The polysaccharide pectin is a major component of the plant cell wall. The pectic glycan homogalacturonan (HG) is a proportionally small but important component of a specialized seed cell wall called mucilage. HG is synthesized in a highly methylesterified form, and, following secretion, is de-methylesterified by pectin methylesterases (PMEs). The degree of methylesterification of HG determines the structural and functional properties of pectin, but how methylesterification is regulated remains largely unknown. Here, we identified two BEL1-Like homeodomain (BLH) transcription factors, BLH2 and BLH4, as positive regulators of HG de-methylesterification in Arabidopsis (Arabidopsis thaliana) seed coat mucilage. BLH2 and BLH4 were significantly expressed in mucilage secretory cells during seed mucilage production. BLH2 and BLH4 single mutants exhibited no obvious mucilage phenotype, but the blh2 blh4 double mutant displayed significantly reduced mucilage adherence to the seed. Reduced mucilage adherence in blh2 blh4 was caused by decreased PME activity in the seed coat, which increased the degree of methylesterification of HG in mucilage. The expression of several PME metabolism-related genes, including PME58, PECTIN METHYLESTERASE INHIBITOR6, SEEDSTICK, and MYB52 was significantly altered in blh2 blh4 seeds. BLH2 and BLH4 directly activated PME58 expression by binding to its TGACAGGT cis-element. Moreover, pme58 mutants exhibited reduced mucilage adherence similar to that of blh2 blh4, and the blh2 blh4 pme58 triple mutant exhibited no additional mucilage adherence defects. Furthermore, overexpression of PME58 in blh2 blh4 rescued the mucilage adherence defect. Together, these results demonstrate that BLH2 and BLH4 redundantly regulate de-methylesterification of HG in seed mucilage by directly activating PME58.

Terpene volatiles are found in many important fruit crops, but their relationship to flavor is poorly understood. Here, we demonstrate using sensory descriptive and discriminant analysis that 1,8-cineole contributes a key floral/eucalyptus note to the aroma of ripe 'Hort16A’ kiwifruit (Actinidia chinensis). Two quantitative trait loci (QTLs) for 1,8-cineole production were identified on linkage groups 27 and 29a in a segregating A. chinensis population, with the QTL on LG29a colocating with a complex cluster of putative terpene synthase (TPS)-encoding genes. Transient expression in Nicotiana benthamiana and analysis of recombinant proteins expressed in Escherichia coli showed four genes in the cluster (AcTPS1a–AcTPS1d) encoded functional TPS enzymes, which produced predominantly sabinene, 1,8-cineole, geraniol, and springene, respectively. The terpene profile produced by AcTPS1b closely resembled the terpenes detected in red-fleshed A. chinensis. AcTPS1b expression correlated with 1,8-cineole content in developing/ripening fruit and also showed a positive correlation with 1,8-cineole content in the mapping population, indicating the basis for segregation is an expression QTL. Transient overexpression of AcTPS1b in Actinidia eriantha fruit confirmed this gene produced 1,8-cineole in Actinidia. Structure-function analysis showed AcTPS1a and AcTPS1b are natural variants at key TPS catalytic site residues previously shown to change enzyme specificity in vitro. Together, our results indicate that AcTPS1b is a key gene for production of the signature flavor terpene 1,8-cineole in ripe kiwifruit. Using a sensory-directed strategy for compound identification provides a rational approach for applying marker-aided selection to improving flavor in kiwifruit as well as other fruits.

First described in 1967, one of the most vexing problems in the care of preterm infants continues to be bronchopulmonary dysplasia (BPD). The clinical presentation and pathological changes associated with BPD, also referred to as chronic lung disease of prematurity, have changed substantially since that initial description by Northway et al. [1]. The condition described in that seminal report, characterised by marked respiratory distress associated with pulmonary oedema due to shunting across the patent ductus arteriosus, was also specific to preterm infants that had received high inspired oxygen concentrations for at least a week.

The aim of this study was to identify factors associated with the death of patients with COVID-19 pneumonia caused by the novel coronavirus SARS-CoV-2.

All clinical and laboratory parameters were collected prospectively from a cohort of patients with COVID-19 pneumonia who were hospitalised to Wuhan Pulmonary Hospital (Wuhan City, Hubei Province, China) between 25 December 2019 and 7 February 2020. Univariate and multivariate logistic regression was performed to investigate the relationship between each variable and the risk of death of COVID-19 pneumonia patients.

