Rank Candidate Research Articles

Short-term electricity load and price forecasting by a new optimal LSTM-NN based prediction algorithm

Nowadays, a basic commodity for a human being to lead a standard lifestyle with human comfort irrespective of the nature of environmental conditions is electric power. The electricity load demand increases tremendously especially for a metropolitan city due to climatic conditions, population growth, local area development, industries expansion, air pollution, thermal device usage, etc. Hence, the accuracy of electricity load and its price forecasting is a deciding factor for the power distribution network to retain as an efficient, sustainable, and secure consumer-friendly network. On the other hand, based on the volatile, intermittent, and uncertain behavior of electricity load and price, an accurate, and robust forecast model should be designed. In this paper, a new hybrid forecast model for short-term electricity load and price prediction has been developed. The proposed method includes three modules: wavelet transform that is used to eliminate fluctuation behaviors of the electricity load and price time series, feature selection based on entropy and mutual information has been proposed to rank candidate inputs and eliminate redundant inputs according to their information value, and a new learning algorithm. The proposed learning method consists of a deep learning algorithm with LSTM networks which improves the accuracy of predictions. The performance of the proposed method has been validated successfully on load and price data collected from the Pennsylvania-New Jersey-Maryland (PJM) and Spain electricity markets. Also, for further test, the load data in Iran have been used.

ProTECT-Prediction of T-Cell Epitopes for Cancer Therapy.

Somatic mutations in cancers affecting protein coding genes can give rise to potentially therapeutic neoepitopes. These neoepitopes can guide Adoptive Cell Therapies and Peptide- and RNA-based Neoepitope Vaccines to selectively target tumor cells using autologous patient cytotoxic T-cells. Currently, researchers have to independently align their data, call somatic mutations and haplotype the patient’s HLA to use existing neoepitope prediction tools. We present ProTECT, a fully automated, reproducible, scalable, and efficient end-to-end analysis pipeline to identify and rank therapeutically relevant tumor neoepitopes in terms of potential immunogenicity starting directly from raw patient sequencing data, or from pre-processed data. The ProTECT pipeline encompasses alignment, HLA haplotyping, mutation calling (single nucleotide variants, short insertions and deletions, and gene fusions), peptide:MHC binding prediction, and ranking of final candidates. We demonstrate the scalability, efficiency, and utility of ProTECT on 326 samples from the TCGA Prostate Adenocarcinoma cohort, identifying recurrent potential neoepitopes from TMPRSS2-ERG fusions, and from SNVs in SPOP. We also compare ProTECT with results from published tools. ProTECT can be run on a standalone computer, a local cluster, or on a compute cloud using a Mesos backend. ProTECT is highly scalable and can process TCGA data in under 30 min per sample (on average) when run in large batches. ProTECT is freely available at https://www.github.com/BD2KGenomics/protect.

GAM feature selection to discover predominant factors for mortality of weekend and weekday admission to the ICUs

Abstract “Weekend effect” on mortality is a common controversial topic among many hospitals. Although the mortality of patients associated with weekend Intensive Care Units (ICUs) admission has been demonstrated slightly higher than that of patients admitted on weekdays in many studies, the underlying causal mechanisms and the potential factors are not clear at present. In this study, we extract medical record features from the database and propose a Generalized Additive Model(GAM) feature selection method to identify the main contribution features for analyzing this issue. The GAM feature selection system could rank candidate features by its importance, which turns out to be effective in reducing the complexity of a medical issue. The best lists of features are acquired by the weekday GAM model and the weekend GAM model separately. Fourteen out of forty-one features are identified for the reduced list of features. Both models’ reduced lists of features have ten identical characteristics, and the other four are different. The prediction accuracy with the reduced list of features is 79.90% for the weekday model and 78.56% for the weekend model. The contrast experiment has validated the feature ranking results. Furthermore, variables of the same feature classes are also different from weekday admission to weekend admission. We expect that the proposed GAM feature selection method could contribute to solving more medical issues in the future.

