Engineering Papers⌕ Search

Engineering topics

Ramanathan, Arvind

Publications and source records attributed to Ramanathan, Arvind.

At least 73 records · Page 4

Modulating Enzyme Activity by Altering Protein Dynamics with Solvent

Optimal enzyme activity depends on a number of factors, including structure and dynamics. The role of enzyme structure is well recognized; however, the linkage between protein dynamics and enzyme activity has given rise to a contentious debate. We have developed an approach that uses an aqueous mixture of organic solvent to control the functionally relevant enzyme dynamics (without changing the structure), which in turn modulates the enzyme activity. Using this approach, we predicted that the hydride transfer reaction catalyzed by the enzyme dihydrofolate reductase (DHFR) from Escherichia coli in aqueous mixtures of isopropanol (IPA) with water will decrease by ~3 fold at 20% (v/v) IPA concentration. Stopped-flow kinetic measurements find that the pH-independent k hydride rate decreases by 2.2 fold. X-ray crystallographic enzyme structures show no noticeable differences, while computational studies indicate that the transition state and electrostatic effects were identical for water and mixed solvent conditions; quasi-elastic neutron scattering studies show that the dynamical enzyme motions are suppressed. Our approach provides a unique avenue to modulating enzyme activity through changes in enzyme dynamics. Further it provides vital insights that show the altered motions of DHFR cause significant changes in the enzyme's ability to access its functionally relevant conformational substates, explaining the decreased k hydride rate. This approach has important implications for obtaining fundamental insights into the role of rate-limiting dynamics in catalysis and as well as for enzyme engineering.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

PathRepHAN: Hierarchical attention networks for pathology report classification

Developers at ORNL explored how a deep learning (DL) approach based on hierarchical attention networks (HANs) can improve model performance for multiple information extraction tasks from unstructured cancer pathology reports compared to conventional methods that do not sufficiently capture syntactic and semantic contexts from free-text documents. The HAN was implemented for 2 information extraction tasks: (1) primary site, matched to 12 International Classification of Diseases for Oncology topography codes (7 breast, 5 lung primary sites), and (2) histological grade classification, matched to G1–G4. Our results demonstrate that for both information tasks, HAN performed significantly better compared to the conventional ML and DL techniques.

Ramanathan, Arvind↗

SATYA: Defending Against Adversarial Attacks Using Statistical HypothesisTesting

The paper presents a new defense against adversarial attacks for deep neural networks. We demonstrate the effectiveness of our approach against the popular adversarial image generation method DeepFool. Our approach uses Wald’s Sequential Probability Ratio Test to sufficiently sample a carefully chosen neighborhood around an input image to determine the correct label of the image. On a benchmark of 50,000 randomly chosen adversarial images generated by DeepFool we demonstrate that our method SATYA is able to recover the correct labels for 95.76% of the images for CaffeNet and 97.43% of the correct label for GoogLeNet.

Raj, Sunny↗

Testing autonomous cyber-physical systems using fuzzing features from convolutional neural networks: work-in-progress

Autonomous cyber-physical systems rely on modern machine learning methods such as deep neural networks to control their interactions with the physical world. Testing of such intelligent cyber-physical systems is a challenge due to the huge state space associated with high-resolution visual sensory inputs. We demonstrate how fuzzing the input using patterns obtained from the convolutional filters of an unrelated convolutional neural network can be used to test computer vision algorithms implemented in intelligent cyber-physical systems. Our method discovers interesting counterexamples to a pedestrian detection algorithm implemented in the popular OpenCV library. Our approach also unearths counterexamples to the correct behavior of an autonomous car similar to NVIDIA's end-to-end self-driving deep neural net running on the Udacity open-source simulator.

Raj, Sunny↗

Visualization for Classification in Deep Neural Networks

Recently, the techniques based on Deep Neural Networks (DNNs) have achieved a great performance in classification tasks in a wide range of applications, such as image recognition and natural language processing. However, DNN developers face a lot of trial and error during the development process and spend their efforts in debugging their network model through analyzing and understanding the classification results. As such, tools are needed that help the developers not only understand the results, but also suggest the ways to improve their model. In this paper, we propose a visual analytics tool for visualizing the classification results during the iterative development pipeline of a DNN model. Our tool enables exploring the classification results from any type of neural network models, identifying misclassified samples, examining the predicted score distributions of samples, and showing how the outcomes progressively change during the training process.

Chae, Junghoon↗

Statistical Hypothesis Testing using CNN Features for Synthesis of Adversarial Counterexamples to Human and Object Detection Vision Systems

Validating the correctness of human detection vision systems is crucial for safety applications such as pedestrian collision avoidance in autonomous vehicles. The enormous space of possible inputs to such an intelligent system makes it difficult to design test cases for such systems. In this report, we present our tool MAYA that uses an error model derived from a convolutional neural network (CNN) to explore the space of images similar to a given input image, and then tests the correctness of a given human or object detection system on such perturbed images. We demonstrate the capability of our tool on the pre-trained Histogram-of-Oriented-Gradients (HOG) human detection algorithm implemented in the popular OpenCV toolset and the Caffe object detection system pre-trained on the ImageNet benchmark. Our tool may serve as a testing resource for the designers of intelligent human and object detection systems.

