Plastic waste has caused a global environmental crisis. Biocatalytic depolymerization mediated by enzymes has emerged as an efficient and sustainable alternative for plastic treatment and recycling. However, it is challenging and time-consuming to discover novel plastic-degrading enzymes using conventional cultivation-based or omics methods. There is a growing interest in developing effective computational methods to identify new enzymes with desirable plastic degradation functionalities by exploring the ever-increasing databases of protein sequences. In this study, we designed an innovative machine learning-based framework, named PEZy-Miner, to mine for enzymes with high potential in degrading plastics of interest. Two datasets integrating information from experimentally verified enzymes and homologs with unknown plastic-degrading activity were created respectively, covering eleven types of plastic substrates. Protein language models and binary classification models were developed to predict enzymatic degradation of plastics along with confidence and uncertainty estimation. PEZy-Miner exhibited high prediction accuracy and stability when validated on experimentally verified enzymes. Furthermore, by masking the experimentally verified enzymes and blending them into homolog dataset, PEZy-Miner effectively concentrated the experimentally verified entries by 14∼30 times while shortlisting promising plastic-degrading enzyme candidates. We applied PEZy-Miner to 0.1 million putative sequences, out of which 27 new sequences were identified with high confidence. This study provided a new computational tool for mining and recommending promising new plastic-degrading enzymes.
Zhenrui Yue, Huimin Zeng, Yang Zhang, Lanyu Shang, Dong Wang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
Despite recent progress in improving the performance of misinformation detection systems, classifying misinformation in an unseen domain remains an elusive challenge. To address this issue, a common approach is to introduce a domain critic and encourage domain-invariant input features. However, early misinformation often demonstrates both conditional and label shifts against existing misinformation data (e.g., class imbalance in COVID-19 datasets), rendering such methods less effective for detecting early misinformation. In this paper, we propose contrastive adaptation network for early misinformation detection (CANMD). Specifically, we leverage pseudo labeling to generate high-confidence target examples for joint training with source data. We additionally design a label correction component to estimate and correct the label shifts (i.e., class priors) between the source and target domains. Moreover, a contrastive adaptation loss is integrated in the objective function to reduce the intra-class discrepancy and enlarge the inter-class discrepancy. As such, the adapted model learns corrected class priors and an invariant conditional distribution across both domains for improved estimation of the target data distribution. To demonstrate the effectiveness of the proposed CANMD, we study the case of COVID-19 early misinformation detection and perform extensive experiments using multiple real-world datasets. The results suggest that CANMD can effectively adapt misinformation detection systems to the unseen COVID-19 target domain with significant improvements compared to the state-of-the-art baselines.
1 September 2021 in Information Processing & Management
This article overviews the state of the art, research challenges, and future directions in our vision: integrating social explanation into explainable artificial intelligence (XAI) to combat misinformation. In our context, “social explanation” is an explanatory approach that reveals the social aspect of misinformation by analyzing sociocontextual cues, such as user attributes, user engagement metrics, diffusion patterns, and user comments. Our vision is motivated by the research gap in the existing XAI that tends to overlook the broader social context in which misinformation spreads. In this article, we first define social explanation, demonstrating it through examples, enabling technologies, and real-world applications. We then outline the unique benefits social explanation brings to the fight against misinformation and discuss the challenges that make our vision complex. The significance of this article lies in introducing the “social explanation” concept in XAI, which has been underexplored in the previous literature. Also, we demonstrate how social explanations can be effectively employed to tackle misinformation and promote collaboration across diverse fields by drawing upon interdisciplinary techniques spanning from computer science, social computing, human–computer interaction, to psychology. We hope that this article will advance progress in the field of XAI and contribute to the ongoing efforts to counter misinformation.
Zhenrui Yue, Huimin Zeng, Yimeng Lu, Lanyu Shang, Yang Zhang, Dong Wang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.