Continual knowledge infusion into pre-trained biomedical language models.

MOTIVATION: Biomedical language models produce meaningful concept representations that are useful for a variety of biomedical natural language processing (bioNLP) applications such as named entity recognition, relationship extraction and question answering. Recent research trends have shown that the contextualized language models (e.g. BioBERT, BioELMo) possess tremendous representational power and are able to achieve impressive accuracy gains. However, these models are still unable to learn high-quality representations for concepts with low context information (i.e. rare words). Infusing the complementary information from knowledge-bases (KBs) is likely to be helpful when the corpus-specific information is insufficient to learn robust representations. Moreover, as the biomedical domain contains numerous KBs, it is imperative to develop approaches that can integrate the KBs in a continual fashion. RESULTS: We propose a new representation learning approach that progressively fuses the semantic information from multiple KBs into the pretrained biomedical language models. Since most of the KBs in the biomedical domain are expressed as parent-child hierarchies, we choose to model the hierarchical KBs and propose a new knowledge modeling strategy that encodes their topological properties at a granular level. Moreover, the proposed continual learning technique efficiently updates the concepts representations to accommodate the new knowledge while preserving the memory efficiency of contextualized language models. Altogether, the proposed approach generates knowledge-powered embeddings with high fidelity and learning efficiency. Extensive experiments conducted on bioNLP tasks validate the efficacy of the proposed approach and demonstrates its capability in generating robust concept representations.

Continual representation learning for evolving biomedical bipartite networks.

MOTIVATION: Many real-world biomedical interactions such as 'gene-disease', 'disease-symptom' and 'drug-target' are modeled as a bipartite network structure. Learning meaningful representations for such networks is a fundamental problem in the research area of Network Representation Learning (NRL). NRL approaches aim to translate the network structure into low-dimensional vector representations that are useful to a variety of biomedical applications. Despite significant advances, the existing approaches still have certain limitations. First, a majority of these approaches do not model the unique topological properties of bipartite networks. Consequently, their straightforward application to the bipartite graphs yields unsatisfactory results. Second, the existing approaches typically learn representations from static networks. This is limiting for the biomedical bipartite networks that evolve at a rapid pace, and thus necessitate the development of approaches that can update the representations in an online fashion. RESULTS: In this research, we propose a novel representation learning approach that accurately preserves the intricate bipartite structure, and efficiently updates the node representations. Specifically, we design a customized autoencoder that captures the proximity relationship between nodes participating in the bipartite bicliques (2 × 2 sub-graph), while preserving both the global and local structures. Moreover, the proposed structure-preserving technique is carefully interleaved with the central tenets of continual machine learning to design an incremental learning strategy that updates the node representations in an online manner. Taken together, the proposed approach produces meaningful representations with high fidelity and computational efficiency. Extensive experiments conducted on several biomedical bipartite networks validate the effectiveness and rationality of the proposed approach.

MeSHProbeNet: a self-attentive probe net for MeSH indexing.

MOTIVATION: MEDLINE is the primary bibliographic database maintained by National Library of Medicine (NLM). MEDLINE citations are indexed with Medical Subject Headings (MeSH), which is a controlled vocabulary curated by the NLM experts. This greatly facilitates the applications of biomedical research and knowledge discovery. Currently, MeSH indexing is manually performed by human experts. To reduce the time and monetary cost associated with manual annotation, many automatic MeSH indexing systems have been proposed to assist manual annotation, including DeepMeSH and NLM's official model Medical Text Indexer (MTI). However, the existing models usually rely on the intermediate results of other models and suffer from efficiency issues. We propose an end-to-end framework, MeSHProbeNet (formerly named as xgx), which utilizes deep learning and self-attentive MeSH probes to index MeSH terms. Each MeSH probe enables the model to extract one specific aspect of biomedical knowledge from an input article, thus comprehensive biomedical information can be extracted with different MeSH probes and interpretability can be achieved at word level. MeSH terms are finally recommended with a unified classifier, making MeSHProbeNet both time efficient and space efficient. RESULTS: MeSHProbeNet won the first place in the latest batch of Task A in the 2018 BioASQ challenge. The result on the last test set of the challenge is reported in this paper. Compared with other state-of-the-art models, such as MTI and DeepMeSH, MeSHProbeNet achieves the highest scores in all the F-measures, including Example Based F-Measure, Macro F-Measure, Micro F-Measure, Hierarchical F-Measure and Lowest Common Ancestor F-measure. We also intuitively show how MeSHProbeNet is able to extract comprehensive biomedical knowledge from an input article.

Towards self-learning based hypotheses generation in biomedical text domain.

Motivation: The overwhelming amount of research articles in the domain of bio-medicine might cause important connections to remain unnoticed. Literature Based Discovery is a sub-field within biomedical text mining that peruses these articles to formulate high confident hypotheses on possible connections between medical concepts. Although many alternate methodologies have been proposed over the last decade, they still suffer from scalability issues. The primary reason, apart from the dense inter-connections between biological concepts, is the absence of information on the factors that lead to the edge-formation. In this work, we formulate this problem as a collaborative filtering task and leverage a relatively new concept of word-vectors to learn and mimic the implicit edge-formation process. Along with single-class classifier, we prune the search-space of redundant and irrelevant hypotheses to increase the efficiency of the system and at the same time maintaining and in some cases even boosting the overall accuracy. Results: We show that our proposed framework is able to prune up to 90% of the hypotheses while still retaining high recall in top-K results. This level of efficiency enables the discovery algorithm to look for higher-order hypotheses, something that was infeasible until now. Furthermore, the generic formulation allows our approach to be agile to perform both open and closed discovery. We also experimentally validate that the core data-structures upon which the system bases its decision has a high concordance with the opinion of the experts.This coupled with the ability to understand the edge formation process provides us with interpretable results without any manual intervention. Availability and implementation: The relevant JAVA codes are available at: https://github.com/vishrawas/Medline-Code_v2. Supplementary information: Supplementary data are available at Bioinformatics online.

A survey on literature based discovery approaches in biomedical domain.

Literature Based Discovery (LBD) refers to the problem of inferring new and interesting knowledge by logically connecting independent fragments of information units through explicit or implicit means. This area of research, which incorporates techniques from Natural Language Processing (NLP), Information Retrieval and Artificial Intelligence, has significant potential to reduce discovery time in biomedical research fields. Formally introduced in 1986, LBD has grown to be a significant and a core task for text mining practitioners in the biomedical domain. Together with its inter-disciplinary nature, this has led researchers across domains to contribute in advancing this field of study. This survey attempts to consolidate and present the evolution of techniques in this area. We cover a variety of techniques and provide a detailed description of the problem setting, the intuition, the advantages and limitations of various influential papers. We also list the current bottlenecks in this field and provide a general direction of research activities for the future. In an effort to be comprehensive and for ease of reference for off-the-shelf users, we also list many publicly available tools for LBD. We hope this survey will act as a guide to both academic and industry (bio)-informaticians, introduce the various methodologies currently employed and also the challenges yet to be tackled.