Build Regression Models Research Articles

Impact of Image Content on Medical Crowdfunding Success: A Machine Learning Approach.

As crowdfunding sites proliferate, visual content often serves as the initial bridge connecting a project to its potential backers, underscoring the importance of image selection in effectively engaging an audience. This paper aims to explore the relationship between images and crowdfunding success in cancer-related crowdfunding projects. We used the Alibaba Cloud platform to detect individual features in images. In addition, we used the Recognize Anything Model to label images and obtain content tags. Furthermore, the discourse atomic topic model was used to generate image topics. After obtaining the image features and image content topics, we built regression models to investigate the factors that influence the results of crowdfunding success. Images with a higher proportion of young people (β=0.0753; P<.001), a larger number of people (β=0.00822; P<.001), and a larger proportion of smiling faces (β=0.0446; P<.001) had a higher success rate. Image content related to good things and patient health also contributed to crowdfunding success (β=0.082, P<.001; and β=0.036, P<.001, respectively). In addition, the interaction between image topics and image characteristics had a significant effect on the final fundraising outcome. For example, when smiling faces are considered in conjunction with the image topics, using more smiling faces in the rest and play theme increased the amount of money raised (β=0.0152; P<.001). We also examined causality through a counterfactual analysis, which confirmed the influence of the variables on crowdfunding success, consistent with the results of our regression models. In the realm of web-based medical crowdfunding, the importance of uploaded images cannot be overstated. Image characteristics, including the number of people depicted and the presence of youth, significantly improve fundraising results. In addition, the thematic choice of images in cancer crowdfunding efforts has a profound impact. Images that evoke beauty and resonate with health issues are more likely to result in increased donations. However, it is critical to recognize that reinforcing character traits in images of different themes has different effects on the success of crowdfunding campaigns.

Decision Tree Regression with Residual Outlier Detection

This paper introduces a framework for identifying outliers in predictions made by regression tree models. Existing robust regression approaches tend to focus on the construction stage, which builds regression models that are less sensitive to outliers. In contrast, our approach focuses on identifying outliers during the prediction stage. The process of our proposed approach begins with building a regression tree using a training dataset. Predictions significantly deviating from the mean within each terminal node are automatically labeled as outliers. We show how the labelled data can be explored to better understand the characteristics of the outliers. We also identify the situations under which the data exploration may not work well. Further, we make use of the outlier labels and training data to construct an anomaly detector. Our results show that the proposed method can effectively detect outliers that may exist within datasets. Such outliers, when removed, result in improved data quality. Insights into its effectiveness and potential caveats are also discussed.

StableMate: a statistical method to select stable predictors in omics data.

Identifying statistical associations between biological variables is crucial to understanding molecular mechanisms. Most association studies are based on correlation or linear regression analyses, but the identified associations often lack reproducibility and interpretability due to the complexity and variability of omics datasets, making it difficult to translate associations into meaningful biological hypotheses. We developed StableMate, a regression framework, to address these challenges through a process of variable selection across heterogeneous datasets. Given datasets from different environments, such as experimental batches, StableMate selects environment-agnostic (stable) and environment-specific predictors in predicting the response of interest. Stable predictors represent robust functional dependencies with the response, and can be used to build regression models that make generalizable predictions in unseen environments. We applied StableMate to (i) RNA sequencing data of breast cancer to discover genes that consistently predict estrogen receptor expression across disease status; (ii) metagenomics data to identify microbial signatures that show persistent association with colon cancer across study cohorts; and (iii) single-cell RNA sequencing data of glioblastoma to discern signature genes associated with thedevelopment of pro-tumour microglia regardless of cell location. Our case studies demonstrate that StableMate is adaptable to regression and classification analyses and achieves comprehensive characterization of biological systems for different omics data types.

"What's in a name?": Using mpox as a case study to understand the importance of communication, advocacy, and information accuracy in disease nomenclature.

