An official website of the United States government
Cellular signaling pathways are responsible for decision making that sustains life. Most signaling pathways include post-translational modification cycles, that process multiple inputs and are tightly interconnected. Here we consider a model for phosphorylation/dephosphorylation cycles, and we show that under some assumptions they can operate as molecular neurons or perceptrons, that generate sigmoidal-like activation functions by processing sums of inputs with positive and negative weights. We carry out a steady-state and structural stability analysis for single molecular perceptrons as well as for feedforward interconnections, concluding that interconnected phosphorylation/dephosphorylation cycles may work as multilayer biomolecular neural networks (BNNs) with the capacity to perform a variety of computations. As an application, we design signaling networks that behave as linear and non-linear classifiers.
more »
« less
Engineering sequestration-based biomolecular classifiers with shared resources
Constructing molecular classifiers that enable cells to recognize linear and non-linear input patterns would expand the biocomputational capabilities of engineered cells, thereby unlocking their potential in diagnostics and therapeutic applications. While several biomolecular classifier schemes have been designed, the effect of biological constraints such as resource limitation and competitive binding on the function of those classifiers has been left unexplored. Here, we first demonstrate the design of a sigma factor-based perceptron as a molecular classifier working on the principles of molecular sequestration between the sigma factor and its anti-sigma molecule. We then investigate how the output of the biomolecular perceptron,i.e., its response pattern or decision boundary, is affected by the competitive binding of sigma factors to a pool of shared and limited resources of core RNA polymerase. Finally, we reveal the influence of sharing limited resources on multi-layer perceptron neural networks and outline design principles that enable the construction of non-linear classifiers using sigma-based biomolecular neural networks in the presence of competitive resource-sharing effects.
more »
« less
- Award ID(s):
- 1935265
- PAR ID:
- 10525194
- Publisher / Repository:
- bioRxiv
- Date Published:
- Format(s):
- Medium: X
- Institution:
- bioRxiv
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Advances in both hardware and software are enabling rapid proliferation of in situ plankton imaging methods, requiring more effective machine learning approaches to image classification. Deep Learning methods, such as convolutional neural networks (CNNs), show marked improvement over traditional feature‐based supervised machine learning algorithms, but require careful optimization of hyperparameters and adequate training sets. Here, we document some best practices in applying CNNs to zooplankton and marine snow images and note where our results differ from contemporary Deep Learning findings in other domains. We boost the performance of CNN classifiers by incorporating metadata of different types and illustrate how to assimilate metadata beyond simple concatenation. We utilize both geotemporal (e.g., sample depth, location, time of day) and hydrographic (e.g., temperature, salinity, chlorophylla) metadata and show that either type by itself, or both combined, can substantially reduce error rates. Incorporation of context metadata also boosts performance of the feature‐based classifiers we evaluated: Random Forest, Extremely Randomized Trees, Gradient Boosted Classifier, Support Vector Machines, and Multilayer Perceptron. For our assessments, we use an original data set of 350,000 in situ images (roughly 50% marine snow and 50% non‐snow sorted into 26 categories) from a novel in situZooglider. We document asymptotically increasing performance with more computationally intensive techniques, such as substantially deeper networks and artificially augmented data sets. Our best model achieves 92.3% accuracy with our 27‐class data set. We provide guidance for further refinements that are likely to provide additional gains in classifier accuracy.more » « less
-
Deep neural networks (DNNs) come with many forms, such as convolutional neural networks, multilayer perceptron and recurrent neural networks, to meet diverse needs of machine learning applications. However, existing DNN accelerator designs, when used to execute multiple neural networks, suffer from underutilization of processing elements, heavy feature map traffic, and large area overhead. In this paper, we propose a novel approach, Polymorphic Accelerators, to address the flexibility issue fundamentally. We introduce the abstraction of logical accelerators to decouple the fixed mapping with physical resources. Three procedures are proposed that work collaboratively to reconfigure the accelerator for the current network that is being executed and to enable cross-layer data reuse among logical accelerators. Evaluation results show that the proposed approach achieves significant improvement in data reuse, inference latency and performance, e.g., 1.52x and 1.63x increase in throughput compared with state-of-the-art flexible dataflow approach and resource partitioning approach, respectively. This demonstrates the effectiveness and promise of polymorphic accelerator architecture.more » « less
-
null (Ed.)Cells possess a multiplicity of non-membrane-bound compartments, which form via liquid-liquid phase separation. These condensates assemble and dissolve as needed to enable central cellular functions. One important class of condensates is those composed of two associating polymer species that form one-to-one specific bonds. What are the physical principles that underlie phase separation in such systems? To address this question, we employed coarse-grained molecular dynamics simulations to examine how the phase boundaries depend on polymer valence, stoichiometry, and binding strength. We discovered a striking phenomenon – for sufficiently strong binding, phase separation is suppressed at rational polymer stoichiometries, which we termed the magic-ratio effect. We further developed an analytical dimer-gel theory that confirmed the magic-ratio effect and disentangled the individual roles of polymer properties in shaping the phase diagram. Our work provides new insights into the factors controlling the phase diagrams of biomolecular condensates, with implications for natural and synthetic systems.more » « less
-
Abstract Acid-base reactions are ubiquitous, easy to prepare, and execute without sophisticated equipment. Acids and bases are also inherently complementary and naturally map to a universal representation of “0” and “1.” Here, we propose how to leverage acids, bases, and their reactions to encode binary information and perform information processing based upon the majority and negation operations. These operations form a functionally complete set that we use to implement more complex computations such as digital circuits and neural networks. We present the building blocks needed to build complete digital circuits using acids and bases for dual-rail encoding data values as complementary pairs, including a set of primitive logic functions that are widely applicable to molecular computation. We demonstrate how to implement neural network classifiers and some classes of digital circuits with acid-base reactions orchestrated by a robotic fluid handling device. We validate the neural network experimentally on a number of images with different formats, resulting in a perfect match to thein-silicoclassifier. Additionally, the simulation of our acid-base classifier matches the results of thein-silicoclassifier with approximately 99% similarity.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Posted Content:
- https://doi.org/10.1101/2024.04.15.589451
