End-to-End n-ary Relation Extraction for Combination Drug Therapies

Combination drug therapies are treatment regimens that involve two or more drugs, administered more commonly for patients with cancer, HIV, malaria, or tuberculosis. Currently there are over 350K articles in PubMed that use the combination drug therapy MeSH heading with at least 10K articles published per year over the past two decades. Extracting combination therapies from scientific literature inherently constitutes an n-ary relation extraction problem. Unlike in the general n-ary setting where n is fixed (e.g., drug-gene-mutation relations where n = 3), extracting combination therapies is a special setting where n ≥ 2 is dynamic, depending on each instance. Recently, Tiktinsky et al. (NAACL 2022) introduced a first of its kind dataset, CombDrugExt, for extracting such therapies from literature. Here, we use a sequence-to-sequence style end-to-end extraction method to achieve an F1-Score of 66.7% on the CombDrugExt test set for positive (or effective) combinations. This is an absolute ≈ 5% F1-score improvement even over the prior best relation classification score with spotted drug entities (hence, not end-to-end). Thus our effort introduces a state-of-the-art first model for end-to-end extraction that is already superior to the best prior non end-to-end model for this task. Our model seamlessly extracts all drug entities and relations in a single pass and is highly suitable for dynamic n-ary extraction scenarios.

Targeted Therapies in Cancer: To Be or Not to Be, Selective

Development of targeted therapies in recent years revealed several nonchemotherapeutic options for patients. Chief among targeted therapies is small molecule kinase inhibitors targeting key oncogenic signaling proteins. Through competitive and noncompetitive inhibition of these kinases, and therefore the pathways they activate, cancers can be slowed or completely eradicated, leading to partial or complete remissions for many cancer types. Unfortunately, for many patients, resistance to targeted therapies, such as kinase inhibitors, ultimately develops and can necessitate multiple lines of treatment. Drug resistance can either be de novo or acquired after months or years of drug exposure. Since resistance can be due to several unique mechanisms, there is no one-size-fits-all solution to this problem. However, combinations that target complimentary pathways or potential escape mechanisms appear to be more effective than sequential therapy. Combinations of single kinase inhibitors or alternately multikinase inhibitor drugs could be used to achieve this goal. Understanding how to efficiently target cancer cells and overcome resistance to prior lines of therapy became imperative to the success of cancer treatment. Due to the complexity of cancer, effective treatment options in the future will likely require mixing and matching these approaches in different cancer types and different disease stages.