Search NASA⌕ Search

SEARCH · Search NASA

Results for “Range Of Learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

Deep Learning Identifies High-$z$ Galaxies in a Central Blue Nugget Phase in a Characteristic Mass Range

We use machine learning to identify in color images of high-redshift galaxies an astrophysical phenomenon predicted by cosmological simulations. This phenomenon, called the blue nugget (BN) phase, is the compact star-forming phase in the central regions of many growing galaxies that follows an earlier phase of gas compaction and is followed by a central quenching phase. We train a convolutional neural network (CNN) with mock "observed" images of simulated galaxies at three phases of evolution— pre-BN, BN, and post-BN—and demonstrate that the CNN successfully retrieves the three phases in other simulated galaxies. We show that BNs are identified by the CNN within a time window of ~0.15 Hubble times. When the trained CNN is applied to observed galaxies from the CANDELS survey at $z$ = 1–3, it successfully identifies galaxies at the three phases. We find that the observed BNs are preferentially found in galaxies at a characteristic stellar mass range, 10 9.2–10.3 $M_⊙$ at all redshifts. This is consistent with the characteristic galaxy mass for BNs as detected in the simulations and is meaningful because it is revealed in the observations when the direct information concerning the total galaxy luminosity has been eliminated from the training set. This technique can be applied to the classification of other astrophysical phenomena for improved comparison of theory and observations in the era of large imaging surveys and cosmological simulations.

79 ASTRONOMY AND ASTROPHYSICS↗

Accurate prediction of global-density-dependent range-separation parameters based on machine learning

In this work, we develop an accurate and efficient XGBoost machine learning model for predicting the global-density-dependent range-separation parameter, ωGDD, for long-range corrected functional (LRC)-ωPBE. This ωGDDML model has been built using a wide range of systems (11 466 complexes, ten different elements, and up to 139 heavy atoms) with fingerprints for the local atomic environment and histograms of distances for the long-range atomic correlation for mapping the quantum mechanical range-separation values. The promising performance on the testing set with 7046 complexes shows a mean absolute error of 0.001 117 a0−1 and only five systems (0.07%) with an absolute error larger than 0.01 a0−1, which indicates the good transferability of our ωGDDML model. In addition, the only required input to obtain ωGDDML is the Cartesian coordinates without electronic structure calculations, thereby enabling rapid predictions. LRC-ωPBE(ωGDDML) is used to predict polarizabilities for a series of oligomers, where polarizabilities are sensitive to the asymptotic density decay and are crucial in a variety of applications, including the calculations of dispersion corrections and refractive index, and surpasses the performance of all other popular density functionals except for the non-tuned LRC-ωPBE. Finally, LRC-ωPBE (ωGDDML) combined with (extended) symmetry-adapted perturbation theory is used in calculating noncovalent interactions to further show that the traditional ab initio system-specific tuning procedure can be bypassed. The present study not only provides an accurate and efficient way to determine the range-separation parameter for LRC-ωPBE but also shows the synergistic benefits of fusing the power of physically inspired density functional LRC-ωPBE and the data-driven ωGDDML model.

Chemistry↗

Analysis of Fuel Cell Markets in Japan and the US: Experience Curve Development and Cost Reduction Disaggregation

Fuel cells are both a longstanding and emerging technology for stationary and transportation applications, and their future use will likely be critical for the deep decarbonization of global energy systems. As we look into future applications, a key challenge for policy-makers and technology market forecasters who seek to track and/or accelerate their market adoption is the ability to forecast market costs of the fuel cells as technology innovations are incorporated into market products. Specifically, there is a need to estimate technology learning rates, which are rates of cost reduction versus production volume. Unfortunately, no literature exists for forecasting future learning rates for fuel cells. In this paper, we look retrospectively to estimate learning rates for two fuel cell deployment programs: (1) the micro-combined heat and power (CHP) program in Japan, and (2) the Self-Generation Incentive Program (SGIP) in California. These two examples have a relatively broad set of historical market data and thus provide an informative and international comparison of distinct fuel cell technologies and government deployment programs. We develop a generalized procedure for disaggregating experience-curve cost-reductions in order to disaggregate the Japanese fuel cell micro-CHP market into its constituent components, and we derive and present a range of learning rates that may explain observed market trends. Finally, we explore the differences in the technology development ecosystem and market conditions that may have contributed to the observed differences in cost reduction and draw policy observations for the market adoption of future fuel cell technologies. The scientific and policy contributions of this paper are the first comparative experience curve analysis of past fuel cell technologies in two distinct markets, and the first quantitative comparison of a detailed cost model of fuel cell systems with actual market data. The resulting approach is applicable to analyzing other fuel cell markets and other energy-related technologies, and highlights the data needed for cost modeling and quantitative assessment of key cost reduction components.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Assembling a Cyber Range to Evaluate Artificial Intelligence / Machine Learning (AI/ML) Security Tools

