Asynchronous parallel Bayesian optimization for AI-driven cloud laboratories.
Ontology highlight
ABSTRACT: Motivation
The recent emergence of cloud laboratories-collections of automated wet-lab instruments that are accessed remotely, presents new opportunities to apply Artificial Intelligence and Machine Learning in scientific research. Among these is the challenge of automating the process of optimizing experimental protocols to maximize data quality.Results
We introduce a new deterministic algorithm, called PaRallel OptimizaTiOn for ClOud Laboratories (PROTOCOL), that improves experimental protocols via asynchronous, parallel Bayesian optimization. The algorithm achieves exponential convergence with respect to simple regret. We demonstrate PROTOCOL in both simulated and real-world cloud labs. In the simulated lab, it outperforms alternative approaches to Bayesian optimization in terms of its ability to find optimal configurations, and the number of experiments required to find the optimum. In the real-world lab, the algorithm makes progress toward the optimal setting.Data availability and implementation
PROTOCOL is available as both a stand-alone Python library, and as part of a R Shiny application at https://github.com/clangmead/PROTOCOL. Data are available at the same repository.Supplementary information
Supplementary data are available at Bioinformatics online.
SUBMITTER: Frisby TS
PROVIDER: S-EPMC8275326 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Traditional optimization methods using one variable at a time approach waste time and chemicals and assume that different parameters are independent from one another. Hence, a simpler, more practical, and rapid process for predicting reaction conditions that can be applied to several manufacturing environmentally sustainable processes is highly desirable. In this study, biaryl compounds were synthesized efficiently using an organic Brønsted acid catalyst in a flow system. Bayesian optimization-assisted multi-parameter screening, which employs one-hot encoding and appropriate acquisition function, rapidly predicted the suitable conditions for the synthesis of 2-amino-2'-hydroxy-biaryls (maximum yield of 96%). The established protocol was also applied in an optimization process for the efficient synthesis of 2,2'-dihydroxy biaryls (up to 97% yield). The optimized reaction conditions were successfully applied to gram-scale synthesis. We believe our algorithm can be beneficial as it can screen a reactor design without complicated quantification and descriptors.
| S-EPMC9814103 | biostudies-literature
Project description:The COVID-19 disease causes pneumonia in many patients that in the most serious cases evolves into the Acute Distress Respiratory Syndrome (ARDS), requiring assisted ventilation and intensive care. In this context, identification of patients at high risk of developing ARDS is a key point for early clinical management, better clinical outcome and optimization in using the limited resources available in the intensive care units. We propose an AI-based prognostic system that makes predictions of oxygen exchange with arterial blood by using as input lung Computed Tomography (CT), the air flux in lungs obtained from biomechanical simulations and Arterial Blood Gas (ABG) analysis. We developed and investigated the feasibility of this system on a small clinical database of proven COVID-19 cases where the initial CT and various ABG reports were available for each patient. We studied the time evolution of the ABG parameters and found correlation with the morphological information extracted from CT scans and disease outcome. Promising results of a preliminary version of the prognostic algorithm are presented. The ability to predict the evolution of patients' respiratory efficiency would be of crucial importance for disease management.
| S-EPMC9969369 | biostudies-literature
Project description:Chemistry42 is a software platform for de novo small molecule design and optimization that integrates Artificial Intelligence (AI) techniques with computational and medicinal chemistry methodologies. Chemistry42 efficiently generates novel molecular structures with optimized properties validated in both in vitro and in vivo studies and is available through licensing or collaboration. Chemistry42 is the core component of Insilico Medicine's Pharma.ai drug discovery suite. Pharma.ai also includes PandaOmics for target discovery and multiomics data analysis, and inClinico─a data-driven multimodal forecast of a clinical trial's probability of success (PoS). In this paper, we demonstrate how the platform can be used to efficiently find novel molecular structures against DDR1 and CDK20.
