Independent Validation Data Research Articles

Improving the prediction of arsenic contents in agricultural soils by combining the reflectance spectroscopy of soils and rice plants

Visible and near-infrared reflectance spectroscopy provides a beneficial tool for investigating soil heavy metal contamination. This study aimed to investigate mechanisms of soil arsenic prediction using laboratory based soil and leaf spectra, compare the prediction of arsenic content using soil spectra with that using rice plant spectra, and determine whether the combination of both could improve the prediction of soil arsenic content. A total of 100 samples were collected and the reflectance spectra of soils and rice plants were measured using a FieldSpec3 portable spectroradiometer (350–2500nm). After eliminating spectral outliers, the reflectance spectra were divided into calibration (n=62) and validation (n=32) data sets using the Kennard-Stone algorithm. Genetic algorithm (GA) was used to select useful spectral variables for soil arsenic prediction. Thereafter, the GA-selected spectral variables of the soil and leaf spectra were individually and jointly employed to calibrate the partial least squares regression (PLSR) models using the calibration data set. The regression models were validated and compared using independent validation data set. Furthermore, the correlation coefficients of soil arsenic against soil organic matter, leaf arsenic and leaf chlorophyll were calculated, and the important wavelengths for PLSR modeling were extracted. Results showed that arsenic prediction using the leaf spectra (coefficient of determination in validation, Rv2=0.54; root mean square error in validation, RMSEv=12.99mgkg−1; and residual prediction deviation in validation, RPDv=1.35) was slightly better than using the soil spectra (Rv2=0.42, RMSEv=13.35mgkg−1, and RPDv=1.31). However, results also showed that the combinational use of soil and leaf spectra resulted in higher arsenic prediction (Rv2=0.63, RMSEv=11.94mgkg−1, RPDv=1.47) compared with either soil or leaf spectra alone. Soil spectral bands near 480, 600, 670, 810, 1980, 2050 and 2290nm, leaf spectral bands near 700, 890 and 900nm in PLSR models were important wavelengths for soil arsenic prediction. Moreover, soil arsenic showed significantly positive correlations with soil organic matter (r=0.62, p<0.01) and leaf arsenic (r=0.77, p<0.01), and a significantly negative correlation with leaf chlorophyll (r=−0.67, p<0.01). The results showed that the prediction of arsenic contents using soil and leaf spectra may be based on their relationships with soil organic matter and leaf chlorophyll contents, respectively. Although RPD of 1.47 was below the recommended RPD of >2 for soil analysis, arsenic prediction in agricultural soils can be improved by combining the leaf and soil spectra.

Detailed dynamic land cover mapping of Chile: Accuracy improvement by integrating multi-temporal data

Abstract Stretching over 4300 km north to south, Chile is a special country with complicated landscapes and rich biodiversity. Accurate and timely updated land cover map of Chile in detailed classification categories is highly demanded for many applications. A conclusive land cover map integrated from multi-seasonal mapping results and a seasonal dynamic map series were produced using Landsat 8 imagery mainly acquired in 2013 and 2014, supplemented by MODIS Enhanced Vegetation Index data, high resolution imagery on Google Earth, and Shuttle Radar Topography Mission DEM data. The overall accuracy is 80% for the integrated map at level 1 and 73% for level 2 based on independent validation data. Accuracies for seasonal map series were also assessed, which is around 70% for each season, greatly improved by integrated use of seasonal information. The importance of growing season imagery was proved in our analysis. The analysis of the spatial variation of accuracies among various ecoregions indicates that the accuracy for land cover mapping decreases gradually from central Chile to both north and south. More mapping efforts for those ecoregions are needed. In addition, the training dataset includes sample points spatially distributed in the whole country, temporally distributed throughout the year, and categorically encompassing all land cover types. This training dataset constitutes a universal sample set allowing us to map land cover from any Landsat 8 image acquired in Chile without additional ad hoc training sample collection.

