Changing word meanings in biomedical literature reveal pandemics and new technologies.

While we often think of words as having a fixed meaning that we use to describe a changing world, words are also dynamic and changing. Scientific research can also be remarkably fast-moving, with new concepts or approaches rapidly gaining mind share. We examined scientific writing, both preprint and pre-publication peer-reviewed text, to identify terms that have changed and examine their use. One particular challenge that we faced was that the shift from closed to open access publishing meant that the size of available corpora changed by over an order of magnitude in the last two decades. We developed an approach to evaluate semantic shift by accounting for both intra- and inter-year variability using multiple integrated models. This analysis revealed thousands of change points in both corpora, including for terms such as 'cas9', 'pandemic', and 'sars'. We found that the consistent change-points between pre-publication peer-reviewed and preprinted text are largely related to the COVID-19 pandemic. We also created a web app for exploration that allows users to investigate individual terms ( https://greenelab.github.io/word-lapse/ ). To our knowledge, our research is the first to examine semantic shift in biomedical preprints and pre-publication peer-reviewed text, and provides a foundation for future work to understand how terms acquire new meanings and how peer review affects this process.

Hetnet connectivity search provides rapid insights into how two biomedical entities are related.

Hetnets, short for "heterogeneous networks", contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet connects 11 types of nodes - including genes, diseases, drugs, pathways, and anatomical structures - with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious not only how metformin is related to breast cancer, but also how the GJA1 gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any two nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). We find that predictions are broadly similar to those from previously described supervised approaches for certain node type pairs. Scoring of individual paths is based on the most specific paths of a given type. Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search . We provide an open source implementation of these methods in our new Python package named hetmatpy .

Expanding a database-derived biomedical knowledge graph via multi-relation extraction from biomedical abstracts.

BACKGROUND: Knowledge graphs support biomedical research efforts by providing contextual information for biomedical entities, constructing networks, and supporting the interpretation of high-throughput analyses. These databases are populated via manual curation, which is challenging to scale with an exponentially rising publication rate. Data programming is a paradigm that circumvents this arduous manual process by combining databases with simple rules and heuristics written as label functions, which are programs designed to annotate textual data automatically. Unfortunately, writing a useful label function requires substantial error analysis and is a nontrivial task that takes multiple days per function. This bottleneck makes populating a knowledge graph with multiple nodes and edge types practically infeasible. Thus, we sought to accelerate the label function creation process by evaluating how label functions can be re-used across multiple edge types. RESULTS: We obtained entity-tagged abstracts and subsetted these entities to only contain compounds, genes, and disease mentions. We extracted sentences containing co-mentions of certain biomedical entities contained in a previously described knowledge graph, Hetionet v1. We trained a baseline model that used database-only label functions and then used a sampling approach to measure how well adding edge-specific or edge-mismatch label function combinations improved over our baseline. Next, we trained a discriminator model to detect sentences that indicated a biomedical relationship and then estimated the number of edge types that could be recalled and added to Hetionet v1. We found that adding edge-mismatch label functions rarely improved relationship extraction, while control edge-specific label functions did. There were two exceptions to this trend, Compound-binds-Gene and Gene-interacts-Gene, which both indicated physical relationships and showed signs of transferability. Across the scenarios tested, discriminative model performance strongly depends on generated annotations. Using the best discriminative model for each edge type, we recalled close to 30% of established edges within Hetionet v1. CONCLUSIONS: Our results show that this framework can incorporate novel edges into our source knowledge graph. However, results with label function transfer were mixed. Only label functions describing very similar edge types supported improved performance when transferred. We expect that the continued development of this strategy may provide essential building blocks to populating biomedical knowledge graphs with discoveries, ensuring that these resources include cutting-edge results.

Characterization of the genome and silk-gland transcriptomes of Darwin's bark spider (Caerostris darwini).

