Harnessing interpretable and unsupervised machine learning to address big data from modern X-ray diffraction.

The information content of crystalline materials becomes astronomical when collective electronic behavior and their fluctuations are taken into account. In the past decade, improvements in source brightness and detector technology at modern X-ray facilities have allowed a dramatically increased fraction of this information to be captured. Now, the primary challenge is to understand and discover scientific principles from big datasets when a comprehensive analysis is beyond human reach. We report the development of an unsupervised machine learning approach, X-ray diffraction (XRD) temperature clustering (X-TEC), that can automatically extract charge density wave order parameters and detect intraunit cell ordering and its fluctuations from a series of high-volume X-ray diffraction measurements taken at multiple temperatures. We benchmark X-TEC with diffraction data on a quasi-skutterudite family of materials, (CaxSr[Formula: see text])3Rh4Sn13, where a quantum critical point is observed as a function of Ca concentration. We apply X-TEC to XRD data on the pyrochlore metal, Cd2Re2O7, to investigate its two much-debated structural phase transitions and uncover the Goldstone mode accompanying them. We demonstrate how unprecedented atomic-scale knowledge can be gained when human researchers connect the X-TEC results to physical principles. Specifically, we extract from the X-TEC-revealed selection rules that the Cd and Re displacements are approximately equal in amplitude but out of phase. This discovery reveals a previously unknown involvement of [Formula: see text] Re, supporting the idea of an electronic origin to the structural order. Our approach can radically transform XRD experiments by allowing in operando data analysis and enabling researchers to refine experiments by discovering interesting regions of phase space on the fly.

Determining subpopulation methylation profiles from bisulfite sequencing data of heterogeneous samples using DXM.

Epigenetic changes, such as aberrant DNA methylation, contribute to cancer clonal expansion and disease progression. However, identifying subpopulation-level changes in a heterogeneous sample remains challenging. Thus, we have developed a computational approach, DXM, to deconvolve the methylation profiles of major allelic subpopulations from the bisulfite sequencing data of a heterogeneous sample. DXM does not require prior knowledge of the number of subpopulations or types of cells to expect. We benchmark DXM's performance and demonstrate improvement over existing methods. We further experimentally validate DXM predicted allelic subpopulation-methylation profiles in four Diffuse Large B-Cell Lymphomas (DLBCLs). Lastly, as proof-of-concept, we apply DXM to a cohort of 31 DLBCLs and relate allelic subpopulation methylation profiles to relapse. We thus demonstrate that DXM can robustly find allelic subpopulation methylation profiles that may contribute to disease progression using bisulfite sequencing data of any heterogeneous sample.

Disruptions of network connectivity predict impairment in multiple behavioral domains after stroke.

Deficits following stroke are classically attributed to focal damage, but recent evidence suggests a key role of distributed brain network disruption. We measured resting functional connectivity (FC), lesion topography, and behavior in multiple domains (attention, visual memory, verbal memory, language, motor, and visual) in a cohort of 132 stroke patients, and used machine-learning models to predict neurological impairment in individual subjects. We found that visual memory and verbal memory were better predicted by FC, whereas visual and motor impairments were better predicted by lesion topography. Attention and language deficits were well predicted by both. Next, we identified a general pattern of physiological network dysfunction consisting of decrease of interhemispheric integration and intrahemispheric segregation, which strongly related to behavioral impairment in multiple domains. Network-specific patterns of dysfunction predicted specific behavioral deficits, and loss of interhemispheric communication across a set of regions was associated with impairment across multiple behavioral domains. These results link key organizational features of brain networks to brain-behavior relationships in stroke.

Fast, Continuous Audiogram Estimation Using Machine Learning.

OBJECTIVES: Pure-tone audiometry has been a staple of hearing assessments for decades. Many different procedures have been proposed for measuring thresholds with pure tones by systematically manipulating intensity one frequency at a time until a discrete threshold function is determined. The authors have developed a novel nonparametric approach for estimating a continuous threshold audiogram using Bayesian estimation and machine learning classification. The objective of this study was to assess the accuracy and reliability of this new method relative to a commonly used threshold measurement technique. DESIGN: The authors performed air conduction pure-tone audiometry on 21 participants between the ages of 18 and 90 years with varying degrees of hearing ability. Two repetitions of automated machine learning audiogram estimation and one repetition of conventional modified Hughson-Westlake ascending-descending audiogram estimation were acquired by an audiologist. The estimated hearing thresholds of these two techniques were compared at standard audiogram frequencies (i.e., 0.25, 0.5, 1, 2, 4, 8 kHz). RESULTS: The two threshold estimate methods delivered very similar estimates at standard audiogram frequencies. Specifically, the mean absolute difference between estimates was 4.16 ± 3.76 dB HL. The mean absolute difference between repeated measurements of the new machine learning procedure was 4.51 ± 4.45 dB HL. These values compare favorably with those of other threshold audiogram estimation procedures. Furthermore, the machine learning method generated threshold estimates from significantly fewer samples than the modified Hughson-Westlake procedure while returning a continuous threshold estimate as a function of frequency. CONCLUSIONS: The new machine learning audiogram estimation technique produces continuous threshold audiogram estimates accurately, reliably, and efficiently, making it a strong candidate for widespread application in clinical and research audiometry.