Breast cancer subtype predictors revisited: from consensus to concordance?

BackgroundAt the molecular level breast cancer comprises a heterogeneous set of subtypes associated with clear differences in gene expression and clinical outcomes. Single sample predictors (SSPs) are built via a two-stage approach consisting of clustering and subtype predictor construction based on the cluster labels of individual cases. SSPs have been criticized because their subtype assignments for the same samples were only moderately concordant (Cohen’s κ<0.6).MethodsWe propose a semi-supervised approach where for five datasets, consensus sets were constructed consisting of those samples that were concordantly subtyped by a number of different predictors. Next, nine subtype predictors - three SSPs, three subtype classification models (SCMs) and three novel rule-based predictors based on the St. Gallen surrogate intrinsic subtype definitions (STGs) - were constructed on the five consensus sets and their associated consensus subtype labels. The predictors were validated on a compendium of over 4,000 uniformly preprocessed Affymetrix microarrays. Concordance between subtype predictors was assessed using Cohen’s kappa statistic.ResultsIn this standardized setup, subtype predictors of the same type (either SCM, SSP, or STG) but with a different gene list and/or consensus training set were associated with almost perfect levels of agreement (median κ>0.8). Interestingly, for a given predictor type a change in consensus set led to higher concordance than a change to another gene list. The more challenging scenario where the predictor type, gene list and training set were all different resulted in predictors with only substantial levels of concordance (median κ=0.74) on independent validation data.ConclusionsOur results demonstrate that for a given subtype predictor type stringent standardization of the preprocessing stage, combined with carefully devised consensus training sets, leads to predictors that show almost perfect levels of concordance. However, predictors of a different type are only substantially concordant, despite reaching almost perfect levels of concordance on training data.Electronic supplementary materialThe online version of this article (doi:10.1186/s12920-016-0185-6) contains supplementary material, which is available to authorized users.

Retrieval of Wind Stress at the Ocean Surface From AltiKa Measurements

Wind stress is an important parameter in generating the ocean surface currents. Here, for the first time, we directly estimate this parameter at the ocean surface using all the observations from AltiKa and the accompanying radiometer that affect the wind stress estimates and radar signal propagation through the atmosphere. For this purpose, we used an artificial neural network approach using in situ estimates as the dependent parameter and satellite records as the independent parameters. In the absence of sufficient in situ measurements, wind stress is generally inferred from wind speed at 10-m height obtained from spaceborne scatterometers and altimeters which has been extrapolated to the surface to estimate stress, assuming certain atmospheric conditions that are rarely correct. Hence, we obtained this parameter directly at the ocean surface from satellite records. The estimates for the independent validation data set have a standard deviation of the difference between the in situ and satellite-derived values of 0.032 Nm−2 with Pearson's correlation coefficient of 0.96 significant at 99% confidence level.

Index Test Method for Estimating the Effective Preconsolidation Stress in Clay Deposits

AbstractThe effective preconsolidation stress (σp′) of clay is classically determined from one-dimensional consolidation tests on undisturbed samples but a first-order approximate value can be estimated from its plasticity and water content characteristics. In this paper, initially a twofold simple empirical model for predicting σp′ that bifurcates at an overconsolidation ratio (OCR) of 3 is developed, and then its validity and generality are evaluated using an external (independent) validation data set that includes 500 records from 50 different sites. The proposed model is accompanied by a discriminant function that uses water content and plasticity characteristics to separate soils with OCR<3 (contractive) versus soils with OCR≥3 (dilative). The results of applying the new and existing simple empirical models to the validation data set indicate that the predictive capability of the new model is quite superior to prior existing approaches that have unacceptable performance.

Predicting Occurrence of Spine Surgery Complications Using "Big Data" Modeling of an Administrative Claims Database.

