Search

Abstract Tandem repeats are frequent across the human genome, and variation in repeat length has been linked to a variety of traits. Recent improvements in long read sequencing technologies have the potential to greatly improve tandem repeat analysis, especially for long or complex repeats. Here, we introduce LongTR, which accurately genotypes tandem repeats from high-fidelity long reads available from both PacBio and Oxford Nanopore Technologies. LongTR is freely available at https://github.com/gymrek-lab/longtr and https://zenodo.org/doi/10.5281/zenodo.11403979 .

Abstract Tandem repeats (TRs) represent one of the largest sources of genetic variation in humans and are implicated in a range of phenotypes. Here we present a deep characterization of TR variation based on high coverage whole genome sequencing from 3550 diverse individuals from the 1000 Genomes Project and H3Africa cohorts. We develop a method, EnsembleTR, to integrate genotypes from four separate methods resulting in high-quality genotypes at more than 1.7 million TR loci. Our catalog reveals novel sequence features influencing TR heterozygosity, identifies population-specific trinucleotide expansions, and finds hundreds of novel eQTL signals. Finally, we generate a phased haplotype panel which can be used to impute most TRs from nearby single nucleotide polymorphisms (SNPs) with high accuracy. Overall, the TR genotypes and reference haplotype panel generated here will serve as valuable resources for future genome-wide and population-wide studies of TRs and their role in human phenotypes.

Abstract Continuous, comfortable, convenient (C3), and accurate blood pressure (BP) measurement and monitoring are needed for early diagnosis of various cardiovascular diseases. To supplement the limited C3 BP measurement of existing cuff-based BP technologies, though they may achieve reliable accuracy, cuffless BP measurement technologies, such as pulse transit/arrival time, pulse wave analysis, and image processing, have been studied to obtain C3 BP measurement. One of the recent cuffless BP measurement technologies, innovative machine-learning and artificial intelligence-based technologies that can estimate BP by extracting BP-related features from photoplethysmography (PPG)-based waveforms have attracted interdisciplinary attention of the medical and computer scientists owing to their handiness and effectiveness for both C3 and accurate, i.e., C3A, BP measurement. However, C3A BP measurement remains still unattainable because the accuracy of the existing PPG-based BP methods was not sufficiently justified for subject-independent and highly varying BP, which is a typical case in practice. To circumvent this issue, a novel convolutional neural network(CNN)- and calibration-based model (PPG2BP-Net) was designed by using a comparative paired one-dimensional CNN structure to estimate highly varying intrasubject BP. To this end, approximately $$70\%$$ 70 % , $$20\%$$ 20 % , and $$10\%$$ 10 % of 4185 cleaned, independent subjects from 25,779 surgical cases were used for training, validating, and testing the proposed PPG2BP-Net, respectively and exclusively (i.e., subject-independent modelling). For quantifying the intrasubject BP variation from an initial calibration BP, a novel ‘standard deviation of subject-calibration centring (SDS)’ metric is proposed wherein high SDS represents high intrasubject BP variation from the calibration BP and vice versa. PPG2BP-Net achieved accurately estimated systolic and diastolic BP values despite high intrasubject variability. In 629-subject data acquired after 20 minutes following the A-line (arterial line) insertion, low error mean and standard deviation of $$0.209\pm 7.509$$ 0.209 ± 7.509 and $$0.150\pm 4.549\;\textrm{mmHg}$$ 0.150 ± 4.549 mmHg for highly varying A-line systolic and diastolic BP values, respectively, where their SDSs are 15.375 and 8.745. This study moves one step forward in developing the C3A cuffless BP estimation devices that enable the push and agile pull services.

As the demand for multi-chip products with high capacity and small size increases, semiconductor packaging facilities have been faced with complicated constraints such as re-entrant flows, sequence dependent setups, and alternative routes, which leads to difficulties in scheduling semiconductor manufacturing operations. Furthermore, due to the frequent variations in the relative importance between objectives as well as the variabilities in initial setup status, available machines, and production requirements, practitioners are obliged to obtain a schedule within a short amount of computation time. In this paper, we propose a novel two-phase framework that aims to quickly produce a schedule of semiconductor packaging facilities by using case-based reasoning for minimizing the weighted sum of machine loss time and waiting time of jobs. Specifically, in the case generation phase, a case database is constructed by solving case scheduling problems using an existing solver. The case reasoning phase is responsible for repairing operation type sequences in the cases to produce a schedule for an unseen scheduling problem whose production requirements, available machines, initial setup status, and weight between performance measures are different from those of cases. The extensive experimental results demonstrated that the proposed approach requires a short computation time similar to the rule-based methods while maintaining the quality of the schedules comparable to that of the existing metaheuristics.