In total, 179 patients with COVID-19 pneumonia (97 male and 82 female) were included in the present prospective study, of whom 21 died. Univariate and multivariate logistic regression analysis revealed that age ≥65 years (OR 3.765, 95% CI 1.146-17.394; p=0.023), pre-existing concurrent cardiovascular or cerebrovascular diseases (OR 2.464, 95% CI 0.755-8.044; p=0.007), CD3⁺CD8⁺ T-cells ≤75 cells·μL^–1 (OR 3.982, 95% CI 1.132-14.006; p<0.001) and cardiac troponin I ≥0.05 ng·mL^–1 (OR 4.077, 95% CI 1.166-14.253; p<0.001) were associated with an increase in risk of mortality from COVID-19 pneumonia. In a sex-, age- and comorbid illness-matched case–control study, CD3⁺CD8⁺ T-cells ≤75 cells·μL^–1 and cardiac troponin I ≥0.05 ng·mL^–1 remained as predictors for high mortality from COVID-19 pneumonia.

We identified four risk factors: age ≥65 years, pre-existing concurrent cardiovascular or cerebrovascular diseases, CD3⁺CD8⁺ T-cells ≤75 cells·μL^–1 and cardiac troponin I ≥0.05 ng·mL^–1. The latter two factors, especially, were predictors for mortality of COVID-19 pneumonia patients.

The coronavirus disease 2019 (COVID-19) epidemic, which was first reported in December 2019 in Wuhan, China, has caused 80 904 confirmed cases as of 9 March 2020, with 28 673 cases being reported outside of China. It has been declared a pandemic by the World Health Organization (WHO), has exhibited human-to-human transmissibility and has spread rapidly across countries [1]. Although the Chinese government has taken various measures to control city-to-city transmission (e.g. shutting down cities, extending holidays) and many other countries have implemented measures (such as airport screening and testing patients who have reported symptoms), the number of cases is still increasing quickly throughout the world.

Pulmonary endarterectomy (PEA) is the treatment of choice of chronic thromboembolic pulmonary hypertension (CTEPH) [1]. However, successfully operated patients may continue to suffer from dyspnoea and limitation of exercise capacity, despite improvement or even normalisation of pulmonary artery pressure (PAP), cardiac output (CO) and pulmonary vascular resistance (PVR) [2]. This absence of complete symptomatic recovery has been explained by a decreased right ventricular (RV) function reserve due to persistent increased afterload [3, 4], related to decreased pulmonary arterial compliance (PCa) more than to mildly increased PVR [5, 6]. There is therefore interest in assessing PCa in patients during the follow-up of PEA.

Background

Chronic lung disease of prematurity (CLD), also called bronchopulmonary dysplasia, is a major consequence of preterm birth, but the role of the microbiome in its development remains unclear. Therefore, we assessed the progression of the bacterial community in ventilated preterm infants over time in the upper and lower airways, and assessed the gut–lung axis by comparing bacterial communities in the upper and lower airways with stool findings. Finally, we assessed whether the bacterial communities were associated with lung inflammation to suggest dysbiosis.

Purpose of review

Diverse adverse events have been associated with administration of glatiramer acetate (GA), mainly local reactions at the injection site. Other, less frequent generalized reactions include isolated postinjection reactions and anaphylaxis, which may lead to discontinuation of GA.

Objective

To determine the contributions of apraxia of speech (AOS) and anomia to conversational dysfluency.

Objective

To explore practice differences in the diagnosis and management of autoimmune encephalitis (AE), which is complicated by issues with sensitivity/specificity of antibody testing, nonspecific MRI/EEG/CSF findings, and competing differential diagnoses.

Objective

To assess the risk of subsequent stroke among older patients discharged from an emergency department (ED) without a diagnosis of TIA or stroke.

Background

Transient loss of consciousness (TLOC) is a common reason for presentation to primary/emergency care; over 90% are because of epilepsy, syncope, or psychogenic non-epileptic seizures (PNES). Misdiagnoses are common, and there are currently no validated decision rules to aid diagnosis and management. We seek to explore the utility of machine-learning techniques to develop a short diagnostic instrument by extracting features with optimal discriminatory values from responses to detailed questionnaires about TLOC manifestations and comorbidities (86 questions to patients, 31 to TLOC witnesses).

Early recognition of longus colli calcific tendinitis can prevent unnecessary interventions including antibiotics and surgical procedures.

