There has always been high interest in predicting the solder joint fatigue life in advanced packaging with high accuracy and efficiency. Artificial Intelligence Plus (AI+) is becoming increasingly popular as computational facilities continue to develop. This study will introduce machine learning (a core component of AI). With machine learning, metamodels that approximate the attributes of systems or functions are created to predict the fatigue life of advanced packaging. However, the prediction ability is highly dependent on the size and distribution of the training data. Increasing the amount of training data is the most intuitive approach to improve prediction performance, but this implies a higher computational cost. In this research, the adaptive sampling methods are applied to build the machine learning model with a small dataset sampled from an existing database. The performance of the model will be visualized using predefined criteria. Moreover, ensemble learning can be used to improve the performance of AI models after they have been fully trained.

Myxoid liposarcoma (MLPS) is a rare sarcoma, typically arising in deep soft tissues during the fourth to fifth decades of life. Histologically, MLPS is composed of uniform oval cells within a background of myxoid stroma and chicken-wire capillaries. Genetically, MLPS is characterized by the FUS/EWSR1::DDIT3 fusion gene, which generally results from balanced interchromosomal translocation and is detectable via DDIT3 break-apart fluorescence in situ hybridization (FISH). Here, we report an unusual intra-articular MLPS case, negative for DDIT3 break-apart FISH but positive for EWSR1::DDIT3. An 18-year-old female was referred to our hospital complaining of an intra-articular mass in the right knee joint. Histologically, the tumor was mainly composed of mature adipocytes, brown fat-like cells, and lipoblasts. Nanopore sequencing detected DNA rearrangements between EWSR1 and DDIT3 and clustered complex rearrangements involving multiple chromosomes, suggesting chromoplexy. Methylation classification using random forest, t-distributed stochastic neighbor embedding, and unsupervised hierarchical clustering correctly classified the tumor as MLPS. The copy number was almost flat. The TERT promoter C-124T was also detected. This report highlights, for the first time, the potential value of a fast and low-cost nanopore sequencer for diagnosing sarcomas.

Compressive sensing (CS) is recognized for its adeptness at compressing signals, making it a pivotal technology in the context of sensor data acquisition. With the proliferation of image data in Internet of Things (IoT) systems, CS is expected to reduce the transmission cost of signals captured by various sensor devices. However, the quality of CS-reconstructed signals inevitably degrades as the sampling rate decreases, which poses a challenge in terms of the inference accuracy in downstream computer vision (CV) tasks. This limitation imposes an obstacle to the real-world application of existing CS techniques, especially for reducing transmission costs in sensor-rich environments. In response to this challenge, this paper contributes a CV-oriented adaptive CS framework based on saliency detection to the field of sensing technology that enables sensor systems to intelligently prioritize and transmit the most relevant data. Unlike existing CS techniques, the proposal prioritizes the accuracy of reconstructed images for CV purposes, not only for visual quality. The primary objective of this proposal is to enhance the preservation of information critical for CV tasks while optimizing the utilization of sensor data. This work conducts experiments on various realistic scenario datasets collected by real sensor devices. Experimental results demonstrate superior performance compared to existing CS sampling techniques across the STL10, Intel, and Imagenette datasets for classification and KITTI for object detection. Compared with the baseline uniform sampling technique, the average classification accuracy shows a maximum improvement of 26.23%, 11.69%, and 18.25%, respectively, at specific sampling rates. In addition, even at very low sampling rates, the proposal is demonstrated to be robust in terms of classification and detection as compared to state-of-the-art CS techniques. This ensures essential information for CV tasks is retained, improving the efficacy of sensor-based data acquisition systems.

Estimating dispersion in populations that are extremely rare, hidden, geographically clustered, and hard to access is a well-known challenge. Conventional sampling approaches tend to overestimate the variance, even though it should be genuinely reduced. In this environment, adaptive cluster sampling is considered to be the most efficient sampling technique as it provides generally a lower variance than the other conventional probability sampling designs for the assessment of rare and geographically gathered population parameters like mean, total, variance, etc. The use of auxiliary data is very common to obtain the precise estimates of the estimators by taking advantage of the correlation between the survey variable and the auxiliary data. In this article, we introduced a generalized estimator for estimating the variance of populations that are rare, hidden, geographically clustered and hard-to-reached. The proposed estimator leverages both actual and transformed auxiliary data through adaptive cluster sampling. The expressions of approximate bias and mean square error of the proposed estimator are derived up to the first-order approximation using Taylor expansion. Some special cases are also obtained using the known parameters associated with the auxiliary variable. The proposed class of estimators is compared with available estimators using simulation and real data applications.

Mathematical optimization lies at the core of many science and industry applications. One important issue with many current optimization strategies is a well-known trade-off between the number of function evaluations and the probability to find the global, or at least sufficiently high-quality local optima. In machine learning (ML), and by extension in active learning - for instance for autonomous experimentation - mathematical optimization is often used to find the underlying uncertain surrogate model from which subsequent decisions are made and therefore ML relies on high-quality optima to obtain the most accurate models. Active learning often has the added complexity of missing offline training data; therefore, the training has to be conducted during the data collection which can stall the acquisition if standard methods are used. In this work, we highlight recent efforts to create a high-performance hybrid optimization algorithm (HGDL), combining derivative-free global optimization strategies with local, derivative-based optimization, ultimately yielding an ordered list of unique local optima. Redundancies are avoided by deflating the objective function around earlier encountered optima. HGDL is designed to take full advantage of parallelism by having the most computationally expensive process, the local first and second-order-derivative-based optimizations, run in parallel on separate compute nodes in separate processes. In addition, the algorithm runs asynchronously; as soon as the first solution is found, it can be used while the algorithm continues to find more solutions. We apply the proposed optimization and training strategy to Gaussian-Process-driven stochastic function approximation and active learning.

