RESUMO
Biomedical research papers often combine disjoint concepts in novel ways, such as when describing a newly discovered relationship between an understudied gene with an important disease. These concepts are often explicitly encoded as metadata keywords, such as the author-provided terms included with many documents in the MEDLINE database. While substantial recent work has addressed the problem of text generation in a more general context, applications, such as scientific writing assistants, or hypothesis generation systems, could benefit from the capacity to select the specific set of concepts that underpin a generated biomedical text. We propose a conditional language model following the transformer architecture. This model uses the "encoder stack" to encode concepts that a user wishes to discuss in the generated text. The "decoder stack" then follows the masked self-attention pattern to perform text generation, using both prior tokens as well as the encoded condition. We demonstrate that this approach provides significant control, while still producing reasonable biomedical text.
Assuntos
Pesquisa Biomédica , Mineração de Dados/métodos , Escrita Médica , Humanos , MEDLINE , PublicaçõesRESUMO
HIV-1 Associated Neurocognitive Disorder (HAND) is a common and clinically detrimental complication of HIV infection. Viral proteins, including Tat, released from infected cells, cause neuronal toxicity. Substance abuse in HIV-infected patients greatly influences the severity of neuronal damage. To repurpose small molecule inhibitors for anti-HAND therapy, we employed MOLIERE, an AI-based literature mining system that we developed. All human genes were analyzed and prioritized by MOLIERE to find previously unknown targets connected to HAND. From the identified high priority genes, we narrowed the list to those with known small molecule ligands developed for other applications and lacking systemic toxicity in animal models. To validate the AI-based process, the selective small molecule inhibitor of DDX3 helicase activity, RK-33, was chosen and tested for neuroprotective activity. The compound, previously developed for cancer treatment, was tested for the prevention of combined neurotoxicity of HIV Tat and cocaine. Rodent cortical cultures were treated with 6 or 60 ng/ml of HIV Tat and 10 or 25 µM of cocaine, which caused substantial toxicity. RK-33 at doses as low as 1 µM greatly reduced the neurotoxicity of Tat and cocaine. Transcriptome analysis showed that most Tat-activated transcripts are microglia-specific genes and that RK-33 blocks their activation. Treatment with RK-33 inhibits the Tat and cocaine-dependent increase in the number and size of microglia and the proinflammatory cytokines IL-6, TNF-α, MCP-1/CCL2, MIP-2, IL-1α and IL-1ß. These findings reveal that inhibition of DDX3 may have the potential to treat not only HAND but other neurodegenerative diseases. Graphical Abstract RK-33, selective inhibitor of Dead Box RNA helicase 3 (DDX3) protects neurons from combined Tat and cocaine neurotoxicity by inhibition of microglia activation and production of proinflammatory cytokines.
Assuntos
Azepinas/farmacologia , Cocaína/toxicidade , RNA Helicases DEAD-box/antagonistas & inibidores , Imidazóis/farmacologia , Microglia/efeitos dos fármacos , Produtos do Gene tat do Vírus da Imunodeficiência Humana/toxicidade , Complexo AIDS Demência/tratamento farmacológico , Complexo AIDS Demência/enzimologia , Animais , Azepinas/uso terapêutico , Células Cultivadas , RNA Helicases DEAD-box/metabolismo , Inibidores da Captação de Dopamina/toxicidade , Relação Dose-Resposta a Droga , Feminino , Imidazóis/uso terapêutico , Masculino , Microglia/enzimologia , Ratos , Ratos Sprague-DawleyRESUMO
The first step of many research projects is to define and rank a short list of candidates for study. In the modern rapidity of scientific progress, some turn to automated hypothesis generation (HG) systems to aid this process. These systems can identify implicit or overlooked connections within a large scientific corpus, and while their importance grows alongside the pace of science, they lack thorough validation. Without any standard numerical evaluation method, many validate general-purpose HG systems by rediscovering a handful of historical findings, and some wishing to be more thorough may run laboratory experiments based on automatic suggestions. These methods are expensive, time consuming, and cannot scale. Thus, we present a numerical evaluation framework for the purpose of validating HG systems that leverages thousands of validation hypotheses. This method evaluates a HG system by its ability to rank hypotheses by plausibility; a process reminiscent of human candidate selection. Because HG systems do not produce a ranking criteria, specifically those that produce topic models, we additionally present novel metrics to quantify the plausibility of hypotheses given topic model system output. Finally, we demonstrate that our proposed validation method aligns with real-world research goals by deploying our method within MOLIERE, our recent topic-driven HG system, in order to automatically generate a set of candidate genes related to HIV-associated neurodegenerative disease (HAND). By performing laboratory experiments based on this candidate set, we discover a new connection between HAND and Dead Box RNA Helicase 3 (DDX3). Reproducibility: code, validation data, and results can be found at sybrandt.com/2018/validation.
RESUMO
Hypothesis generation is becoming a crucial time-saving technique which allows biomedical researchers to quickly discover implicit connections between important concepts. Typically, these systems operate on domain-specific fractions of public medical data. MOLIERE, in contrast, utilizes information from over 24.5 million documents. At the heart of our approach lies a multi-modal and multi-relational network of biomedical objects extracted from several heterogeneous datasets from the National Center for Biotechnology Information (NCBI). These objects include but are not limited to scientific papers, keywords, genes, proteins, diseases, and diagnoses. We model hypotheses using Latent Dirichlet Allocation applied on abstracts found near shortest paths discovered within this network, and demonstrate the effectiveness of MOLIERE by performing hypothesis generation on historical data. Our network, implementation, and resulting data are all publicly available for the broad scientific community.