In this case study, we will describe the design and assembly of a cyber security test range we have built at Oak Ridge National Laboratory in Oak Ridge, TN, USA. The range is designed to provide a flexible environment to evaluate cyber security tools—particularly those involving AI/ML—in a way that provides realistic environments and where we can control the experiments to determine the strengths and weaknesses of the tools. We have designed in the ability to repeat the evaluations, so additional tools can be evaluated and compared at a later time. The system is one that can be scaled up or down for experiment sizes. At the time of the conference we will have completed two full-scale, national, government challenges on this range. These challenges are evaluating the performance and operating costs for AI/ML-based cyber security tools for application into large, government-sized environments. These evaluations will be described, in order to provide motivation and context for various design decisions and adaptations we have made. The first challenge measured end-point security tools against 100K malware samples chosen across a range of types. The second is network detection of attempted penetration and exploitations with varying levels of covertness in a high-volume, business network. The scale of each of these challenges is requiring us to create automation systems to repeat the experiments identically for each tool. Preventing there being easy signs of malicious activity for the AI/ML tools to focus on has been a particularly interesting and challenging aspect of designing and executing these challenge events. After the events, the range continues to be used for other research such as adversarial machine learning where the repeatability, scale, and automation required for the national challenge events become essential elements for research.

Nichols, Jeff↗

Ten simple rules for drawing scientific comics

Institutions around the world are fighting to improve science communication all the time. From calls for journal papers to be simplified to encouraging scientists to take more of an active role through community engagement, there is an impetus to demystify and improve public understanding and engagement with science. Technology has greatly helped expand the range of learning styles that a lecturer can call on to reach people in new ways. Social media outlets like Twitter, Facebook, Instagram, and Tumblr have expanded the reach of science communication within and across scientific disciplines and to the lay public. Here, with all the videos, interactive quizzes, and instant feedback it can be easy to overlook one of the simplest methods for communicating complex ideas: comics.

99 GENERAL AND MISCELLANEOUS↗

(Active) Learning on Groups of Data with Information-Theoretic Estimators

A wide range of machine learning problems, including astronomical inference about galaxy clusters, scene classification, parametric statistical inference, and predictions of public opinion, can be well-modeled as learning a function on (samples from) distributions. This project explores problems in learning such functions via kernel methods, particularly for large-scale problems. When learning from large numbers of distributions, the computation of typical methods scales between quadratically and cubically, and so they are not amenable to large datasets. We investigate the approach of approximate embeddings into Euclidean spaces such that inner products in the embedding space approximate kernel values between the source distributions. We first improve the understanding of the workhorse methods of random Fourier features: we show that of the two approaches in common usage, one is strictly superior. We then present a new embedding for a class of information-theoretic distribution distances, and evaluate it and existing embeddings on several real-world applications.

97 MATHEMATICS AND COMPUTING↗

Machine learning for fundamental spectroscopic and thermodynamic data of actinides and lanthanides

Accurately modeling optical spectra with absolute radiometric intensities is vital for nuclear forensics applications that depend on characterizing optical emissions from energetic nuclear phenomena. This requires precise knowledge of the individual atomic transition probabilities, known as Einstein A-coefficients, for each emission line. Obtaining these values theoretically or experimentally is often impractical due to the complex electronic structures and the number of transitions involved in atoms relevant to nuclear applications. In this study, we explore the use of machine learning to predict the Einstein A coefficients for atomic transitions. Seven models were evaluated that ranged from deep learning to decision tree algorithms, and found that gradient boosting performed best, specifically the Extreme Gradient Boosting (XGB) architecture, achieving a precision of 86% across transitions of 36 elements. Furthermore, the model was cross-validated using published transition probabilities reported in the literature and applied to estimate Pu plasma temperatures from a previous experiment conducted at Savannah River National Laboratory.

