Joint estimation of linear non-Gaussian acyclic models

A Bayesian incorporated linear non-Gaussian acyclic model for multiple directed graph estimation to study brain emotion circuit development in adolescence

Emotion perception is essential to affective and cognitive development which involves distributed brain circuits. Emotion identification skills emerge in infancy and continue to develop throughout childhood and adolescence. Understanding the development of the brain's emotion circuitry may help us explain the emotional changes during adolescence. In this work, we aim to deepen our understanding of emotion-related functional connectivity (FC) from association to causation. We proposed a Bayesian incorporated linear non-Gaussian acyclic model (BiLiNGAM), which incorporated association model into the estimation pipeline. Simulation results indicated stable and accurate performance over various settings, especially when the sample size was small. We used fMRI data from the Philadelphia Neurodevelopmental Cohort (PNC) to validate the approach. It included 855 individuals aged 8-22 years who were divided into five different adolescent stages. Our network analysis revealed the development of emotion-related intra- and intermodular connectivity and pinpointed several emotion-related hubs. We further categorized the hubs into two types: in-hubs and out-hubs, as the center of receiving and distributing information, respectively. In addition, several unique developmental hub structures and group-specific patterns were discovered. Our findings help provide a directed FC template of brain network organization underlying emotion processing during adolescence.

Learning debiased graph representations from the OMOP common data model for synthetic data generation

BACKGROUND

Generating synthetic patient data is crucial for medical research, but common approaches build up on black-box models which do not allow for expert verification or intervention. We propose a highly available method which enables synthetic data generation from real patient records in a privacy preserving and compliant fashion, is interpretable and allows for expert intervention.

METHODS

Our approach ties together two established tools in medical informatics, namely OMOP as a data standard for electronic health records and Synthea as a data synthetization method. For this study, data pipelines were built which extract data from OMOP, convert them into time series format, learn temporal rules by 2 statistical algorithms (Markov chain, TARM) and 3 algorithms of causal discovery (DYNOTEARS, J-PCMCI+, LiNGAM) and map the outputs into Synthea graphs. The graphs are evaluated quantitatively by their individual and relative complexity and qualitatively by medical experts.

RESULTS

The algorithms were found to learn qualitatively and quantitatively different graph representations. Whereas the Markov chain results in extremely large graphs, TARM, DYNOTEARS, and J-PCMCI+ were found to reduce the data dimension during learning. The MultiGroupDirect LiNGAM algorithm was found to not be applicable to the problem statement at hand.

CONCLUSION

Only TARM and DYNOTEARS are practical algorithms for real-world data in this use case. As causal discovery is a method to debias purely statistical relationships, the gradient-based causal discovery algorithm DYNOTEARS was found to be most suitable.

Causal identification of single-cell experimental perturbation effects with CINEMA-OT

Recent advancements in single-cell technologies allow characterization of experimental perturbations at single-cell resolution. While methods have been developed to analyze such experiments, the application of a strict causal framework has not yet been explored for the inference of treatment effects at the single-cell level. Here we present a causal-inference-based approach to single-cell perturbation analysis, termed CINEMA-OT (causal independent effect module attribution + optimal transport). CINEMA-OT separates confounding sources of variation from perturbation effects to obtain an optimal transport matching that reflects counterfactual cell pairs. These cell pairs represent causal perturbation responses permitting a number of novel analyses, such as individual treatment-effect analysis, response clustering, attribution analysis, and synergy analysis. We benchmark CINEMA-OT on an array of treatment-effect estimation tasks for several simulated and real datasets and show that it outperforms other single-cell perturbation analysis methods. Finally, we perform CINEMA-OT analysis of two newly generated datasets: (1) rhinovirus and cigarette-smoke-exposed airway organoids, and (2) combinatorial cytokine stimulation of immune cells. In these experiments, CINEMA-OT reveals potential mechanisms by which cigarette-smoke exposure dulls the airway antiviral response, as well as the logic that governs chemokine secretion and peripheral immune cell recruitment.

The arrow-of-time in neuroimaging time series identifies causal triggers of brain function

Moving from association to causal analysis of neuroimaging data is crucial to advance our understanding of brain function. The arrow-of-time (AoT), that is, the known asymmetric nature of the passage of time, is the bedrock of causal structures shaping physical phenomena. However, almost all current time series metrics do not exploit this asymmetry, probably due to the difficulty to account for it in modeling frameworks. Here, we introduce an AoT-sensitive metric that captures the intensity of causal effects in multivariate time series, and apply it to high-resolution functional neuroimaging data. We find that causal effects underlying brain function are more distinctively localized in space and time than functional activity or connectivity, thereby allowing us to trace neural pathways recruited in different conditions. Overall, we provide a mapping of the causal brain that challenges the association paradigm of brain function.