Surgical procedures are performed in the United States in a wide variety of clinical settings and with variation in clinical outcomes. In May 2012, the Task Force for Children’s Surgical Care, an ad hoc multidisciplinary group comprising physicians representing specialties relevant to pediatric perioperative care, was convened to generate recommendations to optimize the delivery of children’s surgical care. This group generated a white paper detailing the consensus opinions of the involved experts. Following these initial recommendations, the American College of Surgeons (ACS), Children’s Hospital Association, and Task Force for Children’s Surgical Care, with input from all related perioperative specialties, developed and published specific and detailed resource and quality standards designed to improve children’s surgical care (https://www.facs.org/quality-programs/childrens-surgery/childrens-surgery-verification). In 2015, with the endorsement of the American Academy of Pediatrics (https://pediatrics.aappublications.org/content/135/6/e1538), the ACS established a pilot verification program. In January 2017, after completion of the pilot program, the ACS Children’s Surgery Verification Quality Improvement Program was officially launched. Verified sites are listed on the program Web site at https://www.facs.org/quality-programs/childrens-surgery/childrens-surgery-verification/centers, and more than 150 are interested in verification. This report provides an update on the ACS Children’s Surgery Verification Quality Improvement Program as it continues to evolve.

OBJECTIVES:

To test the hypotheses that minority children with long-bone fractures are less likely to (1) receive analgesics, (2) receive opioid analgesics, and (3) achieve pain reduction.

Cystinuria is an autosomal recessive disorder characterized by excessive urinary excretion of cystine, resulting in recurrent cystine kidney stones, often presenting in childhood. Current treatment options for cystinuria include dietary and/or fluid measures and potassium citrate to reduce cystine excretion and/or increase solubility. Tiopronin and D-penicillamine are used in refractory cases to bind cystine in urine, albeit with serious side effects. A recent study revealed efficacy of nutritional supplement α-lipoic acid (ALA) treatment in preventing kidney stones in a mouse model of cystinuria. Here, we report 2 pediatric patients (6 and 15 years old) with cystinuria who received regular doses of ALA in addition to conventional therapy with potassium citrate. Both patients tolerated ALA without any adverse effects and had reduced frequency of symptomatic and asymptomatic kidney stones with disappearance of existing kidney stones in 1 patient after 2 months of ALA therapy. ALA treatment markedly improved laboratory markers of cystine solubility in urine with increased cystine capacity (–223 to –1 mg/L in patient 1 and +140 to +272 mg/L in patient 2) and decreased cystine supersaturation (1.7 to 0.88 in patient 1 and 0.64 to 0.48 in patient 2) without any changes in cystine excretion or urine pH. Our findings suggest that ALA improves solubility of cystine in urine and prevents stone formation in patients with cystinuria who do not respond to diet and citrate therapy.

OBJECTIVES:

Children born very preterm (VPT) are at an increased risk of developing mental health (MH) disorders. Our aim for this study was to assess rates of MH disorders in children born VPT and term at 13 years of age and stability of MH disorders between ages 7 and 13 years by using a diagnostic measure.

BACKGROUND:

Although autodialer centralized reminder and recall (C-R/R) from state immunization information systems (IISs) has been shown to raise childhood vaccination rates, its impact on human papillomavirus (HPV) vaccination rates is unclear.

OBJECTIVES:

To describe (1) the developmental trajectories of peer victimization from 6 to 17 years of age and (2) the early childhood behaviors and family characteristics associated with the trajectories.

BACKGROUND:

Several studies have investigated the association of breastfeeding status with offspring mortality in Africa, but most studies were from one center only or had limited statistical power to draw robust conclusions.

BACKGROUND AND OBJECTIVES:

Early diagnosis of cerebral palsy (CP) is critical in obtaining evidence-based interventions when plasticity is greatest. In 2017, international guidelines for early detection of CP were published on the basis of a systematic review of evidence. Our study aim was to reduce the age at CP diagnosis throughout a network of 5 diverse US high-risk infant follow-up programs through consistent implementation of these guidelines.

OBJECTIVES:

Standing orders are an effective way to increase vaccination rates, yet little is known about how pediatricians use this strategy for childhood immunizations. We assessed current use of, barriers to using, and factors associated with use of standing orders for vaccination among pediatricians.

We describe an atypical pediatric case of immunoglobulin A vasculitis (IgAV), also referred to as Henoch-Schönlein purpura, in which formation of spontaneous hematoma of the paraspinal muscles developed. Spontaneous or unprovoked hematomas rarely occur in IgAV. These manifestations have not been described specifically in the pediatric literature as coinciding with IgAV. These findings are alarming for nonaccidental trauma, particularly in a patient without underlying blood dyscrasia. Our objective for this report is to highlight the possible association of muscular hematoma formation with IgAV and to help providers consider this association when trauma and hemophilia has been ruled out.