Historically, many diseases have been named after the species or location of discovery, the discovering scientists, or the most impacted population. However, species-specific disease names often misrepresent the true reservoir; location-based disease names are frequently targeted with xenophobia; some of the discovering scientists have darker histories; and impacted populations have been stigmatized for this association. Acknowledging these concerns, the World Health Organization now proposes naming diseases after their causative pathogen or symptomatology. Recently, this guidance has been retrospectively applied to a disease at the center of an outbreak rife with stigmatization and misinformation: mpox (f.k.a. 'monkeypox'). This disease, historically endemic to west and central Africa, has prompted racist remarks as it spread globally in 2022 in an epidemic ongoing today. Moreover, its elevated prevalence among men who have sex with men has yielded increased stigma against the LGBTQ+ community. To address these prejudicial associations, 'monkeypox' was renamed 'mpox' in November 2022. We used publicly available data from Google Search Trends to determine which countries were quicker to adopt this name change-and understand factors that limit or facilitate its use. Specifically, we built regression models to quantify the relationship between 'mpox' search intensity in a given country and the country's type of political regime, robustness of sociopolitical and health systems, level of pandemic preparedness, extent of gender and educational inequalities, and temporal evolution of mpox cases through December 2023. Our results suggest that, when compared to 'monkeypox' search intensity, 'mpox' search intensity was significantly higher in countries with any history of mpox outbreaks or higher levels of LGBTQ+ acceptance; meanwhile, 'mpox' search intensity was significantly lower in countries governed by leaders who had recently propagated infectious disease misinformation. Among infectious diseases with stigmatizing names, mpox is among the first to be revised retrospectively. While the adoption of a given disease name will be context-specific-depending in part on its origins and the affected subpopulations-our study provides generalizable insights, applicable to future changes in disease nomenclature.

Анализ компромисса между точностью и сложностью идентифицированных моделей динамических систем

One of the rapidly developing areas of the modern control theory is the identification of systems associated with the construction of mathematical models of systems in the form of a set of mathematical relationships that adequately reflect the basic properties of the system. Symbolic regression methods are becoming more and more popular in the problems of structural-parametric identification of systems based on available observations and experimental data, which allow building regression models in the form of codes of mathematical expressions in a symbolic form. Among the known numerical evolutionary methods of symbolic regression, the universally acknowledged “favorite” is the method of genetic programming”, the application of which allows us to describe the search for solving a problem as the construction of a regression model by enumerating various arbitrary superpositions of functions from some predetermined set. In this case, the important indicators determining the quality of identification of the mathematical model of the system are the accuracy and complexity of the identified model. Often, the system model obtained as a result of solving identification problem is not accurate enough or excessively complex. As a result, the solution to the identification problem is inextricably linked to ensuring sufficient accuracy and simplicity of the identified model. In this connection, it is natural to adhere to the principle of balanced identification, which indicates the search for a compromise between the accuracy of reproduction and the measure of complexity of the identified model. The purpose of this paper, which develops the concept of balanced identification, is to analyze the trade-off between the accuracy and complexity of models of dynamic systems identified by genetic programming. In this paper we introduce a functional "accuracy-complexity", which allows us to balance the trade-off between these key indicators of the identified models when solving the identification problem. The effectiveness of the proposed functional is demonstrated on the example of computer identification by genetic programming of a Lorentz dynamical system.

The Impact of Blockchain Technology on Financial Markets and Its Future Trends: An Economic Perspective Based on Data Analysis

Based on the economic perspective of data analysis, this paper deeply discusses the impact of blockchain technology on the financial market and its future trend. By using econometrics, we systematically analyze how blockchain technology can change the operation mechanism of financial markets, improve transaction efficiency, reduce transaction costs, and enhance the security and transparency of financial markets. The study has found that the decentralized nature of blockchain technology can help to break down the barriers of the traditional financial market and promote the popularization and inclusiveness of financial services. At the same time, the automatic execution function of smart contracts simplifies the process of financial transactions and reduces the risk of human intervention and fraud. In addition, the blockchain technology has also enhanced the trust mechanism of the financial markets by improving the security and traceability of the data. In terms of econometric analysis, we use a large amount of financial data to empirically test the impact of blockchain technology on the performance of the financial market by building regression models, time series analysis and other methods. The results show that there is a significant positive correlation between the application of blockchain technology and financial market efficiency, liquidity and stability. Looking into the future, with the continuous innovation and improvement of blockchain technology, its application in the financial market will be more extensive and deeper. On the one hand, blockchain technology is expected to promote the further digitalization and intelligence of the financial market, and improve the convenience and personalization of financial services. On the other hand, blockchain technology will also promote the cross-border integration and innovation of the financial market, and inject new vitality into the global economic development.

