Compute Regression Coefficients Research Articles

Utilizing Liquid–liquid phase separation-related lncRNAs to predict the prognosis and treatment response of PCa

BackgroundStudies have indicated a close association between genes linked to liquid–liquid phase separation (LLPS) and the progression of prostate cancer (PCa). However, the interplay among long non-coding RNAs (lncRNAs) linked to LLPS in PCa remains elusive. Therefore, we constructed a prediction model based on LLPS-related LncRNA in PCa to explore its relationship with the prognosis and drug treatment of PCa.MethodsWe obtained clinical and sequencing data from TCGA and LLPS genes from the Phase Separation Protein Database. By analyzing the differential expression of LLPS-related genes and lncRNAs in prostate cancer, and using Poisson correlation, we identified LLPS-related lncRNAs. Prognostic LLPS-lncRNAs were found through prognostic correlation analysis and included in a Cox model to compute regression coefficients. Patients were scored and divided into high- and low-risk groups. Independent prognostic factors were integrated into a prognostic nomogram with risk and Gleason scores. We also conducted drug sensitivity analyses, GSEA, and validated the impact of key lncRNAs through functional experiments.ResultsOur study identified five LLPS-associated lncRNAs that are of prognostic importance. And found notable disparities in biochemical recurrence rates and survival outcomes between these risk groups, with the low-risk cohort exhibiting superior prognostic indicators. Moreover, our prediction nomogram demonstrated robust predictive accuracy and significant clinical utility. Furthermore, our model exhibited promising capabilities in forecasting patient sensitivity to various conventional therapeutic drugs, thereby highlighting its potential in personalized treatment strategies. GSEA showed that these lncRNAs may influence PCa prognosis and sensitivity to therapeutic agents by affecting pathways such as cell cycle. Knockdown of AC009812.4 could inhibit the ability of PCa cells to proliferate, migrate and invade, and compare to paracancerous tissue, AC009812.4 in PCa tissue has significantly higher expression.ConclusionOur research uncovers the prognostic significance of lncRNAs associated with LLPS in PCa and established a model exhibiting excellent predictive accuracy for prognosis. Those lncRNAs may influence progress of PCa as well as sensitivity to therapy drugs through pathways such as cell cycle.

Raise Estimation: An Alternative Approach in The Presence of Problematic Multicollinearity

When adopting the Ordinary Least Squares (OLS) method to compute regression coefficients, the results become unreliable when two or more predictor variables are linearly related to one another. The confidence interval of the estimates becomes longer as a result of the increased variance of the OLS estimator, which also causes test procedures to have the potential to generate deceptive results. Additionally, it is difficult to determine the marginal contribution of the associated predictors since the estimates depend on the other predictor variables that are included in the model. This makes the determination of the marginal contribution difficult. Ridge Regression (RR) is a popular alternative to consider in this scenario; however, doing so impairs the standard approach for statistical testing. The Raise Method (RM) is a technique that was developed to combat multicollinearity while maintaining statistical inference. In this work, we offer a novel approach for determining the raise parameter, because the traditional one is a function of actual coefficients, which limits the use of Raise Method in real-world circumstances. Using simulations, the suggested method was compared to Ordinary Least Squares and Ridge Regression in terms of its capacity to forecast, stability of its coefficients, and probability of obtaining unacceptable coefficients at different levels of sample size, linear dependence, and residual variance. According to the findings, the technique that we designed turns out to be quite effective. Finally, a practical application is discussed.

Studying hydraulic conductivity of asphalt concrete using a database

A new database called AC/k-1624 containing over 1600 measurements of saturated hydraulic conductivity of asphalt concrete has been assembled and analysed. AC/k-1624 was used to investigate the effect of the grading entropy parameters on saturated hydraulic conductivity. A new prediction model comprising both air voids and grading entropy is presented. The database analysis using different predictors of asphalt hydraulic conductivity reveals that the gradation does affect the hydraulic conductivity, but the air void level is necessary to make reasonable a-priori assessments of hydraulic conductivity for asphalt concrete. The new empirical model is shown to have a good predictive capacity for hydraulic conductivity fitting more securely at higher values with more scatter observed at lower values. The effects of test type, gradation classification and Nominal Maximum Aggregate Size (NMAS) are also studied, revealing in general relatively modest influences on the computed regression coefficients.

