Probabilistic prediction of material stability: integrating convex hulls into active learning.

Active learning is a valuable tool for efficiently exploring complex spaces, finding a variety of uses in materials science. However, the determination of convex hulls for phase diagrams does not neatly fit into traditional active learning approaches due to their global nature. Specifically, the thermodynamic stability of a material is not simply a function of its own energy, but rather requires energetic information from all other competing compositions and phases. Here we present convex hull-aware active learning (CAL), a novel Bayesian algorithm that chooses experiments to minimize the uncertainty in the convex hull. CAL prioritizes compositions that are close to or on the hull, leaving significant uncertainty in other compositions that are quickly determined to be irrelevant to the convex hull. The convex hull can thus be predicted with significantly fewer observations than approaches that focus solely on energy. Intrinsic to this Bayesian approach is uncertainty quantification in both the convex hull and all subsequent predictions (e.g., stability and chemical potential). By providing increased search efficiency and uncertainty quantification, CAL can be readily incorporated into the emerging paradigm of uncertainty-based workflows for thermodynamic prediction.

A Unified Comparison of User Modeling Techniques for Predicting Data Interaction and Detecting Exploration Bias.

The visual analytics community has proposed several user modeling algorithms to capture and analyze users' interaction behavior in order to assist users in data exploration and insight generation. For example, some can detect exploration biases while others can predict data points that the user will interact with before that interaction occurs. Researchers believe this collection of algorithms can help create more intelligent visual analytics tools. However, the community lacks a rigorous evaluation and comparison of these existing techniques. As a result, there is limited guidance on which method to use and when. Our paper seeks to fill in this missing gap by comparing and ranking eight user modeling algorithms based on their performance on a diverse set of four user study datasets. We analyze exploration bias detection, data interaction prediction, and algorithmic complexity, among other measures. Based on our findings, we highlight open challenges and new directions for analyzing user interactions and visualization provenance.

Efficient Discovery of Visible Light-Activated Azoarene Photoswitches with Long Half-Lives Using Active Search.

Photoswitches are molecules that undergo a reversible, structural isomerization after exposure to certain wavelengths of light. The dynamic control offered by molecular photoswitches is favorable for materials chemistry, photopharmacology, and catalysis applications. Ideal photoswitches absorb visible light and have long-lived metastable isomers. We used high-throughput virtual screening to predict the absorption maxima (λmax) of the E-isomer and half-life (t1/2) of the Z-isomer. However, computing the photophysical and kinetic stabilities with density functional theory of each entry of a virtual molecular library containing thousands or millions of molecules is prohibitively time-consuming. We applied active search, a machine-learning technique, to intelligently search a chemical search space of 255 991 photoswitches based on 29 known azoarenes and their derivatives. We iteratively trained the active search algorithm on whether a candidate absorbed visible light (λmax > 450 nm). Active search was found to triple the discovery rate compared to random search. Further, we projected 1962 photoswitches to 2D using the Uniform Manifold Approximation and Projection algorithm and found that λmax depends on the core, which is tunable by substituents. We then incorporated a second stage of screening to predict the stabilities of the Z-isomers for the top candidates of each core. We identified four ideal photoswitches that concurrently satisfy the following criteria: λmax > 450 nm and t1/2 > 2 h.These candidates had λmax and t1/2 range from 465 to 531 nm and hours to days, respectively.

IDCube Lite: Free Interactive Discovery Cube software for multi- and hyperspectral applications.

Multi- and hyperspectral imaging modalities encompass a growing number of spectral techniques that find many applications in geospatial, biomedical, machine vision and other fields. The rapidly increasing number of applications requires convenient easy-to-navigate software that can be used by new and experienced users to analyse data, and develop, apply and deploy novel algorithms. Herein, we present our platform, IDCube Lite, an Interactive Discovery Cube that performs essential operations in hyperspectral data analysis to realise the full potential of spectral imaging. The strength of the software lies in its interactive features that enable the users to optimise parameters and obtain visual input for the user in a way not previously accessible with other software packages. The entire software can be operated without any prior programming skills allowing interactive sessions of raw and processed data. IDCube Lite, a free version of the software described in the paper, has many benefits compared to existing packages and offers structural flexibility to discover new, hidden features that allow users to integrate novel computational methods.

A comparison of prediction approaches for identifying prodromal Parkinson disease.

Identifying people with Parkinson disease during the prodromal period, including via algorithms in administrative claims data, is an important research and clinical priority. We sought to improve upon an existing penalized logistic regression model, based on diagnosis and procedure codes, by adding prescription medication data or using machine learning. Using Medicare Part D beneficiaries age 66-90 from a population-based case-control study of incident Parkinson disease, we fit a penalized logistic regression both with and without Part D data. We also built a predictive algorithm using a random forest classifier for comparison. In a combined approach, we introduced the probability of Parkinson disease from the random forest, as a predictor in the penalized regression model. We calculated the receiver operator characteristic area under the curve (AUC) for each model. All models performed well, with AUCs ranging from 0.824 (simplest model) to 0.835 (combined approach). We conclude that medication data and random forests improve Parkinson disease prediction, but are not essential.

Competing Models: Inferring Exploration Patterns and Information Relevance via Bayesian Model Selection.

