Does using stepwise variable selection to build sequential path analysis models make sense?

Causal inference methods--mainly path analysis and structural equation modeling--offer plant physiologists information about cause-and-effect relationships among plant traits. Recently, an unusual approach to causal inference through stepwise variable selection has been proposed and used in various works on plant physiology. The approach should not be considered correct from a biological point of view. Here, it is explained why stepwise variable selection should not be used for causal inference, and shown what strange conclusions can be drawn based upon the former analysis when one aims to interpret cause-and-effect relationships among plant traits.     

A more accurate method for colocalisation analysis allowing for multiple causal variants

In genome-wide association studies (GWAS) it is now common to search for, and find, multiple causal variants located in close proximity. It has also become standard to ask whether different traits share the same causal variants, but one of the popular methods to answer this question, coloc, makes the simplifying assumption that only a single causal variant exists for any given trait in any genomic region. Here, we examine the potential of the recently proposed Sum of Single Effects (SuSiE) regression framework, which can be used for fine-mapping genetic signals, for use with coloc. SuSiE is a novel approach that allows evidence for association at multiple causal variants to be evaluated simultaneously, whilst separating the statistical support for each variant conditional on the causal signal being considered. We show this results in more accurate coloc inference than other proposals to adapt coloc for multiple causal variants based on conditioning. We therefore recommend that coloc be used in combination with SuSiE to optimise accuracy of colocalisation analyses when multiple causal variants exist.     

Making Causal Claims about Environmentally Induced Adverse Effects

Causal inferences are a vital and intrinsic part of assessing the risk of adverse effects on human populations and ecological resources from biological, chemical, physical, and psychosocial stressors. While it is well known that a statistical association does not necessarily imply a causal association, the central role of causal theory in health and ecological risk assessment is often overlooked. In this article, we present a succinct account of causal theory in the health sciences, emphasize the importance of differentiating between formal and informal approaches to causal inference, describe the weight-of-evidence process that is currently the predominant means of inferring causality in the context of science-based regulatory decisions, and discuss the effects of causal theory on the current and future practice of risk assessment. Our aim is to highlight the significance of decisions about causation and causal inference, and to suggest that explicit, well-considered choices will serve to strengthen the scientific underpinnings of regulatory decision-making.     

Bayesian cue integration as a developmental outcome of reward mediated learning

Average human behavior in cue combination tasks is well predicted by bayesian inference models. As this capability is acquired over developmental timescales, the question arises, how it is learned. Here we investigated whether reward dependent learning, that is well established at the computational, behavioral, and neuronal levels, could contribute to this development. It is shown that a model free reinforcement learning algorithm can indeed learn to do cue integration, i.e. weight uncertain cues according to their respective reliabilities and even do so if reliabilities are changing. We also consider the case of causal inference where multimodal signals can originate from one or multiple separate objects and should not always be integrated. In this case, the learner is shown to develop a behavior that is closest to bayesian model averaging. We conclude that reward mediated learning could be a driving force for the development of cue integration and causal inference.     

Covariate selection strategies for causal inference: Classification and comparison

When causal effects are to be estimated from observational data, we have to adjust for confounding. A central aim of covariate selection for causal inference is therefore to determine a set that is sufficient for confounding adjustment, but other aims such as efficiency or robustness can be important as well. In this paper, we review six general approaches to covariate selection that differ in the targeted type of adjustment set. We discuss and illustrate their advantages and disadvantages using causal diagrams. Moreover, the approaches and different ways of implementing them are compared empirically in an extensive simulation study. We conclude that there are considerable differences between the approaches but none of them is uniformly best, with performance depending on the chosen adjustment method as well as the true confounding structure. Any prior structural knowledge on the causal relations is helpful to choose the most appropriate method.     