Exploring Causal Physical Mechanisms via Non-Gaussian Linear Models and Deep Kernel Learning: Applications for Ferroelectric Domain Structures

Rapid emergence of multimodal imaging in scanning probe, electron, and optical microscopies has brought forth the challenge of understanding the information contained in these complex data sets, targeting the intrinsic correlations between different channels, and further exploring the underpinning causal physical mechanisms. Here, we develop such an analysis framework for Piezoresponse Force Microscopy. We argue that under certain conditions, we can bootstrap experimental observations with the prior knowledge of materials structure to get information on certain nonobserved properties, and demonstrate linear causal analysis for PFM observables. We further demonstrate that the strength of individual causal links between complex descriptors can be ascertained using the deep kernel learning (DKL) model. In this DKL analysis, we use the prior information on domain structure within the image to predict the physical properties. This analysis demonstrates the correlative relationships between morphology, piezoresponse, elastic property, etc., at nanoscale. The prediction of morphology and other physical parameters illustrates a mutual interaction between surface condition and physical properties in ferroelectric materials. This analysis is universal and can be extended to explore the correlative relationships of other multichannel data sets, and allow for high-fidelity reconstruction of underpinning functionalities and physical mechanisms.

An Efficient Entropy-Based Causal Discovery Method for Linear Structural Equation Models With IID Noise Variables

The discovery of causal relationships from the observational data is an important task. To identify the unique causal structure belonging to a Markov equivalence class, a number of algorithms, such as the linear non-Gaussian acyclic model (LiNGAM), have been proposed. However, two challenges remain to be met: 1) these algorithms fail to work on the data which follow linear structural equation model with Gaussian noise and 2) they misjudge the causal direction when the data contain additional measurement errors. In this paper, we propose an entropy-based two-phase iterative algorithm for arbitrary distribution data with additional measurement errors under some mild assumptions. In the first phase of the algorithm, based on the property that entropy can measure the amount of information behind the data with arbitrary distribution, we design a general approach for the identification of exogenous variable on both Gaussian and non-Gaussian data, and we give the corresponding theoretical derivation. In the second phase, to eliminate the effects of measurement errors, we revise the value of the exogenous variable by removing its measurement error and further use the revised value to remove its effect on the remaining variables. Experimental results on real-world causal structures are presented to demonstrate the effectiveness and stability of our method. We also apply the proposed algorithm on the mobile-base-station data with measurement errors, and the results further prove the effectiveness of our algorithm.

Mapping Listvenite Occurrences in the Damage Zones of Northern Victoria Land, Antarctica Using ASTER Satellite Remote Sensing Data

Listvenites normally form during hydrothermal/metasomatic alteration of mafic and ultramafic rocks and represent a key indicator for the occurrence of ore mineralizations in orogenic systems. Hydrothermal/metasomatic alteration mineral assemblages are one of the significant indicators for ore mineralizations in the damage zones of major tectonic boundaries, which can be detected using multispectral satellite remote sensing data. In this research, Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) multispectral remote sensing data were used to detect listvenite occurrences and alteration mineral assemblages in the poorly exposed damage zones of the boundaries between the Wilson, Bowers and Robertson Bay terranes in Northern Victoria Land (NVL), Antarctica. Spectral information for detecting alteration mineral assemblages and listvenites were extracted at pixel and sub-pixel levels using the Principal Component Analysis (PCA)/Independent Component Analysis (ICA) fusion technique, Linear Spectral Unmixing (LSU) and Constrained Energy Minimization (CEM) algorithms. Mineralogical assemblages containing Fe2+, Fe3+, Fe-OH, Al-OH, Mg-OH and CO3 spectral absorption features were detected in the damage zones of the study area by implementing PCA/ICA fusion to visible and near infrared (VNIR) and shortwave infrared (SWIR) bands of ASTER. Silicate lithological groups were mapped and discriminated using PCA/ICA fusion to thermal infrared (TIR) bands of ASTER. Fraction images of prospective alteration minerals, including goethite, hematite, jarosite, biotite, kaolinite, muscovite, antigorite, serpentine, talc, actinolite, chlorite, epidote, calcite, dolomite and siderite and possible zones encompassing listvenite occurrences were produced using LSU and CEM algorithms to ASTER VNIR+SWIR spectral bands. Several potential zones for listvenite occurrences were identified, typically in association with mafic metavolcanic rocks (Glasgow Volcanics) in the Bowers Mountains. Comparison of the remote sensing results with geological investigations in the study area demonstrate invaluable implications of the remote sensing approach for mapping poorly exposed lithological units, detecting possible zones of listvenite occurrences and discriminating subpixel abundance of alteration mineral assemblages in the damage zones of the Wilson-Bowers and Bowers-Robertson Bay terrane boundaries and in intra-Bowers and Wilson terranes fault zones with high fluid flow. The satellite remote sensing approach developed in this research is explicitly pertinent to detecting key alteration mineral indicators for prospecting hydrothermal/metasomatic ore minerals in remote and inaccessible zones situated in other orogenic systems around the world.