Early childhood exposure to secondhand smoke and behavioural problems in preschoolers

Evidence on behavioural abnormalities in children exposed to secondhand smoke is limited. This study examined the relation between infant/ toddler cotinine concentration, a biomarker of secondhand smoke exposure, and behavioural problems in preschoolers who were unexposed to maternal smoking during gestation. A prospective cohort of 301 non-smoking mothers with their young children aged ≤18 months visiting postnatal primary care clinics in Hong Kong was enrolled in 2012 and followed by telephone survey 3 years afterwards. Saliva was collected at baseline for cotinine assay. Child behavioural health at 3-year follow-up was assessed by the parent-reported Strengths and Difficulties Questionnaire (SDQ). We conducted multivariable linear regressions to compute regression coefficients (b) of SDQ scores in relation to salivary cotinine level. Mean ± SD age of children at follow-up was 3.7 ± 0.5 years and 50.8% were boys. After adjusting for age, sex, birthweight, household income, housing type, maternal education and depressive symptoms, greater cotinine concentrations during early childhood were associated with greater conduct problems (b = 0.90, 95% CI 0.03–1.76) and hyperactivity/ inattention (b = 1.12, 95% CI 0.07–2.17) at preschool age. This study corroborates previous findings on the potential role of secondhand smoke in development of child behavioural problems.

Predicting the Frequency and Intensity of Climate Extremes by Regression Models

This study examines the relationship of climate extremes indices with the large-scale factors like Sea Level Pressure (SLP) and Sea Surface Temperature (SST). The prediction of extreme indices is carried out and is based on statistical downscaling using the extreme indices data, National Centers for Environmental Prediction (NCEP) monthly SLP and SST reanalysis data. For this purpose, five extreme indices (PRCPTOT, R95p, RX5day, TN90p and TX90p) are developed by using homogenized and high quality daily data of temperature and precipitation for the period 1961-2010 of 10 meteorological stations of monsoon-dominated region of Pakistan. These indices are then average to develop an average time series of each extreme index. To check the assumption of regression model, extreme indices data are tested for heteroscedasticity, auto-correlation and normality. All extreme indices are independent, normal and homogeneous. These indices data are then used as predictand and SLP & SST datasets are used as predictors in regression model. Data for period 1961-2000 and 2001-2010 is used for training and validation purpose respectively. Stepwise regression procedure is adopted to compute regression coefficients based on algorithm of Jennrich. Predictors having strong correlation with extreme indices are identified and a regression model is developed using these predictors and also apply cross-validation technique. Performance of regression model and cross validation models is tested by using statistical measures (Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and bias). The performance is seen reasonably high both in training and validation period. The actual and estimated values show a close agreement. It is seen that ensemble mean prediction obtain from crossvalidation models well estimated the extreme indices than the regression model. This study is useful because extremes have a large impact on human society & economy and causing huge losses of the country. The timely prediction of extremes is a major factor and will help the policy makers to take necessary measures for reducing the huge losses.

Anomaly Detection Using Power Signature of Consumer Electrical Devices

Abstract —The use of the smart grid for developing intelligent applications is a current trend of great importance. One advantage lies in the possibility of direct monitoring of all devices connected to the electrical network in order to prevent possible malfunctions. Therefore, this paper proposes a method for an automatic detection of the malfunctioning of low-intelligence consumer electrical devices. Malfunctioning means any deviation of a household devi ce from its normal operating schedule. The method is based on a comparison technique, consisting in the correlation between the current power signature of a device and an ideal signature (the standard signature provided by the manufacturer). The first step of this method is to achieve a simplified form of power signature which keeps all the original features. Further, the signal is segmented based on the data provided by an event detection algorithm (values of the first derivatives) and each resulting component is approximated using a regression function. The final step consists of an analysis based on the correlation between the computed regression coefficients and the coefficients of the standard signal. Following this analysis all the differences are classified as a malfunctioning of the analyzed device. Index Terms —Feature extraction, Pattern matching, Signal analysis, Signal processing.