Optimum Municipal Solid Waste Disposal Site Selection Using Gis Based Multi-Criteria Decision Analysis: A Case of Nekemte Town, Oromia Regional State, Ethiopia

Solid waste is a major global concern particularly in developing countries. Municipal landfill site selection is becoming the main challenge as a result of various factors. To make the site to be selected environmentally sound, socially acceptable and economically feasible, GIS based multi-criteria decision analysis ( MCDA ) method that has the capability to combine spatially referenced data with experts’ value judgment was used in this study. The analytic hierarchy process ( AHP ) was the major technique of MCDA used to derive the weights of the nine criteria considered – distance from road network, geology, distance from fault lines, soil permeability, slope, distance from rivers/streams, distance from lakes, distance from the built-up areas and land use/land cover types. After creating Multiple-ring Buffers for road network, fault lines, rivers/streams, lakes and built-up areas by reviewing various literatures, all the criteria were standardized by reclassifying them into suitability classes. The weights of the reclassified criteria were derived using AHP Pair-wise Comparison Matrix in Microsoft Excel and then combined together using the Weighted Overlay tool in ArcGIS to produce the composite suitability map of the study area. Accordingly, 0.43% and 0.02% of the study area are unsuitable and highly suitable, respectively. The remaining 41.64%, 51.12%, and 6.8% of the study area are poorly suitable, moderately suitable and suitable, respectively. The raster composite suitability map of study area was then converted into vector map to select candidate disposal sites. Accordingly, six candidate municipal solid waste disposal sites were selected, evaluated with respect to their area (size), distance from center and distance from the nearby built-up area. They were weighted with respect to these three evaluating criteria using AHP Pair-wise Comparison Matrix and finally mapped and ranked. The first, second and third ranked candidate disposal sites have an area of 46 ha, 29 ha and 35ha, respectively. The first and second candidate sites are located in Burka Jato sub-town, while the third one is located in Sorga sub-town. In order to reduce the adverse impact of surface water pollution in the downstream, runoff should not flow into and out of the MSW disposal sites. To minimize groundwater pollution, detailed investigation on sub-surface condition of the site should be made during design. Greenhouse gases collection should also be designed to reduce air pollution. Keywords: multi-criteria decision analysis; analytic hierarchy process; Pair-wise Comparison Matrix; Weight Overlay DOI: 10.7176/JEES/10-11-01 Publication date: November 30 th 2020

Diagnosis of camelina seed yield and quality across an on-farm experimental network

Camelina [Camelina sativa (L.) Crantz] is an emerging oilseed crop combining both industrial and agronomic advantages. Camelina seed yield, oil and protein contents, and fatty-acid composition, vary across genotypes, environments, and agricultural practices. However, no studies have been conducted to identify and rank major limiting factors explaining yield and quality variations under on-farm conditions. Camelina performance was measured on 39 experimental strips corresponding to five camelina crop management routes (grown as an intercrop or sole crop), implemented in nine farmers’ fields across northern France in 2017 and 2018. The ranking of candidate limiting factors, defined a priori from scientific literature, was carried out using a model mixing method based on the Akaike Information Criterion. Main limiting factors of camelina yield (ranging from 62 to 2585 kg ha−1) were nitrogen crop status at flowering stage and downy mildew. Camelina yield was indeed positively correlated with the Nitrogen Nutrition Index at flowering stage (R2 = 0.44, p = 0.007). Oil content varied from 36.6 to 46.5 % and was negatively correlated with protein content. Main indicators explaining oil content variations were grain filling duration and downy mildew. Both poly-unsaturated and linolenic acid contents were positively correlated to grain filling duration, and negatively correlated to temperature during grain filling period. Camelina nitrogen status at flowering stage was mainly explained by N uptake of the intercropped species (pea or barley), and the amount of available inorganic nitrogen in the soil between sowing and flowering. Downy mildew was influenced by both weather conditions and the amount of weed biomass.This study showed a large variability in camelina seed yield and quality under on-farm conditions. The identification of the major limiting factors made it possible to pinpoint ways of improving camelina performance namely choosing genotypes with high resistance to mildew, better managing nitrogen fertilization or delaying camelina sowing date. Finally we also identified major research topics to be addressed to support the adoption of this new crop by farmers as the elaboration of the critical nitrogen dilution curve.

