Comparison of biomedical relationship extraction methods and models for knowledge graph creation
University of Manchester（曼彻斯特大学）；Bayer Pharmaceuticals R&D（拜耳制药研发）
Nikola Milosevic, Wolfgang Thielemann
备注：
Paper submitted to Journal of Semantic Web
发表信息：
Nikola Milosevic, Wolfgang Thielemann, Comparison of biomedical relationship extraction methods and models for knowledge graph creation, Journal of Web Semantics, 2022, 100756, ISSN 1570-8268,
Biomedical research is growing at such an exponential pace that scientists, researchers, and practitioners are no more able to cope with the amount of published literature in the domain. The knowledge presented in the literature needs to be systematized in such a way that claims and hypotheses can be easily found, accessed, and validated. Knowledge graphs can provide such a framework for semantic knowledge representation from literature. However, in order to build a knowledge graph, it is necessary to extract knowledge as relationships between biomedical entities and normalize both entities and relationship types. In this paper, we present and compare few rule-based and machine learning-based (Naive Bayes, Random Forests as examples of traditional machine learning methods and DistilBERT, PubMedBERT, T5 and SciFive-based models as examples of modern deep learning transformers) methods for scalable relationship extraction from biomedical literature, and for the integration into the knowledge graphs. We examine how resilient are these various methods to unbalanced and fairly small datasets. Our experiments show that transformer-based models handle well both small (due to pre-training on a large dataset) and unbalanced datasets. The best performing model was the PubMedBERT-based model fine-tuned on balanced data, with a reported F1-score of 0.92. DistilBERT-based model followed with F1-score of 0.89, performing faster and with lower resource requirements. BERT-based models performed better then T5-based generative models.
Xi’an Jiaotong University（西安交通大学）；The First Affiliated Hospital of Xi’an Jiaotong University（西安交通大学第一附属医院）
Constructing large-scaled medical knowledge graphs can significantly boost healthcare applications for medical surveillance, bring much attention from recent research. An essential step in constructing large-scale MKG is extracting information from medical reports. Recently, information extraction techniques have been proposed and show promising performance in biomedical information extraction. However, these methods only consider limited types of entity and relation due to the noisy biomedical text data with complex entity correlations. Thus, they fail to provide enough information for constr…
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；University of California, Los Angeles（加州大学洛杉矶分校）
Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. One of the main challenges is to identify nested structured events that are associated with non-indicative trigger words. We propose to incorporate domain knowledge from Unified Medical Language System (UMLS) to a pre-trained language model via Graph Edge-conditioned Attention Networks (GEANet) and hierarchical graph representation. To better recognize the trigger words, each sentence is first grounded to a sentence graph based on a jointly modeled hierarchical knowledge graph fro…
Knowledge Graph Extraction from Biomedical Literature for Alkaptonuria Rare Disease
Department of Computer Science, University of Pisa（计算机科学系，比萨大学）；Department of Biotechnology, Chemistry and Pharmacy, University of Siena（生物技术、化学与药学系，锡耶纳大学）；Department of Information Engineering and Mathematics, University of Siena（信息工程与数学系，锡耶纳大学）；Department of Scienze Economiche e Aziendali, University of Sassari（经济与企业科学系，萨萨里大学）；Department of Computer Science and Engineering, University of Bologna（计算机科学与工程系，博洛尼亚大学）
Universidade Federal Rural de Pernambuco（伯南布哥州联邦农村大学）；Aix-Marseille Université（艾克斯-马赛大学）；Universidade Federal de Pernambuco（伯南布哥州联邦大学）
Relation Extraction (RE), the task of detecting and characterizing semantic relations between entities in text, has gained much importance in the last two decades, mainly in the biomedical domain. Many papers have been published on Relation Extraction using supervised machine learning techniques. Most of these techniques rely on statistical methods, such as feature-based and tree-kernels-based methods. Such statistical learning techniques are usually based on a propositional hypothesis space for representing examples, i.e., they employ an attribute-value representation of features. This kind o…
Harbin Institute of Technology（哈尔滨工业大学）；Cornell University（康奈尔大学）
