphoma (HL) and diffuse large B-cell lymphoma (DLBCL). Methods: We retrospectively collected 420 patients (169 sarcoidosis, 140 HL, and 111 DLBCL) who underwent pretreatment ¹⁸F-FDG PET/CT at the University Hospital of Liege. The studies were randomly distributed to 4 physicians, who gave their diagnostic suggestion among the 3 diseases. The individual and pooled performance of the physicians was then calculated. Interobserver variability was evaluated using a sample of 34 studies interpreted by all physicians. Volumes of interest were delineated over the lesions and the liver using MIM software, and 215 radiomics features were extracted using the RadiomiX Toolbox. Models were developed combining clinical data (age, sex, and weight) and radiomics (original and tumor-to-liver TLR radiomics), with 7 different feature selection approaches and 4 different machine-learning (ML) classifiers, to differentiate sarcoidosis and lymphomas on both lesion-based and patient-based approaches. Results: For identifying lymphoma versus sarcoidosis, physicians' pooled sensitivity, specificity, area under the receiver-operating-characteristic curve (AUC), and accuracy were 0.99 (95% CI, 0.97-1.00), 0.75 (95% CI, 0.68-0.81), 0.87 (95% CI, 0.84-0.90), and 89.3%, respectively, whereas for identifying HL in the tumor population, it was 0.58 (95% CI, 0.49-0.66), 0.82 (95% CI, 0.74-0.89), 0.70 (95% CI, 0.64-0.75) and 68.5%, respectively. Moderate agreement was found among observers for the diagnosis of lymphoma versus sarcoidosis and HL versus DLBCL, with Fleiss κ-values of 0.66 (95% CI, 0.45-0.87) and 0.69 (95% CI, 0.45-0.93), respectively. The best ML models for identifying lymphoma versus sarcoidosis showed an AUC of 0.94 (95% CI, 0.93-0.95) and 0.85 (95% CI, 0.82-0.88) in lesion- and patient-based approaches, respectively, using TLR radiomics (plus age for the second). To differentiate HL from DLBCL, we obtained an AUC of 0.95 (95% CI, 0.93-0.96) in the lesion-based approach using TLR radiomics and 0.86 (95% CI, 0.80-0.91) in the patient-based approach using original radiomics and age. Conclusion: Characterization of sarcoidosis and lymphoma lesions is feasible using ML and radiomics, with very good to excellent performance, equivalent to or better than that of physicians, who showed significant interobserver variability in their assessment.

Automated Open-Hardware Multiwell Imaging Station for Microorganisms Observation

Bright field microscopes are particularly useful tools for biologists for cell and tissue observation, phenotyping, cell counting, and so on. Direct cell observation provides a wealth of information on cells’ nature and physiological condition. Microscopic analyses are, however, time-consuming and usually not easy to parallelize. We describe the fabrication of a stand-alone microscope able to automatically collect samples with 3D printed pumps, and capture images at up to 50× optical magnification with a digital camera at a good throughput (up to 24 different samples can be collected and scanned in less than 10 min). Furthermore, the proposed device can store and analyze pictures using computer vision algorithms running on a low power integrated single board computer. Our device can perform a large set of tasks, with minimal human intervention, that no single commercially available machine can perform. The proposed open-hardware device has a modular design and can be freely reproduced at a very competitive price with the use of widely documented and user-friendly components such as Arduino, Raspberry pi, and 3D printers.

Open-hardware wireless controller and 3D-printed pumps for efficient liquid manipulation

Many routines in biological experiments require the precise handling of liquid volumes in the range of microliters up to liters. In this paper, we describe a new wireless controller that is adapted to liquid manipulation tasks, in particular when combined with the proposed 3D-printed pumps. It can be built from widely available electronic components and managed with open-source software. The use of peristaltic pumps enables to move volumes from milliliters to liters with a relative error below 1% or a syringe pump capable of injecting volumes in the range of milliliters with microliter accuracy. The system is remotely controllable over WiFi and easily automated using the MQTT communication protocol. The programming of the microcontroller is performed on the Arduino IDE. The WiFi settings and the calibration value can be easily modified, stored and exported in the form of a JSON file to create a user friendly, plug and play and easily scalable device. Additional sensors or actuators can be added, allowing the system to adapt to various usages. Finally, in addition to its low manufacturing cost and its capability to fit a large variety of tasks involving liquid handling, our system has been specifically designed for research environments where adaptability and repeatability of experiments is essential.