Estimating causal effects of air quality regulations using principal stratification for spatially correlated multivariate intermediate outcomes

Methods for causal inference regarding health effects of air quality regulations are met with unique challenges because (1) changes in air quality are intermediates on the causal pathway between regulation and health, (2) regulations typically affect multiple pollutants on the causal pathway towards health, and (3) regulating a given location can affect pollution at other locations, that is, there is interference between observations. We propose a principal stratification method designed to examine causal effects of a regulation on health that are and are not associated with causal effects of the regulation on air quality. A novel feature of our approach is the accommodation of a continuously scaled multivariate intermediate response vector representing multiple pollutants. Furthermore, we use a spatial hierarchical model for potential pollution concentrations and ultimately use estimates from this model to assess validity of assumptions regarding interference. We apply our method to estimate causal effects of the 1990 Clean Air Act Amendments among approximately 7 million Medicare enrollees living within 6 miles of a pollution monitor.     

Combining the strengths of inverse-variance weighting and Egger regression in Mendelian randomization using a mixture of regressions model

With the increasing availability of large-scale GWAS summary data on various traits, Mendelian randomization (MR) has become commonly used to infer causality between a pair of traits, an exposure and an outcome. It depends on using genetic variants, typically SNPs, as instrumental variables (IVs). The inverse-variance weighted (IVW) method (with a fixed-effect meta-analysis model) is most powerful when all IVs are valid; however, when horizontal pleiotropy is present, it may lead to biased inference. On the other hand, Egger regression is one of the most widely used methods robust to (uncorrelated) pleiotropy, but it suffers from loss of power. We propose a two-component mixture of regressions to combine and thus take advantage of both IVW and Egger regression; it is often both more efficient (i.e. higher powered) and more robust to pleiotropy (i.e. controlling type I error) than either IVW or Egger regression alone by accounting for both valid and invalid IVs respectively. We propose a model averaging approach and a novel data perturbation scheme to account for uncertainties in model/IV selection, leading to more robust statistical inference for finite samples. Through extensive simulations and applications to the GWAS summary data of 48 risk factor-disease pairs and 63 genetically uncorrelated trait pairs, we showcase that our proposed methods could often control type I error better while achieving much higher power than IVW and Egger regression (and sometimes than several other new/popular MR methods). We expect that our proposed methods will be a useful addition to the toolbox of Mendelian randomization for causal inference.     

Successful Reconstruction of a Physiological Circuit with Known Connectivity from Spiking Activity Alone

Identifying the structure and dynamics of synaptic interactions between neurons is the first step to understanding neural network dynamics. The presence of synaptic connections is traditionally inferred through the use of targeted stimulation and paired recordings or by post-hoc histology. More recently, causal network inference algorithms have been proposed to deduce connectivity directly from electrophysiological signals, such as extracellularly recorded spiking activity. Usually, these algorithms have not been validated on a neurophysiological data set for which the actual circuitry is known. Recent work has shown that traditional network inference algorithms based on linear models typically fail to identify the correct coupling of a small central pattern generating circuit in the stomatogastric ganglion of the crab Cancer borealis. In this work, we show that point process models of observed spike trains can guide inference of relative connectivity estimates that match the known physiological connectivity of the central pattern generator up to a choice of threshold. We elucidate the necessary steps to derive faithful connectivity estimates from a model that incorporates the spike train nature of the data. We then apply the model to measure changes in the effective connectivity pattern in response to two pharmacological interventions, which affect both intrinsic neural dynamics and synaptic transmission. Our results provide the first successful application of a network inference algorithm to a circuit for which the actual physiological synapses between neurons are known. The point process methodology presented here generalizes well to larger networks and can describe the statistics of neural populations. In general we show that advanced statistical models allow for the characterization of effective network structure, deciphering underlying network dynamics and estimating information-processing capabilities.     