97 MATHEMATICS AND COMPUTING↗

Constellation: A science graph network for scalable data and knowledge discovery in extreme-scale scientific collaborations

Constellation's overarching goal is the federation of information from resources within an extreme-scale scientific collaboration to enable the scalable discovery of data and new knowledge pathways. The resource fabric is comprised of petascale supercomputers and storage systems, users, jobs, datasets and lifecycle artifacts. For an extreme-scale supercomputing center, normal operations can generate hundreds of millions of data products and metadata entries describing the resource fabric. Constellation federates the information extracted from the resources using a custom, transformative science graph network; constructs rich metadata indexes and higher-order derived metadata from the extracted information; and conducts scalable graph analytics to unravel hidden data pathways. Our implementation and deployment for a production, supercomputing facility shows that the graph can scale to more than 750 million vertices, its domain agnostic indexing can answer interesting science queries, and its analytics can aid in structural, topological and temporal analysis to identify usage hotspots.

Vazhkudai, Sudharshan S.↗

Folding propensity of intrinsically disordered proteins by osmotic stress

Proteins imparted with intrinsic disorder conduct a range of essential cellular functions. To better understand the folding and hydration properties of intrinsically disordered proteins (IDPs), we used osmotic stress to induce conformational changes in nuclear co-activator binding domain (NCBD) and activator for thyroid hormone and retinoid receptor (ACTR). Osmotic stress was applied by the addition of small and polymeric osmolytes, where we discovered that water contributions to NCBD folding always exceeded those for ACTR. Both NCBD and ACTR were found to gain a-helical structure with increasing osmotic stress, consistent with their folding upon NCBD/ACTR complex formation. Using small-angle neutron scattering (SANS), we further characterized NCBD structural changes with the osmolyte ethylene glycol. Here a large reduction in overall size initially occurred before substantial secondary structural change. In conclusion, by focusing on folding propensity, and linked hydration changes, we uncover new insights that may be important for how IDP folding contributes to binding.

59 BASIC BIOLOGICAL SCIENCES↗

Analyzing the impact of modeling choices and assumptions in compartmental epidemiological models

In this study, computational models have become increasingly used as part of modeling, predicting, and understanding how infectious diseases spread within large populations. These models can be broadly classified into differential equation-based models (EBM) and agent-based models (ABM). Both types of models are central in aiding public health officials design intervention strategies in case of large epidemic outbreaks. We examine these models in the context of illuminating their hidden assumptions and the impact these may have on the model outcomes. Very few ABM/EBMs are evaluated for their suitability to address a particular public health concern, and drawing relevant conclusions about their suitability requires reliable and relevant information regarding the different modeling strategies and associated assumptions. Hence, there is a need to determine how the different modeling strategies, choices of various parameters, and the resolution of information for EBMs and ABMs affect outcomes, including predictions of disease spread. In this study, we present a quantitative analysis of how the selection of model types (i.e., EBM vs. ABM), the underlying assumptions that are enforced by model types to model the disease propagation process, and the choice of time advance (continuous vs. discrete) affect the overall outcomes of modeling disease spread. Our study reveals that the magnitude and velocity of the simulated epidemic depends critically on the selection of modeling principles, various assumptions of disease process, and the choice of time advance.

60 APPLIED LIFE SCIENCES↗

The Biosurveillance Analytics Resource Directory (BARD): Facilitating the use of epidemiological models for infectious disease surveillance

Epidemiological modeling for infectious disease is important for disease management and its routine implementation needs to be facilitated through better description of models in an operational context. A standardized model characterization process that allows selection or making manual comparisons of available models and their results is currently lacking. A key need is a universal framework to facilitate model description and understanding of its features. Los Alamos National Laboratory (LANL) has developed a comprehensive framework that can be used to characterize an infectious disease model in an operational context. The framework was developed through a consensus among a panel of subject matter experts. In this paper, we describe the framework, its application to model characterization, and the development of the Biosurveillance Analytics Resource Directory (BARD; http://brd.bsvgateway.org/brd/), to facilitate the rapid selection of operational models for specific infectious/communicable diseases. We offer this framework and associated database to stakeholders of the infectious disease modeling field as a tool for standardizing model description and facilitating the use of epidemiological models.