Atomic spectroscopy↗

Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networks

Generative Adversarial Networks (GANs) are becoming popular choices for unsupervised learning. At the same time there is a concerted effort in the machine learning community to expand the range of tasks in which learning can be applied as well as to utilize methods from other disciplines to accelerate learning. With this in mind, in the current work we suggest ways to enforce given constraints in the output of a GAN both for interpolation and extrapolation. The two cases need to be treated differently. For the case of interpolation, the incorporation of constraints is built into the training of the GAN. The incorporation of the constraints respects the primary game-theoretic setup of a GAN so it can be combined with existing algorithms. However, it can exacerbate the problem of instability during training that is well-known for GANs. We suggest adding small noise to the constraints as a simple remedy that has performed well in our numerical experiments. The case of extrapolation (prediction) is more involved. First, we employ a modified interpolation training process that uses noisy data but does {\it not} necessarily enforce the constraints during training. Second, the resulting modified interpolator is used for extrapolation where the constraints are enforced after each step through projection on the space of constraints.

Stinis, Panagiotis↗

A deep potential model with long-range electrostatic interactions

Machine learning models for the potential energy of multi-atomic systems, such as the deep potential (DP) model, make molecular simulations with the accuracy of quantum mechanical density functional theory possible at a cost only moderately higher than that of empirical force fields. However, the majority of these models lack explicit long-range interactions and fail to describe properties that derive from the Coulombic tail of the forces. To overcome this limitation, we extend the DP model by approximating the long-range electrostatic interaction between ions (nuclei + core electrons) and valence electrons with that of distributions of spherical Gaussian charges located at ionic and electronic sites. The latter are rigorously defined in terms of the centers of the maximally localized Wannier distributions, whose dependence on the local atomic environment is modeled accurately by a deep neural network. In the DP long-range (DPLR) model, the electrostatic energy of the Gaussian charge system is added to short-range interactions that are represented as in the standard DP model. The resulting potential energy surface is smooth and possesses analytical forces and virial. Missing effects in the standard DP scheme are recovered, improving on accuracy and predictive power. By including long-range electrostatics, DPLR correctly extrapolates to large systems the potential energy surface learned from quantum mechanical calculations on smaller systems. We illustrate the approach with three examples: the potential energy profile of the water dimer, the free energy of interaction of a water molecule with a liquid water slab, and the phonon dispersion curves of the NaCl crystal.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Monitoring of Temperature Measurements for Different Flow Regimes in Water and Galinstan with Long Short-Term Memory Networks and Transfer Learning of Sensors

Temperature sensing is one of the most common measurements of a nuclear reactor monitoring system. The coolant fluid flow in a reactor core depends on the reactor power state. We investigated the monitoring and estimation of the thermocouple time series using machine learning for a range of flow regimes. Measurement data were obtained, in two separate experiments, in a flow loop filled with water and with liquid metal Galinstan. We developed long short-term memory (LSTM) recurrent neural networks (RNNs) for sensor predictions by training on the sensor’s own prior history, and transfer learning LSTM (TL-LSTM) by training on a correlated sensor’s prior history. Sensor cross-correlations were identified by calculating the Pearson correlation coefficient of the time series. The accuracy of LSTM and TL-LSTM predictions of temperature was studied as a function of Reynolds number (Re). The root-mean-square error (RMSE) for the test segment of time series of each sensor was shown to linearly increase with Re for both water and Galinstan fluids. Using linear correlations, we estimated the range of values of Re for which RMSE is smaller than the thermocouple measurement uncertainty. For both water and Galinstan fluids, we showed that both LSTM and TL-LSTM provide reliable estimations of temperature for typical flow regimes in a nuclear reactor. The LSTM runtime was shown to be substantially smaller than the data acquisition rate, which allows for performing estimation and validation of sensor measurements in real time.