ON THE LOW HERITABILITY OF LIFE-HISTORY TRAITS

Life-history traits such as longevity and fecundity often show low heritability. This is usually interpreted in terms of Fisher's fundamental theorem to mean that populations are near evolutionary equilibrium and genetic variance in total fitness is low. We develop the causal relationship between metric traits and life-history traits to show that a life-history trait is expected to have a low heritability whether or not the population is at equilibrium. This is because it is subject to all the environmental variation in the metric traits that affect it plus additional environmental variation. There is no simple prediction regarding levels of additive genetic variance in life-history traits, which may be high at equilibrium. Several other patterns in the inheritance of life-history traits are readily predicted from the causal model. These include the strength of genetic correlations between life-history traits, levels of nonadditive genetic variance, and the inevitability of genotype-environment interaction.     

miniTUBA: medical inference by network integration of temporal data using Bayesian analysis

MOTIVATION: Many biomedical and clinical research problems involve discovering causal relationships between observations gathered from temporal events. Dynamic Bayesian networks are a powerful modeling approach to describe causal or apparently causal relationships, and support complex medical inference, such as future response prediction, automated learning, and rational decision making. Although many engines exist for creating Bayesian networks, most require a local installation and significant data manipulation to be practical for a general biologist or clinician. No software pipeline currently exists for interpretation and inference of dynamic Bayesian networks learned from biomedical and clinical data. RESULTS: miniTUBA is a web-based modeling system that allows clinical and biomedical researchers to perform complex medical/clinical inference and prediction using dynamic Bayesian network analysis with temporal datasets. The software allows users to choose different analysis parameters (e.g. Markov lags and prior topology), and continuously update their data and refine their results. miniTUBA can make temporal predictions to suggest interventions based on an automated learning process pipeline using all data provided. Preliminary tests using synthetic data and laboratory research data indicate that miniTUBA accurately identifies regulatory network structures from temporal data. AVAILABILITY: miniTUBA is available at http://www.minituba.org.     

Inferring causal phenotype networks from segregating populations

A major goal in the study of complex traits is to decipher the causal interrelationships among correlated phenotypes. Current methods mostly yield undirected networks that connect phenotypes without causal orientation. Some of these connections may be spurious due to partial correlation that is not causal. We show how to build causal direction into an undirected network of phenotypes by including causal QTL for each phenotype. We evaluate causal direction for each edge connecting two phenotypes, using a LOD score. This new approach can be applied to many different population structures, including inbred and outbred crosses as well as natural populations, and can accommodate feedback loops. We assess its performance in simulation studies and show that our method recovers network edges and infers causal direction correctly at a high rate. Finally, we illustrate our method with an example involving gene expression and metabolite traits from experimental crosses.     

Political Attitudes Develop Independently of Personality Traits

The primary assumption within the recent personality and political orientations literature is that personality traits cause people to develop political attitudes. In contrast, research relying on traditional psychological and developmental theories suggests the relationship between most personality dimensions and political orientations are either not significant or weak. Research from behavioral genetics suggests the covariance between personality and political preferences is not causal, but due to a common, latent genetic factor that mutually influences both. The contradictory assumptions and findings from these research streams have yet to be resolved. This is in part due to the reliance on cross-sectional data and the lack of longitudinal genetically informative data. Here, using two independent longitudinal genetically informative samples, we examine the joint development of personality traits and attitude dimensions to explore the underlying causal mechanisms that drive the relationship between these features and provide a first step in resolving the causal question. We find change in personality over a ten-year period does not predict change in political attitudes, which does not support a causal relationship between personality traits and political attitudes as is frequently assumed. Rather, political attitudes are often more stable than the key personality traits assumed to be predicting them. Finally, the results from our genetic models find that no additional variance is accounted for by the causal pathway from personality traits to political attitudes. Our findings remain consistent with the original construction of the five-factor model of personality and developmental theories on attitude formation, but challenge recent work in this area.     