Currently, there is a rapidly increasing need for high-quality biomedical knowledge graphs (BioKG) that provide direct and precise biomedical knowledge. In the context of COVID-19, this issue is even more necessary to be highlighted. However, most BioKG construction inevitably includes numerous conflicts and noises deriving from incorrect knowledge descriptions in literature and defective information extraction techniques. Many studies have demonstrated that reasoning upon the knowledge graph is effective in eliminating such conflicts and noises. This paper proposes a method BioGRER to improve…
Epistemic AI accelerates biomedical discovery by finding hidden connections in the network of biomedical knowledge. The Epistemic AI web-based software platform embodies the concept of knowledge mapping, an interactive process that relies on a knowledge graph in combination with natural language processing (NLP), information retrieval, relevance feedback, and network analysis. Knowledge mapping reduces information overload, prevents costly mistakes, and minimizes missed opportunities in the research process. The platform combines state-of-the-art methods for information extraction with machine…
Soochow University（苏州大学）；The Hong Kong Polytechnic University（香港理工大学）
Causal relation extraction of biomedical entities is one of the most complex tasks in biomedical text mining, which involves two kinds of information: entity relations and entity functions. One feasible approach is to take relation extraction and function detection as two independent sub-tasks. However, this separate learning method ignores the intrinsic correlation between them and leads to unsatisfactory performance. In this paper, we propose a joint learning model, which combines entity relation extraction and entity function detection to exploit their commonality and capture their inter-re…
School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University（香港理工大学中文及双语学系）
This paper gives an overview of the Caderige project. This project involves teams from different areas (biology, machine learning, natural language processing) in order to develop high-level analysis tools for extracting structured information from biological bibliographical databases, especially Medline. The paper gives an overview of the approach and compares it to the state of the art.
In this research, we present our work participation for the DrugProt task of BioCreative VII challenge. Drug-target interactions (DTIs) are critical for drug discovery and repurposing, which are often manually extracted from the experimental articles. There are >32M biomedical articles on PubMed and manually extracting DTIs from such a huge knowledge base is challenging. To solve this issue, we provide a solution for Track 1, which aims to extract 10 types of interactions between drug and protein entities. We applied an Ensemble Classifier model that combines BioMed-RoBERTa, a state of art lan…
LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction
ASUS Intelligent Cloud Services (AICS)（ASUS智能云服务）；Imperial College London（伦敦帝国学院）；University of Manchester（曼彻斯特大学）；National University of Singapore（新加坡国立大学）
Merged ChemProt-DrugProt for Relation Extraction from Biomedical Literature
San Diego Supercomputer Center, University of California San Diego 1；Department of Computer Science \& Engineering, University of California San Diego 2；Department of Computer Science, Virginia Commonwealth University 3
Advancing Chinese biomedical text mining with community challenges
Sichuan University（四川大学）；West China Hospital（华西医院）；Tongji University（同济大学）；Shanghai Business School（上海商学院）；Takeda Co. Ltd.（武田制药有限公司）；Harbin Institute of Technology（哈尔滨工业大学）
We advance the state of the art in biomolecular interaction extraction with three contributions: (i) We show that deep, Abstract Meaning Representations (AMR) significantly improve the accuracy of a biomolecular interaction extraction system when compared to a baseline that relies solely on surface- and syntax-based features; (ii) In contrast with previous approaches that infer relations on a sentence-by-sentence basis, we expand our framework to enable consistent predictions over sets of sentences (documents); (iii) We further modify and expand a graph kernel learning framework to enable conc…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；Chan Zuckerberg Initiative（陈·扎克伯格倡议）
We introduce ChemDisGene, a new dataset for training and evaluating multi-class multi-label document-level biomedical relation extraction models. Our dataset contains 80k biomedical research abstracts labeled with mentions of chemicals, diseases, and genes, portions of which human experts labeled with 18 types of biomedical relationships between these entities (intended for evaluation), and the remainder of which (intended for training) has been distantly labeled via the CTD database with approximately 78\% accuracy. In comparison to similar preexisting datasets, ours is both substantially lar…
Université Rennes 1（雷恩第一大学）；IRISA（法国计算机科学与随机系统研究所）；Sorbonne University（索邦大学）；Université de technologie de Compiègne（贡比涅技术大学）；CNRS（法国国家科学研究中心）