Postoperative metrics are increasingly important in determining standards of quality for physicians and hospitals. Although complications following spinal surgery have been described, procedural and patient variables have yet to be incorporated into a predictive model of adverse-event occurrence. We sought to develop a predictive model of complication occurrence after spine surgery. We used longitudinal prospective data from a national claims database and developed a predictive model incorporating complication type and frequency of occurrence following spine surgery procedures. We structured our model to assess the impact of features such as preoperative diagnosis, patient comorbidities, location in the spine, anterior versus posterior approach, whether fusion had been performed, whether instrumentation had been used, number of levels, and use of bone morphogenetic protein (BMP). We assessed a variety of adverse events. Prediction models were built using logistic regression with additive main effects and logistic regression with main effects as well as all 2 and 3-factor interactions. Least absolute shrinkage and selection operator (LASSO) regularization was used to select features. Competing approaches included boosted additive trees and the classification and regression trees (CART) algorithm. The final prediction performance was evaluated by estimating the area under a receiver operating characteristic curve (AUC) as predictions were applied to independent validation data and compared with the Charlson comorbidity score. The model was developed from 279,135 records of patients with a minimum duration of follow-up of 30 days. Preliminary assessment showed an adverse-event rate of 13.95%, well within norms reported in the literature. We used the first 80% of the records for training (to predict adverse events) and the remaining 20% of the records for validation. There was remarkable similarity among methods, with an AUC of 0.70 for predicting the occurrence of adverse events. The AUC using the Charlson comorbidity score was 0.61. The described model was more accurate than Charlson scoring (p < 0.01). We present a modeling effort based on administrative claims data that predicts the occurrence of complications after spine surgery. We believe that the development of a predictive modeling tool illustrating the risk of complication occurrence after spine surgery will aid in patient counseling and improve the accuracy of risk modeling strategies.

Improving essential fish habitat designation to support sustainable ecosystem-based fisheries management

A major limitation to fully integrated ecosystem based fishery management approaches is a lack of information on the spatial distribution of marine species and the environmental conditions shaping these distributions. This is particularly problematic for deep-water species that are hard to sample and are data poor. The past decade has seen the rapid development of a suite of advanced species distribution, or ecological niche, modelling approaches developed specifically to support efficient and targeted management. However, model performance can vary significantly and the appropriateness of which methods are best for a given application remains questionable. Species distribution models were developed for three commercially valuable Hawaiian deep-water eteline snappers: Etelis coruscans (Onaga), Etelis carbunculus (Ehu) and Pristipomoides filamentosus (Opakapaka). Distributional data for these species was relatively sparse. To identify the best method, model performance and distributional accuracy was assessed and compared using three approaches: Generalised Additive Models (GAM), Boosted Regression Trees (BRT) and Maximum Entropy (MaxEnt). Independent spatial validation data found MaxEnt consistently provided better model performance with ‘good’ model predictions (AUC =>0.8). Each species was influenced by a unique combination of environmental conditions, with depth, terrain (slope) and substrate (low lying unconsolidated sediments), being the three most important in shaping their distributions. Sustainable fisheries management, marine spatial planning and environmental decision support systems rely on an understanding species distribution patterns and habitat linkages. This study demonstrates that predictive species distribution modelling approaches can be used to accurately model and map sparse species distribution data across marine landscapes. The approach used herein was found to be an accurate tool to delineate species distributions and associated habitat linkages, account for species-specific differences and support sustainable ecosystem-based management.

Historical Maps from Modern Images: Using Remote Sensing to Model and Map Century-Long Vegetation Change in a Fire-Prone Region.