Analyzing interaction data provides an opportunity to learn about users, uncover their underlying goals, and create intelligent visualization systems. The first step for intelligent response in visualizations is to enable computers to infer user goals and strategies through observing their interactions with a system. Researchers have proposed multiple techniques to model users, however, their frameworks often depend on the visualization design, interaction space, and dataset. Due to these dependencies, many techniques do not provide a general algorithmic solution to user exploration modeling. In this paper, we construct a series of models based on the dataset and pose user exploration modeling as a Bayesian model selection problem where we maintain a belief over numerous competing models that could explain user interactions. Each of these competing models represent an exploration strategy the user could adopt during a session. The goal of our technique is to make high-level and in-depth inferences about the user by observing their low-level interactions. Although our proposed idea is applicable to various probabilistic model spaces, we demonstrate a specific instance of encoding exploration patterns as competing models to infer information relevance. We validate our technique's ability to infer exploration bias, predict future interactions, and summarize an analytic session using user study datasets. Our results indicate that depending on the application, our method outperforms established baselines for bias detection and future interaction prediction. Finally, we discuss future research directions based on our proposed modeling paradigm and suggest how practitioners can use this method to build intelligent visualization systems that understand users' goals and adapt to improve the exploration process.

New analysis pipeline for high-throughput domain-peptide affinity experiments improves SH2 interaction data.

Protein domain interactions with short linear peptides, such as those of the Src homology 2 (SH2) domain with phosphotyrosine-containing peptide motifs (pTyr), are ubiquitous and important to many biochemical processes of the cell. The desire to map and quantify these interactions has resulted in the development of high-throughput (HTP) quantitative measurement techniques, such as microarray or fluorescence polarization assays. For example, in the last 15 years, experiments have progressed from measuring single interactions to covering 500,000 of the 5.5 million possible SH2-pTyr interactions in the human proteome. However, high variability in affinity measurements and disagreements about positive interactions between published data sets led us here to reevaluate the analysis methods and raw data of published SH2-pTyr HTP experiments. We identified several opportunities for improving the identification of positive and negative interactions and the accuracy of affinity measurements. We implemented model-fitting techniques that are more statistically appropriate for the nonlinear SH2-pTyr interaction data. We also developed a method to account for protein concentration errors due to impurities and degradation or protein inactivity and aggregation. Our revised analysis increases the reported affinity accuracy, reduces the false-negative rate, and increases the amount of useful data by adding reliable true-negative results. We demonstrate improvement in classification of binding versus nonbinding when using machine-learning techniques, suggesting improved coherence in the reanalyzed data sets. We present revised SH2-pTyr affinity results and propose a new analysis pipeline for future HTP measurements of domain-peptide interactions.

Conjoint psychometric field estimation for bilateral audiometry.

Behavioral testing in perceptual or cognitive domains requires querying a subject multiple times in order to quantify his or her ability in the corresponding domain. These queries must be conducted sequentially, and any additional testing domains are also typically tested sequentially, such as with distinct tests comprising a test battery. As a result, existing behavioral tests are often lengthy and do not offer comprehensive evaluation. The use of active machine-learning kernel methods for behavioral assessment provides extremely flexible yet efficient estimation tools to more thoroughly investigate perceptual or cognitive processes without incurring the penalty of excessive testing time. Audiometry represents perhaps the simplest test case to demonstrate the utility of these techniques. In pure-tone audiometry, hearing is assessed in the two-dimensional input space of frequency and intensity, and the test is repeated for both ears. Although an individual's ears are not linked physiologically, they share many features in common that lead to correlations suitable for exploitation in testing. The bilateral audiogram estimates hearing thresholds in both ears simultaneously by conjoining their separate input domains into a single search space, which can be evaluated efficiently with modern machine-learning methods. The result is the introduction of the first conjoint psychometric function estimation procedure, which consistently delivers accurate results in significantly less time than sequential disjoint estimators.

Bioinspired polarization vision enables underwater geolocalization.

With its never-ending blue color, the underwater environment often seems monotonic and featureless. However, to an animal with polarization-sensitive vision, it is anything but bland. The rich repertoire of underwater polarization patterns-a consequence of light's air-to-water transmission and in-water scattering-can be exploited both as a compass and for geolocalization purposes. We demonstrate that, by using a bioinspired polarization-sensitive imager, we can determine the geolocation of an observer based on radial underwater polarization patterns. Our experimental data, recorded at various locations around the world, at different depths and times of day, indicate that the average accuracy of our geolocalization is 61 km, or 6 m of error for every 1 km traveled. This proof-of-concept study of our bioinspired technique opens new possibilities in long-distance underwater navigation and suggests additional mechanisms by which marine animals with polarization-sensitive vision might perform both local and long-distance navigation.

Active Search for Computer-aided Drug Design.

We consider lead discovery as active search in a space of labelled graphs. In particular, we extend our recent data-driven adaptive Markov chain approach, and evaluate it on a focused drug design problem, where we search for an antagonist of an αv integrin, the target protein that belongs to a group of Arg-Gly-Asp integrin receptors. This group of integrin receptors is thought to play a key role in idiopathic pulmonary fibrosis, a chronic lung disease of significant pharmaceutical interest. As an in silico proxy of the binding affinity, we use a molecular docking score to an experimentally determined αvß6 protein structure. The search is driven by a probabilistic surrogate of the activity of all molecules from that space. As the process evolves and the algorithm observes the activity scores of the previously designed molecules, the hypothesis of the activity is refined. The algorithm is guaranteed to converge in probability to the best hypothesis from an a priori specified hypothesis space. In our empirical evaluations, the approach achieves a large structural variety of designed molecular structures for which the docking score is better than the desired threshold. Some novel molecules, suggested to be active by the surrogate model, provoke a significant interest from the perspective of medicinal chemistry and warrant prioritization for synthesis. Moreover, the approach discovered 19 out of the 24 active compounds which are known to be active from previous biological assays.