Artificial intelligence in genomics: transforming the diagnosis of hereditary spastic paraplegia

Hereditary spastic paraplegia (HSP) represents a genetically and clinically heterogeneous group of neurodegenerative disorders characterized by progressive spasticity and weakness of the lower limbs. Accurate diagnosis remains challenging due to the expanding spectrum of causative genes, overlapping features with hereditary cerebellar ataxias, and the presence of clinical mimics. Recent advances in artificial intelligence (AI)-driven genomics have begun to transform variant detection, interpretation, and pathogenicity classification. Accelerated next-generation sequencing platforms such as NVIDIA Parabricks and Illumina DRAGEN markedly shorten analysis times while maintaining clinical-grade accuracy. Emerging tools such as Dynamicasome, which integrates molecular dynamics simulations with deep learning, address long-standing limitations by capturing structural disruptions beyond sequence conservation. Complementary approaches like SpliceAI and Exomiser expand the diagnostic window through improved splicing prediction and phenotype-driven variant prioritization. These innovations are particularly relevant in high-consanguinity populations such as Pakistan, where recessive variants are prevalent and diagnostic delays are common. Wider adoption of free AI-based platforms, alongside bioinformatics training and institutional collaboration, has the potential to accelerate early molecular diagnosis, enable timely genetic counseling, and ultimately reshape the clinical management of HSP and other rare neurogenetic disorders.