Pantopoulou, Stella↗

Transfer learning for metamaterial design and simulation

Abstract We demonstrate transfer learning as a tool to improve the efficacy of training deep learning models based on residual neural networks (ResNets). Specifically, we examine its use for study of multi-scale electrically large metasurface arrays under open boundary conditions in electromagnetic metamaterials. Our aim is to assess the efficiency of transfer learning across a range of problem domains that vary in their resemblance to the original base problem for which the ResNet model was initially trained. We use a quasi-analytical discrete dipole approximation (DDA) method to simulate electrically large metasurface arrays to obtain ground truth data for training and testing of our deep neural network. Our approach can save significant time for examining novel metasurface designs by harnessing the power of transfer learning, as it effectively mitigates the pervasive data bottleneck issue commonly encountered in deep learning. We demonstrate that for the best case when the transfer task is sufficiently similar to the target task, a new task can be effectively trained using only a few data points yet still achieve a test mean absolute relative error of 3 % with a pre-trained neural network, realizing data reduction by a factor of 1000.

Peng, Rixi↗

Seismic signal augmentation to improve generalization of deep neural networks

Deep learning has emerged as an effective approach for seismic data processing in general, and for earthquake monitoring in particular. The ability of deep learning models to generalize beyond the training and validation data is important for comprehensive earthquake monitoring; this ability furthermore depends on the availability of a sufficiently large and complete training dataset. However, this requirement can prove challenging to meet due to significant effort and time for data collection and labeling. Data augmentation provides an efficient and effective approach for increasing the dimension of training samples and improving generalization to unseen samples. In this paper, we present augmentation methods appropriate for seismic waveforms and demonstrate their ability to reduce bias and increase performance. Furthermore, these augmentation methods can be applied to a wide range of deep learning applications designed for seismic data.

58 GEOSCIENCES↗

WE-A-16A-01: International Medical Physics Symposium: Increasing Access to Medical Physics Education/Training and Research Excellence

