BRITE Institute and Department of Pharmaceutical Sciences, North Carolina Central University, Durham, NC 27707, USA.
Molecules. 2020 Aug 28;25(17):3933. doi: 10.3390/molecules25173933.
Drug repurposing is an effective means for rapid drug discovery. The aim of this study was to develop and validate a computational methodology based on Literature-Wide Association Studies (LWAS) of PubMed to repurpose existing drugs for a rare inflammatory breast cancer (IBC). We have developed a methodology that conducted LWAS based on the text mining technology Word2Vec. 3.80 million "cancer"-related PubMed abstracts were processed as the corpus for Word2Vec to derive vector representation of biological concepts. These vectors for drugs and diseases served as the foundation for creating similarity maps of drugs and diseases, respectively, which were then employed to find potential therapy for IBC. Three hundred and thirty-six (336) known drugs and three hundred and seventy (370) diseases were expressed as vectors in this study. Nine hundred and seventy (970) previously known drug-disease association pairs among these drugs and diseases were used as the reference set. Based on the hypothesis that similar drugs can be used against similar diseases, we have identified 18 diseases similar to IBC, with 24 corresponding known drugs proposed to be the repurposing therapy for IBC. The literature search confirmed most known drugs tested for IBC, with four of them being novel candidates. We conclude that LWAS based on the Word2Vec technology is a novel approach to drug repurposing especially useful for rare diseases.
药物重定位是快速发现药物的有效手段。本研究旨在开发和验证一种基于 PubMed 的文献广泛关联研究（LWAS）的计算方法，以便将现有药物重新用于治疗罕见的炎性乳腺癌（IBC）。我们开发了一种基于文本挖掘技术 Word2Vec 的 LWAS 方法。将 380 万篇与“癌症”相关的 PubMed 摘要作为语料库，供 Word2Vec 进行处理，以获得生物概念的向量表示。这些药物和疾病的向量分别作为创建药物和疾病相似性图谱的基础，然后用于寻找 IBC 的潜在治疗方法。在这项研究中，有 336 种已知药物和 370 种疾病被表示为向量。这些药物和疾病中有 970 对已知的药物-疾病关联对被用作参考集。基于相似药物可用于治疗相似疾病的假设，我们确定了 18 种与 IBC 相似的疾病，并提出了 24 种相应的已知药物作为 IBC 的重新定位治疗方法。文献检索证实了大多数已知的药物都被用于 IBC 测试，其中四种是新的候选药物。我们得出结论，基于 Word2Vec 技术的 LWAS 是一种用于药物重新定位的新方法，特别是对罕见疾病非常有用。