Project Score database: a resource for investigating cancer cell dependencies and prioritizing therapeutic targets.

CRISPR genetic screens in cancer cell models are a powerful tool to elucidate oncogenic mechanisms and to identify promising therapeutic targets. The Project Score database (https://score.depmap.sanger.ac.uk/) uses genome-wide CRISPR–Cas9 dropout screening data in hundreds of highly annotated cancer cell models to identify genes required for cell fitness and prioritize novel oncology targets. The Project Score database currently allows users to investigate the fitness effect of 18 009 genes tested across 323 cancer cell models. Through interactive interfaces, users can investigate data by selecting a specific gene, cancer cell model or tissue type, as well as browsing all gene fitness scores. Additionally, users can identify and rank candidate drug targets based on an established oncology target prioritization pipeline, incorporating genetic biomarkers and clinical datasets for each target, and including suitability for drug development based on pharmaceutical tractability. Data are freely available and downloadable. To enhance analyses, links to other key resources including Open Targets, COSMIC, the Cell Model Passports, UniProt and the Genomics of Drug Sensitivity in Cancer are provided. The Project Score database is a valuable new tool for investigating genetic dependencies in cancer cells and the identification of candidate oncology targets.

Globular Clusters Lost by the Sagittarius Dwarf Spheroidal Galaxy

In this work a search was carried out for globular clusters belonging to the Sagittarius (Sgr) tidal stream using the analysis of spatial positions, radial velocities relative to the Galactic Standard of Rest (V_{GSR}),proper motions and ratio of "age -- metallicity" ([Fe/H]) for globular clusters and for stars in the tidal stream. As a result, three categories of globular clusters were obtained: A -- most certainly in the stream: Terzan 8, Whiting 1, Arp 2, NGC 6715, Terzan 7, Pal 12; B -- kinematic outliers: Pal 5, NGC 5904, NGC 5024, NGC 5053, NGC 5272, NGC 288; C -- lowest rank candidates: NGC 6864, NGC 5466, NGC 5897, NGC 7492, NGC 4147.

Hawks and Doves: Adjusting for Bias in Residency Interview Scoring

Individual interviews are an important part of the residency interview process. Programs may use these scores to calculate rankings used in the match process. Individual interviewers can introduce bias by consistently scoring candidates higher or lower than their peers. The order of interview or year of interview also has the potential to introduce bias. This study seeks to determine if interviewers or timing introduces bias into interview scores and to provide a method to adjust for this bias. Interview scores at a single general surgery residency program were obtained over 3 years. The mean interview score and standard error were calculated for each interviewer. The difference in average score between years and by order of interview was evaluated with a linear mixed model. Individual interviewer mean scores were ranked from lowest scores to highest scores. Each candidate's interview score was then plotted against the combined rank of their respective interviewers and significance was calculated for linear regression. The average deviation of each interviewer was calculated to obtain an adjustment score individualized for each interviewer. One thousand three hundred and five interview scores from 91 interviewers were included in the analysis. Interview scoring ranged from 1 (lowest) to 4 (highest). The average score was 3.35 (standard deviation [SD] 0.56). The interviewers conducted an average of 14 (SD 11.4) interviews during the study period. Each interviewer averaged 8.25 interviews per year (SD 5). There was no difference in scores by year (p = 0.20) or by order of interview (p = 0.33). Plotting average applicant score against rank of interviewers revealed a variance between the lowest scoring and highest scoring interviewers revealing a progressive bias (see Figure 3; p < 0.0001). The calculated adjustment factor was added or subtracted to each interviewer's score and the linear model was recalculated. The new plot revealed a lack of bias between interviewer ranking and scores (p = 0.32). In a large cohort of residency interviewers, interview scores demonstrated significant interviewer bias. This bias has the potential to significantly alter an applicant's rank list position. An adjustment score can be calculated to reduce this bias in interview scores. Prospective validation of this adjustment will be helpful in determining its utility in candidate ranking.

