Computational catalyst discovery: Active classification through myopic multiscale sampling.

The recent boom in computational chemistry has enabled several projects aimed at discovering useful materials or catalysts. We acknowledge and address two recurring issues in the field of computational catalyst discovery. First, calculating macro-scale catalyst properties is not straightforward when using ensembles of atomic-scale calculations [e.g., density functional theory (DFT)]. We attempt to address this issue by creating a multi-scale model that estimates bulk catalyst activity using adsorption energy predictions from both DFT and machine learning models. The second issue is that many catalyst discovery efforts seek to optimize catalyst properties, but optimization is an inherently exploitative objective that is in tension with the explorative nature of early-stage discovery projects. In other words, why invest so much time finding a "best" catalyst when it is likely to fail for some other, unforeseen problem? We address this issue by relaxing the catalyst discovery goal into a classification problem: "What is the set of catalysts that is worth testing experimentally?" Here, we present a catalyst discovery method called myopic multiscale sampling, which combines multiscale modeling with automated selection of DFT calculations. It is an active classification strategy that seeks to classify catalysts as "worth investigating" or "not worth investigating" experimentally. Our results show an ∼7-16 times speedup in catalyst classification relative to random sampling. These results were based on offline simulations of our algorithm on two different datasets: a larger, synthesized dataset and a smaller, real dataset.

Development of the life impact burn recovery evaluation (LIBRE) profile: assessing burn survivors' social participation.

PURPOSE: Measuring the impact burn injuries have on social participation is integral to understanding and improving survivors' quality of life, yet there are no existing instruments that comprehensively measure the social participation of burn survivors. This project aimed to develop the Life Impact Burn Recovery Evaluation Profile (LIBRE), a patient-reported multidimensional assessment for understanding the social participation after burn injuries. METHODS: 192 questions representing multiple social participation areas were administered to a convenience sample of 601 burn survivors. Exploratory factor analysis and confirmatory factor analysis (CFA) were used to identify the underlying structure of the data. Using item response theory methods, a Graded Response Model was applied for each identified sub-domain. The resultant multidimensional LIBRE Profile can be administered via Computerized Adaptive Testing (CAT) or fixed short forms. RESULTS: The study sample included 54.7% women with a mean age of 44.6 (SD 15.9) years. The average time since burn injury was 15.4 years (0-74 years) and the average total body surface area burned was 40% (1-97%). The CFA indicated acceptable fit statistics (CFI range 0.913-0.977, TLI range 0.904-0.974, RMSEA range 0.06-0.096). The six unidimensional scales were named: relationships with family and friends, social interactions, social activities, work and employment, romantic relationships, and sexual relationships. The marginal reliability of the full item bank and CATs ranged from 0.84 to 0.93, with ceiling effects less than 15% for all scales. CONCLUSIONS: The LIBRE Profile is a promising new measure of social participation following a burn injury that enables burn survivors and their care providers to measure social participation.

Protein subcellular location pattern classification in cellular images using latent discriminative models.

MOTIVATION: Knowledge of the subcellular location of a protein is crucial for understanding its functions. The subcellular pattern of a protein is typically represented as the set of cellular components in which it is located, and an important task is to determine this set from microscope images. In this article, we address this classification problem using confocal immunofluorescence images from the Human Protein Atlas (HPA) project. The HPA contains images of cells stained for many proteins; each is also stained for three reference components, but there are many other components that are invisible. Given one such cell, the task is to classify the pattern type of the stained protein. We first randomly select local image regions within the cells, and then extract various carefully designed features from these regions. This region-based approach enables us to explicitly study the relationship between proteins and different cell components, as well as the interactions between these components. To achieve these two goals, we propose two discriminative models that extend logistic regression with structured latent variables. The first model allows the same protein pattern class to be expressed differently according to the underlying components in different regions. The second model further captures the spatial dependencies between the components within the same cell so that we can better infer these components. To learn these models, we propose a fast approximate algorithm for inference, and then use gradient-based methods to maximize the data likelihood. RESULTS: In the experiments, we show that the proposed models help improve the classification accuracies on synthetic data and real cellular images. The best overall accuracy we report in this article for classifying 942 proteins into 13 classes of patterns is about 84.6%, which to our knowledge is the best so far. In addition, the dependencies learned are consistent with prior knowledge of cell organization. AVAILABILITY: http://murphylab.web.cmu.edu/software/.

Expression of TNFAIP3 in intestinal epithelial cells protects from DSS- but not TNBS-induced colitis.

Intestinal epithelial cells (IEC) maintain gastrointestinal homeostasis by providing a physical and functional barrier between the intestinal lumen and underlying mucosal immune system. The activation of NF-κB and prevention of apoptosis in IEC are required to maintain the intestinal barrier and prevent colitis. How NF-κB activation in IEC prevents colitis is not fully understood. TNFα-induced protein 3 (TNFAIP3) is a NF-κB-induced gene that acts in a negative-feedback loop to inhibit NF-κB activation and also to inhibit apoptosis; therefore, we investigated whether TNFAIP3 expression in the intestinal epithelium impacts susceptibility of mice to colitis. Transgenic mice expressing TNFAIP3 in IEC (villin-TNFAIP3 Tg mice) were exposed to dextran sodium sulfate (DSS) or 2,4,6-trinitrobenzene sulfonic acid (TNBS), and the severity and characteristics of mucosal inflammation and barrier function were compared with wild-type mice. Villin-TNFAIP3 Tg mice were protected from DSS-induced colitis and displayed reduced production of NF-κB-dependent inflammatory cytokines. Villin-TNFAIP3 Tg mice were also protected from DSS-induced increases in intestinal permeability and induction of IEC death. Villin-TNFAIP3 Tg mice were not protected from colitis induced by TNBS. These results indicate that TNFAIP3 expression in IEC prevents colitis involving DSS-induced IEC death, but not colitis driven by T cell-mediated inflammation. As TNFAIP3 inhibits NF-κB activation and IEC death, expression of TNFAIP3 in IEC may provide an avenue to inhibit IEC NF-κB activation without inducing IEC death and inflammation.

Automatic construction of active appearance models as an image coding problem.

The automatic construction of Active Appearance Models (AAMs) is usually posed as finding the location of the base mesh vertices in the input training images. In this paper, we repose the problem as an energy-minimizing image coding problem and propose an efficient gradient-descent algorithm to solve it.