Score-based Method Research Articles

Automatic planning for functional lung avoidance radiotherapy based on function-guided beam angle selection and plan optimization

Objective. This study aims to develop a fully automatic planning framework for functional lung avoidance radiotherapy (AP-FLART). Approach. The AP-FLART integrates a dosimetric score-based beam angle selection method and a meta-optimization-based plan optimization method, both of which incorporate lung function information to guide dose redirection from high functional lung (HFL) to low functional lung (LFL). It is applicable to both contour-based FLART (cFLART) and voxel-based FLART (vFLART) optimization options. A cohort of 18 lung cancer patient cases underwent planning-CT and SPECT perfusion scans were collected. AP-FLART was applied to generate conventional RT (ConvRT), cFLART, and vFLART plans for all cases. We compared automatic against manual ConvRT plans as well as automatic ConvRT against FLART plans, to evaluate the effectiveness of AP-FLART. Ablation studies were performed to evaluate the contribution of function-guided beam angle selection and plan optimization to dose redirection. Main results. Automatic ConvRT plans generated by AP-FLART exhibited similar quality compared to manual counterparts. Furthermore, compared to automatic ConvRT plans, HFL mean dose, V 20, and V 5 were significantly reduced by 1.13 Gy (p < .001), 2.01% (p < .001), and 6.66% (p < .001) respectively for cFLART plans. Besides, vFLART plans showed a decrease in lung functionally weighted mean dose by 0.64 Gy (p < .01), fV 20 by 0.90% (p = 0.099), and fV 5 by 5.07% (p < .01) respectively. Though inferior conformity was observed, all dose constraints were well satisfied. The ablation study results indicated that both function-guided beam angle selection and plan optimization significantly contributed to dose redirection. Significance. AP-FLART can effectively redirect doses from HFL to LFL without severely degrading conventional dose metrics, producing high-quality FLART plans. It has the potential to advance the research and clinical application of FLART by providing labor-free, consistent, and high-quality plans.

Towards a distributed nodes selection mechanism for federated learning applied to blockchain-based IoT

Integrating blockchain (BC) with Federated Learning (FL) shows promise but presents challenges, particularly in the selection of the most appropriate IoT nodes for sensitive tasks. Existing Artificial Intelligence (AI) based approaches are tailored to dynamic environments, but they are complex and resource-intensive. On the other hand, score-based methods are faster to implement but lack flexibility. In this paper, we propose a two-step hybrid solution which uses the reputation score approach to train a DRL model, creating a framework that combines the efficiency of deterministic methods with the adaptability of AI-based solutions. In fact, we designed a score-based method relying on devices attributes and behavior making the system operational from the outset. Also, this allows the gathering of relevant real-time data for training the DRL model. Besides, the variations in the performances of IoT devices pose a challenge in achieving synchronous aggregation. To address this, we designed a multi-level aggregation mechanism, which allows local models to be uploaded to the BC, where an aggregator is in charge of validation. The validated models are then aggregated into intermediate models. This process continues until a global model is formed. To evaluate our approach, we created several simulation scenarios including the number of nodes to assess scalability, the dropout rate to estimate availability, and the percentage of malicious nodes to evaluate the robustness of the system against attacks. These experiments aimed to demonstrate the effectiveness of our approach. The obtained results are promising highlighting its robustness and flexibility showing improved performance, security, and availability.

A score-based filter for nonlinear data assimilation

We propose a score-based generative sampling method for solving the nonlinear filtering problem with superior accuracy. A major drawback of existing nonlinear filtering methods, e.g., particle filters, is the low accuracy in handling high-dimensional nonlinear problems. To overcome this issue, we incorporate the score-based diffusion model into the recursive Bayesian filter framework to develop a novel score-based filter (SF). The key idea of SF is to store the information of the recursively updated filtering density function in the score function, instead of storing the information in a set of finite Monte Carlo samples (used in particle filters and ensemble Kalman filters). By leveraging the reverse-time diffusion process, SF can generate unlimited samples to characterize the filtering density. An essential aspect of SF is its analytical update step, gradually incorporating data information into the score function. This step is crucial in mitigating the degeneracy issue faced when dealing with very high-dimensional nonlinear filtering problems. Three benchmark problems are used to demonstrate the performance of our method. In particular, SF provides surprisingly impressive performance in reliably capturing/tracking the 100-dimensional stochastic Lorenz system that is a well-known challenging problem for existing filtering methods.