In this paper, we tackle the problem of extracting frequent opinions from uncertain databases. We introduce the foundation of an opinion mining approach with the definition of pattern and support measure. The support measure is derived from the commitment definition. A new algorithm called OpMiner that extracts the set of frequent opinions modelled as a mass functions is detailed. Finally, we apply our approach on a real-world biomedical database that stores opinions of experts to evaluate the reliability level of biomedical data. Performance analysis showed a better quality patterns for our p…
Rice University（莱斯大学）；The University of Texas Health Science Center at Houston（得克萨斯大学休斯顿健康科学中心）
This paper describes an initial dataset and automatic natural language processing (NLP) method for extracting concepts related to precision oncology from biomedical research articles. We extract five concept types: Cancer, Mutation, Population, Treatment, Outcome. A corpus of 250 biomedical abstracts were annotated with these concepts following standard double-annotation procedures. We then experiment with BERT-based models for concept extraction. The best-performing model achieved a precision of 63.8%, a recall of 71.9%, and an F1 of 67.1. Finally, we propose additional directions for researc…
Advancing Italian Biomedical Information Extraction with Transformers-based Models: Methodological Insights and Multicenter Practical Application
IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli（IRCCS 圣乔瓦尼迪奥法特贝内弗拉特利研究所）；University of Pavia（帕维亚大学）；IRCCS Istituto Auxologico Italiano（IRCCS 意大利奥索洛吉科研究所）；Università degli Studi di Milano（米兰大学）；IRCCS Istituti Clinici Scientifici Maugeri（IRCCS 莫盖里临床科学研究所）；IRCCS Mondino Foundation（IRCCS 蒙迪诺基金会）
AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis
IBM Research（IBM研究院）；Dublin City University（都柏林城市大学）；UCL（伦敦大学学院）；University of Oxford（牛津大学）；IT:U Interdisciplinary Transformation University Austria（奥地利 interdisciplinary Transformation 大学）
Case Western University（凯斯西储大学）；National Cancer Institute（国家癌症研究所）；Vietnam National University（越南国家大学）；University of Science, Vietnam National University（越南国家大学科学大学）
In this report, we introduce SciFive, a domain-specific T5 model that has been pre-trained on large biomedical corpora. Our model outperforms the current SOTA methods (i.e. BERT, BioBERT, Base T5) on tasks in named entity relation, relation extraction, natural language inference, and question-answering. We show that text-generation methods have significant potential in a broad array of biomedical NLP tasks, particularly those requiring longer, more complex outputs. Our results support the exploration of more difficult text generation tasks and the development of new methods in this area
Recently, kernelized locality sensitive hashcodes have been successfully employed as representations of natural language text, especially showing high relevance to biomedical relation extraction tasks. In this paper, we propose to optimize the hashcode representations in a nearly unsupervised manner, in which we only use data points, but not their class labels, for learning. The optimized hashcode representations are then fed to a supervised classifier following the prior work. This nearly unsupervised approach allows fine-grained optimization of each hash function, which is particularly suita…
College of Information and Computer Science, University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校信息与计算机科学学院）；Department of Computer Science, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校计算机科学系）；Department of Medicine, University of Massachusetts Medical School（马萨诸塞大学医学院医学系）；Center for Healthcare Organization and Implementation Research, Bedford Veterans Affairs Medical Center（贝德福德退伍军人事务医疗中心医疗保健组织与实施研究中心）
Language Models (LMs) have performed well on biomedical natural language processing applications. In this study, we conducted some experiments to use prompt methods to extract knowledge from LMs as new knowledge Bases (LMs as KBs). However, prompting can only be used as a low bound for knowledge extraction, and perform particularly poorly on biomedical domain KBs. In order to make LMs as KBs more in line with the actual application scenarios of the biomedical domain, we specifically add EHR notes as context to the prompt to improve the low bound in the biomedical domain. We design and validate…
Indraprastha Institute of Information Technology Delhi（德里英德拉普拉斯信息技术学院）
Deep learning models trained using massive amounts of data tend to capture one view of the data and its associated mapping. Different deep learning models built on the same training data may capture different views of the data based on the underlying techniques used. For explaining the decisions arrived by blackbox deep learning models, we argue that it is essential to reproduce that model's view of the training data faithfully. This faithful reproduction can then be used for explanation generation. We investigate two methods for data view extraction: hill-climbing approach and a GAN-driven ap…