Modeling health and well-being measures using ZIP code spatial neighborhood patterns

Individual-level assessment of health and well-being permits analysis of community well-being and health risk evaluations across several dimensions of health. It also enables comparison and rankings of reported health and well-being for large geographical areas such as states, metropolitan areas, and counties. However, there is large variation in reported well-being within such large spatial units underscoring the importance of analyzing well-being at more granular levels, such as ZIP codes. In this paper, we address this problem by modeling well-being data to generate ZIP code tabulation area (ZCTA)-level rankings through spatially informed statistical modeling. We build regression models for individual-level overall well-being index and scores from five subscales (Physical, Financial, Social, Community, Purpose) using individual-level demographic characteristics as predictors while including a ZCTA-level spatial effect. The ZCTA neighborhood information is incorporated by using a graph Laplacian matrix; this enables estimation of the effect of a ZCTA on well-being using individual-level data from that ZCTA as well as by borrowing information from neighboring ZCTAs. We deploy our model on well-being data for the U.S. states of Massachusetts and Georgia. We find that our model can capture the effects of demographic features while also offering spatial effect estimates for all ZCTAs, including ones with no observations, under certain conditions. These spatial effect estimates provide community health and well-being rankings of ZCTAs, and our method can be deployed more generally to model other outcomes that are spatially dependent as well as data from other states or groups of states.

Revenue Dependence Analysis of the Domestic and Foreign Manufacturers of Goods in the Field of Information and Communication Services on the Rate of Foreign Currency

Payments for goods and services between Russian consumers and foreign suppliers are made in US currency. Dollar to ruble exchange rate is constantly changing, that creates difficulties in forecast estimates of trade transactions and affects the competitiveness of domestic producers. In this paper, the authors built regression models and determined the closeness of the relationship between the US dollar exchange rate and the revenue of foreign and domestic producers of goods in the field of information and communication services in order to compare the terms of trade and assess the competitiveness of domestic producers. As a result, of the study, it was found that the revenue of foreign companies, manufacturers of goods in the field of information and communication services directly depends on the US dollar rate. On the contrary, the US dollar exchange rate is an insignificant factor for the revenue of domestic companies. This distribution makes trade conditions unequal and jeopardizes the competitiveness of the domestic producer. The conducted studies indicate the need to increase the real level of the weighted average rate of import customs duty to the optimal size, since only at the optimal level of the analyzed rate, domestic companies will be able to be in equal economic conditions.

A strategy based on statistical modelling and multi-objective optimization to design a dishwasher cleaning cycle

This study proposes a novel approach based on statistical learning and multi-objective optimization to reduce the need for experiments during the design phase of new cleaning cycles for household dishwashers. We first build regression models associated with the feature selection methods to predict the outputs of a dishwasher cleaning cycle by using the existing cleaning cycles’ program flows as input data and the results of the performance laboratory tests of the related cleaning cycles as output data. Then, a multi-objective optimization problem is defined by assigning the regression models and chosen features as objective functions and unknown decision variables, respectively. Obtained optimization problem is then solved by using evolutionary algorithms according to the designer’s preferences (or customers’ needs).

Patellar tendon biomechanical and morphologic properties and their relationship to serum clinical variables in persons with prediabetes and type 2 diabetes.

Tendon biomechanical properties and fibril organization are altered in patients with diabetes compared to healthy individuals, yet few biomarkers have been associated with in vivo tendon properties. We investigated the relationships between in vivo imaging-based tendon properties, serum variables, and patient characteristics across healthy controls (n = 14, age: 45 ± 5 years, body mass index [BMI]: 24 ± 1, hemoglobin A1c [HbA1c]: 5.3 ± 0.1%), prediabetes (n = 14, age: 54 ± 5 years, BMI: 29 ± 2; HbA1c: 5.7 ± 0.1), and type 2 diabetes (n = 13, age: 55 ± 3 years, BMI: 33 ± 2, HbA1c: 6.7 ± 0.3). We used ultrasound speckle-tracking and measurements from magnetic resonance imaging (MRI) to estimate the patellar tendon in vivo tangent modulus. Analysis of plasma c-peptide, interleukin-1β (IL-1β), IL-6, IL-8,tumor necrosis factor-α (TNF-α), adiponectin, leptin, insulin-like growth factor 1 (IGF-1), and C-reactive protein (CRP) was completed. We built regression models incorporating statistically significant covariates and indicators for the clinically defined groups. We found that tendon cross-sectional area normalized to body weight (BWN CSA) and modulus were lower in patients with type 2 diabetes than in healthy controls (p < 0.05). Our regression analysis revealed that a model that included BMI, leptin, high-density lipoprotein (HDL), low-density lipoprotein (LDL), age, and group explained ~70% of the variability in BWN CSA (R2 = 0.70, p < 0.001). For modulus, including the main effects LDL, groups, HbA1c, age, BMI, cholesterol, IGF-1, c-peptide, leptin, and IL-6, accounted for ~54% of the variability in modulus (R2 = 0.54, p < 0.05). While BWN CSA and modulus were lower in those with diabetes, group was a poor predicter of tendon properties when considering the selected covariates. These data highlight the multifactorial nature of tendon changes with diabetes and suggest that blood variables could be reliable predictors of tendon properties.