59 BASIC BIOLOGICAL SCIENCES↗

Conformational Sub-states and Populations in Enzyme Catalysis

reactants in the active site, chemical turnover, and release of products. In addition to formation of crucial structural interactions between enzyme and substrate(s), coordinated motions within the enzyme substrate complex allow reaction to proceed at a much faster rate, compared to the reaction in solution and in the absence of enzyme. An increasing number of enzyme systems show the presence of conserved protein motions that are important for function. A wide variety of motions are naturally sampled (over femtosecond to millisecond time-scales) as the enzyme complex moves along the energetic landscape, driven by temperature and dynamical events from the surrounding environment. Areas of low energy along the landscape form conformational sub-states, which show higher conformational populations than surrounding areas. A small number of these protein conformational sub-states contain functionally important structural and dynamical features, which assist the enzyme mechanism along the catalytic cycle. Identification and characterization of these higher-energy (also called excited) sub-states and the associated populations are challenging, as these sub-states are very short-lived and therefore rarely populated. Specialized techniques based on computer simulations, theoretical modeling, and nuclear magnetic resonance have been developed for quantitative characterization of these sub-states and populations. This chapter discusses these techniques and provides examples of their applications to enzyme systems.

Agarwal, Pratul K↗

Integrating Symbolic and Statistical Methods for Testing Intelligent Systems Applications to Machine Learning and Computer Vision

Embedded intelligent systems ranging from tiny im- plantable biomedical devices to large swarms of autonomous un- manned aerial systems are becoming pervasive in our daily lives. While we depend on the flawless functioning of such intelligent systems, and often take their behavioral correctness and safety for granted, it is notoriously difficult to generate test cases that expose subtle errors in the implementations of machine learning algorithms. Hence, the validation of intelligent systems is usually achieved by studying their behavior on representative data sets, using methods such as cross-validation and bootstrapping.In this paper, we present a new testing methodology for studying the correctness of intelligent systems. Our approach uses symbolic decision procedures coupled with statistical hypothesis testing to. We also use our algorithm to analyze the robustness of a human detection algorithm built using the OpenCV open-source computer vision library. We show that the human detection implementation can fail to detect humans in perturbed video frames even when the perturbations are so small that the corresponding frames look identical to the naked eye.

Jha, Sumit Kumar↗

ORBiT: Oak Ridge biosurveillance toolkit for public health dynamics

Background: The digitization of health-related information through electronic health records (EHR) and electronic healthcare reimbursement claims and the continued growth of self-reported health information through social media provides both tremendous opportunities and challenges in developing effective biosurveillance tools. With novel emerging infectious diseases being reported across different parts of the world, there is a need to build systems that can track, monitor and report such events in a timely manner. Further, it is also important to identify susceptible geographic regions and populations where emerging diseases may have a significant impact. Methods: In this paper, we present an overview of Oak Ridge Biosurveillance Toolkit (ORBiT), which we have developed specifically to address data analytic challenges in the realm of public health surveillance. In particular, ORBiT provides an extensible environment to pull together diverse, large-scale datasets and analyze them to identify spatial and temporal patterns for various biosurveillance-related tasks. Results: We demonstrate the utility of ORBiT in automatically extracting a small number of spatial and temporal patterns during the 2009-2010 pandemic H1N1 flu season using claims data. These patterns provide quantitative insights into the dynamics of how the pandemic flu spread across different parts of the country. We discovered that the claims data exhibits multi-scale patterns from which we could identify a small number of states in the United States (US) that act as “bridge regions” contributing to one or more specific influenza spread patterns. Similar to previous studies, the patterns show that the south-eastern regions of the US were widely affected by the H1N1 flu pandemic. Several of these south-eastern states act as bridge regions, which connect the north-east and central US in terms of flu occurrences. Conclusions: These quantitative insights show how the claims data combined with novel analytical techniques can provide important information to decision makers when an epidemic spreads throughout the country. Taken together ORBiT provides a scalable and extensible platform for public health surveillance.

97 MATHEMATICS AND COMPUTING↗

Discovery of Small Molecules that Inhibit the Disordered Protein, p27 Kip1

In disordered proteins we see that they are highly prevalent in biological systems. They control myriad signaling and regulatory processes, and their levels and/or cellular localization are often altered in human disease. In contrast to folded proteins, disordered proteins, due to conformational heterogeneity and dynamics, are not considered viable drug targets. We challenged this paradigm by identifying through NMR-based screening small molecules that bound specifically, albeit weakly, to the disordered cell cycle regulator, p27 Kip1 (p27). Moreover, two groups of molecules bound to sites created by transient clusters of aromatic residues within p27. Conserved chemical features within these two groups of small molecules exhibited complementarity to their binding sites within p27, establishing structure-activity relationships for small molecule: disordered protein interactions. Finally, one compound counteracted the Cdk2/cyclin A inhibitory function of p27 in vitro, providing proof-of- principle that small molecules can inhibit the function of a disordered protein (p27) through sequestration in a conformation incapable of folding and binding to a natural regulatory target (Cdk2/cyclin A).

59 BASIC BIOLOGICAL SCIENCES↗