Transactions on Intelligent Computing Systems - Articles

Watanabe, K., Amoah, C., Lemaire, O., Beaumont, O.

The admixture model is widely applied to estimate and interpret population structure among individuals. Here we consider a “standard admixture” model that assumes the admixed populations are unrelated and also a generalized model, where the admixed populations themselves are related via coancestry (or covariance) of allele frequencies. The generalized model yields a potentially more realistic and substantially more flexible model that we call “super admixture”. This super admixture model provides a one-to-one mapping in terms of probability moments with the kinship model, the latter of which is a general model of genome-wide relatedness and structure based on identity-by-descent. We introduce a method to estimate the super admixture model that is based on method of moments, does not rely on likelihoods, is computationally efficient, and scales to massive sample sizes. We apply the method to several human data sets and show that the admixed populations are indeed substantially related, implying the proposed method captures a new and important component of evolutionary history and structure in the admixture model. We show that the fitted super admixture model estimates relatedness between all pairs of individuals at a resolution similar to the kinship model. The super admixture model therefore provides a tractable, forward-generating probabilistic model of complex structure and relatedness that should be useful in a variety of scenarios. Updated in version 2 to clarify the scope of the analysis.

Dąbrowski, E., Kapoor, R.

Intrinsically disordered proteins (IDPs) are proteins that contain intrinsically disordered regions (IDRs), which lack stable three-dimensional structures under physiological conditions. These regions are known to play crucial roles in many biological processes. While IDRs can be predicted from their amino acid sequences, and several accurate IDR prediction programs have been developed, such programs often require substantial computational resources, including long execution times, large databases for homology searches, and advanced computer architectures. Since DNA sequence data continues to grow rapidly, particularly at a genomic scale, there is an increasing need for fast and accurate IDR prediction programs that demand fewer computational resources. In this study, we developed DARUMA (Disorder order clAssifier by Rapid and User-friendly MAchine), an IDR prediction program designed for speed and ease of use. DARUMA uses a one-dimensional convolutional neural network (1D-CNN) that processes the physicochemical properties of amino acid residues instead of relying on sequence profiles. DARUMA employs a simple neural network that predicts IDRs using the output of 1D-CNN as input features. To ensure easy installation on users’ systems, DARUMA was written entirely in Python using standard and NumPy libraries.

Chen, D., Storey, J.

The admixture model is widely applied to estimate and interpret population structure among individuals. Here we consider a “standard admixture” model that assumes the admixed populations are unrelated and also a generalized model, where the admixed populations themselves are related via coancestry (or covariance) of allele frequencies. The generalized model yields a potentially more realistic and substantially more flexible model that we call “super admixture”. This super admixture model provides a one-to-one mapping in terms of probability moments with the kinship model, the latter of which is a general model of genome-wide relatedness and structure based on identity-by-descent. We introduce a method to estimate the super admixture model that is based on method of moments, does not rely on likelihoods, is computationally efficient, and scales to massive sample sizes. We apply the method to several human data sets and show that the admixed populations are indeed substantially related, implying the proposed method captures a new and important component of evolutionary history and structure in the admixture model. We show that the fitted super admixture model estimates relatedness between all pairs of individuals at a resolution similar to the kinship model. The super admixture model therefore provides a tractable, forward-generating probabilistic model of complex structure and relatedness that should be useful in a variety of scenarios.

Shorten, C., Khoshgoftaar, T., Furht, B.

Natural Language Processing (NLP) is one of the most captivating applications of Deep Learning. In this survey, we consider how the Data Augmentation training strategy can aid in its development. We begin with the major motifs of Data Augmentation summarized into strengthening local decision boundaries, brute force training, causality and counterfactual examples, and the distinction between meaning and form. We follow these motifs with a concrete list of augmentation frameworks that have been developed for text data. Deep Learning generally struggles with the measurement of generalization and characterization of overfitting. We highlight studies that cover how augmentations can construct test sets for generalization. NLP is at an early stage in applying Data Augmentation compared to Computer Vision. We highlight the key differences and promising ideas that have yet to be tested in NLP. For the sake of practical implementation, we describe tools that facilitate Data Augmentation such as the use of consistency regularization, controllers, and offline and online augmentation pipelines, to preview a few. Finally, we discuss interesting topics around Data Augmentation in NLP such as task-specific augmentations, the use of prior knowledge in self-supervised learning versus Data Augmentation, intersections with transfer and multi-task learning, and ideas for AI-GAs (AI-Generating Algorithms). We hope this paper inspires further research interest in Text Data Augmentation.

Petrov, A., Rao, R., Rao, A., Olsen, O., Rao, R., Olsen, D.

Data-driven machine learning (ML) has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. However, without access to sufficient data, ML will be prevented from reaching its full potential and, ultimately, from making the transition from research to clinical practice. This paper considers key factors contributing to this issue, explores how federated learning (FL) may provide a solution for the future of digital health and highlights the challenges and considerations that need to be addressed.

Shorten, C., Khoshgoftaar, T., Furht, B.

Natural Language Processing (NLP) is one of the most captivating applications of Deep Learning. In this survey, we consider how the Data Augmentation training strategy can aid in its development. We begin with the major motifs of Data Augmentation summarized into strengthening local decision boundaries, brute force training, causality and counterfactual examples, and the distinction between meaning and form. We follow these motifs with a concrete list of augmentation frameworks that have been developed for text data. Deep Learning generally struggles with the measurement of generalization and characterization of overfitting. We highlight studies that cover how augmentations can construct test sets for generalization. NLP is at an early stage in applying Data Augmentation compared to Computer Vision. We highlight the key differences and promising ideas that have yet to be tested in NLP. For the sake of practical implementation, we describe tools that facilitate Data Augmentation such as the use of consistency regularization, controllers, and offline and online augmentation pipelines, to preview a few. Finally, we discuss interesting topics around Data Augmentation in NLP such as task-specific augmentations, the use of prior knowledge in self-supervised learning versus Data Augmentation, intersections with transfer and multi-task learning, and ideas for AI-GAs (AI-Generating Algorithms). We hope this paper inspires further research interest in Text Data Augmentation.