Combining semi-automated image analysis techniques with machine learning algorithms to accelerate large-scale genetic studies

Genetic analyses of plant root systems require large datasets of extracted architectural traits. To quantify such traits from images of root systems, researchers often have to choose between automated tools (that are prone to error and extract only a limited number of architectural traits) or semi-automated ones (that are highly time consuming). We trained a Random Forest algorithm to infer architectural traits from automatically extracted image descriptors. The training was performed on a subset of the dataset, then applied to its entirety. This strategy allowed us to (i) decrease the image analysis time by 73% and (ii) extract meaningful architectural traits based on image descriptors. We also show that these traits are sufficient to identify the quantitative trait loci that had previously been discovered using a semi-automated method. We have shown that combining semi-automated image analysis with machine learning algorithms has the power to increase the throughput of large-scale root studies. We expect that such an approach will enable the quantification of more complex root systems for genetic studies. We also believe that our approach could be extended to other areas of plant phenotyping.

Study of Meta-analysis strategies for network inference using information-theoretic approaches

Background

Reverse engineering of gene regulatory networks (GRNs) from gene expression data is a classical challenge in systems biology. Thanks to high-throughput technologies, a massive amount of gene-expression data has been accumulated in the public repositories. Modelling GRNs from multiple experiments (also called integrative analysis) has; therefore, naturally become a standard procedure in modern computational biology. Indeed, such analysis is usually more robust than the traditional approaches, which suffer from experimental biases and the low number of samples by analysing individual datasets.

To date, there are mainly two strategies for the problem of interest: the first one (“data merging”) merges all datasets together and then infers a GRN whereas the other (“networks ensemble”) infers GRNs from every dataset separately and then aggregates them using some ensemble rules (such as ranksum or weightsum). Unfortunately, a thorough comparison of these two approaches is lacking.

Results

In this work, we are going to present another meta-analysis approach for inferring GRNs from multiple studies. Our proposed meta-analysis approach, adapted to methods based on pairwise measures such as correlation or mutual information, consists of two steps: aggregating matrices of the pairwise measures from every dataset followed by extracting the network from the meta-matrix. Afterwards, we evaluate the performance of the two commonly used approaches mentioned above and our presented approach with a systematic set of experiments based on in silico benchmarks.

Conclusions

We proposed a first systematic evaluation of different strategies for reverse engineering GRNs from multiple datasets. Experiment results strongly suggest that assembling matrices of pairwise dependencies is a better strategy for network inference than the two commonly used ones.

Using a Structural Root System Model to Evaluate and Improve the Accuracy of Root Image Analysis Pipelines

Root system analysis is a complex task, often performed with fully automated image analysis pipelines. However, the outcome is rarely verified by ground-truth data, which might lead to underestimated biases. We have used a root model, ArchiSimple, to create a large and diverse library of ground-truth root system images (10,000). For each image, three levels of noise were created. This library was used to evaluate the accuracy and usefulness of several image descriptors classically used in root image analysis softwares. Our analysis highlighted that the accuracy of the different traits is strongly dependent on the quality of the images and the type, size, and complexity of the root systems analyzed. Our study also demonstrated that machine learning algorithms can be trained on a synthetic library to improve the estimation of several root system traits. Overall, our analysis is a call to caution when using automatic root image analysis tools. If a thorough calibration is not performed on the dataset of interest, unexpected errors might arise, especially for large and complex root images. To facilitate such calibration, both the image library and the different codes used in the study have been made available to the community.

