This model is a fine-tuned model of BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext (hugging-face card). The current model was developed for the web-based ANDDigest system for the classification of the short names of cell components in texts on the basis of their context (the name considered to be short if it's length is 4 symbols or less). The analyzed name should be replaced in text with tag.
Input:
Any biomedical text where a name of classified object is replaced with tag, for example, this pubmed abstract:
Merkel cell carcinoma in lymph nodes with and without primary origin. The prognosis of <andsystem-candidate> with lymph node involvement was better in patients with an unknown than a known primary. Treatment with a uniform aggressive combined chemoradiation regimen, with or without lymphadenectomy, led to better survival rates than previously reported.
In this example MCC abbreviation, which refers to the Merkel cell carcinoma, was replaced with <andsystem-candidate>. Please keep in mind that maximum length of input sequence for BERT is limited to 512 tokens.
Output:
LABEL_0 refers to the probability of the FALSE recognition, i.e. if the context of <andsystem-candidate> doesn't corresponds to the context specific for cell components.
LABEL_1 refers to the probability of the TRUE recognition, i.e. when the context of <andsystem-candidate> corresponds to the context specific for cell components.
The optimal threshold value for the short names of cell components for the LABEL_1, was calculated using a gold standard (add link). It is >= 0.9999737739562988.
The Mathew Correlation Coefficient of the model for the long names (>= 15 symbols) is 0.989.
The ROC AUC value of the model, calculated for the short names (<= 4 symbols) is 0.907.
- Downloads last month
- 0