Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling. In these studies, models were pre-trained with a substantial amount of unlabeled data, and the representations were transferred to various downstream tasks. Most pre-training methods solely rely on language modeling and often exhibit limited performance. In this paper, we introduce a novel pre-training scheme called PLUS , which stands for P rotein sequence representations L earned U sing S tructural information. PLUS consists of masked language modeling and a complementary protein-specific pre-training task, namely same-family prediction. PLUS can be used to pre-train various model architectures. In this work, we use PLUS to pre-train a bidirectional recurrent neural network and refer to the resulting model as PLUS-RNN. Our experiment results demonstrate that PLUS-RNN outperforms other models of similar size solely pre-trained with the language modeling in six out of seven widely used protein biology tasks. Furthermore, we present the results from our qualitative interpretation analyses to illustrate the strengths of PLUS-RNN. PLUS provides a novel way to exploit evolutionary relationships among unlabeled proteins and is broadly applicable across a variety of protein biology tasks. We expect that the gap between the numbers of unlabeled and labeled proteins will continue to grow exponentially, and the proposed pre-training method will play a larger role. All the data and codes used in this study are available at https://github.com/mswzeus/PLUS .
22 November 2023 in IEEE Transactions on Knowledge and Data Engineering
In addition to its success in representation learning, contrastive learning is effective in image anomaly detection. Although contrastive learning depends significantly on data augmentation methods, time-series data augmentation for time-series anomaly detection is not investigated sufficiently. Additionally, although time-series data share a temporal context, the existing contrastive loss contrasts temporally related samples, in which deteriorated anomaly detection performance is observed on time-series data. Herein, we propose contrastive multivariate time-series anomaly detection (CTAD), a multivariate time-series anomaly detection framework that addresses these challenges by incorporating a one-class learning scheme into the contrastive loss based on meticulously designed time-series data augmentations. Specifically, we propose seven types of general time-series data augmentations to be applied variable- and point- wise, and provide guidance on data augmentation methods for contrastive time-series anomaly detection. The superiority of the one-class contrastive loss and the appropriate selection of time-series data augmentation allow CTAD to achieve outstanding performance in multiple datasets, even using a simple long short-term memory network. Furthermore, CTAD is robust to noise as it trains a noise-invariant network. This enables up to 47× faster and 20× more memory-efficient anomaly detection performance compared with existing methods while affording robustness, which are essential considerations in real-world applications.
A molecule is a complex of heterogeneous components, and the spatial arrangements of these components determine the whole molecular properties and characteristics. With the advent of deep learning in computational chemistry, several studies have focused on how to predict molecular properties based on molecular configurations. MA message-passing neural network provides an effective framework for capturing molecular geometric features with the perspective of a molecule as a graph. However, most of these studies assumed that all heterogeneous molecular features, such as atomic charge, bond length, or other geometric features, always contribute equivalently to the target prediction, regardless of the task type. In this study, we propose a dual-branched neural network for molecular property prediction based on both the message-passing framework and standard multilayer perceptron neural networks. Our model learns heterogeneous molecular features with different scales, which are trained flexibly according to each prediction target. In addition, we introduce a discrete branch to learn single-atom features without local aggregation, apart from message-passing steps. We verify that this novel structure can improve the model performance. The proposed model outperforms other recent models with sparser representations. Our experimental results indicate that, in the chemical property prediction tasks, the diverse chemical nature of targets should be carefully considered for both model performance and generalizability. Finally, we provide the intuitive analysis between the experimental results and the chemical meaning of the target.
Heat shock proteins (HSPs) play a pivotal role as molecular chaperones against unfavorable conditions. Although HSPs are of great importance, their computational identification remains a significant challenge. Previous studies have two major limitations. First, they relied heavily on amino acid composition features, which inevitably limited their prediction performance. Second, their prediction performance was overestimated because of the independent two-stage evaluations and train-test data redundancy. To overcome these limitations, we introduce two novel deep learning algorithms: (1) time-efficient DeepHSP and (2) high-performance DeeperHSP. We propose a convolutional neural network (CNN)-based DeepHSP that classifies both non-HSPs and six HSP families simultaneously. It outperforms state-of-the-art algorithms, despite taking 14–15 times less time for both training and inference. We further improve the performance of DeepHSP by taking advantage of protein transfer learning. While DeepHSP is trained on raw protein sequences, DeeperHSP is trained on top of pre-trained protein representations. Therefore, DeeperHSP remarkably outperforms state-of-the-art algorithms increasing F1 scores in both cross-validation and independent test experiments by 20% and 10%, respectively. We envision that the proposed algorithms can provide a proteome-wide prediction of HSPs and help in various downstream analyses for pathology and clinical research.
In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks. However, many existing models fail to fully consider the geometric information on molecular structures, resulting in less intuitive representations. Moreover, the widely used message passing mechanism is limited to providing the interpretation of experimental results from a chemical perspective. To address these challenges, we introduce a novel transformer-based framework for molecular representation learning, named the geometry-aware transformer (GeoT). The GeoT learns molecular graph structures through attention-based mechanisms specifically designed to offer reliable interpretability as well as molecular property prediction. Consequently, the GeoT can generate attention maps of the interatomic relationships associated with training objectives. In addition, the GeoT demonstrates performance comparable to that of MPNN-based models while achieving reduced computational complexity. Our comprehensive experiments, including an empirical simulation, reveal that the GeoT effectively learns chemical insights into molecular structures, bridging the gap between artificial intelligence and molecular sciences.
Personality detection plays a pivotal role in social interactions, machine learning (ML), and natural language processing (NLP). Its goal is to discern an individual’s traits from their behavior and expressions. The prevalence of text-based communication has sparked interest in inferring personality from written content. However, challenges persist in accurately interpreting traits like the Big-Five or Myers-Briggs Type Indicator. These challenges stem from the reliance on self-reported surveys for labeling, which introduces uncertainties as individual assessments may not consistently align with their actual personality. In this paper, we propose novel curriculum strategies that employ class-based term frequency-inverse document frequency (c-TF-IDF) to enhance personality detection performance. By leveraging a curriculum approach that mirrors human learning progression, starting from simpler tasks and moving toward more complex ones, these strategies aim to train models on progressively challenging scenarios. Our experimental results demonstrate that these proposed curriculum-based strategies improve the accuracy of personality detection compared to previously suggested methods. This study contributes to advance understanding of text-based cues for personality inference. It has the potential to enrich various fields, including human-computer interaction, personalized recommendations, and targeted marketing.