| S-EPMC9930109 | biostudies-literature
Project description:Simulations of electrical activity of networks of morphologically detailed neuron models allow for a better understanding of the brain. State-of-the-art simulations describe the dynamics of ionic currents and biochemical processes within branching topological representations of the neurons. Acceleration of such simulation is possible in the weak scaling limit by modeling neurons as indivisible computation units and increasing the computing power. Strong scaling and simulations close to biological time are difficult, yet required, for the study of synaptic plasticity and other use cases requiring simulation of neurons for long periods of time. Current methods rely on parallel Gaussian Elimination, computing triangulation and substitution of many branches simultaneously. Existing limitations are: (a) high heterogeneity of compute time per neuron leads to high computational load imbalance; and (b) difficulty in providing a computation model that fully utilizes the computing resources on distributed multi-core architectures with Single Instruction Multiple Data (SIMD) capabilities. To address these issues, we present a strategy that extracts flow-dependencies between parameters of the ODEs and the algebraic solver of individual neurons. Based on the resulting map of dependencies, we provide three techniques for memory, communication, and computation reorganization that yield a load-balanced distributed asynchronous execution. The new computation model distributes datasets and balances computational workload across a distributed memory space, exposing a tree-based parallelism of neuron topological structure, an embarrassingly parallel execution model of neuron subtrees, and a SIMD acceleration of subtree state updates. The capabilities of our methods are demonstrated on a prototype implementation developed on the core compute kernel of the NEURON scientific application, built on the HPX runtime system for the ParalleX execution model. Our implementation yields an asynchronous distributed and parallel simulation that accelerates single neuron to medium-sized neural networks. Benchmark results display better strong scaling properties, finer-grained parallelism, and lower time to solution compared to the state of the art, on a wide range of distributed multi-core compute architectures.
| S-EPMC6664068 | biostudies-literature
Project description:SignificanceWith the increase in artificial intelligence in real-world applications, there is interest in building hybrid systems that take both human and machine predictions into account. Previous work has shown the benefits of separately combining the predictions of diverse machine classifiers or groups of people. Using a Bayesian modeling framework, we extend these results by systematically investigating the factors that influence the performance of hybrid combinations of human and machine classifiers while taking into account the unique ways human and algorithmic confidence is expressed.
| S-EPMC8931210 | biostudies-literature
Project description:Data exchange over the Internet and other access channels is on the rise, leads to the insecurity of consequences. Many experiments have been conducted to investigate time-efficient and high-randomized encryption methods for the data. The latest studies, however, have still been debated because of different factors. The study outcomes do not yield completely random keys for encryption methods that are longer than this. Prominent repetition makes the processes predictable and susceptible to assaults. Furthermore, recently generated keys need recent algorithms to run at a high volume of transactional data successfully. In this article, the proposed solutions to these two critical issues are presented. In the beginning, one must use the chaotic series of events for generating keys is sufficient to obtain a high degree of randomness. Moreover, this work also proposes a novel and non-traditional validation test to determine the true randomness of the keys produced from a correlation algorithm. An approximate 100% probability of the vital phase over almost infinitely long-time intervals minimizes the algorithms' complexity for the higher volume of data security. It is suggested that these algorithms are mainly intended for cloud-based transactions. Data volume is potentially higher and extremely changeable 3% to 4% of the improvement in data transmission time with suggested algorithms. This research has the potential to improve communication systems over ten years by unblocking decades-long bottlenecks.
| S-EPMC8372001 | biostudies-literature
Project description:Acute gastrointestinal infection (AGI) represents a significant public health concern. To control and treat AGI, it is critical to quickly and accurately identify its causes. The use of novel multiplex molecular assays for pathogen detection and identification provides a unique opportunity to improve pathogen detection, and better understand risk factors and burden associated with AGI in the community. In this study, de-identified results from BioFire® FilmArray® Gastrointestinal (GI) Panel were obtained from January 01, 2016 to October 31, 2018 through BioFire® Syndromic Trends (Trend), a cloud database. Data was analyzed to describe the occurrence of pathogens causing AGI across United States sites and the relative rankings of pathogens monitored by FoodNet, a CDC surveillance system were compared. During the period of the study, the number of tests performed increased 10-fold and overall, 42.6% were positive for one or more pathogens. Seventy percent of the detections were bacteria, 25% viruses, and 4% parasites. Clostridium difficile, enteropathogenic Escherichia coli (EPEC) and norovirus were the most frequently detected pathogens. Seasonality was observed for several pathogens including astrovirus, rotavirus, and norovirus, EPEC, and Campylobacter. The co-detection rate was 10.2%. Enterotoxigenic E. coli (ETEC), Plesiomonas shigelloides, enteroaggregative E. coli (EAEC), and Entamoeba histolytica were detected with another pathogen over 60% of the time, while less than 30% of C. difficile and Cyclospora cayetanensis were detected with another pathogen. Positive correlations among co-detections were found between Shigella/Enteroinvasive E. coli with E. histolytica, and ETEC with EAEC. Overall, the relative ranking of detections for the eight GI pathogens monitored by FoodNet and BioFire Trend were similar for five of them. AGI data from BioFire Trend is available in near real-time and represents a rich data source for the study of disease burden and GI pathogen circulation in the community, especially for those pathogens not often targeted by surveillance.
