TWIRLS, an automated topic-wise inference method based on massive literature, suggests a possible mechanism via ACE2 for the pathological changes in the human host after coronavirus infection

Xiaoyang Ji; Chunming Zhang; Yubo Zhai; Zhonghai Zhang; Yiqing Xue; Chunli Zhang; Guangming Tan; Gang Niu

To determine the specificity of the entity, we made a choice between different texts in the local samples. We removed numbers, symbols, verbs, and garbled characters to obtain clean versions of the local samples. The coronavirus study-specific entities (CSSE) were then identified in only the clean texts containing CSHGs. Based on the clean selected samples, we next built a local dictionary of candidate CSSEs containing 49,293 words after deduplication. Before calculating the random distribution of each entity, we included the synonymous entities into a same entity number (including singular or plural words, active and passive forms, different tenses, suffixes that do not change the meaning, etc.). For example, synonymous entities such as coronaviral, coronavirus, coronaviruses were grouped into one entity as coronavirus and assigned the same number (see entity number in Table S1 , Sheet 1 first column). The previous method of merging synonymous entities was based on a dictionary [9, 10] , which not only relied on the integrity of the dictionary, but also required a long retrieval time. To automatically solve the synonymous entity problem, TWIRLS classifies similar strings based on whether there is a significant statistical association between the character blocks in a set of candidate entities including various synonymous entities (see Methods). After cleaning and processing, CSSEs were identified by TWIRLS using a similar method to that for CSHG as described above.