The Impact of the Flight to Quality on Office Rents and Vacancy Rates in Tokyo

Abstract With the rapid spread of telecommuting since the COVID-19 pandemic, companies have been relocating to high-end business centers, thereby enhancing the workplace experience for employees, a phenomenon called the "flight to quality." However, this trend’s impact on rents and vacancy rates in individual office buildings has not been extensively studied. To determine the effects of the flight-to-quality phenomenon on individual buildings, we examine the impact of modern amenities, which directly influence employee lifestyles, on rents and vacancy rates in the Tokyo office market. Using a propensity score-based quasi-experimental method, we find that commercial properties with such modern amenities command higher rents and experience lower vacancy rates than those without. The difference in vacancy rates has increased since 2020. However, the significance of these amenities diminishes for properties less competitive in age, size, and location. The results indicate that the "flight to quality" may further polarize the office real estate market into two categories: one for high-end buildings experiencing increasing demand, and another for those with modest amenities experiencing decreasing demand. The findings have implications for office building owners/investors and the government, make educated decisions as to whether to invest in modern amenities, join the quality competition, or encourage urban restructuring.

Transarterial Chemoembolization Combined with Tyrosine Kinase Inhibitors Plus Immune Checkpoint Inhibitors Versus Tyrosine Kinase Inhibitors Plus Immune Checkpoint Inhibitors in Unresectable Hepatocellular Carcinoma with First- or Lower-Order Portal Vein Tumor Thrombosis.

To compare the efficacy of transarterial chemoembolization (TACE) combined with tyrosine kinase inhibitors (TKIs) plus immune checkpoint inhibitors (ICIs) (TACE-TKI-ICI) versus TKIs plus ICIs (TKI-ICI) for unresectable hepatocellular carcinoma (HCC) with first- or lower-order portal vein tumor thrombosis (PVTT). A retrospective study was performed in HCC patients with first- or lower-order PVTT receiving TKIs (Lenvatinib or sorafenib) plus ICIs (camrelizumab, sintilimab, or atezolizumab) with or without TACE from four institutions between January 2019 and January 2022. Propensity score-based method was performed to minimize bias by confounding factors. Tumor response, progression-free survival (PFS), overall survival (OS), and adverse events (AEs) were evaluated and compared between the two groups. After inverse probability of treatment weighting, two balanced pseudopopulations were created: 106 patients in the TACE-TKI-ICI group and 109 patients in the TKI-ICI group. The objective response rate was higher in the TACE-TKI-ICI group (50.9% vs. 28.4%, P < 0.001). The median PFS and OS were significantly longer in the TACE-TKI-ICI group than in the TKI-ICI group (PFS: 9.1 vs. 5.0months, P = 0.005; OS: 19.1 vs. 12.7months, P = 0.002). In Cox regression, TACE-TKI-ICI treatment was an independent predictor of favorable OS. Treatment-related grade 3/4 AEs were comparable between the two groups (22.6% vs. 17.9%, P = 0.437). TACE-TKI-ICI therapy contributed to better tumor control, PFS and OS than TKI-ICI therapy in unresectable HCC patients with first- or lower-order PVTT.

Empirical analysis of social impacts of a rural social enterprise: insights for local and regional development

ABSTRACT In developing countries the most marginalised and disadvantaged people are in rural, remote and regional areas and social enterprises in these areas – rural social enterprises (RSEs) – have been identified as key development actors in this context. However, their impacts are rarely rigorously measured. Our study fills this gap by measuring an RSE’s social impact in a developing country. A smallholder farmers’ survey (n = 1021) is utilised in a propensity score-based method which allowed us to generate counterfactual and estimate outcomes between members and non-members of an RSE. This method was complemented by a stakeholder focus group discussion. Predictors of participation and social impacts of the RSE are identified besides an evaluation of its interventions. Results generate implications for social enterprise practitioners, supporters and policymakers interested in applying RSEs as local and regional development actors as well as researchers involved in social impact measurement.

Contrast-specific propensity scores for causal inference with multiple interventions.

Existing methods that use propensity scores for heterogeneous treatment effect estimation on non-experimental data do not readily extend to the case of more than two treatment options. In this work, we develop a new propensity score-based method for heterogeneous treatment effect estimation when there are three or more treatment options, and prove that it generates unbiased estimates. We demonstrate our method on a real patient registry of patients in Singapore with diabetic dyslipidemia. On this dataset, our method generates heterogeneous treatment recommendations for patients among three options: Statins, fibrates, and non-pharmacological treatment to control patients' lipid ratios (total cholesterol divided by high-density lipoprotein level). In our numerical study, our proposed method generated more stable estimates compared to a benchmark method based on a multi-dimensional propensity score.

