# This Shasta assembly configuration was tested under the following conditions: # - ONT R10 chemistry, fast mode, chimera rate around 2%. # - Guppy 6 basecaller with "super" accuracy. # - Human genome at low coverage (one flowcell, coverage around 35x). # - Haploid assembly. # Under these conditions it produced a haploid assembly with N50 around 20 Mb # and with base level accuracy limited mostly by heterozygosity # of the human genome. # This configuration might also be usable for other genomes and at higher coverage, # but that was not tested. [Reads] representation = 0 minReadLength = 10000 noCache = True [Kmers] k = 14 [MinHash] minHashIterationCount = 100 minBucketSize = 10 maxBucketSize = 40 minFrequency = 5 [Align] alignMethod = 3 downsamplingFactor = 0.05 matchScore = 6 sameChannelReadAlignment.suppressDeltaThreshold = 30 minAlignedMarkerCount = 1000 minAlignedFraction = 0.85 maxSkip = 20 maxDrift = 10 maxTrim = 20 [ReadGraph] creationMethod = 0 maxAlignmentCount = 15 [MarkerGraph] simplifyMaxLength = 10,100,1000,10000,100000 crossEdgeCoverageThreshold = 3 # Adaptive estimation of coverage threshold to generate marker graph vertices. minCoverage = 0 [Assembly] consensusCaller = Modal detangleMethod = 2