In response to a world in which cancer is a growing global health challenge, there is now a greater need for US Medical Physicists and other Radiation Oncology professionals across institutions to work together and be more globally engaged in the fight against cancer. There are currently many opportunities for Medical Physicists to contribute to alleviating this pressing need, especially in helping enhance access to Medical Physics Education/training and Research Excellence across international boundaries, particularly for low and middle-income countries (LMIC), which suffer from a drastic shortage of accessible knowledge and quality training programs in radiotherapy. Many Medical Physicists are not aware of the range of opportunities that even with small effort could have a high impact. Faculty at the two CAMPEP-accredited Medical Physics Programs in New England: the University of Massachusetts Lowell and Harvard Medical School have developed a growing alliance to increase Access to Medical Physics Education/training and Research Excellence (AMPERE), and facilitate greater active involvement of U.S. Medical Physicists in helping the global fight against cancer and cancer disparities. In this symposium, AMPERE Alliance members and partners from Europe and Africa will present and discuss the growing global cancer challenge, the dearth of knowledge, research, and other barriers to providing life-saving radiotherapy in LMIC, mechanisms for meeting these challenges, the different opportunities for participation by Medical Physicists, including students and residents, and how participation can be facilitated to increase AMPERE for global health. Learning Objectives: To learn about the growing global cancer challenge, areas of greatest need and limitations to accessing knowledge and quality radiotherapy training programs, especially in LMIC; To learn about the range of opportunities for Medical Physicists, including students and residents, to work together in global health to help increase AMPERE and alleviate the growing global burden of cancer; To present and discuss a new model for harmonizing Medical Physics Training across countries and how this model (UMass and Heidelberg) could be extended to LMIC in collaboration with the IAEA; To highlight a new platform and program for facilitating contributions by Medical Physicists to increase AMPERE towards the elimination of global cancer disparities. Challenges in Cancer Control in Africa Twalib A. Ngoma, MD, Professor, Executive Director, Ocean Road Cancer Institute, Dar Es Salaam, Tanzania Cancer care in Africa is beset by lack of attention, political will, cancer registries, cancer plans, human resources, financial resources and treatment facilities.. As a result of this, cancer patients in Africa are far more likely to die of their disease than those in developed countries. According to data from the WHO 750,000 new cancer cases occur in Africa every year and this number is predicted to rise by 70% by 2020. To make matters worse, an estimated 75% of cancer patients in Africa have advanced or incurable cancers at diagnosis making palliative care the most realistic approach to their management. Furthermore, Cancer prevention is nearly nonexistent, cancer detection is rare and treatment usually comes too late and is inefficient. The overall mortality-to-incidence ratio for men with cancer in the Africa is 0.75 compared with 0.54 in the developed world while the ratios for women in Africa, is 0.65 compared with 0.45 for women in the developed world. There is also limited access to radiotherapy. According to the International Atomic Energy Agency (IAEA), whilst developed countries usually have one radiotherapy machine per 250,000 people, most African nations have only one machine per ten million people. The above numbers are alarming and speak for themselves. The only solution to improve this alarming situation is to address the major challenges which African countries face in provision of cancer services which include but not limited to lack of cancer registries, lack of funding, lack of human resources, lack of radiotherapy machines, lack of cancer drugs and lack of accessible and affordable cancer screening, early diagnosis, treatment or palliative care services. Since there are considerable differences among African countries, in my presentation I will share with the audience how we address cancer control challenges in Tanzania in general and specifically in radiation oncology. The African continent cancer plan 2013 2017 Folakemi Odedina, PhD, Professor and Director of Health Disparities, UF Health Cancer Center, University of Florida The burden of cancer is rising in Africa, in addition to current heavy burden of communicable, and other non-cancer related non—communicable diseases. Conquering cancer in Africa will require a comprehensive collaborative approach with cancer clinicians, scientists, patients, advocates, policy makers and community leaders working hand-in-hand at the local, state, national, and continent levels with the primary mission: To reduce the number of deaths from cancer and improve the quality of life of cancer patients, survivors and caregivers. Unfortunately, less than 40% of African countries have a credible cancer control policy and program. The African Organization for Research and Training in Cancer (AORTIC) decided to create an African Cancer Plan to provide cost-effective strategies that can be employed throughout the continent to fight cancer. Based on the African proverb that “It takes a village to raise a child”, the Cancer Plan provides specific strategies that can be used by individuals, employers, organizations and policy-makers to fight cancer. In addition, we have provided overarching strategies to address cancer in Africa and targeted 5-year plan for prostate, breast, cervix, lung and liver cancers. In developing this Cancer Plan, our primary goal is to decrease cancer incidence and mortality in Africa. This goal can only be achieved by stakeholders and dedicated individuals to lead and implement the strategies outlined in this plan. If you are interested in partnering with AORTIC to reduce the burden of cancer in Africa, please send an email to info@aortic-africa.org. Synergies in research and clinical care through international collaboration Thomas Bortfeld and David Gierga, Massachusetts General Hospital, Harvard Medical School, MA Medical Physics relies on high technology that is not distributed equally. The whole spectrum of Medical Physics technologies is not available at every hospital or research institute, and not even in every high income country. One example is heavy ion therapy equipment which is currently only available in Japan, Germany and Italy. There is also a large global variation in terms of research infrastructure and focus. A student of Medical physics cannot gain broad experience, certainly not hands-on experience, by staying at one place only. While it is debatable what a good trade-off between breadth and depth in Medical Physics education is, it is generally agreed upon that some breadth is necessary. Researchers in Medical Physics have to cross borders if they need specific technologies for their projects. Therefore it is self-evident that international programs in Medical Physics education and research make sense. Yet, very few programs of this type exist. In this presentation we will report on our own experience of pursuing an international career in Medical Physics, with international student programs, and with the international exchange of researchers. We will present new or planned opportunities such as the medical beamline at CERN in Geneva. We will also report on the synergies in clinical care through international collaborations between partners in high and low income countries. One example is the partnership of the MGH/Harvard Medical School community with the oncology community and government of Botswana to form the BOTSOGO (BOTSwana Oncology Global Outreach) initiative. This collaborative effort in oncology care was spurred by existing relationships in HIV/AIDS research and care delivery developed within the Botswana-Harvard AIDS Institute Partnership (BHP). The initial efforts of the BOTSOGO initiative have been organized as follows: 1) on-site visits to share expertise in clinical cancer care for capacity building purposes (e.g. cervical brachytherapy), 