Understanding the age structure of vegetation is important for effective land management, especially in fire-prone landscapes where the effects of fire can persist for decades and centuries. In many parts of the world, such information is limited due to an inability to map disturbance histories before the availability of satellite images (~1972). Here, we describe a method for creating a spatial model of the age structure of canopy species that established pre-1972. We built predictive neural network models based on remotely sensed data and ecological field survey data. These models determined the relationship between sites of known fire age and remotely sensed data. The predictive model was applied across a 104,000 km2 study region in semi-arid Australia to create a spatial model of vegetation age structure, which is primarily the result of stand-replacing fires which occurred before 1972. An assessment of the predictive capacity of the model using independent validation data showed a significant correlation (rs = 0.64) between predicted and known age at test sites. Application of the model provides valuable insights into the distribution of vegetation age-classes and fire history in the study region. This is a relatively straightforward method which uses widely available data sources that can be applied in other regions to predict age-class distribution beyond the limits imposed by satellite imagery.

Validation Study: Response-Predictive Gene Expression Profiling of Glioma Progenitor Cells In Vitro.

BackgroundIn a previous publication we introduced a novel approach to identify genes that hold predictive information about treatment outcome. A linear regression model was fitted by using the least angle regression algorithm (LARS) with the expression profiles of a construction set of 18 glioma progenitor cells enhanced for brain tumor initiating cells (BTIC) before and after in vitro treatment with the tyrosine kinase inhibitor Sunitinib. Profiles from treated progenitor cells allowed predicting therapy-induced impairment of proliferation in vitro. Prediction performance was validated in leave one out cross validation.MethodsIn this study, we used an additional validation set of 18 serum-free short-term treated in vitro cell cultures to test the predictive properties of the signature in an independent cohort. We assessed proliferation rates together with transcriptome-wide expression profiles after Sunitinib treatment of each individual cell culture, following the methods of the previous publication.ResultsWe confirmed treatment-induced expression changes in our validation set, but our signature failed to predict proliferation inhibition. Neither re-calculation of the combined dataset with all 36 BTIC cultures nor separation of samples into TCGA subclasses did generate a proliferation prediction.ConclusionAlthough the gene signature published from our construction set exhibited good prediction accuracy in cross validation, we were not able to validate the signature in an independent validation data set. Reasons could be regression to the mean, the moderate numbers of samples, or too low differences in the response to proliferation inhibition in the validation set. At this stage and based on the presented results, we conclude that the signature does not warrant further developmental steps towards clinical application.

Adequate sample size for developing prediction models is not simply related to events per variable

ObjectivesThe choice of an adequate sample size for a Cox regression analysis is generally based on the rule of thumb derived from simulation studies of a minimum of 10 events per variable (EPV). One simulation study suggested scenarios in which the 10 EPV rule can be relaxed. The effect of a range of binary predictors with varying prevalence, reflecting clinical practice, has not yet been fully investigated. Study Design and SettingWe conducted an extended resampling study using a large general-practice data set, comprising over 2 million anonymized patient records, to examine the EPV requirements for prediction models with low-prevalence binary predictors developed using Cox regression. The performance of the models was then evaluated using an independent external validation data set. We investigated both fully specified models and models derived using variable selection. ResultsOur results indicated that an EPV rule of thumb should be data driven and that EPV ≥ 20 ​ generally eliminates bias in regression coefficients when many low-prevalence predictors are included in a Cox model. ConclusionHigher EPV is needed when low-prevalence predictors are present in a model to eliminate bias in regression coefficients and improve predictive accuracy.

Predicting manual arm strength: A direct comparison between artificial neural network and multiple regression approaches