Predicting functional properties of milk powder based on manufacturing data in an industrial-scale powder plant

The fundamental science relating key physical and functional properties of milk powder to plant operating conditions is complex and largely unknown. Consequently this paper takes a data-driven approach to relate the routinely measured plant conditions to one vital function property known as sediment in an industrial-scale powder plant. Data from four consecutive production seasons was examined, and linear regression models based on a chosen set of processing variables were used to predict the sediment values. The average prediction error was well within the range of the uncertainty of the laboratory test. The models could be used to predict the effect of each individual plant variable on the sediment values which could be beneficial in quality optimisation. In addition the choice of the training data set used to compute regression coefficients was studied and the resultant regression models were compared to alternative PLS models built on the same data.

A Production Estimation Algorithm in Commingled Oil Wells Based Kernel Partial Least Square

Commingling is employed in the petroleum industry to enhance oil recovery and reduce costs. It is of great importance to monitor the production of each oil well oilfields. Nowadays, more and more oilfields use chromatographic fingerprint to estimate single-zone production allocation. In order to insure the efficiency and affectivity of the commingled oil well exploiting, the productivity contribution of every single layer must be acquainted. Kernel partial least squares (KPLS) is a promising regression method for tackling nonlinear systems because it can efficiently compute regression coefficients in high-dimensional feature spaces by means of nonlinear kernel functions. Unlike other nonlinear partial least squares (PLS) techniques KPLS does not entail any nonlinear optimization procedures and has a complexity similar to that of linear PLS. Using the technology of crude oil chromatography fingerprint, an algorithm for predicting productivity contribution based on KPLS is proposed. The validity of the method is proved by laboratory artificial experiments. The maximum absolute error of predicted and real proportion is less than 10%. The model can also be applied to other wells which are similar to those used in the experiment. The experiment results show the prediction model is feasible.

Encoding of forelimb forces by corticospinal tract activity in the rat.

In search of a solution to the long standing problems encountered in traditional brain computer interfaces (BCI), the lateral descending tracts of the spinal cord present an alternative site for taping into the volitional motor signals. Due to the convergence of the cortical outputs into a final common pathway in the descending tracts of the spinal cord, neural interfaces with the spinal cord can potentially acquire signals richer with volitional information in a smaller anatomical region. The main objective of this study was to evaluate the feasibility of extracting motor control signals from the corticospinal tract (CST) of the rat spinal cord. Flexible substrate, multi-electrode arrays (MEA) were implanted in the CST of rats trained for a lever pressing task. This novel use of flexible substrate MEAs allowed recording of CST activity in behaving animals for up to three weeks with the current implantation technique. Time-frequency and principal component analyses (PCA) were applied to the neural signals to reconstruct isometric forelimb forces. Computed regression coefficients were then used to predict isometric forces in additional trials. The correlation between measured and predicted forces in the vertical direction averaged across six animals was 0.67 and R2 value was 0.44. Force regression in the horizontal directions was less successful, possibly due to the small amplitude of forces. Neural signals above and near the high gamma band made the largest contributions to prediction of forces. The results of this study support the feasibility of a spinal cord computer interface (SCCI) for generation of command signals in paralyzed individuals.

A Self-Adaptive Regression-Based Multivariate Data Compression Scheme with Error Bound in Wireless Sensor Networks

Wireless sensor networks (WSNs) have limited energy and transmission capacity, so data compression techniques have extensive applications. A sensor node with multiple sensing units is called a multimodal or multivariate node. For multivariate stream on a sensor node, some data streams are elected as the base functions according to the correlation coefficient matrix, and the other streams from the same node can be expressed in relation to one of these base functions using linear regression. By designing an incremental algorithm for computing regression coefficients, a multivariate data compression scheme based on self-adaptive regression with infinite norm error bound for WSNs is proposed. According to error bounds and compression incomes, the self-adaption means that the proposed algorithms make decisions automatically to transmit raw data or regression coefficients, and to select the number of data involved in regression. The algorithms in the scheme can simultaneously explore the temporal and multivariate correlations among the sensory data. Theoretically and experimentally, it is concluded that the proposed algorithms can effectively exploit the correlations on the same sensor node and achieve significant reduction in data transmission. Furthermore, the algorithms perform consistently well even when multivariate stream data correlations are less obvious or non-stationary.

Objective method for estimating asymptotic parameters, with an application to sequence alignment.