BACKGROUND:

There is a dearth of evidence regarding the association of use of electronic cigarettes (e-cigarettes) with certain product characteristics and adolescent and young adult risk of unhealthy tobacco use patterns (eg, frequency of combustible cigarette smoking), which is needed to inform the regulation of e-cigarettes.

Multienvironment trials (METs) are widely used to assess the performance of promising crop germplasm. Though seldom designed to elucidate genetic mechanisms, MET data sets are often much larger than could be duplicated for genetic research and, given proper interpretation, may offer valuable insights into the genetics of adaptation across time and space. The Cooperative Dry Bean Nursery (CDBN) is a MET for common bean (Phaseolus vulgaris) grown for > 70 years in the United States and Canada, consisting of 20–50 entries each year at 10–20 locations. The CDBN provides a rich source of phenotypic data across entries, years, and locations that is amenable to genetic analysis. To study stable genetic effects segregating in this MET, we conducted genome-wide association studies (GWAS) using best linear unbiased predictions derived across years and locations for 21 CDBN phenotypes and genotypic data (1.2 million SNPs) for 327 CDBN genotypes. The value of this approach was confirmed by the discovery of three candidate genes and genomic regions previously identified in balanced GWAS. Multivariate adaptive shrinkage (mash) analysis, which increased our power to detect significant correlated effects, found significant effects for all phenotypes. Mash found two large genomic regions with effects on multiple phenotypes, supporting a hypothesis of pleiotropic or linked effects that were likely selected on in pursuit of a crop ideotype. Overall, our results demonstrate that statistical genomics approaches can be used on MET phenotypic data to discover significant genetic effects and to define genomic regions associated with crop improvement.

In plant–pathogen relations, disease symptoms arise from the interaction of the host and pathogen genomes. Host–pathogen functional gene interactions are well described, whereas little is known about how the pathogen genetic variation modulates both organisms’ transcriptomes. To model and generate hypotheses on a generalist pathogen control of gene expression regulation, we used the Arabidopsis thaliana–Botrytis cinerea pathosystem and the genetic diversity of a collection of 96 B. cinerea isolates. We performed expression-based genome-wide association (eGWA) for each of 23,947 measurable transcripts in Arabidopsis (host), and 9267 measurable transcripts in B. cinerea (pathogen). Unlike other eGWA studies, we detected a relative absence of locally acting expression quantitative trait loci (cis-eQTL), partly caused by structural variants and allelic heterogeneity hindering their identification. This study identified several distantly acting trans-eQTL linked to eQTL hotspots dispersed across Botrytis genome that altered only Botrytis transcripts, only Arabidopsis transcripts, or transcripts from both species. Gene membership in the trans-eQTL hotspots suggests links between gene expression regulation and both known and novel virulence mechanisms in this pathosystem. Genes annotated to these hotspots provide potential targets for blocking manipulation of the host response by this ubiquitous generalist necrotrophic pathogen.

Secondary branch number per panicle plays a crucial role in regulating grain number and yield in rice. Here, we report the positional cloning and functional characterization for SECONDARY BRANCH NUMBER7 (qSBN7), a quantitative trait locus affecting secondary branch per panicle and grain number. Our research revealed that the causative variants of qSBN7 are located in the distal promoter region of FRIZZLE PANICLE (FZP), a gene previously associated with the repression of axillary meristem development in rice spikelets. qSBN7 is a novel allele of FZP that causes an ~56% decrease in its transcriptional level, leading to increased secondary branch and grain number, and reduced grain length. Field evaluations showed that qSBN7 increased grain yield by 10.9% in a temperate japonica variety, TN13, likely due to its positive effect on sink capacity. Our findings suggest that incorporation of qSBN7 can increase yield potential and improve the breeding of elite rice varieties.