NetBenchmark: a bioconductor package for reproducible benchmarks of gene regulatory network inference

BACKGROUND

In the last decade, a great number of methods for reconstructing gene regulatory networks from expression data have been proposed. However, very few tools and datasets allow to evaluate accurately and reproducibly those methods. Hence, we propose here a new tool, able to perform a systematic, yet fully reproducible, evaluation of transcriptional network inference methods.

RESULTS

Our open-source and freely available Bioconductor package aggregates a large set of tools to assess the robustness of network inference algorithms against different simulators, topologies, sample sizes and noise intensities.

CONCLUSIONS

The benchmarking framework that uses various datasets highlights the specialization of some methods toward network types and data. As a result, it is possible to identify the techniques that have broad overall performances.

Predictive regulatory models in Drosophila melanogaster by integrative inference of transcriptional networks

Gaining insights on gene regulation from large-scale functional data sets is a grand challenge in systems biology. In this article, we develop and apply methods for transcriptional regulatory network inference from diverse functional genomics data sets and demonstrate their value for gene function and gene expression prediction. We formulate the network inference problem in a machine-learning framework and use both supervised and unsupervised methods to predict regulatory edges by integrating transcription factor (TF) binding, evolutionarily conserved sequence motifs, gene expression, and chromatin modification data sets as input features. Applying these methods to Drosophila melanogaster, we predict ∼300,000 regulatory edges in a network of ∼600 TFs and 12,000 target genes. We validate our predictions using known regulatory interactions, gene functional annotations, tissue-specific expression, protein–protein interactions, and three-dimensional maps of chromosome conformation. We use the inferred network to identify putative functions for hundreds of previously uncharacterized genes, including many in nervous system development, which are independently confirmed based on their tissue-specific expression patterns. Last, we use the regulatory network to predict target gene expression levels as a function of TF expression, and find significantly higher predictive power for integrative networks than for motif or ChIP-based networks. Our work reveals the complementarity between physical evidence of regulatory interactions (TF binding, motif conservation) and functional evidence (coordinated expression or chromatin patterns) and demonstrates the power of data integration for network inference and studies of gene regulation at the systems level.

[Family environment and dental health disparities among urban children in Burkina Faso]

BACKGROUND

Dental caries is the most common multifactorial disease in children and has substantial negative impact on daily life. In sub-Saharan Africa, few data are available on the relationship between dental caries and the social and family environment of children. The objectives of the present study were firstly to assess the level of prevalence and severity of dental caries of children in Ouagadougou, the capital city of Burkina Faso and secondly to determine whether or not individual factors, family and living conditions are linked with dental health disparities within the population.

METHODS

Interview and clinical data were obtained from a household-based cross-sectional survey. A two-stage stratified sampling technique was applied in four areas of Ouagadougou representing different stages of urbanization.

RESULTS

The final study population included 1606 children aged 6-12 years. For the overall group the total caries prevalence rate was 48.2%. Results showed that the dental health status of the mother, social integration of the householder and socioeconomic level of the household were associated with the dental health of children. Disparities in dental health were prominent; poor dental health was relatively frequent in children from households poorly integrated into social networks with rather acceptable standard in terms of material wealth.

CONCLUSION

Our study showed that individual factors as well as family-related and environmental factors had an influence on their caries experience. The rapidly changing lifestyle affects oral health and the burden of oral diseases is expected to increase initially in people of upper classes and later in disadvantaged people. Disease prevention focussing on common risk factors of chronic diseases should be enhanced. In addition, the accessibility of quality fluoride products (e.g. toothpaste, salt, water) should be facilitated as soon as possible.