Score-based transport modeling for mean-field Fokker-Planck equations

We use the score-based transport modeling method to solve the mean-field Fokker-Planck equations, which we call MSBTM. We establish an upper bound on the time derivative of the Kullback-Leibler (KL) divergence to MSBTM numerical estimation from the exact solution, thus validates the MSBTM approach. Besides, we provide an error analysis for the algorithm. In numerical experiments, we study three types of mean-field Fokker-Planck equation and their corresponding dynamics of particles in interacting systems. The MSBTM algorithm is numerically validated through qualitative and quantitative comparison between the MSBTM solutions, the results of integrating the associated stochastic differential equation and the analytical solutions if available.

Association Between Cannabis Use and Opioid Consumption, Pain, and Respiratory Complications After Surgery: A Retrospective Cohort Analysis.

Cannabis is a widely used illicit drug with effects on different pain pathways. However, interactions between cannabis and postoperative pain are unclear. Cannabis smoking also affects the lungs, but the impact of cannabis use on postoperative pulmonary complications is unknown. We hypothesized that preoperative cannabis use in adults having elective surgery is associated with higher postoperative opioid consumption. Secondarily, we tested the hypothesis that cannabis use is associated with higher pain scores, hypoxemia (oxygen saturation [Sp o2 ]/fraction of inspired oxygen [F io2 ] ratio), and higher postoperative pulmonary complications compared to nonuse of cannabis. In this retrospective study, we included adult patients who had elective surgeries at Cleveland Clinic Main Campus between January 2010 and December 2020. The exposure was use of cannabis within 30 days before surgery, and the control group never used cannabis. Patients who had regional anesthesia or chronic pain diagnosis were excluded. The primary outcome was postoperative opioid consumption; 3 secondary outcomes were time-weighted average (TWA) postoperative pain score, TWA Sp o2 /F io2 ratio, and composite of pulmonary complications after surgery. We assessed the association between cannabis use and opioid consumption during the first 24 postoperative hours using linear regression on log-transformed opioid consumption with a propensity score-based method (inverse probability of treatment weighting [IPTW]) adjusting for confounders. We further adjusted for imbalanced confounding variables after IPTW was applied. In total, 1683 of 34,521 patients were identified as cannabis users. Cannabis use was associated with increased opioid consumption, with an adjusted ratio of geometric means (95% confidence interval [CI]) of 1.30 (1.22-1.38; P < .0001) for cannabis users versus nonusers. Secondarily, (1) cannabis use was associated with increased TWA pain score, with a difference in means of 0.57 (95% CI, 0.46-0.67; P < .0001); (2) cannabis use was not associated with TWA Sp o2 /F io2 , with an adjusted difference in means of 0.5 (95% CI, -3.1 to 4.2; P = .76); and (3) cannabis use was not associated with a collapsed composite of pulmonary complications, with estimated odds ratio of 0.90 (95% CI, 0.71-1.13; P = .34). Adult cannabis users undergoing surgeries were found to have significantly higher postoperative opioid consumption and pain scores than nonusers. Cannabis use did not have a clinically meaningful association with hypoxia or composite pulmonary complications.

A Novel Score-Based LiDAR Point Cloud Degradation Analysis Method

A Novel Score-Based LiDAR Point Cloud Degradation Analysis Method

Important statistical points for clinical research: from basics to applications

Clinical research is conducted to investigate physicians' clinical questions and to clarify research hypotheses. When conducting clinical research, it is important to carefully consider the research design in advance. An optimal design that meets the objectives of the study and addresses practical implementation issues is desirable. Randomized comparisons during the final confirmatory phase may be the best tool for comparing treatments. However, not all clinical questions can be answered through randomized controlled trials. This article summarizes the basics of clinical study design and explains the role of randomization. It also introduces a propensity score-based method that has gained attention as a statistical method for comparing treatment groups when randomization is not feasible, and is increasingly being utilized in clinical research.

