This paper focuses on the transition of automatic speaker verification systems from time delay neural networks (TDNN) to ResNet-based networks. TDNN-based systems use a statistics pooling layer to aggregate temporal information which is suitable for two-dimensional tensors. Even though ResNet-based models produce three-dimensional tensors, they continue to incorporate the statistics pooling layer. However, the reduction in spatial dimensions in ResNet due to convolution operations, including the temporal axis, raises concerns about temporal information loss and its compatibility with statistics pooling. To address this, we introduce Temporal-Bottleneck ResNet (TB-ResNet), a ResNet-based system that can utilize the nature of statistics pooling more effectively by capturing and retaining frame-level contexts through a temporal bottleneck configuration in its building blocks. The performance of TB-ResNets outperforms the original ResNet counterparts on VoxCeleb1, achieving a significant reduction in both the equal error rate and the minimum detection cost function.

The breakthrough high-throughput measurement of the cis-regulatory activity of millions of randomly generated promoters provides an unprecedented opportunity to systematically decode the cis-regulatory logic that determines the expression values. We developed an end-to-end transformer encoder architecture named Proformer to predict the expression values from DNA sequences. Proformer used a Macaron-like Transformer encoder architecture, where two half-step feed forward (FFN) layers were placed at the beginning and the end of each encoder block, and a separable 1D convolution layer was inserted after the first FFN layer and in front of the multi-head attention layer. The sliding k-mers from one-hot encoded sequences were mapped onto a continuous embedding, combined with the learned positional embedding and strand embedding (forward strand vs. reverse complemented strand) as the sequence input. Moreover, Proformer introduced multiple expression heads with mask filling to prevent the transformer models from collapsing when training on relatively small amount of data. We empirically determined that this design had significantly better performance than the conventional design such as using the global pooling layer as the output layer for the regression task. These analyses support the notion that Proformer provides a novel method of learning and enhances our understanding of how cis-regulatory sequences determine the expression values.

Congenital heart disease affects about 1% of newborns, posing risks like heart failure and mortality. Developing countries often lack resources for diagnosis and treatment. The George B. Moody PhysioNet Challenge 2022 aims to develop systems for detecting murmurs and clinical outcome events using phonocardiogram (PCG) data, offering a cost-effective method for diagnosing cardiac diseases without invasive procedures. We proposed a deep learning model for this task and achieved the 5th rank out of 40 teams in both Track 1 (murmur detection) and Track 2 (clinical outcome prediction). This paper describes our methods and additional experiments. To extract features from the PCG, we employed techniques including Constant Q Transform (CQT) and Mel-scaled spectrogram (Mel-spectrogram) to generate two-dimensional representations in the frequency–time domain. Additionally, we extracted the Peak Interval (PI) feature, which measures the distance between peaks in the PCG data. This feature is useful because the peak intervals should be shorter in PCG recordings with murmurs. We also considered the sequence and mean of PI as additional features. Our proposed system, titled ‘Phonocardiogram-based Heart murmur Detection using Spectrogram and PI features (SpectroHeart),’ employs the Mel-spectrogram and PI features to detect heart murmurs and assess clinical outcomes. We believe that our deep learning-based system has great potential for automatically detecting heart signals from PCG.

The voice assistant market is overgrowing, and mainstream services like Bixby (Samsung), Alexa (Amazon), and Siri (Apple) are quickly being upgraded to support advanced commands. Such capabilities make them lucrative targets for attackers to exploit. Voice spoofing attacks involve recording voice commands of a target victim and simply replaying them through a loudspeaker. The "2019 Automatic Speaker Verification Spoofing And Countermeasures Challenge" (ASVspoof) competition aims to facilitate the design of highly accurate voice spoofing attack detection systems. However, most of the presented models do not take frequency-level modeling into account in their modeling architecture and do not consider model complexity. To design a light-weight system with frequency-level modeling, we propose two systems: 1) Double Depthwise Separable (DDWS) convolution and 2) BC-ResNet with max feature map (MFM) activation (BC-ResMax). We evaluate the accuracy by equal error rate (EER) using the ASVspoof 2019 dataset. Our single models of parallel DDWS, sequential DDWS, and BC-ResMax model achieved spoofing attack detection EER of 2.63%, 2.08% and 2.59% in the LA dataset, and 0.47%, 0.63% and 0.49% in the PA dataset, achieving comparable performance with other top ensemble systems from the competition. Furthermore, parallel DDWS, sequential DDWS, and BC-ResMax used only 45K, 28K and 29K numbers of parameters which are far fewer than existing models.

BACKGROUND: DCLEAR is an R package used for single cell lineage reconstruction. The advances of CRISPR-based gene editing technologies have enabled the prediction of cell lineage trees based on observed edited barcodes from each cell. However, the performance of existing reconstruction methods of cell lineage trees was not accessed until recently. In response to this problem, the Allen Institute hosted the Cell Lineage Reconstruction Dream Challenge in 2020 to crowdsource relevant knowledge from across the world. Our team won sub-challenges 2 and 3 in the challenge competition. RESULTS: The DCLEAR package contained the R codes, which was submitted in response to sub-challenges 2 and 3. Our method consists of two steps: (1) distance matrix estimation and (2) the tree reconstruction from the distance matrix. We proposed two novel methods for distance matrix estimation as outlined in the DCLEAR package. Using our method, we find that two of the more sophisticated distance methods display a substantially improved level of performance compared to the traditional Hamming distance method. DCLEAR is open source and freely available from R CRAN and from under the GNU General Public License, version 3. CONCLUSIONS: DCLEAR is a powerful resource for single cell lineage reconstruction.