Abstract Ammonia (NH3) is an important, albeit sticky, precursor for producing secondary inorganic aerosols (SIA), especially in the form of ammonium nitrate (NH4NO3) and ammonium sulfate ((NH4)2SO4). To reduce SIAs, many researchers have attempted to measure the concentration of ambient NH3 using real-time or passive methods. However, NH3 is a highly sticky gas and is therefore difficult to measure using real-time methods without incurring losses during measurement. In this study, four different tubing materials, semi seamless tubes, perfluoroalkoxy (PFA), polytetrafluoroethylene (PTFE), and polyvinylidene fluoride (PVDF), were used to ascertain the adsorption of NH3 in inlets using real-time instruments. Without heating sample tubes and at 0% relative humidity (RH), this study shows that PTFE had the least adsorption(i.e., 0% at 1 and 2m of sample tube), and semi-seamless tubes had the highest adsorption (i.e., 27.5% at 1 m of sample tube). To calculate the adsorption of NH3 under ambient conditions, at various inlet lengths, the RH of NH3 was varied from 20% to 80%, which showed that shorter inlets and higher RH lower NH3 adsorption at inlets (i.e., 1.74 ppb m−1 at 80% RH and 7.48 ppb m−1 at 20% RH). Additionally, inlet heating was effective in reducing the adsorption of NH3 as the RH decreased. Applying the inlet system (i.e., 2 m of PTFE tube with heating) showed excellent correlation (slope: 0.995 and coefficient: 0.992) between two different real-time measurements while measuring ambient air.

Variable number tandem repeats (VNTRs) are implicated in human diseases yet have been difficult to analyse computationally. Here, the authors describe a neural network method, adVNTR-NN, that allows rapid and accurate genotyping of VNTRs from large whole genome sequencing datasets.

Summary: The human genome contains more than one million tandem repeats (TRs), DNA sequences containing multiple approximate copies of a motif repeated contiguously. TRs account for significant genetic variation, with 50 + diseases attributed to changes in motif number. A few diseases have been to be caused by small indels in variable number tandem repeats (VNTRs) including poly-cystic kidney disease type 1 (MCKD1) and monogenic type 1 diabetes. However, small indels in VNTRs are largely unexplored mainly due to the long and complex structure of VNTRs with multiple motifs. We developed a method, code-adVNTR, that utilizes multi-motif hidden Markov models to detect both, motif count variation and small indels, within VNTRs. In simulated data, code-adVNTR outperformed GATK-HaplotypeCaller in calling small indels within large VNTRs. We used code-adVNTR to characterize coding VNTRs in the 1000 genomes data identifying many population-specific variants, and to reliably call MUC1 mutations for MCKD1.

Parallel machine scheduling with sequence-dependent family setups has attracted much attention from academia and industry due to its practical applications. In a real-world manufacturing system, however, solving the scheduling problem becomes challenging since it is required to address urgent and frequent changes in demand and due-dates of products. To minimize the total tardiness of the scheduling problem, we propose a deep reinforcement learning (RL) based scheduling framework in which trained neural networks (NNs) are able to solve unseen scheduling problems without re-training even when such changes occur. Specifically, we propose state and action representations whose dimensions are independent of production requirements and due-dates of jobs while accommodating family setups. At the same time, an NN architecture with parameter sharing was utilized to improve the training efficiency. Extensive experiments demonstrate that the proposed method outperforms the recent metaheuristics, rule-based, and other RL-based methods in terms of total tardiness. Moreover, the computation time for obtaining a schedule by our framework is shorter than those of the metaheuristics and other RL-based methods.

Human motion similarity is practiced in many fields, including action recognition, anomaly detection, and human performance evaluation. While many computer vision tasks have benefited from deep learning, measuring motion similarity has attracted less attention, particularly due to the lack of large datasets. To address this problem, we introduce two datasets: a synthetic motion dataset for model training and a dataset containing human annotations of real-world video clip pairs for motion similarity evaluation. Furthermore, in order to compute the motion similarity from these datasets, we propose a deep learning model that produces motion embeddings suitable for measuring the similarity between different motions of each human body part. The network is trained with the proposed motion variation loss to robustly distinguish even subtly different motions. The proposed approach outperforms the other baselines considered in terms of correlations between motion similarity predictions and human annotations while being suitable for real-time action analysis. Both datasets and codes are released to the public.

