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 names of biological pathways in texts on the basis of their context. 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:
Deficient Mismatch Repair and Lymphocytic Response to Tumor as Prognostic Markers in Stage II Colon Cancer Patients. OBJECTIVE: To investigate the relationship between colon cancer subtypes defined by the status of tumor-infiltrating lymphocytes and mismatch repair (MMR) combination with clinicopathological features and survival. STUDY DESIGN: Observational study. PLACE AND DURATION OF STUDY: Department of Medical Oncology, HaydarpaAŸa Numune Research and Training Hospital, Istanbul, Turkey, from July 2010 to March 2020. METHODOLOGY: Eighty-three patients with operated stage II colon cancer were included in the study. Pathology, surgery and oncological treatment and follow-up information were obtained from patient files; And statistical analyses were performed on overall survival . Tumor-infiltrating lymphocytes and mismatch repair status was determined with the help of immunohistochemistry. RESULTS: TIL-high and deficient <andsystem-candidate> status were detected in 26 patients (31.3%) and 21 patients (25.3%), respectively. Tumors were divided into four subgroups according to tumor-infiltrating lymphocytes and MMR status. TIL-high/deficient mmr tumors had the most favourable prognosis, while TIL-low/proficient MMR tumors exhibited poor overall survival. CONCLUSION: The combination of tumor-infiltrating lymphocytes and MMR could enable us to differentiate patients' survival outcomes in more details. Therefore, considering that the tumor-infiltrating lymphocytes and MMR status, evaluated by IHC, may be a cost-effective and effective option for risk classification in patients with stage II colon cancer. Key Word: Lymphocytic response, Mismatch repair, Prognosis, Tumor-infiltrating lymphocytes, Stage II cancer, Colon cancer.
In this example MMR abbreviation, which refers to the mismatch repair, 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 biological pathways.
LABEL_1 refers to the probability of the TRUE recognition, i.e. when the context of <andsystem-candidate> corresponds to the context specific for biological pathways.
The optimal threshold value for the short names of biological pathways for the LABEL_1, was calculated using a gold standard (add link). It is >= 0.999702513217926.
The Mathew Correlation Coefficient of the model for the long names (>= 15 symbols) is 0.987.
The ROC AUC value of the model, calculated for the short names (<= 4 symbols) is 0.877.
- Downloads last month
- 1