Figure 5From: EnzyMiner: automatic identification of protein level mutations and their impact on target enzymes from PubMed abstractsPerformance of Probabilistic Indexing with different processing options. Model 1: White space tokenizer, no stemming, unigram. Model 2: Alphanumeric tokenizer, no stemming, unigram. Model 3: White space tokenizer, stemming, unigram. Model 4: White space tokenizer, no stemming, bigram. Model 5: Alphanumeric tokenizer, stemming, unigram. Model 6: Alphanumeric tokenizer, no stemming, bigram. Model 7: White space tokenizer, stemming, bigram. Model 8: Alphanumeric tokenizer, stemming, bigram.Back to article page