Computational systems biology provides multiple formalisms for modelling of biochemical processes among which the rule-based approach is one of the most suitable. Its main advantage is a compact and precise mechanistic description of complex processes. However, state-of-the-art rule-based languages still suffer several shortcomings that limit their use in practice. In particular, the elementary (low-level) syntax and semantics of rule-based languages complicate model construction and maintenance for users outside computer science. On the other hand, mathematical models based on differential equations (ODEs) still make the most typical used modelling framework. In consequence, robust re-interpretation and integration of models are difficult, thus making the systems biology paradigm technically challenging. Though several high-level languages have been developed at the top of rulebased principles, none of them provides a satisfactory and complete solution for semi-automated description and annotation of heterogeneous biophysical processes integrated at the cellular level. We present the second generation of a rule-based language called Biochemical Space Language (BCSL) that combines the advantages of different approaches and thus makes an effort to overcome several problems of existing solutions. BCSL relies on the formal basis of the rule-based methodology while preserving user-friendly syntax of plain chemical equations. BCSL combines the following aspects: the level of abstraction that hides structural and quantitative details but yet gives a precise mechanistic view of systems dynamics; executable semantics allowing formal analysis and consistency checking at the level of the language; universality allowing the integration of different biochemical mechanisms; scalability and compactness of the specification; hierarchical specification and composability of chemical entities; and support for genome-scale annotation.

Chemical named entity recognition (NER) is a significant step for many downstream applications like entity linking for the chemical text-mining pipeline. However, the identification of chemical entities in a biomedical text is a challenging task due to the diverse morphology of chemical entities and the different types of chemical nomenclature. In this work, we describe our approach that was submitted for BioCreative version 7 challenge Track 2, focusing on the ‘Chemical Identification’ task for identifying chemical entities and entity linking, using MeSH. For this purpose, we have applied a two-stage approach as follows (a) usage of fine-tuned BioBERT for identification of chemical entities (b) semantic approximate search in MeSH and PubChem databases for entity linking. There was some friction between the two approaches, as our rule-based approach did not harmonise optimally with partially recognized words forwarded by the BERT component. For our future work, we aim to resolve the issue of the artefacts arising from BERT tokenizers and develop joint learning of chemical named entity recognition and entity linking using pre-trained transformer-based models and compare their performance with our preliminary approach. Next, we will improve the efficiency of our approximate search in reference databases during entity linking. This task is non-trivial as it entails determining similarity scores of large sets of trees with respect to a query tree. Ideally, this will enable flexible parametrization and rule selection for the entity linking search.

No abstract

Introduction.Nearly 80% of people diagnosed with idiopathic REM sleep behaviour disorder (iRBD) via video-polysomnography (v-PSG) are expected to be in the prodromal stage of an alpha-synucleinopathy. Signs of autonomic dysfunction can appear earlier than motor or cognitive alpha-synucleinopathy symptoms. Heart Rate Variability (HRV) can potentially be an objective measurement of autonomic dysfunction, and furthermore can be obtained directly from v-PSG.Objectives. The aim of this study was to evaluate dysautonomia in iRBD subjects using HRV obtained during different sleep stages and wakefulness from v-PSG. Material and methods.Subjects positively screened by an RBD screening questionnaire (RBD-SQ) underwent v-PSG to diagnose RBD. HRV obtained from v-PSG recordings was correlated to dysautonomia evaluated from a Non-Motor Symptoms Scale (NMSS) questionnaire. Optimal cut-off values of HRV parameters to predict dysautonomia were calculated using receiver operating characteristics (ROC) -area under the curve (AUC) analysis. The effect of confounder variables was predicted with binomial logistic regression and multiple regression analyses.Results. Out of 72 positively screened subjects, 29 subjects were diagnosed as iRBD (mean age 66 ± 7.7 years) by v-PSG. Eighty--three per cent of the iRBD subjects in our cohort were at the time of diagnosis classified as having possible or probable prodromal Parkinson's Disease (pPD) compared to zero subjects being positively screened in the control group. The iRBD-positive subjects showed significant inverse correlations of NMSS score, particularly to log low-frequency (LF) component of HRV during wakefulness: r = -0.59 (p = 0.001). Based on ROC analysis and correlation between NMSS score, log LF during wakefulness (AUC 0.74, cut-off 4.69, sensitivity 91.7%, specificity 64.7%, p = 0.028) was considered as the most accurate predictor of dysautonomia in the iRBD group. Apnoea-hypopnoea index (AHI) negatively predicted dysautonomia in the iRBD group. None of the HRV components was able to predict the presence of iRBD in the full cohort. Age, gender, and PSG variables were significant confounders of HRV prediction.Conclusions. The presented study did not confirm the possibility of using HRV from v-PSG records of patients with iRBD to predict dysautonomia expressed by questionnaire methods. This is probably due to several confounding factors capable of influencing HRV in such a cohort.

The BioCreative National Library of Medicine (NLM)-Chem track calls for a community effort to fine-tune automated recognition of chemical names in the biomedical literature. Chemicals are one of the most searched biomedical entities in PubMed, and—as highlighted during the coronavirus disease 2019 pandemic—their identification may significantly advance research in multiple biomedical subfields. While previous community challenges focused on identifying chemical names mentioned in titles and abstracts, the full text contains valuable additional detail. We, therefore, organized the BioCreative NLM-Chem track as a community effort to address automated chemical entity recognition in full-text articles. The track consisted of two tasks: (i) chemical identification and (ii) chemical indexing. The chemical identification task required predicting all chemicals mentioned in recently published full-text articles, both span [i.e. named entity recognition (NER)] and normalization (i.e. entity linking), using Medical Subject Headings (MeSH). The chemical indexing task required identifying which chemicals reflect topics for each article and should therefore appear in the listing of MeSH terms for the document in the MEDLINE article indexing. This manuscript summarizes the BioCreative NLM-Chem track and post-challenge experiments. We received a total of 85 submissions from 17 teams worldwide. The highest performance achieved for the chemical identification task was 0.8672 F-score (0.8759 precision and 0.8587 recall) for strict NER performance and 0.8136 F-score (0.8621 precision and 0.7702 recall) for strict normalization performance. The highest performance achieved for the chemical indexing task was 0.6073 F-score (0.7417 precision and 0.5141 recall). This community challenge demonstrated that (i) the current substantial achievements in deep learning technologies can be utilized to improve automated prediction accuracy further and (ii) the chemical indexing task is substantially more challenging. We look forward to further developing biomedical text–mining methods to respond to the rapid growth of biomedical literature. The NLM-Chem track dataset and other challenge materials are publicly available at https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/. Database URL https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/