In ergonomics, strength prediction has typically been accomplished using linked-segment biomechanical models, and independent estimates of strength about each axis of the wrist, elbow and shoulder joints. It has recently been shown that multiple regression approaches, using the simple task-relevant inputs of hand location and force direction, may be a better method for predicting manual arm strength (MAS) capabilities. Artificial neural networks (ANNs) also serve as a powerful data fitting approach, but their application to occupational biomechanics and ergonomics is limited. Therefore, the purpose of this study was to perform a direct comparison between ANN and regression models, by evaluating their ability to predict MAS with identical sets of development and validation MAS data. Multi-directional MAS data were obtained from 95 healthy female participants at 36 hand locations within the reach envelope. ANN and regression models were developed using a random, but identical, sample of 85% of the MAS data (n=456). The remaining 15% of the data (n=80) were used to validate the two approaches. When compared to the development data, the ANN predictions had a much higher explained variance (90.2% vs. 66.5%) and much lower RMSD (9.3N vs. 17.2N), vs. the regression model. The ANN also performed better with the independent validation data (r2=78.6%, RMSD=15.1) compared to the regression approach (r2=65.3%, RMSD=18.6N). These results suggest that ANNs provide a more accurate and robust alternative to regression approaches, and should be considered more often in biomechanics and ergonomics evaluations.

Determination of rice root density at the field level using visible and near-infrared reflectance spectroscopy

To improve our understanding of biomass allocation and soil carbon cycling in paddy fields, information on the root biomass of rice is fundamental. The commonly used conventional methods to study root biomass are difficult and time-consuming. In this study, visible and near-infrared (Vis–NIR) reflectance spectroscopy (350–2500nm) was evaluated for the rapid analysis of rice root density from the flat, horizontal surface of a soil core section. A total of 123 intact soil cores (0–40cm depth, with a 8.4cm diameter) were collected from paddy fields in Yujiang, China, and the Vis–NIR reflectance was measured in the laboratory at two depths (5 and 10cm). Three multivariate regression methods (principal component regression, PCR; partial least square regression, PLSR; and support vector machine regression, SVMR) were used to develop models to predict root density, and these models were compared to determine the one with the most accurate predictions. Based on the comparisons with both cross-validation and independent validation data sets, the SVMR model outperformed the PCR and PLSR models. The predictions of root density with the SVMR model were more accurate (coefficient of determination [R2]=0.88; root mean square error [RMSE]=4.28; ratio of standard deviation to RMSE [RPD]=2.83; ratio of performance to inter-quartile distance [RPIQ]=3.23; Slope=0.80) than those with the PCR model (R2=0.81; RMSE=5.58; RPD=2.17; RPIQ=2.47; Slope=0.74) or the PLSR model (R2=0.82; RMSE=5.22; RPD=2.32; RPIQ=2.65; Slope=0.76), based on 73 independent validation samples. In conclusion, the Vis–NIR spectra acquired from the intact soil cores were used to accurately predict rice root density. Therefore, Vis–NIR spectroscopy combined with SVMR calibrations has the potential to detect root densities in paddy soils under field conditions.

Boomerang: A method for recursive reclassification.

While there are many validated prognostic classifiers used in practice, often their accuracy is modest and heterogeneity in clinical outcomes exists in one or more risk subgroups. Newly available markers, such as genomic mutations, may be used to improve the accuracy of an existing classifier by reclassifying patients from a heterogenous group into a higher or lower risk category. The statistical tools typically applied to develop the initial classifiers are not easily adapted toward this reclassification goal. In this article, we develop a new method designed to refine an existing prognostic classifier by incorporating new markers. The two-stage algorithm called Boomerang first searches for modifications of the existing classifier that increase the overall predictive accuracy and then merges to a prespecified number of risk groups. Resampling techniques are proposed to assess the improvement in predictive accuracy when an independent validation data set is not available. The performance of the algorithm is assessed under various simulation scenarios where the marker frequency, degree of censoring, and total sample size are varied. The results suggest that the method selects few false positive markers and is able to improve the predictive accuracy of the classifier in many settings. Lastly, the method is illustrated on an acute myeloid leukemia data set where a new refined classifier incorporates four new mutations into the existing three category classifier and is validated on an independent data set.