Machine learning for ranking day-ahead decisions in the context of short-term operation planning

In operation planning, probabilistic reliability assessment consists in evaluating, for various candidate planning decisions, the induced probability of meeting a reliability target and the expected operating cost over a certain future time period. In this paper, we propose to exploit Monte-Carlo simulation and machine learning to predict operation costs for various day-ahead unit commitment and economic dispatch decisions and a range of realisations of uncertain loads and renewable generations over the next day. We describe how to generate a database, how to apply supervised machine learning to it, and how to use the learnt proxies to rank candidate day-ahead decisions in terms of the expected operating cost they induce over the next day. We illustrate the approach on the IEEE-RTS96 benchmark where we use the DC power-flow approximation and the N−1 criterion to simulate real-time operation and to generate generation schedules in the day-ahead operation planning stage.

New High-quality Strong Lens Candidates with Deep Learning in the Kilo-Degree Survey

Abstract We report new high-quality galaxy-scale strong lens candidates found in the Kilo-Degree Survey data release 4 using machine learning. We have developed a new convolutional neural network (CNN) classifier to search for gravitational arcs, following the prescription by Petrillo et al. and using only r-band images. We have applied the CNN to two “predictive samples”: a luminous red galaxy (LRG) and a “bright galaxy” (BG) sample (r &lt; 21). We have found 286 new high-probability candidates, 133 from the LRG sample and 153 from the BG sample. We have ranked these candidates based on a value that combines the CNN likelihood of being a lens and the human score resulting from visual inspection (P-value), and here we present the highest 82 ranked candidates with P-values ≥0.5. All of these high-quality candidates have obvious arc or pointlike features around the central red defector. Moreover, we define the best 26 objects, all with P-values ≥0.7, as a “golden sample” of candidates. This sample is expected to contain very few false positives; thus, it is suitable for follow-up observations. The new lens candidates come partially from the more extended footprint adopted here with respect to the previous analyses and partially from a larger predictive sample (also including the BG sample). These results show that machine-learning tools are very promising for finding strong lenses in large surveys and more candidates can be found by enlarging the predictive samples beyond the standard assumption of LRGs. In the future, we plan to apply our CNN to the data from next-generation surveys such as the Large Synoptic Survey Telescope, Euclid, and the Chinese Space Station Optical Survey.

Rank aggregation algorithms for fair consensus

Aggregating multiple rankings in a database is an important task well studied by the database community. High-stakes application domains include hiring, lending, and education where multiple decision makers rank candidates and their input is then combined into an overall consensus ranking. While state-of-art aggregation methods succeed in giving equal say to each decision maker, to date no methods ensure fair representation for groups of candidates being ranked, who risk being impacted by discriminatory bias. We present the first solution to this open problem of guaranteeing fairness for disadvantaged groups of candidates, while still producing a good consensus of the base rankings. We design a family of exact fair algorithms achieving optimality for fair rank aggregation. We also develop approximate methods achieving fairness with guaranteed minimal approximation error scaling to millions of candidates in the rankings. A comparative study evaluates our proposed methods, revealing trade-offs between aggregation accuracy and different degrees of unfair bias in a rich variety of rank aggregation scenarios. Our real-world case study demonstrates that our solutions mitigate unfair bias using real-world data.

Robust and fast reconstruction of complex roofs with active sampling from 3D point clouds

AbstractThis article proposes a novel method for the 3D reconstruction of LoD2 buildings from LiDAR data. We propose an active sampling strategy which applies a cascade of filters focusing on promising samples at an early stage, thus avoiding the pitfalls of RANSAC‐based approaches. Filters are based on prior knowledge represented by (nonparametric) density distributions. In our approach samples are pairs of surflets—3D points together with normal vectors derived from a plane approximation of their neighborhood. Surflet pairs provide parameters for model candidates such as azimuth, inclination and ridge height, as well as parameters estimating internal precision and consistency. This provides a ranking of roof model candidates and leads to a small number of promising hypotheses. Building footprints are derived in a preprocessing step using machine learning methods, in particular support vector machines.