Homogeneity pursuit and variable selection in regression models for multivariate abundance data.

When building regression models for multivariate abundance data in ecology, it is important to allow for the fact that the species are correlated with each other. Moreover, there is often evidence species exhibit some degree of homogeneity in their responses to each environmental predictor, and that most species are informed by only a subset of predictors. We propose a generalized estimating equation(GEE) approach for simultaneous homogeneity pursuit (ie, grouping species with similar coefficient values while allowing differing groups for different covariates) and variable selection in regression models for multivariate abundance data. Using GEEs allows us to straightforwardly account for between-response correlations through a (reduced-rank) working correlation matrix. We augment the GEE with both adaptive fused lasso- and adaptive lasso-type penalties, which aim to cluster the species-specific coefficients within each covariate and encourage differing levels of sparsity across the covariates, respectively. Numerical studies demonstrate the strong finite sample performance of the proposed method relative to several existing approaches for modeling multivariate abundance data. Applying the proposed method to presence-absence records collected along the Great Barrier Reef in Australia reveals both a substantial degree of homogeneity and sparsity in species-environmental relationships. We show this leads to a more parsimonious model for understanding the environmental drivers of seabed biodiversity, and results in stronger out-of-sample predictive performance relative to methods that do not accommodate such features.

Computational Modelling of the Nigeria’s Daily Crude Oil Prices During the Russia – Ukraine War.

The study on the computational modelling of Nigeria’s crude oil prices during the Russia – Ukraine war was conducted to determine and select an appropriate model that best describes the functional behaviour of crude oil prices in Nigeria during the Russia – Ukraine war. The research data was the daily price of crude oil prices and the time under review collected from the Central Bank of Nigeria website, and spanned the period from February 24, 2022, to June 13, 2023. The total observations summed up to three hundred and eighteen days (318). Six models were estimated for the study namely; linear, quadratic, cubic, log-linear, linear-log, and log-log models. Nevertheless, the Log-linear Model, which had the values (S= 0.045; R2 = 67.6%; F = 660.29; p=.000), and the smallest accuracy measures (MAE = 0.030; MSE = 0.002; MAPE = 0.034), is adjudged as the best-fit model among the six built regression models. As a result, the Log-linear estimation has the most impact on the crude oil prices of Nigeria during the period of the Russia –Ukraine war under review. The study hereby recommends forecasting crude oil prices using the log-linear model.

APRENDIZADO DE MÁQUINA APLICADO A QSAR

MACHINE LEARNING APLLIED TO QSAR. Over the years the study of the quantitative structure-activity relationship (QSAR) has transformed from a simple regression analysis to the implementation of machine learning (ML) with multiple statistics. Today ML-based QSAR models are quite important and play a notable role in drug design and screening, property prediction, biological activity, etc. ML methods applied to QSAR build classification or regression models to describe/predict the complex relationships between the chemical structure of molecules and biological activity. Even with the increase in scientific publications addressing this topic written in Portuguese, there is still a shortage of scientific articles explaining ML techniques applied to QSAR, how to build models, the types of models, algorithms, for the Brazilian scientific community. And to fill this need, we intend to approach the subject in a simple and didactic way for students and researchers who are starting in this very promising and important area. We will describe the fully explained theory of machine learning by applying QSAR, abstracting the complexity, and well-illustrated.

Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass models

Abstract Airborne laser scanning data are increasingly used to predict forest biomass over large areas. Biomass information cannot be derived directly from airborne laser scanning data; therefore, field measurements of forest plots are required to build regression models. We tested whether simulated laser scanning data of virtual forest plots could be used to train biomass models and thereby reduce the amount of field measurements required. We compared the performance of models that were trained with (i) simulated data only, (ii) a combination of simulated and real data, (iii) real data collected from different study sites, and (iv) real data collected from the same study site the model was applied to. We additionally investigated whether using a subset of the simulated data instead of using all simulated data improved model performance. The best matching subset of the simulated data was sampled by selecting the simulated forest plot with the highest correlation of the return height distribution profile for each real forest plot. For comparison, a randomly selected subset was evaluated. Models were tested on four forest sites located in Poland, the Czech Republic, and Canada. Model performance was assessed by root mean squared error (RMSE), squared Pearson correlation coefficient (r$^{2}$), and mean error (ME) of observed and predicted biomass. We found that models trained solely with simulated data did not achieve the accuracy of models trained with real data (RMSE increase of 52–122 %, r$^{2}$ decrease of 4–18 %). However, model performance improved when only a subset of the simulated data was used (RMSE increase of 21–118 %, r$^{2}$ decrease of 5–14 % compared to the real data model), albeit differences in model performance when using the best matching subset compared to using a randomly selected subset were small. Using simulated data for model training always resulted in a strong underprediction of biomass. Extending sparse real training datasets with simulated data decreased RMSE and increased r$^{2}$, as long as no more than 12–346 real training samples were available, depending on the study site. For three of the four study sites, models trained with real data collected from other sites outperformed models trained with simulated data and RMSE and r$^{2}$ were similar to models trained with data from the respective sites. Our results indicate that simulated data cannot yet replace real data but they can be helpful in some sites to extend training datasets when only a limited amount of real data is available.

A data-driven operating improvement method for the thermal power unit with frequent load changes

In the near and medium term, thermal power generation will still play an important peak-shaving role in providing grid connection to volatile renewable energy. Thermal power units need to adjust from the current load to the given load within a given time period, which provides space for operational improvement. In this paper, we propose an operating improvement method for the thermal power unit based on real-time monitoring data by observation dividing, feature construction and selection, clustering, and machine learning. The unit operation data is categorized into three feature subsets based on domain knowledge, which is used to distinguish different functions of historical data. Subsequently, the optimal feature subset and observations are selected for building regression models, including linear regression (LR), ensemble tree regression (ETR), neural network regression (NNR), and support vector regression (SVR). R-squared (R2), root mean square error (RMSE), and mean absolute error (MAE) are adopted to test the performance of the proposed regression model on the real-time monitoring data of a thermal unit, which has 80,000 observations of 36 different variables. Compared with benchmark methods, the proposed method has lower regression error in the numerical experiment. Thus, we can thereby improve the efficiency of operational management based on the built learning model. Furthermore, in response to peak shaving requirements, the proposed method in this article considers operational optimization over time periods containing multiple time points compared to the traditional operational optimization perspective. With the continuous arrival of monitoring data, the above method can be updated in a timely manner based on the new database to address model adjustments caused by unit aging and other factors.

Diagnostic Signal Method for Fault Identification of Electro-Hydraulic Servo Actuators

In this paper, we develop a fault identification approach for electro-hydraulic servo actuators based on injecting a pre-defined diagnostic signal into the system and then extracting fault-related features from the phase space topology. Next, we build regression models using an artificial neural network, which maps the feature space to fault space to identify the faults represented by the system’s parameters. The performance of the proposed fault identification approach is evaluated when the degradation of permanent armature occurs. The effect of parametric faults on the dynamics is studied and discussed. The different excitation of the system is considered, and the robustness of the proposed method under the condition of noise is also explored. The obtained results indicate the effectiveness of injected diagnostic signals in enriching the dynamics of the system and increasing the quality of extracted features and the accuracy of trained artificial neural networks.

