Gene Prioritization of Resistant Rice Gene against Xanthomas oryzae pv. oryzae by Using Text Mining Technologies

Algorithm 1

Gene prioritization algorithm.

Step 1. Collect NCBI literature in the rice research field, denote the text database as 𝑑_𝑗, here 𝑑_1,2,…,10 = “rice”, “Event”,

  “Binding”, “Catabolism”, “Expression”, “Localization”, “phosphorylation”, “regulation”, “transcript”, "Xoo”;

Step 2. Build phrase dictionary, denote the terms as 𝑡_𝑖.

Step 3. Evaluate the relevance between 𝑡_𝑖 and 𝑑_𝑗 by computing TF*IDF(𝑡_𝑖,𝑑_𝑗,𝐷), here 𝐷 is the total text data set.

Step 4. Rank important 𝑡_𝑖.

Step 5. Retrieve protein in NCBI with annotation include 𝑡_𝑖.

Step 6. Rank candidate protein by using the built-in classifier [17] which is sequence-based.

Step 7. Use Conserved Domain Data (CDD) and Gene Ontology (GO) to verify the result of prioritization.