Prioritizing river basins for intensive monitoring and assessment by the US Geological Survey

The US Geological Survey (USGS) is currently (2020) integrating its water science programs to better address the nation’s greatest water resource challenges now and into the future. This integration will rely, in part, on data from 10 or more intensively monitored river basins from across the USA. A team of USGS scientists was convened to develop a systematic, quantitative approach to prioritize candidate basins for this monitoring investment to ensure that, as a group, the 10 basins will support the assessment and forecasting objectives of the major USGS water science programs. Candidate basins were the level-4 hydrologic units (HUC04) with some of the smaller HUC04s being combined; median candidate-basin area is 46,600 km2. Candidate basins for the contiguous United States (CONUS) were grouped into 18 hydrologic regions. Ten geospatial variables representing land use, climate change, water use, water-balance components, streamflow alteration, fire risk, and ecosystem sensitivity were selected to rank candidate basins within each of the 18 hydrologic regions. The two highest ranking candidate basins in each of the 18 regions were identified as finalists for selection as “Integrated Water Science Basins”; final selection will consider input from a variety of stakeholders. The regional framework, with only one basin selected per region, ensures that as a group, the basins represent the range in major drivers of the hydrologic cycle. Ranking within each region, primarily based on anthropogenic stressors of water resources, ensures that settings representing important water-resource challenges for the nation will be studied.

Revisiting Five Years of CASMI Contests with EPA Identification Tools.

Software applications for high resolution mass spectrometry (HRMS)-based non-targeted analysis (NTA) continue to enhance chemical identification capabilities. Given the variety of available applications, determining the most fit-for-purpose tools and workflows can be difficult. The Critical Assessment of Small Molecule Identification (CASMI) contests were initiated in 2012 to provide a means to evaluate compound identification tools on a standardized set of blinded tandem mass spectrometry (MS/MS) data. Five CASMI contests have resulted in recommendations, publications, and invaluable datasets for practitioners of HRMS-based screening studies. The US Environmental Protection Agency’s (EPA) CompTox Chemicals Dashboard is now recognized as a valuable resource for compound identification in NTA studies. However, this application was too new and immature in functionality to participate in the five previous CASMI contests. In this work, we performed compound identification on all five CASMI contest datasets using Dashboard tools and data in order to critically evaluate Dashboard performance relative to that of other applications. CASMI data was accessed via the CASMI webpage and processed for use in our spectral matching and identification workflow. Relative to applications used by former contest participants, our tools, data, and workflow performed well, placing more challenge compounds in the top five of ranked candidates than did the winners of three contest years and tying in a fourth. In addition, we conducted an in-depth review of the CASMI structure sets and made these reviewed sets available via the Dashboard. Our results suggest that Dashboard data and tools would enhance chemical identification capabilities for practitioners of HRMS-based NTA.

GuiltyTargets: Prioritization of Novel Therapeutic Targets With Network Representation Learning.

The majority of clinical trials fail due to low efficacy of investigated drugs, often resulting from a poor choice of target protein. Existing computational approaches aim to support target selection either via genetic evidence or by putting potential targets into the context of a disease specific network reconstruction. The purpose of this work was to investigate whether network representation learning techniques could be used to allow for a machine learning based prioritization of putative targets. We propose a novel target prioritization approach, GuiltyTargets, which relies on attributed network representation learning of a genome-wide protein-protein interaction network annotated with disease-specific differential gene expression and uses positive-unlabeled (PU) machine learning for candidate ranking. We evaluated our approach on 12 datasets from six diseases of different type (cancer, metabolic, neurodegenerative) within a 10 times repeated 5-fold stratified cross-validation and achieved AUROC values between 0.92 - 0.97, significantly outperforming previous approaches that relied on manually engineered topological features. Moreover, we showed that GuiltyTargets allows for target repositioning across related disease areas. An application of GuiltyTargets to Alzheimer's disease resulted in a number of highly ranked candidates that are currently discussed as targets in the literature. Interestingly, one (COMT) is also the target of an approved drug (Tolcapone) for Parkinson's disease, highlighting the potential for target repositioning with our method. The GuiltyTargets Python package is available on PyPI and all code used for analysis can be found under the MIT License at https://github.com/GuiltyTargets. Attributed network representation learning techniques provide an interesting approach to effectively leverage the existing knowledge about the molecular mechanisms in different diseases. In this work, the combination with positive-unlabeled learning for target prioritization demonstrated a clear superiority compared to classical feature engineering approaches. Our work highlights the potential of attributed network representation learning for target prioritization. Given the overarching relevance of networks in computational biology we believe that attributed network representation learning techniques could have a broader impact in the future.