The “2019 Automatic Speaker Verification Spoofing And Countermeasures Challenge” (ASVspoof) competition aimed to facilitate the design of highly accurate voice spoofing attack detection systems. the competition did not emphasize model complexity and latency requirements; such constraints are strict and integral in real-world deployment. Hence, most of the top performing solutions from the competition all used an ensemble approach, and combined multiple complex deep learning models to maximize detection accuracy - this kind of approach would sit uneasily with real-world deployment constraints. To design a lightweight system, we combined the notions of skip connection (from ResNet) and max feature map (from Light CNN), and evaluated the accuracy of the system using the ASVspoof 2019 dataset. With an optimized constant Q transform (CQT) feature, our single model achieved a replay attack detection equal error rate (EER) of 0.37% on the evaluation set, surpassing the top ensemble system from the competition that achieved an EER of 0.39%.

Voice assistants are quickly being upgraded to support advanced, security-critical commands such as unlocking devices, checking emails, and making payments. In this paper, we explore the feasibility of using users' text-converted voice command utterances as classification features to help identify users' genuine commands, and detect suspicious commands. To maintain high detection accuracy, our approach starts with a globally trained attack detection model (immediately available for new users), and gradually switches to a user-specific model tailored to the utterance patterns of a target user. To evaluate accuracy, we used a real-world voice assistant dataset consisting of about 34.6 million voice commands collected from 2.6 million users. Our evaluation results show that this approach is capable of achieving about 3.4% equal error rate (EER), detecting 95.7% of attacks when an optimal threshold value is used. As for those who frequently use security-critical (attack-like) commands, we still achieve EER below 5%.

BACKGROUND: The single cell RNA sequencing (scRNA-seq) technique begin a new era by allowing the observation of gene expression at the single cell level. However, there is also a large amount of technical and biological noise. Because of the low number of RNA transcriptomes and the stochastic nature of the gene expression pattern, there is a high chance of missing nonzero entries as zero, which are called dropout events. RESULTS: We develop DrImpute to impute dropout events in scRNA-seq data. We show that DrImpute has significantly better performance on the separation of the dropout zeros from true zeros than existing imputation algorithms. We also demonstrate that DrImpute can significantly improve the performance of existing tools for clustering, visualization and lineage reconstruction of nine published scRNA-seq datasets. CONCLUSIONS: DrImpute can serve as a very useful addition to the currently existing statistical tools for single cell RNA-seq analysis. DrImpute is implemented in R and is available at https://github.com/gongx030/DrImpute .

To identify novel genetic variants associated with complex traits and to shed new insights on underlying biology, in addition to the most popular single SNP-single trait association analysis, it would be useful to explore multiple correlated (intermediate) traits at the gene- or pathway-level by mining existing single GWAS or meta-analyzed GWAS data. For this purpose, we present an adaptive gene-based test and a pathway-based test for association analysis of multiple traits with GWAS summary statistics. The proposed tests are adaptive at both the SNP- and trait-levels; that is, they account for possibly varying association patterns (e.g. signal sparsity levels) across SNPs and traits, thus maintaining high power across a wide range of situations. Furthermore, the proposed methods are general: they can be applied to mixed types of traits, and to Z-statistics or P-values as summary statistics obtained from either a single GWAS or a meta-analysis of multiple GWAS. Our numerical studies with simulated and real data demonstrated the promising performance of the proposed methods. AVAILABILITY AND IMPLEMENTATION: The methods are implemented in R package aSPU, freely and publicly available at: https://cran.r-project.org/web/packages/aSPU/ CONTACT: [email protected] information: Supplementary data are available at Bioinformatics online.

BACKGROUND: Gene- and pathway-based analyses offer a useful alternative and complement to the usual single SNP-based analysis for GWAS. On the other hand, most existing gene- and pathway-based tests are not highly adaptive, and/or require the availability of individual-level genotype and phenotype data. It would be desirable to have highly adaptive tests applicable to summary statistics for single SNPs. This has become increasingly important given the popularity of large-scale meta-analyses of multiple GWASs and the practical availability of either single GWAS or meta-analyzed GWAS summary statistics for single SNPs. RESULTS: We extend two adaptive tests for gene- and pathway-level association with a univariate trait to the case with GWAS summary statistics without individual-level genotype and phenotype data. We use the WTCCC GWAS data to evaluate and compare the proposed methods and several existing methods. We further illustrate their applications to a meta-analyzed dataset to identify genes and pathways associated with blood pressure, demonstrating the potential usefulness of the proposed methods. The methods are implemented in R package aSPU, freely and publicly available. AVAILABILITY AND IMPLEMENTATION: https://cran.r-project.org/web/packages/aSPU/ CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.