Beyond the Black Box: Physics-Based and Conservation-Informed Evidence for ACVRL1 Variant Classification in Hereditary Hemorrhagic Telangiectasia and Pulmonary Arterial Hypertension
- 1Department of Clinical Genetics, Vejle Hospital, Sygehus Lillebælt, Beriderbakken 4, 7100 Vejle, Denmark
- 2Department of Regional Health Research, Institute of Health, University of Southern Denmark, Campusvej 55, 5230 Odense, Denmark
Abstract
Missense variants in ACVRL1 (ALK1) cause hereditary hemorrhagic telangiectasia type 2 (HHT2), heritable pulmonary arterial hypertension (PAH), or both in the same patient, and many remain variants of uncertain significance. AlphaMissense classifies them accurately but does not show which evidence drives a call. I annotated 899 ACVRL1 missense variants with protein-stability estimates (FoldX, DynaMut2), a GREMLIN-style conservation score, and structural context. I then trained random-forest classifiers on 311 variants with labels traceable to ClinVar or a publication (296 pathogenic-like, 15 benign-like). A structural/conservation-only classifier (Model 1b) reached a cross-validated ROC-AUC of 0.954 (95% CI 0.916–0.984), and a model adding sequence-based predictors (Model 1) reached 0.979, versus 0.983 for AlphaMissense on the same variants. On variants first reported in 2025–2026, Model 1b scored 0.976, Model 1 0.992, and AlphaMissense 0.992; equivalence within ±0.05 AUC was supported for Model 1 only. Benign variants were the main weakness: Model 1b correctly classified 10/15, against 14/15 for AlphaMissense. Conservation drove most calls, with predicted destabilization contributing to a minority. An interpretable, gene-specific classifier can approach AlphaMissense for ACVRL1 while showing the structural or evolutionary evidence behind each call. Its calls are hypotheses, not functional evidence, and can prioritize VUS for functional testing.
Related
- Osteopetrosis masquerading as hereditary hemolytic anemia: A case report of a 13-year-old girl with massive splenomegaly.
- Systemic Amyloidosis After Liver Transplantation From a Donor With Hereditary Transthyretin Amyloidosis
- Dynamic changes of mitochondrial homeostasis and immune-inflammatory signaling during hemorrhagic shock resuscitation associated ischemia–reperfusion injury
- Transcutaneous spinal cord stimulation for functional recovery in individuals with hereditary spastic paraplegia: Protocol for a pilot clinical trial
- Case Report: Gastrointestinal-onset hereditary transthyretin amyloidosis with cardiomyopathy and equivocal 99mTc-PYP scintigraphy: diagnosis by florbetapir PET-guided skeletal muscle biopsy and genetic testing
BibTeX
@article{brusgaard2026beyond,
title = {{Beyond the Black Box: Physics-Based and Conservation-Informed Evidence for ACVRL1 Variant Classification in Hereditary Hemorrhagic Telangiectasia and Pulmonary Arterial Hypertension}},
author = {Klaus Brusgaard},
journal = {International Journal of Molecular Sciences},
year = {2026},
month = oct,
doi = {10.3390/ijms27219742},
url = {https://www.mdpi.com/1422-0067/27/21/9742},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Beyond the Black Box: Physics-Based and Conservation-Informed Evidence for ACVRL1 Variant Classification in Hereditary Hemorrhagic Telangiectasia and Pulmonary Arterial Hypertension
AU - Klaus Brusgaard
PY - 2026
DA - 2026/10/30
JO - International Journal of Molecular Sciences
DO - 10.3390/ijms27219742
UR - https://www.mdpi.com/1422-0067/27/21/9742
AB - Missense variants in ACVRL1 (ALK1) cause hereditary hemorrhagic telangiectasia type 2 (HHT2), heritable pulmonary arterial hypertension (PAH), or both in the same patient, and many remain variants of uncertain significance. AlphaMissense classifies them accurately but does not show which evidence drives a call. I annotated 899 ACVRL1 missense variants with protein-stability estimates (FoldX, DynaMut2), a GREMLIN-style conservation score, and structural context. I then trained random-forest classifiers on 311 variants with labels traceable to ClinVar or a publication (296 pathogenic-like, 15 benign-like). A structural/conservation-only classifier (Model 1b) reached a cross-validated ROC-AUC of 0.954 (95% CI 0.916–0.984), and a model adding sequence-based predictors (Model 1) reached 0.979, versus 0.983 for AlphaMissense on the same variants. On variants first reported in 2025–2026, Model 1b scored 0.976, Model 1 0.992, and AlphaMissense 0.992; equivalence within ±0.05 AUC was supported for Model 1 only. Benign variants were the main weakness: Model 1b correctly classified 10/15, against 14/15 for AlphaMissense. Conservation drove most calls, with predicted destabilization contributing to a minority. An interpretable, gene-specific classifier can approach AlphaMissense for ACVRL1 while showing the structural or evolutionary evidence behind each call. Its calls are hypotheses, not functional evidence, and can prioritize VUS for functional testing.
SN - 1422-0067
ER -