Combining Random Forest and XGBoost Methods in Detecting Early and Mid-Term Winter Wheat Stripe Rust Using Canopy Level Hyperspectral Measurements

Appropriate modeling methods and feature selection algorithms must be selected to improve the accuracy of early and mid-term remote sensing detection of wheat stripe rust. In the current study, we explored the effectiveness of the random forest (RF) algorithm combined with the extreme gradient boosting (XGboost) method for early and mid-term wheat stripe rust detection based on the vegetation indices extracted from canopy level hyperspectral measurements. Initially, 21 vegetation indices that were related to the early and mid-term winter wheat stripe rust were calculated on the basis of canopy level hyperspectral reflectance. Subsequently, the optimal vegetation index combination for disease detection was determined using correlation analysis (CA) combined with RF algorithms. Then, the disease severity detection model of early and mid-term winter wheat stripe rust was constructed using XGBoost method based on the optimal vegetation index combination. For the evaluation and comparison of the initial results, three commonly used classification methods, namely, RF, backpropagation neural network (BPNN), and support vector machine (SVM), were utilized. The vegetation index combinations determined by the single CA algorithm were also used to construct detection models. Compared with the detection models based on the vegetation index combination obtained using the single CA algorithm, the overall accuracy of the four detection models based on the optimal vegetation index combination based on CA combined with RF algorithms increased by 16.1% (XGBoost), 9.7% (RF), 8.1% (SVM), and 8.1% (BPNN). Among the eight models, the XGBoost detection model based on the optimal vegetation index combination using CA combined with RF algorithms, CA-RF-XGBoost, achieved the highest overall accuracy of 87.1% and the highest kappa coefficient of 0.798. Our results indicate that the RF combined with XGBoost can improve the detection accuracy of early and mid-term winter wheat stripe rust effectively at canopy scale.

Controlling critical mistag-associated false discoveries in metagenetic data

Metagenetic methods are commonplace within ecological and environmental research. One concern with these methods is the phenomenon of critical mistagging, where sequences from one sample are erroneously inferred to have originated from another sample due to errors in the attachment, PCR replication or sequencing of sample-specific dual-index tags. For studies using PCR-based library preparation on large sample sizes, the most cost-effective approach to limiting mistag-associated false detections involves using an unsaturated Latin square dual-indexing design. This allows researchers to estimate mistagging rates during sequencing but the statistical procedures for filtering out detections using this mistag rate have received little attention. We propose a straightforward method to limit mistag-associated false discoveries during metabarcoding applications. We analyzed two Illumina metabarcoding datasets produced using unsaturated Latin square designs to explore the distribution of mistagged sequences across dual-index combinations on a per taxon basis. We tested these data for conformity to the assumptions that 1) mistagging follows a binomial distribution [i.e., X ~ B(n, p)] where p, the probability of a sequence being mistagged, varies minimally across taxa and 2) mistags are distributed uniformly across dual-index combinations. We provide R functions that estimate the 95th percentile of expected mistags per dual-index combination for each taxon under these assumptions. We show that mistagging rates were consistent across taxa within the datasets analyzed and that modelling mistagging as a binomial process with uniform distribution across dual-index combinations enabled robust control of mistag-associated false discoveries. We propose that this method of taxon-specific filtering of detections based on the maximum mistags expected per dual-index combination should be broadly accepted during metagenetic analysis, provided that experimental and control sequence abundances per taxon are strongly correlated. When this assumption is violated, data may be better fit by assuming that the distribution of mistags across combinations follows Poisson characteristics [i.e., X ~ Pois(𝜆)], with 𝜆 empirically estimated from the abundance distribution of mistags among control samples. We provide a second R function for this case, though we have yet to observe such a dataset. Both functions and demonstrations associated with this work are freely available at https://github.com/RTRichar/ModellingCriticalMistags.