For successful artificial music composition, chords and melody must be aligned well. Yet, chord conditioned melody generation remains a challenging task mainly due to its multimodality. While few studies have focused on this task, they face difficulties in generating dynamic rhythm patterns aligned appropriately with a given chord progression. In this paper, we propose a chord conditioned melody Transformer, a K-POP melody generation model, which separately produces rhythm and pitch conditioned on a chord progression. The model is trained in two phases. A rhythm decoder (RD) is trained first, and subsequently a pitch decoder is trained by utilizing the pre-trained RD. Experimental results show that reusing RD at the pitch decoding stage and training with pitch varied rhythm data improve the performance. It was also observed that the samples produced by the model well reflected the key characteristics of dataset in terms of both pitch and rhythm related features, including chord tone ratio and rhythm distribution. Qualitative analysis reveals the model’s capability of generating various melodies in accordance with a given chord progression, as well as the presence of repetitions and variations within the generated melodies. With subjective human listening test, we come to a conclusion that the model was able to successfully produce new melodies that sound pleasant in terms of both rhythm and pitch (Source code available at https://github.com/ckycky3/CMT-pytorch).

One of the fundamental technologies for unmanned combat aerial vehicles and combat simulators is behavior optimization, which finds a behavior that maximizes the probability of winning a battle. With the advent of military science, combat logs became available, allowing machine learning algorithms to be used for the behavior optimization. Due to implicit attributes such as the experience of an operator that are not explicitly presented in log data, existing methods for behavior optimization have limitations in performance improvement. Furthermore, specific behaviors occur with low frequency, resulting in a dataset with imbalanced and empty values. Therefore, we apply a matrix factorization (MF) method, which is one of latent factor models and known for sophisticated imputation of empty values, to the behavior optimization problem of unmanned combat aerial vehicles. A situation-behavior matrix, whose elements are ratings indicating the optimality of behaviors in situations, is defined to implement the MF based method. Experiments for performance comparison were conducted on combat logs, in which the proposed method yielded satisfactory results.

As unmanned aerial vehicles have become popular, the number of accidents caused by an operator’s inattention have increased. To prevent such accidents, the operator should maintain an attention status. However, limited research has been conducted on the brain-computer interface (BCI)-based system with an alerting module for the operator’s attention recovery of unmanned aerial vehicles. Therefore, we introduce a detection and alerting system that prevents an unmanned aerial vehicle operator from falling into inattention status by using the operator’s electroencephalogram signal. The proposed system consists of the following three components: a signal processing module, which collects and preprocesses an electroencephalogram signal of an operator, an inattention detection module, which determines whether an inattention status occurred based on the preprocessed signal, and, lastly, an alert providing module that presents stimulus to an operator when inattention is detected. As a result of evaluating the performance with a real-world dataset, it was shown that the proposed system successfully contributed to the recovery of operator attention in the evaluating dataset, although statistical significance could not be established due to the small number of subjects.

This study documented the current status of wood pallet repair in the United States by identifying the types of processing and equipment usage in repair operations from an automation perspective. The wood pallet repair firms included in the study received an average of approximately 1.28 million cores (i.e., used pallets) for recovery in 2012. A majority of the cores received were stringer-style pallets. The most common pallet size received and repaired was 48 x 40 inch. The most commonly used stringer repair method was the application of companion stringers. It was found that most firms utilized high levels of manual labor, with limited machinery support. The board trimming and pallet sorting/stacking processes had the highest level of automation, while the inspection, nailing, and painting processes utilized manual labor.

The task of sentence completion, which aims to infer the missing text of a given sentence, was carried out to assess the reading comprehension level of machines as well as humans. In this work, we conducted a comprehensive study of various approaches for the sentence completion based on neural language models, which have been advanced in recent years. First, we revisited the recurrent neural network language model (RNN LM), achieving highly competitive results with an appropriate network structure and hyper-parameters. This paper presents a bidirectional version of RNN LM, which surpassed the previous best results on Microsoft Research (MSR) Sentence Completion Challenge and the Scholastic Aptitude Test (SAT) sentence completion questions. In parallel with directly applying RNN LM to sentence completion, we also employed a supervised learning framework that fine-tunes a large pre-trained transformer-based LM with a few sentence-completion examples. By fine-tuning a pre-trained BERT model, this work established state-of-the-art results on the MSR and SAT sets. Furthermore, we performed similar experimentation on newly collected cloze-style questions in the Korean language. The experimental results reveal that simply applying the multilingual BERT models for the Korean dataset was not satisfactory, which leaves room for further research.

Due to the recent explosive growth of location-aware services based on mobile devices, predicting the next places of a user is of increasing importance to enable proactive information services. In this paper, we introduce a data-driven framework that aims to predict the user’s next places using his/her past visiting patterns analyzed from mobile device logs. Specifically, the notion of the spatiotemporal-periodic (STP) pattern is proposed to capture the visits with spatiotemporal periodicity by focusing on a detail level of location for each individual. Subsequently, we present algorithms that extract the STP patterns from a user’s past visiting behaviors and predict the next places based on the patterns. The experiment results obtained by using a real-world dataset show that the proposed methods are more effective in predicting the user’s next places than the previous approaches considered in most cases.