Commonality of functional annotation: a method for prioritization of candidate genes from genome-wide linkage studies

Linkage studies of complex traits frequently yield multiple linkage regions covering hundreds of genes. Testing each candidate gene from every region is prohibitively expensive and computational methods that simplify this process would benefit genetic research. We present a new method based on commonality of functional annotation (CFA) that aids dissection of complex traits for which multiple causal genes act in a single pathway or process. CFA works by testing individual Gene Ontology (GO) terms for enrichment among candidate gene pools, performs multiple hypothesis testing adjustment using an estimate of independent tests based on correlation of GO terms, and then scores and ranks genes annotated with significantly-enriched terms based on the number of quantitative trait loci regions in which genes bearing those annotations appear. We evaluate CFA using simulated linkage data and show that CFA has good power despite being conservative. We apply CFA to published linkage studies investigating age-of-onset of Alzheimer's disease and body mass index and obtain previously known and new candidate genes. CFA provides a new tool for studies in which causal genes are expected to participate in a common pathway or process and can easily be extended to utilize annotation schemes in addition to the GO.     

Testing for causality in covarying traits: genes and latitude in a molecular world

Many traits are assumed to have a causal (necessary) relationship with one another because of their common covariation with a physiological, ecological or geographical factor. Herein, we demonstrate a straightforward test for inferring causality using residuals from regression of the traits with the common factor. We illustrate this test using the covariation with latitude of a proxy for the circadian clock and a proxy for the photoperiodic timer in Drosophila and salmon. A negative result of this test means that further discussion of the adaptive significance of a causal connection between the covarying traits is unwarranted. A positive result of this test provides a point of departure that can then be used as a platform from which to determine experimentally the underlying functional connections and only then to discuss their adaptive significance.     

Causal inference in biomolecular pathways using a Bayesian network approach and an Implicit method

We introduce here the concept of Implicit networks which provide, like Bayesian networks, a graphical modelling framework that encodes the joint probability distribution for a set of random variables within a directed acyclic graph. We show that Implicit networks, when used in conjunction with appropriate statistical techniques, are very attractive for their ability to understand and analyze biological data. Particularly, we consider here the use of Implicit networks for causal inference in biomolecular pathways. In such pathways, an Implicit network encodes dependencies among variables (proteins, genes), can be trained to learn causal relationships (regulation, interaction) between them and then used to predict the biological response given the status of some key proteins or genes in the network. We show that Implicit networks offer efficient methodologies for learning from observations without prior knowledge and thus provide a good alternative to classical inference in Bayesian networks when priors are missing. We illustrate our approach by an application to simulated data for a simplified signal transduction pathway of the epidermal growth factor receptor (EGFR) protein.     

Exploring causal networks of bovine milk fatty acids in a multivariate mixed model context

Background

Knowledge regarding causal relationships among traits is important to understand complex biological systems. Structural equation models (SEM) can be used to quantify the causal relations between traits, which allow prediction of outcomes to interventions applied to such a network. Such models are fitted conditionally on a causal structure among traits, represented by a directed acyclic graph and an Inductive Causation (IC) algorithm can be used to search for causal structures. The aim of this study was to explore the space of causal structures involving bovine milk fatty acids and to select a network supported by data as the structure of a SEM.

Results

The IC algorithm adapted to mixed models settings was applied to study 14 correlated bovine milk fatty acids, resulting in an undirected network. The undirected pathway from C4:0 to C12:0 resembled the de novo synthesis pathway of short and medium chain saturated fatty acids. By using prior knowledge, directions were assigned to that part of the network and the resulting structure was used to fit a SEM that led to structural coefficients ranging from 0.85 to 1.05. The deviance information criterion indicated that the SEM was more plausible than the multi-trait model.

Conclusions

The IC algorithm output pointed towards causal relations between the studied traits. This changed the focus from marginal associations between traits to direct relationships, thus towards relationships that may result in changes when external interventions are applied. The causal structure can give more insight into underlying mechanisms and the SEM can predict conditional changes due to such interventions.