A score-based method of immune status evaluation for healthy individuals with complete blood cell counts

BackgroundWith the COVID-19 outbreak, an increasing number of individuals are concerned about their health, particularly their immune status. However, as of now, there is no available algorithm that effectively assesses the immune status of normal, healthy individuals. In response to this, a new score-based method is proposed that utilizes complete blood cell counts (CBC) to provide early warning of disease risks, such as COVID-19.MethodsFirst, data on immune-related CBC measurements from 16,715 healthy individuals were collected. Then, a three-platform model was developed to normalize the data, and a Gaussian mixture model was optimized with expectation maximization (EM-GMM) to cluster the immune status of healthy individuals. Based on the results, Random Forest (RF), Light Gradient Boosting Machine (LightGBM) and Extreme Gradient Boosting (XGBoost) were used to determine the correlation of each CBC index with the immune status. Consequently, a weighted sum model was constructed to calculate a continuous immunity score, enabling the evaluation of immune status.ResultsThe results demonstrated a significant negative correlation between the immunity score and the age of healthy individuals, thereby validating the effectiveness of the proposed method. In addition, a nonlinear polynomial regression model was developed to depict this trend. By comparing an individual’s immune status with the reference value corresponding to their age, their immune status can be evaluated.ConclusionIn summary, this study has established a novel model for evaluating the immune status of healthy individuals, providing a good approach for early detection of abnormal immune status in healthy individuals. It is helpful in early warning of the risk of infectious diseases and of significant importance.

Exploring the impact of collaboration on eco-innovation in SMEs: a contribution to the business modes of innovation framework

PurposeThe purpose of the study is to investigate how small- and medium-sized enterprises (SMEs) can effectively collaborate for eco-innovation using the business modes of innovation framework to emphasise three types of collaboration: “science, technology, and innovation” (STI), “learning by doing, using, and interacting” (DUI)-Vertical and DUI-Horizontal.Design/methodology/approachThis analysis uses data from 838 SMEs in the Basque Country (2018–2020) to evaluate the effects of the three types of collaboration on eco-innovation. The authors employ a propensity score-based method to address potential bias associated with endogeneity in innovation studies.FindingsThe findings suggest that DUI-Vertical collaboration has a positive relationship with the development of product, process and marketing eco-innovation. Furthermore, DUI-horizontal collaboration is the most effective collaboration mode for SMEs, positively impacting their overall eco-innovation portfolio. Finally, STI collaboration is positively associated with product eco-innovation.Practical implicationsPolicymakers should support SMEs by designing programmes that facilitate collaboration between competing firms to stimulate eco-innovation, but potential challenges of coopetition must be addressed. Rather than a generic, one-size-fit-all approach, SMEs' managers should identify the most appropriate partners corresponding to their specific eco-innovation goal, ensuring a more effective and targeted. Collaboration between science partners and SMEs should be reinforced by approximating the SMEs' needs more effectively.Originality/valueThis study contributes twofold. Firstly, the authors investigate whether the STI and DUI modes of innovation are determinant factors in the introduction of various types of eco-innovation. Secondly, the authors contribute to the literature on business modes of innovation by differentiating between DUI-Vertical (i.e. suppliers, customers and consultancy) and DUI-Horizontal (i.e. competitors) collaboration, thus highlighting the complexity of DUI collaboration forms.

Non-interventional Management of Asymptomatic Diminutive Choledocholithiasis Versus Endoscopic Extraction in Consecutive Patients.

Current guidelines recommend treating choledocholithiasis, regardless of symptoms or stone size, with endoscopic retrograde cholangiopancreatography (ERCP). However, asymptomatic choledocholithiasis, discovered incidentally on imaging, may carry a higher risk of ERCP-related adverse events, and some asymptomatic and diminutive stones may not cause biliary adverse events during extended follow-up. Therefore, we aimed to clarify the best treatment strategies for asymptomatic choledocholithiasis based on stone size. We retrospectively identified patients with incidental imaging-found asymptomatic diminutive (≤ 4mm) or non-diminutive (> 4mm) choledocholithiasis and divided them into two groups: those who did not undergo ERCP and were treated when complications arose (on-demand group) and those who underwent ERCP before being symptomatic (intervention group). Adverse events were defined as any biliary or pancreatic complication related to ERCP or arising during observation or after intervention. The primary outcome was the adjusted overall adverse event-free survival using the propensity score-based matching weights method comparing the two groups of stone size. Among 148 patients identified (median follow-up period, 969days), 68 had diminutive stones and 80 had non-diminutive stones. Of the 68 patients with diminutive stones, 51 were in the on-demand group and 17 in the intervention group. The overall adjusted adverse event-free survival was significantly higher in the on-demand group for diminutive stones (97.4% and 70.1%, respectively, at 3years; p = 0.01). Patients with incidental imaging-detected asymptomatic diminutive choledocholithiasis may benefit from clinical observation, pursuing ERCP when symptoms develop.

