GPUs are used in many settings to accelerate large-scale scientific computation, including simulation, computational biology, and molecular dynamics. However, optimizing codes to run efficiently on GPUs requires developers to have both detailed understanding of the application logic and significant knowledge of parallel programming and GPU architectures. This paper shows that an automated GPU program optimization tool, GEVO, can leverage evolutionary computation to find code edits that reduce the runtime of three important applications, multiple sequence alignment, agent-based simulation and molecular dynamics codes, by 28.9%, 29%, and 17.8% respectively. The paper presents an in-depth analysis of the discovered optimizations, revealing that (1) several of the most important optimizations involve significant epistasis, (2) the primary sources of improvement are application-specific, and (3) many of the optimizations generalize across GPU architectures. In general, the discovered optimizations are not straightforward even for a GPU human expert, showcasing the potential of automated program optimization tools to both reduce the optimization burden for human domain experts and provide new insights for GPU experts.

Ribonucleic acid (RNA) is a fundamental biological molecule that is essential to all living organisms, performing a versatile array of cellular tasks. The function of many RNA molecules is strongly related to the structure it adopts. As a result, great effort is being dedicated to the design of efficient algorithms that solve the “folding problem”—given a sequence of nucleotides, return a probable list of base pairs, referred to as the secondary structure prediction. Early algorithms largely rely on finding the structure with minimum free energy. However, the predictions rely on effective simplified free energy models that may not correctly identify the correct structure as the one with the lowest free energy. In light of this, new, data-driven approaches that not only consider free energy, but also use machine learning techniques to learn motifs are also investigated and recently been shown to outperform free energy–based algorithms on several experimental data sets. In this work, we introduce the new ExpertRNA algorithm that provides a modular framework that can easily incorporate an arbitrary number of rewards (free energy or nonparametric/data driven) and secondary structure prediction algorithms. We argue that this capability of ExpertRNA has the potential to balance out different strengths and weaknesses of state-of-the-art folding tools. We test ExpertRNA on several RNA sequence-structure data sets, and we compare the performance of ExpertRNA against a state-of-the-art folding algorithm. We find that ExpertRNA produces, on average, more accurate predictions of nonpseudoknotted secondary structures than the structure prediction algorithm used, thus validating the promise of the approach. Summary of Contribution: ExpertRNA is a new algorithm inspired by a biological problem. It is applied to solve the problem of secondary structure prediction for RNA molecules given an input sequence. The computational contribution is given by the design of a multibranch, multiexpert rollout algorithm that enables the use of several state-of-the-art approaches as base heuristics and allowing several experts to evaluate partial candidate solutions generated, thus avoiding assuming the reward being optimized by an RNA molecule when folding. Our implementation allows for the effective use of parallel computational resources as well as to control the size of the rollout tree as the algorithm progresses. The problem of RNA secondary structure prediction is of primary importance within the biology field because the molecule structure is strongly related to its functionality. Whereas the contribution of the paper is in the algorithm, the importance of the application makes ExpertRNA a showcase of the relevance of computationally efficient algorithms in supporting scientific discovery.

Selection protocols such as SELEX, where molecules are selected over multiple rounds for their ability to bind to a target of interest, are popular methods for obtaining binders for diagnostic and therapeutic purposes. We show that Restricted Boltzmann Machines (RBMs), an unsupervised two-layer neural network architecture, can successfully be trained on sequence ensembles from single rounds of SELEX experiments for thrombin aptamers. RBMs assign scores to sequences that can be directly related to their fitnesses estimated through experimental enrichment ratios. Hence, RBMs trained from sequence data at a given round can be used to predict the effects of selection at later rounds. Moreover, the parameters of the trained RBMs are interpretable and identify functional features contributing most to sequence fitness. To exploit the generative capabilities of RBMs, we introduce two different training protocols: one taking into account sequence counts, capable of identifying the few best binders, and another based on unique sequences only, generating more diverse binders. We then use RBMs model to generate novel aptamers with putative disruptive mutations or good binding properties, and validate the generated sequences with gel shift assay experiments. Finally, we compare the RBM's performance with different supervised learning approaches that include random forests and several deep neural network architectures.

High-penetration levels of distributed photovoltaic (PV) generation on an electrical distribution circuit present several challenges and opportunities for distribution utilities. Rapidly varying irradiance conditions may cause voltage sags and swells that cannot be compensated by slowly responding utility equipment resulting in a degradation of power quality. Although not permitted under current standards for interconnection of distributed generation, fast-reacting, VAR-capable PV inverters may provide the necessary reactive power injection or consumption to maintain voltage regulation under difficult transient conditions. As side benefit, the control of reactive power injection at each PV inverter provides an opportunity and a new tool for distribution utilities to optimize the performance of distribution circuits, e.g., by minimizing thermal losses. We discuss and compare via simulation various design options for control systems to manage the reactive power generated by these inverters. An important design decision that weighs on the speed and quality of communication required is whether the control should be centralized or distributed (i.e., local). In general, we find that local control schemes are able to maintain voltage within acceptable bounds. We consider the benefits of choosing different local variables on which to control and how the control system can be continuously tuned between robust voltage control, suitable for daytime operation when circuit conditions can change rapidly, and loss minimization better suited for nighttime operation.