Sequence alignment is an indispensable computational tool in modern molecular biology. The model underlying biological sequence alignment is of interest to physicists because it approximates the statistical mechanics of DNA and protein annealing, while bearing an intimate relationship to models of directed polymers in random media. Recent methods for determining the statistics of random sequence alignments have reduced the computation time to less than 1 s, opening up some interesting possibilities for online computation with biological search engines. Before implementation, however, the methods required an objective technique for computing regression coefficients pertinent to an asymptotic regime. Typically, physicists estimate parameters pertinent to an asymptotic regime subjectively: They eyeball their data; estimate the asymptotic regime where the regression model holds with reasonable accuracy; and then regress data only within the estimated asymptotic regime. Our publicly available computer program ARRP replaces the subjective assessment of the asymptotic regime with an objective change-point detection method, increasing confidence in the scientific objectivity of the parameter estimates. Asymptotic regression has potential applications across most of physics.

Improved Algorithm for Quantitative Analyses of Infrared Spectra of Multicomponent Gas Mixtures with Unknown Compositions

We present a major improvement of an algorithm based on a spectral library search for the quantitative analysis of multicomponent gas samples with unknown compositions. A quantitative spectral database of infrared spectra is used as a training set to compute regression coefficients. Concentrations are computed in the principal component space via principal component regression (PCR). In addition to previous algorithms, we introduce a rating for each candidate substance depending on the concentration found with PCR and a filter that removes candidates that are predicted with negative concentrations if their rating is below a certain threshold. Negative concentrations arise when the measured spectrum contains components that are not contained in the database. The PCR is recomputed until all candidates have a rating above the threshold. Then an adaptive filter "subtracts" the substance with the highest rating from both the measured spectrum and the library and appends it to a hit list. The iteration of this procedure directly produces a list of substances in order of descending importance (i.e., contribution to the measured absorbance) with their corresponding concentrations. The algorithm is tested on spectra of multicomponent surgical smoke samples. The four main components (water, methane, ethane, and ethene) are identified correctly (within the top 5 of the hit list) for an appropriate choice of the rating threshold. The algorithm describes the composition of the smoke sample correctly despite the presence of features in the spectrum that cannot be explained by the spectrum of any single substance present in the database.

Subliminal Instrumental Conditioning Demonstrated in the Human Brain

SummaryHow the brain uses success and failure to optimize future decisions is a long-standing question in neuroscience. One computational solution involves updating the values of context-action associations in proportion to a reward prediction error. Previous evidence suggests that such computations are expressed in the striatum and, as they are cognitively impenetrable, represent an unconscious learning mechanism. Here, we formally test this by studying instrumental conditioning in a situation where we masked contextual cues, such that they were not consciously perceived. Behavioral data showed that subjects nonetheless developed a significant propensity to choose cues associated with monetary rewards relative to punishments. Functional neuroimaging revealed that during conditioning cue values and prediction errors, generated from a computational model, both correlated with activity in ventral striatum. We conclude that, even without conscious processing of contextual cues, our brain can learn their reward value and use them to provide a bias on decision making.

Nonlinear Multivariate Quality Estimation and Prediction Based on Kernel Partial Least Squares

A novel nonlinear multivariate quality estimation and prediction method based on kernel partial least-squares (KPLS) was proposed in this article. KPLS is a promising regression method for tackling nonlinear problems because it can efficiently compute regression coefficients in high-dimensional feature space by means of the nonlinear kernel function. It is an efficient method for estimating and predicting quality variables in the nonlinear process by mapping data from the original space into a high-dimensional feature space. It only requires the use of linear algebra, making it as simple as linear multivariate projection methods, and it can handle a wide range of nonlinearities because of its ability to use different kernel functions. Its application results from a simple example, and real data of an industrial oil refinery factory show that the proposed method can effectively capture the nonlinear relationship among variables. In addition, it has a better estimation performance than the partial least-squ...

A novel multivariate regression approach based on kernel partial least squares with orthogonal signal correction

This paper introduces a novel multivariate regression approach based on kernel partial least squares (KPLS) with orthogonal signal correction (OSC). OSC has been proposed as a data preprocessing method that removes from X information not correlated to Y. KPLS is a promising regression method for tackling nonlinear systems because it can efficiently compute regression coefficients in high-dimensional feature spaces by means of nonlinear kernel functions. Unlike other nonlinear partial least squares (PLS) techniques KPLS does not entail any nonlinear optimization procedures and has a complexity similar to that of linear PLS. In this paper, the prediction performance of the proposed approach (OSC-KPLS) is compared to those of PLS, OSC-PLS and KPLS using three examples. OSC-KPLS effectively simplifies both the structure and interpretation of the resulting regression model and shows superior prediction performance compared to linear PLS.