Total fuel-cycle analysis of heavy-duty vehicles using biofuels and natural gas-based alternative fuels

Heavy-duty vehicles (HDVs) present a growing energy and environmental concern worldwide. These vehicles rely almost entirely on diesel fuel for propulsion and create problems associated with local pollution, climate change, and energy security. Given these problems and the expected global expansion of HDVs in transportation sectors, industry and governments are pursuing biofuels and natural gas as potential alternative fuels for HDVs. Using recent lifecycle datasets, this paper evaluates the energy and emissions impacts of these fuels in the HDV sector by conducting a total fuel-cycle (TFC) analysis for Class 8 HDVs for six fuel pathways: (1) petroleum to ultra low sulfur diesel; (2) petroleum and soyoil to biodiesel (methyl soy ester); (3) petroleum, ethanol, and oxygenate to e-diesel; (4) petroleum and natural gas to Fischer-Tropsch diesel; (5) natural gas to compressed natural gas; and (6) natural gas to liquefied natural gas. TFC emissions are evaluated for three greenhouse gases (GHGs) (carbon dioxide, nitrous oxide, and methane) and five other pollutants (volatile organic compounds, carbon monoxide, nitrogen oxides, particulate matter, and sulfur oxides), along with estimates of total energy and petroleum consumption associated with each of the six fuel pathways. Results show definite advantages with biodiesel and compressed natural gas for most pollutants, negligible benefits for e-diesel, and increased GHG emissions for liquefied natural gas and Fischer-Tropsch diesel (from natural gas).

Identification of functional elements and regulatory circuits by Drosophila modENCODE

To gain insight into how genomic information is translated into cellular and developmental programs, the Drosophila model organism Encyclopedia of DNA Elements (modENCODE) project is comprehensively mapping transcripts, histone modifications, chromosomal proteins, transcription factors, replication proteins and intermediates, and nucleosome properties across a developmental time course and in multiple cell lines. We have generated more than 700 data sets and discovered protein-coding, noncoding, RNA regulatory, replication, and chromatin elements, more than tripling the annotated portion of the Drosophila genome. Correlated activity patterns of these elements reveal a functional regulatory network, which predicts putative new functions for genes, reveals stage- and tissue-specific regulators, and enables gene-expression prediction. Our results provide a foundation for directed experimental and computational studies in Drosophila and related species and also a model for systematic data integration toward comprehensive genomic and functional annotation.

minet: A R/Bioconductor package for inferring large transcriptional networks using mutual information

Results

This paper presents the R/Bioconductor package minet (version 1.1.6) which provides a set of functions to infer mutual information networks from a dataset. Once fed with a microarray dataset, the package returns a network where nodes denote genes, edges model statistical dependencies between genes and the weight of an edge quantifies the statistical evidence of a specific (e.g transcriptional) gene-to-gene interaction. Four different entropy estimators are made available in the package minet (empirical, Miller-Madow, Schurmann-Grassberger and shrink) as well as four different inference methods, namely relevance networks, ARACNE, CLR and MRNET. Also, the package integrates accuracy assessment tools, like F-scores, PR-curves and ROC-curves in order to compare the inferred network with a reference one.

Conclusion

The package minet provides a series of tools for inferring transcriptional networks from microarray data. It is freely available from the Comprehensive R Archive Network (CRAN) as well as from the Bioconductor website.

Energy use and emissions from marine vessels: a total fuel life cycle approach

Regional and global air pollution from marine transportation is a growing concern. In discerning the sources of such pollution, researchers have become interested in tracking where along the total fuel life cycle these emissions occur. In addition, new efforts to introduce alternative fuels in marine vessels have raised questions about the energy use and environmental impacts of such fuels. To address these issues, this paper presents the Total Energy and Emissions Analysis for Marine Systems (TEAMS) model. TEAMS can be used to analyze total fuel life cycle emissions and energy use from marine vessels. TEAMS captures "well-to-hull" emissions, that is, emissions along the entire fuel pathway, including extraction, processing, distribution, and use in vessels. TEAMS conducts analyses for six fuel pathways: (1) petroleum to residual oil, (2) petroleum to conventional diesel, (3) petroleum to low-sulfur diesel, (4) natural gas to compressed natural gas, (5) natural gas to Fischer-Tropsch diesel, and (6) soybeans to biodiesel. TEAMS calculates total fuel-cycle emissions of three greenhouse gases (carbon dioxide, nitrous oxide, and methane) and five criteria pollutants (volatile organic compounds, carbon monoxide, nitrogen oxides, particulate matter with aerodynamic diameters of 10 microm or less, and sulfur oxides). TEAMS also calculates total energy consumption, fossil fuel consumption, and petroleum consumption associated with each of its six fuel cycles. TEAMS can be used to study emissions from a variety of user-defined vessels. This paper presents TEAMS and provides example modeling results for three case studies using alternative fuels: a passenger ferry, a tanker vessel, and a container ship.

