pipeline.gv

digraph {
	graph [fontname="times-bold" fontsize="36" style=dotted]
	node [shape="rectangle" width=5]

	subgraph cluster_physical_map {
		graph [label="Physical Map"]

		reads [label="Linked reads (FASTQ)" shape="parallelogram"]
		index_reads [label="Index the minimizers of the linked reads"]
		filter_minimizers [label="Filter singleton and frequent minimizers"]
		overlap_barcodes [label="Identify all pairs of barcodes sharing significant minimizers"]
		separate_molecules [label="Separate barcodes into molecules"]
		mst [label="Find a maximum spanning tree of the molecule overlap graph"]
		backbone [label="Find contiguous paths in the maximum spanning tree"]
		physical_map [label="Physical map of molecules" shape="ellipse"]
	}

	subgraph cluster_scaffold {
		graph [label="Scaffold"]
	
		draft [label="Draft genome assembly (FASTA)" shape="parallelogram"]
		index_draft [label="Index the minimizers of the draft assembly"]
		map_draft [label="Map the draft assembly to the physical map"]
		scaffold [label="Order and orient sequences on the physical map"]
		scaffolds [label="Scaffolds (FASTA)" shape="ellipse"]
	}

	reads -> index_reads
	index_reads -> filter_minimizers
	filter_minimizers -> overlap_barcodes
	overlap_barcodes -> separate_molecules
	separate_molecules -> mst
	mst -> backbone
	backbone -> physical_map

	draft -> index_draft
	index_draft -> map_draft
	physical_map -> map_draft
	map_draft -> scaffold
	scaffold -> scaffolds
}