Development and validation of a new risk assessment model for immunomodulatory drug-associated venous thrombosis among Chinese patients with multiple myeloma

BackgroundIndividuals with multiple myeloma (MM) receiving immunomodulatory drugs (IMiDs) are at risk of developing venous thromboembolism (VTE), a serious complication. There is no established clinical model for predicting VTE in the Chinese population. We develop a new risk assessment model (RAM) for IMiD-associated VTE in Chinese MM patients.MethodsWe retrospectively selected 1334 consecutive MM patients receiving IMiDs from 16 medical centers in China and classified them randomly into the derivation and validation cohorts. A multivariate Cox regression model was used for analysis.ResultsThe overall incidence of IMiD-related VTE in Chinese MM patients was 6.1%. Independent predictive factors of VTE (diabetes, ECOG performance status, erythropoietin-stimulating agent use, dexamethasone use, and VTE history or family history of thrombosis) were identified and merged to develop the RAM. The model identified approximately 30% of the patients in each cohort at high risk for VTE. The hazard ratios (HRs) were 6.08 (P < 0.001) and 6.23 (P < 0.001) for the high-risk subcohort and the low-risk subcohort, respectively, within both the derivation and validation cohorts. The RAM achieved satisfactory discrimination with a C statistic of 0.64. The stratification approach of the IMWG guidelines yielded respective HRs of 1.77 (P = 0.053) and 1.81 (P = 0.063). The stratification approach of the SAVED score resulted in HRs of 3.23 (P = 0.248) and 1.65 (P = 0.622), respectively. The IMWG guideline and the SAVED score-based method yielded C statistics of 0.58 and 0.51, respectively.ConclusionsThe new RAM outperformed the IMWG guidelines and the SAVED score and could potentially guide the VTE prophylaxis strategy for Chinese MM patients.

Aortic Stiffness Is Independently Associated with Intracranial Carotid Artery Calcification in Patients with Ischemic Stroke.

Intracranial carotid artery calcification (ICAC), as a strong contributor to the occurrence of ischemic stroke, might be present in the medial or intimal arterial layer. Traditional cardiovascular risk factors (CVRFs) are associated with ICAC; however, its association with new markers of vascular function is less understood. The paper aimed to evaluate the relationship between carotid-femoral pulse wave velocity (CF-PWV) and ICAC subtypes. We enrolled 65 patients with ischemic stroke. CF-PWV, systolic, diastolic, mean blood pressure, and pulse pressure were measured within 6 ± 2 days after stroke onset, and CT was performed within 24 h. ICAC on the stroke site was classified by two methods: volume and score based. Tertiles of ICAC volume were determined, and low-grade ICAC (T1) was regarded as a reference. According to the score-based method, (dominant) medial and (dominant) intimal ICAC subtypes were determined. Data were analyzed with multivariate logistic regression. Medial and intimal ICAC subtypes were found in 34 (52%) and 24 (37%) patients, respectively. In 11% of patients, no ICAC calcifications were found. CF-PWV was higher in patients with high-grade ICAC (OR = 1.56, 95% CI = 1.03-2.35, p = 0.035). CF-PWV was higher in patients with the medial ICAC subtype (OR = 1.60, 95% CI = 1.00-2.55, p = 0.049) after adjustment for traditional CVRFs. Our study demonstrates that among patients with ischemic stroke, aortic stiffness is independently associated with ICAC and that medial ICAC, compared with intimal ICAC, is accompanied by more advanced aortic stiffness.

AORTIC STIFFNESS IS INDEPENDENTLY ASSOCIATED WITH INTRACRANIAL CAROTID ARTERY CALCIFICATION IN PATIENTS WITH ISCHEMIC STROKE

