ClinVar Variant ACMG Evidence Prediction Results

This CSV file contains predictions for three types of evidence (functional, population, and computational) for all ClinVar variant submissions. <br>The output CSV contains the following columns:<b>Identifier Columns</b><br>SCV: Submission accession number from ClinVar (format: SCV000000000)<br>VCV: Variation accession number from ClinVar (format: VCV000000000)<br>RCV: Record accession number from ClinVar (format: RCV000000000)<br>VariationID: Numerical identifier for the genetic variation<br><br><b>Genomic Coordinates</b><br>GRCh38_Chr: Chromosome number<br>GRCh38_Start: Start position on chromosome (GRCh38/hg38 assembly)<br>GRCh38_Stop: Stop position on chromosome (GRCh38/hg38 assembly)<br>GRCh38_ReferenceAllele: Reference allele sequence<br>GRCh38_AlternateAllele: Alternate allele sequence<br><br><b>Protein-Level Information</b><br>aapos: Amino acid position in the protein<br>aaref: Reference amino acid (single letter code)<br>aaalt: Alternate amino acid (single letter code)<br>gene: Gene symbol (e.g., BRCA1, TP53)<br><br><b>Original Classification</b><br>SubmissionClassification: Original classification provided by the submitter mainly includes pathogenic, likely pathogenic, uncertain significance, benign, likely benign, but also includes other values<br><br><b>Input Text</b><br>Comment: The textual comment/description provided with the variant submission that was used as input to the model<br><br><b>Model Predictions</b>has_evidence: does the text summary contain a specific type of evidence or not (TRUE or FALSE)evidence_confidence: model prediction confidence (0.0 to 1.0)predicted_evidence: if the text summary contains a specific type of evidence, model prediction of whether it is pathogenic or benign (P or B for population or computational evidence, PS3 or BS3 for functional evidence)B_Score: model prediction confidence for being a benign type of evidence (0.0 to 1.0)P_Score: model prediction confidence for being a pathogenic type of evidence (0.0 to 1.0)<br>Notes on Probability Scores Probability scores (B_Score, P_Score) sum to 1.0 for each row. Higher probability indicates greater model confidence for that classification. The predicted_evidence corresponds to the classification with the highest probability score.<br>Model Type: Fine-tuned transformer model for sequence classification<br>Input: Textual comments from variant submissionsTraining Data: ClinVar variant submissions with known classifications and mentions of ACMG evidence guideline