Many complex human traits exhibit differences between sexes. While numerous factors likely contribute to this phenomenon, growing evidence from genome-wide studies suggest a partial explanation: that males and females from the same population possess differing genetic architectures. Despite this, mapping gene-by-sex (GxS) interactions remains a challenge likely because the magnitude of such an interaction is typically and exceedingly small; traditional genome-wide association techniques may be underpowered to detect such events, due partly to the burden of multiple test correction. Here, we developed a local Bayesian regression (LBR) method to estimate sex-specific SNP marker effects after fully accounting for local linkage-disequilibrium (LD) patterns. This enabled us to infer sex-specific effects and GxS interactions either at the single SNP level, or by aggregating the effects of multiple SNPs to make inferences at the level of small LD-based regions. Using simulations in which there was imperfect LD between SNPs and causal variants, we showed that aggregating sex-specific marker effects with LBR provides improved power and resolution to detect GxS interactions over traditional single-SNP-based tests. When using LBR to analyze traits from the UK Biobank, we detected a relatively large GxS interaction impacting bone mineral density within ABO, and replicated many previously detected large-magnitude GxS interactions impacting waist-to-hip ratio. We also discovered many new GxS interactions impacting such traits as height and body mass index (BMI) within regions of the genome where both male- and female-specific effects explain a small proportion of phenotypic variance (R² < 1 x 10^–4), but are enriched in known expression quantitative trait loci.

Single-cross hybrids have been critical to the improvement of maize (Zea mays L.), but the characterization of their genetic architectures remains challenging. Previous studies of hybrid maize have shown the contribution of within-locus complementation effects (dominance) and their differential importance across functional classes of loci. However, they have generally considered panels of limited genetic diversity, and have shown little benefit from genomic prediction based on dominance or functional enrichments. This study investigates the relevance of dominance and functional classes of variants in genomic models for agronomic traits in diverse populations of hybrid maize. We based our analyses on a diverse panel of inbred lines crossed with two testers representative of the major heterotic groups in the U.S. (1106 hybrids), as well as a collection of 24 biparental populations crossed with a single tester (1640 hybrids). We investigated three agronomic traits: days to silking (DTS), plant height (PH), and grain yield (GY). Our results point to the presence of dominance for all traits, but also among-locus complementation (epistasis) for DTS and genotype-by-environment interactions for GY. Consistently, dominance improved genomic prediction for PH only. In addition, we assessed enrichment of genetic effects in classes defined by genic regions (gene annotation), structural features (recombination rate and chromatin openness), and evolutionary features (minor allele frequency and evolutionary constraint). We found support for enrichment in genic regions and subsequent improvement of genomic prediction for all traits. Our results suggest that dominance and gene annotations improve genomic prediction across diverse populations in hybrid maize.

Real geography is continuous, but standard models in population genetics are based on discrete, well-mixed populations. As a result, many methods of analyzing genetic data assume that samples are a random draw from a well-mixed population, but are applied to clustered samples from populations that are structured clinally over space. Here, we use simulations of populations living in continuous geography to study the impacts of dispersal and sampling strategy on population genetic summary statistics, demographic inference, and genome-wide association studies (GWAS). We find that most common summary statistics have distributions that differ substantially from those seen in well-mixed populations, especially when Wright’s neighborhood size is < 100 and sampling is spatially clustered. "Stepping-stone" models reproduce some of these effects, but discretizing the landscape introduces artifacts that in some cases are exacerbated at higher resolutions. The combination of low dispersal and clustered sampling causes demographic inference from the site frequency spectrum to infer more turbulent demographic histories, but averaged results across multiple simulations revealed surprisingly little systematic bias. We also show that the combination of spatially autocorrelated environments and limited dispersal causes GWAS to identify spurious signals of genetic association with purely environmentally determined phenotypes, and that this bias is only partially corrected by regressing out principal components of ancestry. Last, we discuss the relevance of our simulation results for inference from genetic variation in real organisms.

The vertebrate limb serves as an experimental paradigm to study mechanisms that regulate development of the stereotypical skeletal elements. In this study, we simultaneously inactivated Sall4 using Hoxb6Cre and Plzf in mouse embryos, and found that their combined function regulates development of the proximal-anterior skeletal elements in hindlimbs. The Sall4; Plzf double knockout exhibits severe defects in the femur, tibia, and anterior digits, distinct defects compared to other allelic series of Sall4; Plzf. We found that Sall4 regulates Plzf expression prior to hindlimb outgrowth. Further expression analysis indicated that Hox10 genes and GLI3 are severely downregulated in the Sall4; Plzf double knockout hindlimb bud. In contrast, PLZF expression is reduced but detectable in Sall4; Gli3 double knockout limb buds, and SALL4 is expressed in the Plzf; Gli3 double knockout limb buds. These results indicate that Plzf, Gli3, and Hox10 genes downstream of Sall4, regulate femur and tibia development. In the autopod, we show that Sall4 negatively regulates Hedgehog signaling, which allows for development of the most anterior digit. Collectively, our study illustrates genetic systems that regulate development of the proximal-anterior skeletal elements in hindlimbs.

