A fast machine-learning-guided primer design pipeline for selective whole genome amplification
Fig 2
Summary schematic of Stage 4 (Primer set search and evaluation) of the swga2.0 pipeline.
Stage 4 begins with one randomly selected primer for each primer set. Each primer set is built in parallel until the improvements in evaluation score no longer exceed a user-defined parameter (ϵ) or until the maximum number of iterations is reached. A drop-out iteration forces each of the highest-scoring primer sets of size n to reduce to the subset of size n − 1 with the highest computed score.