Objective: Intracranial carotid artery calcification (ICAC), as a strong contributor to the occurrence of ischemic stroke, might be present in the medial or intimal arterial layer. Traditional vascular risk factors are associated with ICAC; however, its association with new markers of vascular function are less understood. The paper aims to evaluate the relationship between carotid-femoral pulse wave velocity (CF-PWV) and ICAC subtypes. Design and method: We enrolled 65 patients with acute ischemic stroke. CF-PWV, systolic, diastolic and mean blood pressure, and pulse pressure (SBP, DBP, MBP, PP) were measured within 6±2 days of stroke onset. CT was performed within 24 hours of stroke onset and ICAC on the stroke site was classified by two methods: volume- and score-based. Tertiles of ICAC volume were determined, and low-grade ICAC (T1) was regarded as a reference. According to the score-based method, medial and intimal ICAC subtypes were determined. Data were analyzed with multivariate logistic regression. Results: Medial and intimal ICAC subtypes were found in 34 (52%) and 24 (37%) patients, respectively. In 11% of patients no ICAC calcifications were found. CF-PWV was higher in patients with high-grade ICAC (OR = 1.56, 95%CI = 1.03-2.35, p = 0.035). CF-PWV was higher in patients with the medial ICAC subtype than in patients with the intimal ICAC subtype (OR = 1.60, 95%CI = 1.00-2.55, p = 0.049) after adjustment for age, MBP, diabetes mellitus, arterial hypertension, hyperlipidemia, and smoking status. Conclusions: Our study demonstrates that among patients with ischemic stroke, aortic stiffness is independently associated with ICAC, and that medial ICAC, compared with intimal ICAC, is accompanied by more advanced aortic stiffness.

Health-Aware Food Recommendation Based on Knowledge Graph and Multi-Task Learning.

Current food recommender systems tend to prioritize either the user's dietary preferences or the healthiness of the food, without considering the importance of personalized health requirements. To address this issue, we propose a novel approach to healthy food recommendations that takes into account the user's personalized health requirements, in addition to their dietary preferences. Our work comprises three perspectives. Firstly, we propose a collaborative recipe knowledge graph (CRKG) with millions of triplets, containing user-recipe interactions, recipe-ingredient associations, and other food-related information. Secondly, we define a score-based method for evaluating the healthiness match between recipes and user preferences. Based on these two prior perspectives, we develop a novel health-aware food recommendation model (FKGM) using knowledge graph embedding and multi-task learning. FKGM employs a knowledge-aware attention graph convolutional neural network to capture the semantic associations between users and recipes on the collaborative knowledge graph and learns the user's requirements in both preference and health by fusing the losses of these two learning tasks. We conducted experiments to demonstrate that FKGM outperformed four competing baseline models in integrating users' dietary preferences and personalized health requirements in food recommendations and performed best on the health task.

Reconstruction of the personal information from human genome reads in gut metagenome sequencing data

Human DNA present in faecal samples can result in a small number of human reads in gut shotgun metagenomic sequencing data. However, it is presently unclear how much personal information can be reconstructed from such reads, and this has not been quantitatively evaluated. Such a quantitative evaluation is necessary to clarify the ethical concerns related to data sharing and to enable efficient use of human genetic information in stool samples, such as for research and forensics. Here we used genomic approaches to reconstruct personal information from the faecal metagenomes of 343 Japanese individuals with associated human genotype data. Genetic sex could be accurately predicted based on the sequencing depth of sex chromosomes for 97.3% of the samples. Individuals could be re-identified from the matched genotype data based on human reads recovered from the faecal metagenomic data with 93.3% sensitivity using a likelihood score-based method. This method also enabled us to predict the ancestries of 98.3% of the samples. Finally, we performed ultra-deep shotgun metagenomic sequencing of five faecal samples as well as whole-genome sequencing of blood samples. Using genotype-calling approaches, we demonstrated that the genotypes of both common and rare variants could be reconstructed from faecal samples. This included clinically relevant variants. Our approach can be used to quantify personal information contained within gut metagenome data.

MatchRanges: generating null hypothesis genomic ranges via covariate-matched sampling.

Deriving biological insights from genomic data commonly requires comparing attributes of selected genomic loci to a null set of loci. The selection of this null set is non-trivial, as it requires careful consideration of potential covariates, a problem that is exacerbated by the non-uniform distribution of genomic features including genes, enhancers, and transcription factor binding sites. Propensity score-based covariate matching methods allow the selection of null sets from a pool of possible items while controlling for multiple covariates; however, existing packages do not operate on genomic data classes and can be slow for large data sets making them difficult to integrate into genomic workflows. To address this, we developed matchRanges, a propensity score-based covariate matching method for the efficient and convenient generation of matched null ranges from a set of background ranges within the Bioconductor framework. Package: https://bioconductor.org/packages/nullranges, Code: https://github.com/nullranges, Documentation: https://nullranges.github.io/nullranges.