During meiotic prophase, concurrent transcription, recombination, and chromosome synapsis place substantial topological strain on chromosomal DNA, but the role of topoisomerases in this context remains poorly defined. Here, we analyzed the roles of topoisomerases I and II (Top1 and Top2) during meiotic prophase in Saccharomyces cerevisiae. We show that both topoisomerases accumulate primarily in promoter-containing intergenic regions of actively transcribing genes, including many meiotic double-strand break (DSB) hotspots. Despite the comparable binding patterns, top1 and top2 mutations have different effects on meiotic recombination. TOP1 disruption delays DSB induction and shortens the window of DSB accumulation by an unknown mechanism. By contrast, temperature-sensitive top2-1 mutants exhibit a marked delay in meiotic chromosome remodeling and elevated DSB signals on synapsed chromosomes. The problems in chromosome remodeling were linked to altered Top2 binding patterns rather than a loss of Top2 catalytic activity, and stemmed from a defect in recruiting the chromosome remodeler Pch2/TRIP13 to synapsed chromosomes. No chromosomal defects were observed in the absence of TOP1. Our results imply independent roles for Top1 and Top2 in modulating meiotic chromosome structure and recombination.

Age-at-onset is one of the critical traits in cohort studies of age-related diseases. Large-scale genome-wide association studies (GWAS) of age-at-onset traits can provide more insights into genetic effects on disease progression and transitions between stages. Moreover, proportional hazards (or Cox) regression models can achieve higher statistical power in a cohort study than a case-control trait using logistic regression. Although mixed-effects models are widely used in GWAS to correct for sample dependence, application of Cox mixed-effects models (CMEMs) to large-scale GWAS is so far hindered by intractable computational cost. In this work, we propose COXMEG, an efficient R package for conducting GWAS of age-at-onset traits using CMEMs. COXMEG introduces fast estimation algorithms for general sparse relatedness matrices including, but not limited to, block-diagonal pedigree-based matrices. COXMEG also introduces a fast and powerful score test for dense relatedness matrices, accounting for both population stratification and family structure. In addition, COXMEG generalizes existing algorithms to support positive semidefinite relatedness matrices, which are common in twin and family studies. Our simulation studies suggest that COXMEG, depending on the structure of the relatedness matrix, is orders of magnitude computationally more efficient than coxme and coxph with frailty for GWAS. We found that using sparse approximation of relatedness matrices yielded highly comparable results in controlling false-positive rate and retaining statistical power for an ethnically homogeneous family-based sample. By applying COXMEG to a study of Alzheimer’s disease (AD) with a Late-Onset Alzheimer’s Disease Family Study from the National Institute on Aging sample comprising 3456 non-Hispanic whites and 287 African Americans, we identified the APOE 4 variant with strong statistical power (P = 1e–101), far more significant than that reported in a previous study using a transformed variable and a marginal Cox model. Furthermore, we identified novel SNP rs36051450 (P = 2e–9) near GRAMD1B, the minor allele of which significantly reduced the hazards of AD in both genders. These results demonstrated that COXMEG greatly facilitates the application of CMEMs in GWAS of age-at-onset traits.

There is increasing interest in developing diagnostics that discriminate individual mutagenic mechanisms in a range of applications that include identifying population-specific mutagenesis and resolving distinct mutation signatures in cancer samples. Analyses for these applications assume that mutagenic mechanisms have a distinct relationship with neighboring bases that allows them to be distinguished. Direct support for this assumption is limited to a small number of simple cases, e.g., CpG hypermutability. We have evaluated whether the mechanistic origin of a point mutation can be resolved using only sequence context for a more complicated case. We contrasted single nucleotide variants originating from the multitude of mutagenic processes that normally operate in the mouse germline with those induced by the potent mutagen N-ethyl-N-nitrosourea (ENU). The considerable overlap in the mutation spectra of these two samples make this a challenging problem. Employing a new, robust log-linear modeling method, we demonstrate that neighboring bases contain information regarding point mutation direction that differs between the ENU-induced and spontaneous mutation variant classes. A logistic regression classifier exhibited strong performance at discriminating between the different mutation classes. Concordance between the feature set of the best classifier and information content analyses suggest our results can be generalized to other mutation classification problems. We conclude that machine learning can be used to build a practical classification tool to identify the mutation mechanism for individual genetic variants. Software implementing our approach is freely available under an open-source license.