Skip to main content


Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Figure 2 | Nonlinear Biomedical Physics

Figure 2

From: Developing combinatorial multi-component therapies (CMCT) of drugs that are more specific and have fewer side effects than traditional one drug therapies

Figure 2

An artificial neural network was used to predict the output effects from all combinations of input drugs given limited information. The value of each drug is presented to one unit in the first layer of the network. The values of the units in each next layer are computed from the values of the units in the previous layer according to eq. (5) and eq. (6). The parameters of the network, the weights and biases, Wi, jN and BiN, are determined using the backpropagation algorithm to match the output effects from the input drugs presented one-at-a-time and pairs-at-a-time. Then the output effects are determined by presenting all possible combinations of drugs to the inputs. The network is represented here schematically. In the study most fully described in the text, there were 15 input units, 60 hidden layer units, and 1 output unit.

Back to article page