Bloodstream infection is a major cause of morbidity and death worldwide. Timely and appropriate treatment can reduce mortality among critically ill patients. Current diagnostic methods are too slow to inform precise antibiotic choice, leading to the prescription of empirical antibiotics, which may fail to cover the resistance profile of the pathogen, risking poor patient outcomes. Additionally, overuse of broad-spectrum antibiotics may lead to more resistant organisms, putting further pressure on the dwindling pipeline of antibiotics, and risk transmission of these resistant organisms in the health care environment. Therefore, rapid diagnostics are urgently required to better inform antibiotic choice early in the course of treatment. Sequencing offers great promise in reducing time to microbiological diagnosis; however, the amount of host DNA compared with the pathogen in patient samples presents a significant obstacle. Various host-depletion and bacterial-enrichment strategies have been used in samples, such as saliva, urine, or tissue. However, these methods have yet to be collectively integrated and/or extensively explored for rapid bloodstream infection diagnosis. Although most of these workflows possess individual strengths, their lack of analytical/clinical sensitivity and/or comprehensiveness demands additional improvements or synergistic application. This review provides a distinctive classification system for various methods based on their working principles to guide future research, and discusses their strengths and limitations and explores potential avenues for improvement to assist the reader in workflow selection.

UNASSIGNED: Shotgun metagenomics has previously proven effective in the investigation of foodborne outbreaks by providing rapid and comprehensive insights into the microbial contaminant. However, culture enrichment of the sample has remained a prerequisite, despite the potential impact on pathogen detection resulting from the growth competition. To circumvent the need for culture enrichment, we explored the use of adaptive sampling using various databases for a targeted nanopore sequencing, compared to shotgun metagenomics alone.
UNASSIGNED: The adaptive sampling method was first tested on DNA of mashed potatoes mixed with DNA of a Staphylococcus aureus strain previously associated with a foodborne outbreak. The selective sequencing was used to either deplete the potato sequencing reads or enrich for the pathogen sequencing reads, and compared to a shotgun sequencing. Then, living S. aureus were spiked at 105 CFU into 25 g of mashed potatoes. Three DNA extraction kits were tested, in combination with enrichment using adaptive sampling, following whole genome amplification. After data analysis, the possibility to characterize the contaminant with the different sequencing and extraction methods, without culture enrichment, was assessed.
UNASSIGNED: Overall, the adaptive sampling outperformed the shotgun sequencing. While the use of a host removal DNA extraction kit and targeted sequencing using a database of foodborne pathogens allowed rapid detection of the pathogen, the most complete characterization was achieved when using solely a database of S. aureus combined with a conventional DNA extraction kit, enabling accurate placement of the strain on a phylogenetic tree alongside outbreak cases.
UNASSIGNED: This method shows great potential for strain-level analysis of foodborne outbreaks without the need for culture enrichment, thereby enabling faster investigations and facilitating precise pathogen characterization. The integration of adaptive sampling with metagenomics presents a valuable strategy for more efficient and targeted analysis of microbial communities in foodborne outbreaks, contributing to improved food safety and public health.

Bacterial plasmids play a major role in the spread of antibiotic resistance genes. However, their characterization via DNA sequencing suffers from the low abundance of plasmid DNA in those samples. Although sample preparation methods can enrich the proportion of plasmid DNA before sequencing, these methods are expensive and laborious, and they might introduce a bias by enriching only for specific plasmid DNA sequences. Nanopore adaptive sampling could overcome these issues by rejecting uninteresting DNA molecules during the sequencing process. In this study, we assess the application of adaptive sampling for the enrichment of low-abundant plasmids in known bacterial isolates using two different adaptive sampling tools. We show that a significant enrichment can be achieved even on expired flow cells. By applying adaptive sampling, we also improve the quality of de novo plasmid assemblies and reduce the sequencing time. However, our experiments also highlight issues with adaptive sampling if target and non-target sequences span similar regions.
OBJECTIVE: Antimicrobial resistance causes millions of deaths every year. Mobile genetic elements like bacterial plasmids are key drivers for the dissemination of antimicrobial resistance genes. This makes the characterization of plasmids via DNA sequencing an important tool for clinical microbiologists. Since plasmids are often underrepresented in bacterial samples, plasmid sequencing can be challenging and laborious. To accelerate the sequencing process, we evaluate nanopore adaptive sampling as an in silico method for the enrichment of low-abundant plasmids. Our results show the potential of this cost-efficient method for future plasmid research but also indicate issues that arise from using reference sequences.

暂无摘要。

Nanopore sequencers can enrich or deplete the targeted DNA molecules in a library by reversing the voltage across individual nanopores. However, it requires substantial computational resources to achieve rapid operations in parallel at read-time sequencing. We present a deep learning framework, NanoDeep, to overcome these limitations by incorporating convolutional neural network and squeeze and excitation. We first showed that the raw squiggle derived from native DNA sequences determines the origin of microbial and human genomes. Then, we demonstrated that NanoDeep successfully classified bacterial reads from the pooled library with human sequence and showed enrichment for bacterial sequence compared with routine nanopore sequencing setting. Further, we showed that NanoDeep improves the sequencing efficiency and preserves the fidelity of bacterial genomes in the mock sample. In addition, NanoDeep performs well in the enrichment of metagenome sequences of gut samples, showing its potential applications in the enrichment of unknown microbiota. Our toolkit is available at https://github.com/lysovosyl/NanoDeep.