Interpretation of high-dimensional linear regression: Effects of nullspace and regularization demonstrated on battery data

High-dimensional linear regression is important in many scientific fields. This article considers discrete measured data of underlying smooth latent processes, as is often obtained from chemical or biological systems. Interpretation in high dimensions is challenging because the nullspace and its interplay with regularization shapes regression coefficients. The data’s nullspace contains all coefficients that satisfy Xw=0, thus allowing very different coefficients to yield identical predictions. We developed an optimization formulation to compare regression coefficients and coefficients obtained by physical engineering knowledge to understand which part of the coefficient differences are close to the nullspace. This nullspace method is tested on a synthetic example and lithium-ion battery data. The case studies show that regularization and z-scoring are design choices that, if chosen corresponding to prior physical knowledge, lead to interpretable regression results. Otherwise, the combination of the nullspace and regularization hinders interpretability and can make it impossible to obtain regression coefficients close to the true coefficients when there is a true underlying linear model. Furthermore, we demonstrate that regression methods that do not produce coefficients orthogonal to the nullspace, such as fused lasso, can improve interpretability. In conclusion, the insights gained from the nullspace perspective help to make informed design choices for building regression models on high-dimensional data and reasoning about potential underlying linear models, which are important for system optimization and improving scientific understanding.

Building regression models of city buses’ fuel consumption

This study is justified by the need to develop route fuel consumption norms for city buses in operation based on the results of the analysis of statistical data on the operation of rolling stock, under weather conditions and the age structure of the bus fleet. At the same time, current modifications of buses and factors affecting their fuel consumption are selected. The criteria for the collection and processing of statistical data in a large city are given, taking into account the capabilities of their modern information systems. The preliminary analysis of the obtained statistical data, the subsequent nonlinear transformation of factors and the component analysis of age indicators is carried out in order to improve the quality of mathematical models of fuel consumption. Based on the obtained regression models, fuel consumption norms are determined for the routes of a large bus transport company for the forecast period. Keywords: rolling stock, city bus, age structure, weather conditions, fuel consumption, regression models

Determinants of singleness among women aged 40 and over in Algeria: what relation to the labor market?

The decrease in the average age of marriage and the increase in loneliness among women in Algeria is a phenomenon that is becoming increasingly visible in society. In the coming years, the number of single people will increase. This article analyses the factors leading to increased loneliness among women aged 40 and over in Algeria based on data from the MICS6/2019 survey. The minimum age threshold was chosen because it corresponds to the age after which the probability of first marriage is almost zero based on Algerian statistics. The methodology of this study is stepwise Wald logistic regression. The paper built regression models based on two samples: the first (24,681 women aged 40 and over) and the second (4,329 women aged 50-54). For an empirical study of loneliness among women, it is proposed to analyze the following determinants: type of employment, type of social protection, place of residence, level of education, and age. Based on the results of the research, four main conclusions were formed. First, the odds of being single are 14.1 times and 4.23 times higher among job-seeking and working women, respectively, compared to non-working women. Due to the loss of hope to get married, women choose career development instead of building a family union. Under these conditions, women integrate into the labor market late. Since most of this category is unemployed and not of retirement age, they have low health insurance coverage. Based on this, to create decent living conditions for single women aged 40 and older, it is advisable to launch a program to improve the qualifications of these women, find ways to integrate them into the working environment and provide them with health insurance. Secondly, the long-term trend indicates that loneliness as a psychological phenomenon will increase every year in society, which will, accordingly, contribute to the strengthening of the imbalance in the marriage market. Late marriage and declining fertility are indicators of new patterns of behavior brought about by economic and social change. Thirdly, the level of well-being is also a statistically significant factor influencing the loneliness of women. Middle-class women are 1.27 times more likely to be single than upper-class women. Fourth, the survey revealed significant regional differences. Women in Algeria’s north-eastern and north-central regions are more likely to remain single. These results can be further explored through qualitative research.

RAG genomic variation causes autoimmune diseases through specific structure-based mechanisms of enzyme dysregulation

Interpreting genetic changes observed in individual patients is a critical challenge. The array of immune deficiency syndromes is typically caused by genetic variation unique to individuals. Therefore, new approaches are needed to interpret functional variation and accelerate genomics interpretation. We constructed the first full-length structural model of human RAG recombinase across four functional states of the recombination process. We functionally tested 182 clinically observed RAG missense mutations. These experiments revealed dysfunction due to recombinase dysfunction and altered chromatin interactions. Structural modeling identified mechanical and energetic roles for each mutation. We built regression models for RAG1 (R2= 0.91) and RAG2 (R2= 0.97) to predict RAG activity changes. We applied our model to 711 additional RAG variants observed in population studies and identified a subset that may impair RAG function. Thus, we demonstrated a fundamental advance in the mechanistic interpretation of human genetic variations spanning from rare and undiagnosed diseases to population health.