Natural silks crafted by spiders comprise some of the most versatile materials known. Artificial silks-based on the sequences of their natural brethren-replicate some desirable biophysical properties and are increasingly utilized in commercial and medical applications today. To characterize the repertoire of protein sequences giving silks their biophysical properties and to determine the set of expressed genes across each unique silk gland contributing to the formation of natural silks, we report here draft genomic and transcriptomic assemblies of Darwin's bark spider, Caerostris darwini, an orb-weaving spider whose dragline is one of the toughest known biomaterials on Earth. We identify at least 31 putative spidroin genes, with expansion of multiple spidroin gene classes relative to the golden orb-weaver, Trichonephila clavipes. We observed substantial sharing of spidroin repetitive sequence motifs between species as well as new motifs unique to C. darwini. Comparative gene expression analyses across six silk gland isolates in females plus a composite isolate of all silk glands in males demonstrated gland and sex-specific expression of spidroins, facilitating putative assignment of novel spidroin genes to classes. Broad expression of spidroins across silk gland types suggests that silks emanating from a given gland represent composite materials to a greater extent than previously appreciated. We hypothesize that the extraordinary toughness of C. darwini major ampullate dragline silk may relate to the unique protein composition of major ampullate spidroins, combined with the relatively high expression of stretchy flagelliform spidroins whose union into a single fiber may be aided by novel motifs and cassettes that act as molecule-binding helices. Our assemblies extend the catalog of sequences and sets of expressed genes that confer the unique biophysical properties observed in natural silks.

Examining linguistic shifts between preprints and publications.

Preprints allow researchers to make their findings available to the scientific community before they have undergone peer review. Studies on preprints within bioRxiv have been largely focused on article metadata and how often these preprints are downloaded, cited, published, and discussed online. A missing element that has yet to be examined is the language contained within the bioRxiv preprint repository. We sought to compare and contrast linguistic features within bioRxiv preprints to published biomedical text as a whole as this is an excellent opportunity to examine how peer review changes these documents. The most prevalent features that changed appear to be associated with typesetting and mentions of supporting information sections or additional files. In addition to text comparison, we created document embeddings derived from a preprint-trained word2vec model. We found that these embeddings are able to parse out different scientific approaches and concepts, link unannotated preprint-peer-reviewed article pairs, and identify journals that publish linguistically similar papers to a given preprint. We also used these embeddings to examine factors associated with the time elapsed between the posting of a first preprint and the appearance of a peer-reviewed publication. We found that preprints with more versions posted and more textual changes took longer to publish. Lastly, we constructed a web application (https://greenelab.github.io/preprint-similarity-search/) that allows users to identify which journals and articles that are most linguistically similar to a bioRxiv or medRxiv preprint as well as observe where the preprint would be positioned within a published article landscape.

Hetnet connectivity search provides rapid insights into how biomedical entities are related.

BACKGROUND: Hetnets, short for "heterogeneous networks," contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet, connects 11 types of nodes-including genes, diseases, drugs, pathways, and anatomical structures-with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious about not only how metformin is related to breast cancer but also how a given gene might be involved in insomnia. FINDINGS: We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any 2 nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. CONCLUSION: We implemented the method on Hetionet and provide an online interface at https://het.io/search. We provide an open-source implementation of these methods in our new Python package named hetmatpy.

Constructing knowledge graphs and their biomedical applications.

Knowledge graphs can support many biomedical applications. These graphs represent biomedical concepts and relationships in the form of nodes and edges. In this review, we discuss how these graphs are constructed and applied with a particular focus on how machine learning approaches are changing these processes. Biomedical knowledge graphs have often been constructed by integrating databases that were populated by experts via manual curation, but we are now seeing a more robust use of automated systems. A number of techniques are used to represent knowledge graphs, but often machine learning methods are used to construct a low-dimensional representation that can support many different applications. This representation is designed to preserve a knowledge graph's local and/or global structure. Additional machine learning methods can be applied to this representation to make predictions within genomic, pharmaceutical, and clinical domains. We frame our discussion first around knowledge graph construction and then around unifying representational learning techniques and unifying applications. Advances in machine learning for biomedicine are creating new opportunities across many domains, and we note potential avenues for future work with knowledge graphs that appear particularly promising.

The Nephila clavipes genome highlights the diversity of spider silk genes and their complex expression.

Spider silks are the toughest known biological materials, yet are lightweight and virtually invisible to the human immune system, and they thus have revolutionary potential for medicine and industry. Spider silks are largely composed of spidroins, a unique family of structural proteins. To investigate spidroin genes systematically, we constructed the first genome of an orb-weaving spider: the golden orb-weaver (Nephila clavipes), which builds large webs using an extensive repertoire of silks with diverse physical properties. We cataloged 28 Nephila spidroins, representing all known orb-weaver spidroin types, and identified 394 repeated coding motif variants and higher-order repetitive cassette structures unique to specific spidroins. Characterization of spidroin expression in distinct silk gland types indicates that glands can express multiple spidroin types. We find evidence of an alternatively spliced spidroin, a spidroin expressed only in venom glands, evolutionary mechanisms for spidroin diversification, and non-spidroin genes with expression patterns that suggest roles in silk production.