Effects of storage and reperfusion oxygen content on substrate metabolism in the isolated rat lung

BACKGROUND

Lung transplantation requires a period of storage and ischemia; we examined the largely unknown effects of that period on intermediary metabolism.

METHODS

Two groups of isolated rat lung blocks (n = 16 each) were flushed with Euro-Collins solution and harvested. The lung blocks were immediately ventilated and either perfused for 30 minutes with an erythrocyte-based solution containing carbon 13 labeled substrates (group 1) or stored for 6 hours at 1 degree C and then reperfused (group 2). Half of each group was reperfused at a physiologic Po2 the other half at high Po2. Analysis of carbon 13 isotopomers was performed to determine substrate utilization through aerobic pathways in lung tissue.

RESULTS

Lungs from both groups oxidized all major substrates. The contribution of fatty acids to acetylcoenzyme acid oxidized in the citric acid cycle was significantly higher in group 2 than in group 1 (31.3% +/- 2.2% versus 22.0% +/- 2.1%, p < 0.05). Perfusate Po2 did not affect substrate preference. Gas exchange was worse in stored lungs.

CONCLUSIONS

After a period of hypothermic ischemia and storage, substrate preference in lung tissue exhibits a switch towards fatty acids. As fatty acid oxidation occurring after ischemia is deleterious in other organs, strategies to inhibit this process in stored lungs may warrant further investigation.

[Compensation in leg length inequality with orthopedic shoe measures]

There are three different methods of compensating for differences in leg length. The first is the construction of special shoes, which is adequate for differences of up to about 3 cm. The heels can be either higher or lower, or a cork sole 5-10 mm thick can be incorporated, the shaft made higher, and supplementary features, such as aids to push-off, can also be implemented. The second method is the wearing of the classic orthopedic boot or shoe, in which the necessary compensation for the shorter leg is incorporated as a part of the orthopedic footwear. The third method is the construction of a shoe within a shoe, for which different designs have crystallized out for the five groups presented. All designs incorporate leather, the tried and tested material, next to the skin. Stabilizing components are made of fiberglass-reinforced synthetic resin or Thermoplast. New materials allow aesthetically acceptable orthopedic footwear. On average, such shoes are 25% lighter than conventional orthopedic boots. The stability and wear-resistance allow large perforations and open-toe designs, which has made it possible to solve the problem of ventilation.

Antigenic relationships of 14 treponemes demonstrated by immunofluorescence

Immunofluorescence was used as an aid in the antigenic grouping of 14 cultivable treponemes. Antisera were prepared versus each treponemal strain, and the antiglobulins were conjugated with fluorescein isothiocyanate. A common antigen-antibody system, detected in the strains studied, was removed by absorption of each conjugate with Reiter or Borrelia vincentii treponemes. Thus, five categories based on shared group-specific antigens were revealed. Serogroup I: Reiter, English Reiter, Kazan, Kazan numbers 2, 4, 5, and 8. Serogroup II: Nichols and Noguchi. Serogroup III: three oral treponemes, MRB, FM, and N-39. Serogroup IV: B. vincentii. Serogroup V: Treponema zuelzerae. The five serogroups apparently are related by an immunofluorescent common antigen.