<p>The most prevalent terminal chromosomal deletion disorder, chromosome 1p36 deletion syndrome, leads to developmental delays and intellectual disabilities and seizures and heart defects and distinct facial appearance. Traditional cytogenetic methods, which include karyotyping, face difficulties in early detection of these abnormalities because it require extensive work and substantial time and it can only identify major genetic changes, which makes it unsuitable for detecting minor genomic alterations that occur during infancy. The field of Deep Learning (DL) has made progress toward improving genomic data analysis and disease-related gene identification since its introduction. Hence, the MultiSight Transformer functions as a proposed framework, which processes gene sequences through its multi-head self-attention mechanism to study 1p36 chromosome 1 deletion effects. The model used training and testing procedures on combined datasets which included genomic variations from chromosome 1 and 1p36 deletion regions that contained copy number variations linked to clinical symptoms of skeletal and gastrointestinal and cardiac and chronic kidney disease. The proposed method enables effective gene sequence classification and prediction of the contribution of 1p36 deletion syndrome to major clinical conditions. The experimental results show that the model reaches an accuracy of 0.97 and a precision of 0.90 and a recall of 0.9195 and an F1-score of 0.90 and an area under the curve (AUC) of 0.94 which demonstrates its strong predictive performance. The findings demonstrate that researchers can enhance the detection accuracy and efficiency of chromosome 1p36 deletion syndrome through the combination of transformer-based deep learning models with genomic data analysis. The findings 1p36 deletion detection research should support early diagnosis and clinical decision-making activities.</p>