Application of Multi-Sensor Satellite Data for Exploration of Zn–Pb Sulfide Mineralization in the Franklinian Basin, North Greenland

Geological mapping and mineral exploration programs in the High Arctic have been naturally hindered by its remoteness and hostile climate conditions. The Franklinian Basin in North Greenland has a unique potential for exploration of world-class zinc deposits. In this research, multi-sensor remote sensing satellite data (e.g., Landsat-8, Phased Array L-band Synthetic Aperture Radar (PALSAR) and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER)) were used for exploring zinc in the trough sequences and shelf-platform carbonate of the Franklinian Basin. A series of robust image processing algorithms was implemented for detecting spatial distribution of pixels/sub-pixels related to key alteration mineral assemblages and structural features that may represent potential undiscovered Zn–Pb deposits. Fusion of Directed Principal Component Analysis (DPCA) and Independent Component Analysis (ICA) was applied to some selected Landsat-8 mineral indices for mapping gossan, clay-rich zones and dolomitization. Major lineaments, intersections, curvilinear structures and sedimentary formations were traced by the application of Feature-oriented Principal Components Selection (FPCS) to cross-polarized backscatter PALSAR ratio images. Mixture Tuned Matched Filtering (MTMF) algorithm was applied to ASTER VNIR/SWIR bands for sub-pixel detection and classification of hematite, goethite, jarosite, alunite, gypsum, chalcedony, kaolinite, muscovite, chlorite, epidote, calcite and dolomite in the prospective targets. Using the remote sensing data and approaches, several high potential zones characterized by distinct alteration mineral assemblages and structural fabrics were identified that could represent undiscovered Zn–Pb sulfide deposits in the study area. This research establishes a straightforward/cost-effective multi-sensor satellite-based remote sensing approach for reconnaissance stages of mineral exploration in hardly accessible parts of the High Arctic environments.

Causal Discovery on Discrete Data with Extensions to Mixture Model

In this article, we deal with the causal discovery problem on discrete data. First, we present a causal discovery method for traditional additive noise models that identifies the causal direction by analyzing the supports of the conditional distributions. Then, we present a causal mixture model to address the problem that the function transforming cause to effect varies across the observations. We propose a novel method called Support Analysis (SA) for causal discovery with the mixture model. Experiments using synthetic and real data are presented to demonstrate the performance of our proposed algorithm.

A pooling-LiNGAM algorithm for effective connectivity analysis of fMRI data

The Independent Component Analysis (ICA)-linear non-Gaussian acyclic model (LiNGAM), an algorithm that can be used to estimate the causal relationship among non-Gaussian distributed data, has the potential value to detect the effective connectivity of human brain areas. Under the assumptions that (a): the data generating process is linear, (b) there are no unobserved confounders, and (c) data have non-Gaussian distributions, LiNGAM can be used to discover the complete causal structure of data. Previous studies reveal that the algorithm could perform well when the data points being analyzed is relatively long. However, there are too few data points in most neuroimaging recordings, especially functional magnetic resonance imaging (fMRI), to allow the algorithm to converge. Smith's study speculates a method by pooling data points across subjects may be useful to address this issue (Smith et al., 2011). Thus, this study focus on validating Smith's proposal of pooling data points across subjects for the use of LiNGAM, and this method is named as pooling-LiNGAM (pLiNGAM). Using both simulated and real fMRI data, our current study demonstrates the feasibility and efficiency of the pLiNGAM on the effective connectivity estimation.

Independent component analysis: recent advances

Independent component analysis is a probabilistic method for learning a linear transform of a random vector. The goal is to find components that are maximally independent and non-Gaussian (non-normal). Its fundamental difference to classical multi-variate statistical methods is in the assumption of non-Gaussianity, which enables the identification of original, underlying components, in contrast to classical methods. The basic theory of independent component analysis was mainly developed in the 1990s and summarized, for example, in our monograph in 2001. Here, we provide an overview of some recent developments in the theory since the year 2000. The main topics are: analysis of causal relations, testing independent components, analysing multiple datasets (three-way data), modelling dependencies between the components and improved methods for estimating the basic model.