Profibrotic circulating proteins and risk of early progressive renal decline in Type 2 Diabetes patients with and without albuminuria

<b>OBJECTIVE</b>: The role of fibrosis in early progressive renal decline in type 2 diabetes is unknown. Circulating WFDC2 (WAP four-disulfide core domain protein 2) and MMP-7 (Matrilysin) are postulated to be biomarkers of renal fibrosis. This study examined an association of circulating levels of these proteins with early progressive renal decline. <p><b>RESEARCH DESIGN AND METHODS</b>: Individuals with type 2 diabetes enrolled in the Joslin Kidney Study with eGFR ≥60 ml/min/1.73m² were followed for 6-12 years to ascertain fast early progressive renal decline defined as eGFR loss ≥5 ml/min/1.73m²/year. </p> <p><b>RESULTS</b>: A total of 1,181 individuals were studied: 681 without and 500 with albuminuria. Median eGFR and ACR at baseline were 97 ml/min/1.73m² and 24 mg/g, respectively. During follow-up, 152 individuals experienced fast early progressive renal decline: 6.9% in those with normoalbuminuria and 21% with albuminuria. In both subgroups risk of renal decline increased with increasing baseline levels of WFDC2 (p <0.0001) and MMP-7 (p <0.0001). After adjustment for relevant clinical characteristics and known biomarkers, an increase by one quartile in the Fibrosis Index (combination of levels of WFDC2 and MMP-7) was associated with higher risk of renal decline (OR 1.63; 95% CI 1.30-2.04). The association was similar and statistically significant among patients with and without albuminuria. </p> <p><b>CONCLUSIONS: </b>Elevation of circulating profibrotic proteins is associated with the development of early progressive renal decline in type 2 diabetes. This association is independent from albuminuria status and points to the importance of the fibrotic process in development of early renal decline. </p>

Profibrotic circulating proteins and risk of early progressive renal decline in Type 2 Diabetes patients with and without albuminuria

<b>OBJECTIVE</b>: The role of fibrosis in early progressive renal decline in type 2 diabetes is unknown. Circulating WFDC2 (WAP four-disulfide core domain protein 2) and MMP-7 (Matrilysin) are postulated to be biomarkers of renal fibrosis. This study examined an association of circulating levels of these proteins with early progressive renal decline. <p><b>RESEARCH DESIGN AND METHODS</b>: Individuals with type 2 diabetes enrolled in the Joslin Kidney Study with eGFR ≥60 ml/min/1.73m² were followed for 6-12 years to ascertain fast early progressive renal decline defined as eGFR loss ≥5 ml/min/1.73m²/year. </p> <p><b>RESULTS</b>: A total of 1,181 individuals were studied: 681 without and 500 with albuminuria. Median eGFR and ACR at baseline were 97 ml/min/1.73m² and 24 mg/g, respectively. During follow-up, 152 individuals experienced fast early progressive renal decline: 6.9% in those with normoalbuminuria and 21% with albuminuria. In both subgroups risk of renal decline increased with increasing baseline levels of WFDC2 (p <0.0001) and MMP-7 (p <0.0001). After adjustment for relevant clinical characteristics and known biomarkers, an increase by one quartile in the Fibrosis Index (combination of levels of WFDC2 and MMP-7) was associated with higher risk of renal decline (OR 1.63; 95% CI 1.30-2.04). The association was similar and statistically significant among patients with and without albuminuria. </p> <p><b>CONCLUSIONS: </b>Elevation of circulating profibrotic proteins is associated with the development of early progressive renal decline in type 2 diabetes. This association is independent from albuminuria status and points to the importance of the fibrotic process in development of early renal decline. </p>

A specific combination of dual index adaptors decreases the sensitivity of amplicon sequencing with the Illumina platform