Prediction of soil surface salinity in arid region of central Iran using auxiliary variables and genetic programming

ABSTRACTSpatial information on soil salinity is increasingly needed for decision making and management practices in arid environments. In this article, we attempted to investigate soil salinity variation via a digital soil mapping approach and genetic programming in an arid region, Chah-Afzal, located in central Iran. A grid sampling strategy with 2-km distance was used. In total, 180 soil surface samples were collected and then analyzed. A symbolic regression was then adopted to correlate electrical conductivity (ECe) with a suite of auxiliary data including predicted maps of apparent electrical conductivity (vertical: ECav and horizontal: ECah), Landsat spectral data and terrain attributes derived from a digital elevation model. The accuracy of the genetic programming model was evaluated using root mean square error (RMSE), mean error (ME), and coefficient of determination (R2) based on an independent validation data set (20% of database or thirty soil samples). In general, results showed that ECah had the strongest influence on the prediction of soil salinity followed by salinity index wetness index, Landsat Band 3, multi-resolution valley bottom flatness index, elevation, and normalized difference vegetation index. Furthermore, results indicated that the genetic programming model predicted ECe over the study area accurately (R2 = 0.87, ME = −1.04 and RMSE = 16.36 dSm−1). Overall, it is suggested that similar applications of this technique could be used for mapping soil salinity in other arid regions of Iran.

Spatial accuracy measures of soft classification in land cover

GIScience 2016 Short Paper Proceedings Spatial accuracy measures of soft classification in land cover N. Tsutsumida 1 and A. Comber 2 Graduate School of Global Environmental Studies, Kyoto University Email: naru@kais.kyoto-u.ac.jp Department of Geography, University of Leeds Email: a.comber@leeds.ac.uk Abstract Accuracy of land cover maps is important for map users. The soft classification of land cover has been developed for avoiding mixed pixel problem, however the proportional map is traditionally assessed only by a global measure, such as R-squared and root mean square error (RMSE), lacking local information of accuracy. We developed a way of local measures of accuracy employed by a geographically weighted (GW) model. GW-Rsquared and GW- RMSE are locally assessed a soft classification map of urban agglomeration as a case study. Lower accuracies are found at the edge of urban boundary surrounding the core of the urban area and such local information is valuable for a deeper understanding of spatial accuracy. 1. Introduction Land cover maps are important for those who are interested in climate change, biodiversity and anthropogenic impacts on terrestrial environments and the accuracy of the map is an important consideration. Traditionally land cover maps classified as categorized classes (hard classification) are assessed by building a confusion matrix that compares predicted and observed classes, with predicted classes derived from the classification and observed classes from independent validation data. Measures of user, producer and overall accuracy and kappa index are calculated from the matrix. The reliability of land cover data classified using continuous measures such as fuzzy set memberships (soft classification) is frequently assessed using measures such as R-squared and root mean square error (RMSE) (Chen et al. 2010; Tsutsumida et al. 2016; Yuan et al. 2008). However these measures only provide global measures of reliability and accuracy, and they do not take spatial configuration into account. Local assessments would be valuable for a deeper understanding of spatial accuracy. 2. Background Spatial accuracy assessments for hard classification of land use and land cover have been considered by some previous studies (Foody 2005; Pontius et al. 2011). In particular, geographically weighted (GW) logistic regression model have recently been developed (Comber et al. 2012; Comber 2013). These generate local confusion matrices at discrete location in the study area and generate spatially distributed estimates (surfaces) of user, producer and overall accuracy. However, little work has focused on spatially distributed accuracy measures for soft classifications. In this study we develop the spatial accuracy measures of soft classification by determining R-squared and RMSE locally. A GW model is applied to develop such measures spatially. 3. Materials A map of fractional impervious surface area (ISA) in Jakarta metropolitan areas, the biggest urban agglomeration in Indonesia, in 2012 was used in this study (Figure 1). This map was