Storage ring nonlinear dynamics optimization with multi-objective multi-generation Gaussian process optimizer

Nonlinear beam dynamics optimization is essential in a low emittance storage ring design. Multi-objective optimization algorithms are needed in order to simultaneously optimize the dynamic aperture and the momentum aperture. In this study we demonstrate the application of a highly efficient stochastic optimization algorithm, the multi-generation Gaussian process optimizer (MG-GPO), to storage ring nonlinear dynamics optimization by successfully applying the method to the SPEAR3 upgrade lattice. It is shown that the new method, owing to its capability of selecting high rank candidates from a large number of trial solutions, converges significantly faster than the commonly used traditional algorithms, multi-objective genetic algorithms (MOGA) and particle swarm optimization (PSO).

Regional Patch Detection of Road Traffic Network

Road traffic network (RTN) structure plays an important role in the field of complex network analysis. In this paper, we propose a regional patch detection method from RTN via community detection of complex network. Firstly, the refined Adapted PageRank algorithm, which combines with the influence factors of the location property weight, the geographic distance weight and the road level weight, is used to calculate the candidate ranking results of key nodes in the RTN. Secondly, the ranking result and the shortest path distance as two significant impact factors are used to select the key points of the RTN, and then the Adapted K-Means algorithm is applied to regional patch detection of the RTN. Finally, based on the experimental data of Zhangwu road traffic network, the analysis results are as follows: Zhangwu is divided into 9 functional structures with key node locations as the core. Regional patch structure is divided according to key points, and the RTN is actually divided into nine small functional communities. Nine functional regional patches constitute a new network structure, maintaining connectivity between the regional patches can improve the overall efficiency of the RTN.

Конструювання політичних партій нового покоління (Constructing New-Generation Political Parties)

Конструювання політичних партій нового покоління (Constructing New-Generation Political Parties)

CopomuS-Ranking Compensatory Mutations to Guide RNA-RNA Interaction Verification Experiments.

In silico RNA-RNA interaction prediction is widely applied to identify putative interaction partners and to assess interaction details in base pair resolution. To verify specific interactions, in vitro evidence can be obtained via compensatory mutation experiments. Unfortunately, the selection of compensatory mutations is non-trivial and typically based on subjective ad hoc decisions. To support the decision process, we introduce our COmPensatOry MUtation Selector CopomuS. CopomuS evaluates the effects of mutations on RNA-RNA interaction formation using a set of objective criteria, and outputs a reliable ranking of compensatory mutation candidates. For RNA-RNA interaction assessment, the state-of-the-art IntaRNA prediction tool is applied. We investigate characteristics of successfully verified RNA-RNA interactions from the literature, which guided the design of CopomuS. Finally, we evaluate its performance based on experimentally validated compensatory mutations of prokaryotic sRNAs and their target mRNAs. CopomuS predictions highly agree with known results, making it a valuable tool to support the design of verification experiments for RNA-RNA interactions. It is part of the IntaRNA package and available as stand-alone webserver for ad hoc application.

CICERO: a versatile method for detecting complex and diverse driver fusions using cancer RNA sequencing data

To discover driver fusions beyond canonical exon-to-exon chimeric transcripts, we develop CICERO, a local assembly-based algorithm that integrates RNA-seq read support with extensive annotation for candidate ranking. CICERO outperforms commonly used methods, achieving a 95% detection rate for 184 independently validated driver fusions including internal tandem duplications and other non-canonical events in 170 pediatric cancer transcriptomes. Re-analysis of TCGA glioblastoma RNA-seq unveils previously unreported kinase fusions (KLHL7-BRAF) and a 13% prevalence of EGFR C-terminal truncation. Accessible via standard or cloud-based implementation, CICERO enhances driver fusion detection for research and precision oncology. The CICERO source code is available at https://github.com/stjude/Cicero.