Neural-symbolic hybrid model for myosin complex in cardiac ventriculum decodes structural bases for inheritable heart disease from its genetic encoding

Abstract

Background: Human ventriculum myosin (βmys) powers contraction sometimes in complex with myosin binding protein C (MYBPC3). The latter regulates βmys activity and impacts overall cardiac function. Nonsynonymous single nucleotide variants (SNVs) change protein sequence in βmys or MYBPC3 causing inheritable heart diseases by affecting the βmys/MYBPC3 complex. Muscle genetics encode instructions for contraction informing native protein construction, functional integration, and inheritable disease impairment. A digital model decodes these instructions and evolves by continuously processing new information content from diverse data modalities in partnership with the human agent. Methods: A general neural-network contraction model characterizes SNV impacts on human health. It rationalizes phenotype and pathogenicity assignment given the SNVs genetic characteristics and in this sense decodes βmys/MYBPC3 complex genetics and implicitly captures ventricular muscle functionality. When a SNV modified domain locates to an inter-protein contact in βmys/MYBPC3 it affects complex coordination. Domains involved, one in βmys and the other in MYBPC3, form coordinated domains (co-domains). Co-domains are bilateral implying potential for their SNV modification probabilities to respond jointly to a common perturbation to reveal their location. Human genetic diversity from the serial founder effect is the common systemic perturbation coupling co-domains that are mapped by a methodology called 2-dimensional correlation genetics (2D-CG). Results: Interpreting the general neural-network contraction model output involves 2D-CG co-domain mapping that provides natural language expressed structural insights. It aligns machine-learned intelligence from the neural network model with human provided structural insight from the 2D-CG map, and other data from the literature, to form a neural-symbolic hybrid model integrating genetic and protein interaction data into a nascent digital twin. This process is the template for combining new information content from diverse data modalities into a digital model that can evolve. The nascent digital twin interprets SNV implications to discover disease mechanism, can evaluate potential remedies for efficacy, and does so without animal models.