| S-EPMC8087049 | biostudies-literature
Project description:Genomic sequence alignment is an important technique to decode genome sequences in bioinformatics. Next-Generation Sequencing technologies produce genomic data of longer reads. Cloud platforms are adopted to address the problems arising from storage and analysis of large genomic data. Existing genes sequencing tools for cloud platforms predominantly consider short read gene sequences and adopt the Hadoop MapReduce framework for computation. However, serial execution of map and reduce phases is a problem in such systems. Therefore, in this paper, we introduce Burrows-Wheeler Aligner's Smith-Waterman Alignment on Parallel MapReduce (BWASW-PMR) cloud platform for long sequence alignment. The proposed cloud platform adopts a widely accepted and accurate BWA-SW algorithm for long sequence alignment. A custom MapReduce platform is developed to overcome the drawbacks of the Hadoop framework. A parallel execution strategy of the MapReduce phases and optimization of Smith-Waterman algorithm are considered. Performance evaluation results exhibit an average speed-up of 6.7 considering BWASW-PMR compared with the state-of-the-art Bwasw-Cloud. An average reduction of 30% in the map phase makespan is reported across all experiments comparing BWASW-PMR with Bwasw-Cloud. Optimization of Smith-Waterman results in reducing the execution time by 91.8%. The experimental study proves the efficiency of BWASW-PMR for aligning long genomic sequences on cloud platforms.
| S-EPMC4709609 | biostudies-literature
Project description:IntroductionThe complexity of Magnetic Resonance Imaging (MRI) sequences requires expert knowledge about the underlying contrast mechanisms to select from the wide range of available applications and protocols. Automation of this process using machine learning (ML) can support the radiologists and MR technicians by complementing their experience and finding the optimal MRI sequence and protocol for certain applications.MethodsWe define domain-specific languages (DSL) both for describing MRI sequences and for formulating clinical demands for sequence optimization. By using various abstraction levels, we allow different key users exact definitions of MRI sequences and make them more accessible to ML. We use a vendor-independent MRI framework (gammaSTAR) to build sequences that are formulated by the DSL and export them using the generic file format introduced by the Pulseq framework, making it possible to simulate phantom data using the open-source MR simulation framework JEMRIS to build a training database that relates input MRI sequences to output sets of metrics. Utilizing ML techniques, we learn this correspondence to allow efficient optimization of MRI sequences meeting the clinical demands formulated as a starting point.ResultsML methods are capable of capturing the relation of input and simulated output parameters. Evolutionary algorithms show promising results in finding optimal MRI sequences with regards to the training data. Simulated and acquired MRI data show high correspondence to the initial set of requirements.DiscussionThis work has the potential to offer optimal solutions for different clinical scenarios, potentially reducing exam times by preventing suboptimal MRI protocol settings. Future work needs to cover additional DSL layers of higher flexibility as well as an optimization of the underlying MRI simulation process together with an extension of the optimization method.
| S-EPMC10406289 | biostudies-literature
Project description:Widespread establishment of peatlands since the Last Glacial Maximum represents the activation of a globally important carbon sink, but the drivers of peat initiation are unclear. The role of climate in peat initiation is particularly poorly understood. We used a general circulation model to simulate local changes in climate during the initiation of 1,097 peatlands around the world. We find that peat initiation in deglaciated landscapes in both hemispheres was driven primarily by warming growing seasons, likely through enhanced plant productivity, rather than by any increase in effective precipitation. In Western Siberia, which remained ice-free throughout the last glacial period, the initiation of the world's largest peatland complex was globally unique in that it was triggered by an increase in effective precipitation that inhibited soil respiration and allowed wetland plant communities to establish. Peat initiation in the tropics was only weakly related to climate change, and appears to have been driven primarily by nonclimatic mechanisms such as waterlogging due to tectonic subsidence. Our findings shed light on the genesis and Holocene climate space of one of the world's most carbon-dense ecosystem types, with implications for understanding trajectories of ecological change under changing future climates.
| S-EPMC5948962 | biostudies-literature