Validation of Breast Cancer Survival Prediction Model with SEER Database

Objective: The accurate estimation of outcome in postoperative breast cancer patients is an essential component of the individualized treatment, decision-making, and patient counseling processes. The disease outcome and prognosis of breast cancer patients may vary according to geographic and ethnic factors. To clarify this topic, we created a new prognostic and predictive model for breast cancer patients, based on clinical and pathological variables. Study design and setting: Clinical and pathological data were collected from 1587 patients with breast cancer who underwent surgical intervention. A survival prediction model was used to allow the analysis of the optimal combination of variables. The area under the receiver operating characteristic (ROC) curve, as applied to an independent validation data set, was used as the measure of accuracy. Results were assessed by comparing the area under the ROC curve with the SEER database. Results: Our predictive model of survival predicted disease outcome for individual patients with breast cancer. The comparison between our predictive model and SEER databases showed that our model underestimated outcome in the SEER cohort and that the SEER model overestimated outcome in our breast cancer patients. Conclusion: Our model may present an alternative as personalized prognostic tool for breast cancer patients. Decision regarding the survival prediction should take every consideration about regional and racial factors into account.

Mapping the Gene Expression Diversity Across Hematological and Lymphoid Malignancies

Gene expression profiles enable global analysis that can interrogate the activity patterns of various cellular pathways across biological conditions. Indeed this approach has generated data across numerous patient populations over the past decades allowing molecular stratification of disease, including hematological and lymphoid malignancies. An emerging theme from cancer genomics studies is the remarkable similarity between specific cancers of different lineages. For example, particular subtypes of bladder cancer resemble breast and lung tumors despite their different tissue of origin. Whether the same may hold true across hematological and lymphoid cancers is currently unknown. In normal development, cells commit to their lineage by activation of densely interconnected transcription factors (TFs), or TF modules, in a series of decision points at which a choice is made between alternative lineage fates. Their mutual exclusivity can be used for discovery of key genes of both normal and malignant hematopoiesis. Importantly, TF translocations represent frequent genetic events in hematological cancer.We harnessed computational methods to organize and characterize samples from 9544 distinct hematological and lymphoid cancer patients, healthy donors and pre-malignant stages generating a pan-cancer resource for interrogating their molecular states. A central part of the resource is a curated transcriptome dataset that we provide across 37 different disease subtypes as an interactive online resource (http://compbio.uta.fi/hemap/). The dimensionality reduction method known as t-Distributed Stochastic Neighbor Embedding (t-SNE) achieved optimal placement of highly similar samples at close proximity in two dimensions, enabling a biologically meaningful visualization of the data set as well as comparative analysis based on gene signatures, drug target expression and regulatory network state. For patient stratification, unsupervised clustering in t-SNE space yielded comparable performance to robust and reproducible classifiers. We further demonstrate with multilevel data from The Cancer Genome Atlas that new samples can be included in context of the existing patient profiles. Data integration highlights the molecular architecture that relates to the clinical and genetic features of the samples studied, revealing new insight on molecular phenotypes that distinguish AML samples that lack a subtype based on current clinical stratification. Finally, we used the resource to provide a roadmap for candidate drug therapies and quantify the regulatory network alterations across hematological malignancies.The divergence of cancer regulatory networks from the reference healthy cell states and mutually exclusive patterns of TF expression that are specific to the different malignancies pave the way towards therapies targeting the cancer epigenome and characterization of downstream targets of TF-fusions or aberrant enhancer usage, as exemplified with independent validation data at the IRX1 and ERG loci. DisclosuresNo relevant conflicts of interest to declare.