Amplicon sequencing is a powerful approach in microbiome studies as it detects live organisms with high sensitivity. This approach determines the composition of sequence variants of marker genes using high-throughput DNA sequencers. The use of dual index adaptors is the fundamental technique for pooling DNA libraries for Illumina sequencers and is believed not to affect the results. However, here, we observed a decrease of sequence quality in samples containing a specific combination of indexes, namely N704 and S507 in Nextera kits, in multiple runs on the Illumina MiSeq sequencer operated in different facilities. This decrease was also observed when sequencing randomly fragmented DNA of Escherichia coli and was not observed when either individual adaptor was used. Each end of the DNA library with this index combination contains a complementary sequence motif, which potentially inhibits proper cluster generation and/or subsequent sequencing. Community analysis of the 16S and 18S rRNA amplicons using QIIME2 revealed significant decreases in α-diversity in the samples containing the N704/S507 index combination, resulting from loss of low-abundance sequence variants during denoising. Our data underscore the importance of quality validation of sequence reads in developing dual index techniques and suggest cautious interpretation of microbiome data containing low-quality sequence reads.

Retrospective Database Analysis of Treatment Patterns Among Patients with Pulmonary Arterial Hypertension

Introduction Release of the 2015 European Society of Cardiology (ESC)/European Respiratory Society (ERS) guidelines put increased emphasis on using combination therapy, either as upfront or sequential therapy among patients with pulmonary arterial hypertension (PAH). However, with these recommendations and the therapy advances made in the last several years, little is known on the real-world treatment patterns among patients with PAH, particularly before and after publication of the 2015 ESC/ERS guidelines. Methods This was a retrospective study of adult commercial and Medicare Advantage with Part D (MAPD) enrollees with at least one claim for a PAH-related medication from January 01, 2012 to March 31, 2017, at least one medical claim with a pulmonary hypertension diagnosis, and continuous health plan enrollment at least 6 months prior to and at least 12 months following the date of the first pharmacy claim for PAH-related therapy (index date). Patients were divided into cohorts based on prescription of monotherapy or combination therapy and index date category (2012–2013, January 2014–July 2015, and August 2015–March 2017). Results Out of 1878 patients, 90.8% initiated with monotherapy and 9.2% initiated with combination therapy. The percentage of patients with index combination therapy increased from 5.7% in 2012–2013 to 13.0% in August 2015–March 2017. Patients with index combination therapy had better persistence (11.6 months versus 10.3 months) and adherence (0.95 versus 0.85). Overall, the discontinuation rate was 40% and was higher in monotherapy versus combination therapy patients (42.8% versus 12.2%). Approximately 30.2% of patients had a second regimen, of which 50% were combination regimens. The time to combination therapy initiation decreased from 10.5 months in 2012–2013 to 3.4 months in August 2015–March 2017. Conclusions The majority of patients initiated monotherapy treatment for PAH, most often a phosphodiesterase 5 inhibitor (PDE5i). Patients with upfront combination therapy increased following publication of the 2015 ESC/ERS guidelines, indicating that physicians responded to the guideline’s option of prescribing upfront combination therapy.

Ant Colony Optimization for Resolving Unit Commitment Issues by Considering Reliability Constraints

Unit Commitment or generator scheduling is one of complex combination issues aiming to obtain the cheapest generating power total costs. Ant Colony Optimization is proposed as a method to solve Unit Commitment issues because it has a better result convergence according to one of journals that reviews methods to solve Unit Commitment issues. Ant Colony Optimization modification into Nodal Ant Colony Optimization as well as addition of several elements are also conducted to overcome Ant Colony Optimization limitations in resolving Unit Commitment issues. Nodal Ant Colony Optimization simulations are then compared with Genetic Algorithm and Simulated Annealing methods which previously has similar simulations. Reliability index combination in a form of Loss of Load Probability and Expected Unserved Energy are also added as reliability constraints in the system. Comparison of three methods shows that Nodal Ant Colony Optimization is able to provide better results up to 0.08% cheaper than Genetic Algorithm or Simulated Annealing methods.