raphael-r/bright-gliner-chromosomal

BRIGHT NER: GLiNER2 fine-tuned for chromosomal

Description

This is a GLiNER2 architecture fine-tuned to extract clinical neuro-oncology entities related to the chromosomal semantic group. It was trained on a synthetic dataset generated for the properly de-identified BRIGHT project dataset (see the generated_data folder in the primary repository).

This model repository was specifically designed to fit within the bright_db overarching namespace.

Fields

It extracts the following fields (described in French):

• ch1p: Délétion 1p
• ch19q: Délétion 19q
• ch1p19q_codel: Codélétion 1p/19q
• ch7p: Gain/perte 7p
• ch7q: Gain/perte 7q
• ch10p: Délétion 10p
• ch10q: Délétion 10q
• ch9p: Délétion 9p
• ch9q: Délétion 9q
• ampli_egfr: Amplification EGFR
• ampli_cdk4: Amplification CDK4
• ampli_mdm2: Amplification MDM2
• ampli_mdm4: Amplification MDM4
• ampli_met: Amplification MET
• fusion_fgfr: Fusion FGFR
• fusion_ntrk: Fusion NTRK
• fusion_autre: Autre fusion

Performance on Validation Set

Aggregates:

• Macro F1: 0.2505 (Precision: 0.1890, Recall: 0.6589)
• Micro F1: 0.3834 (Precision: 0.2421, Recall: 0.9216)

Per-Label Breakdowns:

Label	Precision	Recall	F1
ch1p	0.1653	0.7407	0.2703
ch19q	0.2941	0.3846	0.3333
ch1p19q_codel	0.4269	0.9865	0.5959
ch7p	0.7788	0.9529	0.8571
ch7q	0.2308	1.0000	0.3750
ch10p	0.1176	0.8000	0.2051
ch10q	0.7677	0.9870	0.8636
ch9p	0.1667	1.0000	0.2857
ch9q	0.0152	1.0000	0.0299
ampli_egfr	0.1604	0.8500	0.2698
ampli_cdk4	0.0000	0.0000	0.0000
ampli_mdm2	0.0417	1.0000	0.0800
ampli_mdm4	0.0000	0.0000	0.0000
ampli_met	0.0000	0.0000	0.0000
fusion_fgfr	0.0345	1.0000	0.0667
fusion_ntrk	0.0000	0.0000	0.0000
fusion_autre	0.0130	0.5000	0.0253

Usage

# Inference Code
from gliner2 import GLiNER2

model = GLiNER2.from_pretrained("raphael-r/bright-gliner-chromosomal")
text = "Patient presenting with epileptic seizures..."
entities = model.extract_entities(text)

for entity in entities:
    print(entity["text"], "=>", entity["label"])