Leveraging diffusion models for unsupervised out-of-distribution detection on image manifold.

Out-of-distribution (OOD) detection is crucial for enhancing the reliability of machine learning models when confronted with data that differ from their training distribution. In the image domain, we hypothesize that images inhabit manifolds defined by latent properties such as color, position, and shape. Leveraging this intuition, we propose a novel approach to OOD detection using a diffusion model to discern images that deviate from the in-domain distribution. Our method involves training a diffusion model using in-domain images. At inference time, we lift an image from its original manifold using a masking process, and then apply a diffusion model to map it towards the in-domain manifold. We measure the distance between the original and mapped images, and identify those with a large distance as OOD. Our experiments encompass comprehensive evaluation across various datasets characterized by differences in color, semantics, and resolution. Our method demonstrates strong and consistent performance in detecting OOD images across the tested datasets, highlighting its effectiveness in handling images with diverse characteristics. Additionally, ablation studies confirm the significant contribution of each component in our framework to the overall performance.

Convolutional Networks with Dense Connectivity.

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections-one between each layer and its subsequent layer-our network has [Formula: see text] direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, encourage feature reuse and substantially improve parameter efficiency. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less parameters and computation to achieve high performance.

Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data.

Image-like data from quantum systems promises to offer greater insight into the physics of correlated quantum matter. However, the traditional framework of condensed matter physics lacks principled approaches for analyzing such data. Machine learning models are a powerful theoretical tool for analyzing image-like data including many-body snapshots from quantum simulators. Recently, they have successfully distinguished between simulated snapshots that are indistinguishable from one and two point correlation functions. Thus far, the complexity of these models has inhibited new physical insights from such approaches. Here, we develop a set of nonlinearities for use in a neural network architecture that discovers features in the data which are directly interpretable in terms of physical observables. Applied to simulated snapshots produced by two candidate theories approximating the doped Fermi-Hubbard model, we uncover that the key distinguishing features are fourth-order spin-charge correlators. Our approach lends itself well to the construction of simple, versatile, end-to-end interpretable architectures, thus paving the way for new physical insights from machine learning studies of experimental and numerical data.

Optimizing the Detection of Wakeful and Sleep-Like States for Future Electrocorticographic Brain Computer Interface Applications.

Previous studies suggest stable and robust control of a brain-computer interface (BCI) can be achieved using electrocorticography (ECoG). Translation of this technology from the laboratory to the real world requires additional methods that allow users operate their ECoG-based BCI autonomously. In such an environment, users must be able to perform all tasks currently performed by the experimenter, including manually switching the BCI system on/off. Although a simple task, it can be challenging for target users (e.g., individuals with tetraplegia) due to severe motor disability. In this study, we present an automated and practical strategy to switch a BCI system on or off based on the cognitive state of the user. Using a logistic regression, we built probabilistic models that utilized sub-dural ECoG signals from humans to estimate in pseudo real-time whether a person is awake or in a sleep-like state, and subsequently, whether to turn a BCI system on or off. Furthermore, we constrained these models to identify the optimal anatomical and spectral parameters for delineating states. Other methods exist to differentiate wake and sleep states using ECoG, but none account for practical requirements of BCI application, such as minimizing the size of an ECoG implant and predicting states in real time. Our results demonstrate that, across 4 individuals, wakeful and sleep-like states can be classified with over 80% accuracy (up to 92%) in pseudo real-time using high gamma (70-110 Hz) band limited power from only 5 electrodes (platinum discs with a diameter of 2.3 mm) located above the precentral and posterior superior temporal gyrus.

Physicochemical signatures of nanoparticle-dependent complement activation.

Nanoparticles are potentially powerful therapeutic tools that have the capacity to target drug payloads and imaging agents. However, some nanoparticles can activate complement, a branch of the innate immune system, and cause adverse side-effects. Recently, we employed an in vitro hemolysis assay to measure the serum complement activity of perfluorocarbon nanoparticles that differed by size, surface charge, and surface chemistry, quantifying the nanoparticle-dependent complement activity using a metric called Residual Hemolytic Activity (RHA). In the present work, we have used a decision tree learning algorithm to derive the rules for estimating nanoparticle-dependent complement response based on the data generated from the hemolytic assay studies. Our results indicate that physicochemical properties of nanoparticles, namely, size, polydispersity index, zeta potential, and mole percentage of the active surface ligand of a nanoparticle, can serve as good descriptors for prediction of nanoparticle-dependent complement activation in the decision tree modeling framework.

Predicting a multi-parametric probability map of active tumor extent using random forests.

Glioblastoma Mulitforme is highly infiltrative, making precise delineation of tumor margin difficult. Multimodality or multi-parametric MR imaging sequences promise an advantage over anatomic sequences such as post contrast enhancement as methods for determining the spatial extent of tumor involvement. In considering multi-parametric imaging sequences however, manual image segmentation and classification is time-consuming and prone to error. As a preliminary step toward integration of multi-parametric imaging into clinical assessments of primary brain tumors, we propose a machine-learning based multi-parametric approach that uses radiologist generated labels to train a classifier that is able to classify tissue on a voxel-wise basis and automatically generate a tumor segmentation. A random forests classifier was trained using a leave-one-out experimental paradigm. A simple linear classifier was also trained for comparison. The random forests classifier accurately predicted radiologist generated segmentations and tumor extent.