Determination of Shortwave Earth Reflectances from Visible Radiance Measurements: Error Estimate Using ScaRaB Data

Abstract The error resulting from the use of a visible channel to estimate shortwave (SW) (0.2–4 μm) fluxes reflected by the earth is analyzed. First, the authors compute regression coefficients between visible (0.55–0.65 μm) and SW radiance measurements made by the ScaRaB (Scanner for Radiation Budget) instrument aboard the Meteor-3/7 satellite between March 1994 and February 1995. These regression coefficients are computed from the 10 months of available ScaRaB measurements in different classes of geotypes and different classes of solar and viewing angles. The regression is applied to the visible radiance measurements to simulate the SW measurements in the operational processing of ScaRaB. For instantaneous fluxes, the visible-to-SW conversion gives a standard deviation of the error smaller than 8%. By comparison, the standard deviation of the instantaneous flux error coming from the angular sampling and the bidirectional reflectance uncertainty is estimated to be about 10%. For monthly mean values the ...

A predictive model of survival after radical cystectomy for carcinoma of the bladder

To evaluate the effect of patient and tumour characteristics on the disease-free survival after radical cystectomy for infiltrating bladder cancer, and to use these to help in constructing a meaningful prognostic index. The disease-free survival was initially evaluated in 1026 patients (the reference series, 1969-1990). A multivariate analysis showed that the tumour P stage, grade and nodal involvement were the only factors which had an independent and significant association with survival. The computed regression coefficients were then used to classify patients into one of four risk categories and the results then validated by applying the model to a prospective test series (1991-1995). The 5-year disease-free survival of both groups was similar. When the results for the risk categories of the reference series were compared with those of the test series, there was no significant difference. This comprehensive prognostic model for the results of radical cystectomy was validated and verified in a prospective group of patients. Adjuvant therapies are indicated for patients with a high risk score.

Pediatric coefficients for TRISS analysis.

We computed regression coefficients for TRISS analysis for all 4271 pediatric patients (aged 1 through 14 years) with complete data from the Major Trauma Outcome Study. We then compared predicted pediatric and adult TRISS survival probability norms. There were no statistically significant differences in the predicted and actual numbers of survivors using either norm. Differences in discrimination and reliability between the two norms were minimal. The study confirmed that the TRISS adult blunt norm is highly discriminating and reliable in predicting survival probabilities for pediatric patients. Given that both norms were equally good predictors, and the importance of a consistent system to evaluate trauma care, the authors recommend the continued use of the adult blunt trauma norm for estimating survival probability in children.

Inclusion of Partial Lactations in the Genetic Analysis of Yield Traits by Differential Weighting of Records

Mixed model equations are constructed using the convention of regression on dummy variables that are given values of either unity (presence of the effect) or zero (absence of the effect). In the proposed method, incomplete records were included by computing regression coefficients of sire effects as the regression of the effect on the partial record on the same effect on the complete record. Partial and complete records were treated equally for other effects. Regression and the error components of variance were estimated as simple functions of the length of the partial records. The only additional computation required in sire evaluation was the differential weighting of records in the construction of the mixed model equations. This method was tested on field data and was slightly more accurate than evaluations including partial records without differential weighting and significantly more accurate than evaluations obtained with partial records deleted.

A Comparison of Some Shallow Wind-Driven Currents

Abstract Four sets of current measurements made in water depths ranging between 28 and 38 m over periods ranging from three to five weeks are examined and compared. The response of the water column to wind forcing is examined by computing regression coefficients between the surface wind stress and two different parameterizations of bottom stress in terms of measured currents. Coefficients computed for the different data sets vary by as much as a factor of 4. While such variations might be due to instrumental differences, it seems more likely that the assumed dynamical balance between surface and bottom stress is incomplete, i.e., other forces such as the alongshore pressure gradient are quantitatively important even when the water depth is comparable to the turbulent Ekman layer thickness.