2) developing a forum for multi-disciplinary case discussions and education and 3) relationship building with local stakeholders for long-term sustainability and growth. An international system for the certification of medical physicists Raymond K. Wu, Chairman, IOMP Professional Relations Committee; Chairman, AAPM Exchange Scientist Program Subcommittee An international system for the certification of medical physicists is an important issue. The International Organization for Medical Physicists (IOMP) has in collaboration with a number of member countries established the International Medical Physics Certification Board (IMPCB) to address this issue, and to provide a mechanism to mark the milestone for the professional development of clinical medical physicists. Raymond Wu, PhD, is the CEO of IMPCB and the Chairman of the IOMP Professional Relations Committee. He is the invited speaker recommended by IOMP to give a talk on this important subject. He will give the latest update of the work of IMPCB, its near term goals, and pathways to the goals. He will also discuss the importance of such an International System of certification in the training/education of next generation Medical Physicists, including those in low and middle income countries (LMIC) where such training is crucial in the fight against cancer. Learning Objectives: Understand the certification program as described in the IOMP Policy Statements. Understand the plan of the IMPCB to establish the accreditation process of national certification programs. Understand the goals of this international collaborative effort and the potential impacts to the quality of clinical medical physics practice. Medical Physics Education Across Continents: The UMass Lowell and Heidelberg University Joint Coordination Effort Erno Sajo, Director of Medical Physics, University of Massachusetts at Lowell Medical Physics education has unique flavors across institutions within the US and shows significant differences across continents. In the latter, even the definition of Medical Physics may differ. Not only is there a difference in topical coverage, but often what is considered a cohesive topic in one institution, and taught as a single course, is fragmented among several other courses in the other institution due to a different philosophy. Because of the regulatory and certification requirements, these differences impact the mobility of medical physicists across continents. As a result, physicists who wish to practice in the US or Canada but have completed their education elsewhere often find that they have to take remedial courses or even obtain a new degree in Medical Physics despite the fact that they already have one. Outreach to developing countries, therefore, is even more difficult. The University of Massachusetts Lowell and Heidelberg University recently completed a joint coordination effort, in which they identified topics that are common versus complementary in their medical physics curricula. A student exchange program was developed that permits students to take any of the common topics at the other institution while taking complementary courses as electives, which count towards their degree requirements at their home institution. Thesis research is also mutually accepted. When properly documented, in this way CAMPEP recommendations can be met across the institutions. Therefore, students participating in this program satisfy both the American Board of Radiology (ABR) requirements and the European regulatory requirements. The framework on which this collaboration rests and the cross-comparison methods developed therein may be implemented in other exchange programs and thus a similar approach can be adopted in outreach programs with developing countries. IAEA PACT Program and opportunities for support and collaboration Susan Morgan, Program Coordinator, International Atomic Energy Agency, Vienna, Austria In response to the developing world's cancer crisis, the International Atomic Energy Agency (IAEA) established the Program of Action for Cancer Therapy (PACT) in 2004 to fully realize the public health impact obtained through global partnerships in cancer control and technology transfer in radiation medicine. PACT's vision strives for global partnerships to confront the cancer crisis in developing countries, notably with our sister United Nations agency, the World Health Organization (WHO), and our Joint Programme on Cancer Control established in 2009. The IAEA, through PACT, the WHO, the International Agency for Research on Cancer (IARC) and other cancer-related organizations work together to make a coordinated global response in supporting low and middle income (LMI) IAEA Member States in the implementation of comprehensive national cancer control programmes. PACT's goals are: To build global partnerships of cancer-related organizations committed to addressing the challenge of cancer in LMI Member States in all its aspects; To mobilize resources from charitable trusts, foundations, and others in public and private sectors sources to assist LMI Member States to develop and implement their radiation medicine capacities within a national cancer control programme (NCCP); and, To ensure the effective and sustainable transfer of radiation medicine technologies or knowledge to all LMI Member States where unmet needs exist. PACT work focuses on: imPACT: Assessing Cancer Burden PMDS: Developing Global Partnerships VUCCnet: Promoting Cancer Control Training AGaRT: Making Radiotherapy Accessible Facilitating increased participation and professional development of Medical Physicists and other Radiation Oncology professionals in global health Wilfred Ngwa, Harvard Medical School, University of Massachusetts Lowell, MA The 2014 World Health Organization (WHO) Cancer report highlights an alarming increase in the global burden of cancer. It also highlights what it terms “the cancer divide”, or disparities, evinced by a substantially higher cancer burden in low and middle income countries (LMIC) in Asia, Central/South America and Africa. The WHO even predicts a potential African cancer epidemic by 2020 if significant progress is not made in global cancer control efforts. Evidence that collaborative global health approaches have led to major progress in controlling infectious diseases including in LMIC suggests that similar approaches will be useful for non-communicable diseases like cancer. In consonance with this, leaders in cancer policy from the USA and 14 economically diverse countries recently concluded that successful campaigns to control cancers with existing methods and to improve current strategies will increasingly depend onconcerted multinational collaborations (Sci Transl Med 5, p. 175, 2013). Hence there is growing urgency for increasing collaborative global cancer Care Research and Education (CaRE), as well as support for greater effectiveness of already existing initiatives involving partners from different nations, diverse economic and cultural backgrounds. The good news is that there is a growing awareness of the importance of global health and growing interest including amongst Medical Physicists and other Radiation oncology (RadOnc) professionals to participate in global health. However, many are unaware of currently existing opportunities for participation that even with small effort could have a high impact. Over 50% of cancer patients in the developed world depend on RadOnc professionals for their treatment, and hence participation of RadOnc professionals in global health efforts in the global fight against cancer is crucial. It is also important that the next generation of RadOnc professionals (students, and residents) be trained with a global perspective, to be global health leaders in cancer CaRE. This presentation will highlight a novel platform for enhancing participation and professional development of Medical Physicists and other RadOnc professionals in global health. Ways in which this platform can facilitate contributions by Medical Physicists and other RadOnc Professionals, students and residents in global health towards the elimination of global cancer disparities will be discussed. This will be followed by a panel discussion by some of the pioneers/leaders in collaborative global cancer CaRE on the growing cancer burden, challenges and opportunities for greater active involvement and professional development.