Comparison of six generalized linear models for occurrence of lightning-induced fires in northern Daxing’an Mountains, China

The occurrence of lightning-induced forest fires during a time period is count data featuring over-dispersion (i.e., variance is larger than mean) and a high frequency of zero counts. In this study, we used six generalized linear models to examine the relationship between the occurrence of lightning-induced forest fires and meteorological factors in the Northern Daxing’an Mountains of China. The six models included Poisson, negative binomial (NB), zero-inflated Poisson (ZIP), zero-inflated negative binomial (ZINB), Poisson hurdle (PH), and negative binomial hurdle (NBH) models. Goodness-of-fit was compared and tested among the six models using Akaike information criterion (AIC), sum of squared errors, likelihood ratio test, and Vuong test. The predictive performance of the models was assessed and compared using independent validation data by the data-splitting method. Based on the model AIC, the ZINB model best fitted the fire occurrence data, followed by (in order of smaller AIC) NBH, ZIP, NB, PH, and Poisson models. The ZINB model was also best for predicting either zero counts or positive counts (≥1). The two Hurdle models (PH and NBH) were better than ZIP, Poisson, and NB models for predicting positive counts, but worse than these three models for predicting zero counts. Thus, the ZINB model was the first choice for modeling the occurrence of lightning-induced forest fires in this study, which implied that the excessive zero counts of lightning-induced fires came from both structure and sampling zeros.

A longitudinal biomarker for the extent of skin disease in patients with diffuse cutaneous systemic sclerosis.

To define a pharmacodynamic biomarker based on gene expression in skin that would provide a biologic measure of the extent of disease in patients with diffuse cutaneous systemic sclerosis (dcSSc) and could be used to monitor skin disease longitudinally. Skin biopsy specimens obtained from a cohort of patients with dcSSc (including longitudinal specimens) were analyzed by microarray. Expression of genes correlating with the modified Rodnan skin thickness score (MRSS) were examined for change over time using a NanoString platform, and a generalized estimating equation (GEE) was used to define and validate longitudinally measured pharmacodynamic biomarkers composed of multiple genes. Microarray analysis of genes parsed to include only those correlating with the MRSS revealed prominent clusters of profibrotic/transforming growth factor β-regulated, interferon-regulated/proteasome, macrophage, and vascular marker genes. Using genes changing longitudinally with the MRSS, we defined 2 multigene pharmacodynamic biomarkers. The first was defined mathematically by applying a GEE to longitudinal samples. This modeling method selected cross-sectional THBS1 and longitudinal THBS1 and MS4A4A. The second model was based on a weighted selection of genes, including additional genes that changed statistically significantly over time: CTGF, CD163, CCL2, and WIF1. In an independent validation data set, biomarker levels calculated using both models correlated highly with the MRSS. Skin gene expression can be used effectively to monitor changes in SSc skin disease over time. We implemented 2 relatively simple models on a NanoString platform permitting highly reproducible assays that can be applied directly to samples from patients or collected as part of clinical trials.

Joint assimilation of Aquarius‐derived sea surface salinity and AVHRR‐derived sea surface temperature in an ocean general circulation model using SEEK filter: Implication for mixed layer depth and barrier layer thickness

AbstractSea surface salinity (SSS) from Aquarius mission and sea surface temperature (SST) from Advanced Very High Resolution Radiometer (AVHRR) for the years 2012–2014 are assimilated into the global Massachusetts Institute of Technology General Circulation Model (MITGCM). Investigation of the impact of assimilation of these two data sets on simulated mixed layer depth (MLD) and barrier layer thickness (BLT) forms the core of our study. The method of assimilation is the Singular Evolutive Extended Kalman (SEEK) filter. Several assimilation runs are performed. Single‐parameter assimilation, as well as joint assimilation, is conducted. To begin with, the model simulated SST and SSS are compared with independent Argo observations of these two parameters. Use of latitudinally varying error variances, which is a novel feature of our study, gives rise to the significant improvement in the simulation of SSS and SST. The best result occurs when joint assimilation is performed. Afterward, simulated MLD and BLT are compared with the same parameters derived from Argo observations forming an independent validation data set. Comparisons are performed both in temporal and spatial domains. Significant positive impact of assimilation is found in all the cases studied, and joint assimilation is found to outperform single‐parameter assimilation in each of the cases considered. It is found that simulations of MLD and BLT improve up to 24% and 29%, respectively, when a joint assimilation of SSS and SST is carried out.