Gap junction (GJ) channels in invertebrates have been used to understand cell-to-cell communication in vertebrates. GJs are a common form of intercellular communication channels which connect the cytoplasm of adjacent cells. Dysregulation and structural alteration of the gap junction-mediated communication have been proven to be associated with a myriad of symptoms and tissue-specific pathologies. Animal models relying on the invertebrate nervous system have exposed a relationship between GJs and the formation of electrical synapses during embryogenesis and adulthood. The modulation of GJs as a therapeutic and clinical tool may eventually provide an alternative for treating tissue formation-related diseases and cell propagation. This review concerns the similarities between Hirudo medicinalis innexins and human connexins from nucleotide and protein sequence level perspectives. It also sets forth evidence of computational techniques applied to the study of proteins, sequences, and molecular dynamics. Furthermore, we propose machine learning techniques as a method that could be used to study protein structure, gap junction inhibition, metabolism, and drug development.

Multi-layer perceptron artificial neural networks (MLP-ANNs) were used to predict the concentration of digoxin needed to obtain a cardio-activity of specific biophysical parameters in Tivela stultorum hearts. The inputs of the neural networks were the minimum and maximum values of heart contraction force, the time of ventricular filling, the volume used for dilution, heart rate and weight, volume, length and width of the heart, while the output was the digoxin concentration in dilution necessary to obtain a desired physiological response. ANNs were trained, validated and tested with the dataset of the in vivo experiment results. To select the optimal network, predictions for all the dataset for each configuration of ANNs were made, a maximum 5% relative error for the digoxin concentration was set and the diagnostic accuracy of the predictions made was evaluated. The double-layer perceptron had a barely higher performance than the single-layer perceptron; therefore, both had a good predictive ability. The double-layer perceptron was able to obtain the most accurate predictions of digoxin concentration required in the hearts of T. stultorum using MLP-ANNs.