60 APPLIED LIFE SCIENCES↗

DeepGRN: prediction of transcription factor binding site across cell-types using attention-based deep neural networks

Abstract Background Due to the complexity of the biological systems, the prediction of the potential DNA binding sites for transcription factors remains a difficult problem in computational biology. Genomic DNA sequences and experimental results from parallel sequencing provide available information about the affinity and accessibility of genome and are commonly used features in binding sites prediction. The attention mechanism in deep learning has shown its capability to learn long-range dependencies from sequential data, such as sentences and voices. Until now, no study has applied this approach in binding site inference from massively parallel sequencing data. The successful applications of attention mechanism in similar input contexts motivate us to build and test new methods that can accurately determine the binding sites of transcription factors. Results In this study, we propose a novel tool (named DeepGRN) for transcription factors binding site prediction based on the combination of two components: single attention module and pairwise attention module. The performance of our methods is evaluated on the ENCODE-DREAM in vivo Transcription Factor Binding Site Prediction Challenge datasets. The results show that DeepGRN achieves higher unified scores in 6 of 13 targets than any of the top four methods in the DREAM challenge. We also demonstrate that the attention weights learned by the model are correlated with potential informative inputs, such as DNase-Seq coverage and motifs, which provide possible explanations for the predictive improvements in DeepGRN. Conclusions DeepGRN can automatically and effectively predict transcription factor binding sites from DNA sequences and DNase-Seq coverage. Furthermore, the visualization techniques we developed for the attention modules help to interpret how critical patterns from different types of input features are recognized by our model.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Conformational spread drives the evolution of the calcium–calmodulin protein kinase II

The calcium calmodulin (Ca 2+ /CaM) dependent protein kinase II (CaMKII) decodes Ca 2+ frequency oscillations. The CaMKIIα isoform is predominantly expressed in the brain and has a central role in learning. I matched residue and organismal evolution with collective motions deduced from the atomic structure of the human CaMKIIα holoenzyme to learn how its ring architecture abets function. Protein dynamic simulations showed its peripheral kinase domains (KDs) are conformationally coupled via lateral spread along the central hub. The underlying β-sheet motions in the hub or association domain (AD) were deconvolved into dynamic couplings based on mutual information. They mapped onto a coevolved residue network to partition the AD into two distinct sectors. A second, energetically stressed sector was added to ancient bacterial enzyme dimers for assembly of the ringed hub. The continued evolution of the holoenzyme after AD–KD fusion targeted the sector’s ring contacts coupled to the KD. Among isoforms, the α isoform emerged last and, it alone, mutated rapidly after the poikilotherm–homeotherm jump to match the evolution of memory. The correlation between dynamics and evolution of the CaMKII AD argues single residue substitutions fine-tune hub conformational spread. The fine-tuning could increase CaMKIIα Ca 2+ frequency response range for complex learning functions.

59 BASIC BIOLOGICAL SCIENCES↗