Shasta Python API documentation¶

Indices and tables¶

Class Assembler¶

class shasta.Assembler¶

__init__(self: shasta.Assembler, largeDataFileNamePrefix: str = 'Data/', createNew: bool = False, largeDataPageSize: int = 2097152) → None¶: Assembler constructor.

accessAlignmentCandidateTable(self: shasta.Assembler) → None¶

accessAlignmentCandidates(self: shasta.Assembler) → None¶

accessAlignmentData(self: shasta.Assembler) → None¶

accessAlignmentDataReadWrite(self: shasta.Assembler) → None¶

accessAssemblyGraphEdgeLists(self: shasta.Assembler) → None¶

accessAssemblyGraphEdges(self: shasta.Assembler) → None¶

accessAssemblyGraphOrientedReadsByEdge(self: shasta.Assembler) → None¶

accessAssemblyGraphSequences(self: shasta.Assembler) → None¶

accessAssemblyGraphVertices(self: shasta.Assembler) → None¶

accessCompressedAlignments(self: shasta.Assembler) → None¶

accessKmers(self: shasta.Assembler) → None¶

accessMarkerGraphConsensus(self: shasta.Assembler) → None¶

accessMarkerGraphCoverageData(self: shasta.Assembler) → None¶

accessMarkerGraphEdges(self: shasta.Assembler, accessEdgesReadWrite: bool = False, accessConnectivityReadWrite: bool = False) → None¶

accessMarkerGraphReverseComplementEdge(self: shasta.Assembler) → None¶

accessMarkerGraphReverseComplementVertex(self: shasta.Assembler, readWriteAccess: bool = False) → None¶

accessMarkerGraphVertexRepeatCounts(self: shasta.Assembler) → None¶

accessMarkerGraphVertices(self: shasta.Assembler, readWriteAccess: bool = False) → None¶

accessMarkers(self: shasta.Assembler) → None¶

accessReadGraph(self: shasta.Assembler) → None¶

accessReadGraphReadWrite(self: shasta.Assembler) → None¶

accessSortedMarkers(self: shasta.Assembler) → bool¶

alignOrientedReads(self: shasta.Assembler, readId0: int, strand0: int, readId1: int, strand1: int, maxSkip: int, maxDrift: int, maxMarkerFrequency: int) → None¶

alignOrientedReads1(self: shasta.Assembler, readId0: int, strand0: int, readId1: int, strand1: int, matchCount: int, mismatchCount: int, gapCount: int) → None¶

alignOrientedReads4(self: shasta.Assembler, readId0: int, strand0: int, readId1: int, strand1: int, deltaX: int, deltaY: int, minEntryCountPerCell: int, maxDistanceFromBoundary: int, minAlignedMarkerCount: int, minAlignedFraction: float, maxSkip: int, maxDrift: int, maxTrim: int, maxBand: int, matchScore: int, mismatchScore: int, gapScore: int) → None¶

alignOverlappingOrientedReads(self: shasta.Assembler, readId: int, strand: int, maxSkip: int, maxDrift: int, maxMarkerFrequency: int, minAlignedMarkerCount: int, maxTrim: int) → None¶

alignPseudoPaths(self: shasta.Assembler, arg0: int, arg1: int, arg2: int, arg3: int) → None¶

analyzeAlignmentMatrix(self: shasta.Assembler, readId0: int, strand0: int, readId1: int, strand1: int) → None¶

analyzeAssemblyGraphBubbles(self: shasta.Assembler, debug: bool = True) → None¶

analyzeMarkerGraphForks(self: shasta.Assembler) → None¶

analyzeReadGraph(self: shasta.Assembler) → None¶

assemble(self: shasta.Assembler, threadCount: int = 0, storeCoverageDataCsvLengthThreshold: int = 0) → None¶

assembleAssemblyGraphEdge(self: shasta.Assembler, edgeId: int, storeCoverageData: bool = True) → shasta::AssembledSegment¶

assembleMarkerGraphEdges(self: shasta.Assembler, threadCount: int = 0, markerGraphEdgeLengthThresholdForConsensus: int, storeCoverageData: bool, assembleAllEdges: bool) → None¶

assembleMarkerGraphVertices(self: shasta.Assembler, threadCount: int = 0) → None¶

checkMarkerGraphIsStrandSymmetric(self: shasta.Assembler, threadCount: int = 0) → None¶

cleanupDuplicateMarkers(self: shasta.Assembler, threadCount: int = 0, minCoverage: int, minCoveragePerStrand: int, duplicateMarkersPattern1Threshold: float, pattern1CreateNewVertices: bool, pattern2CreateNewVertices: bool) → None¶

colorCompressedAssemblyGraph(self: shasta.Assembler, gfaId: str) → None¶

colorGfaBySimilarityToSegment(self: shasta.Assembler, segmentId: int, minVertexCount: int, minEdgeCount: int) → None¶

colorGfaKeySegments(self: shasta.Assembler, fileName: str = 'Assembly-BothStrands-Color.csv') → None¶

colorGfaWithTwoReads(self: shasta.Assembler, readId0: int, strand0: int, readId1: int, strand1: int, fileName: str = 'Assembly-BothStrands-Color.csv') → None¶

computeAlignments(self: shasta.Assembler, arg0: shasta.AlignOptions, arg1: int) → None¶

computeAssemblyStatistics(self: shasta.Assembler) → None¶

computeMarkerGraphCoverageHistogram(self: shasta.Assembler) → None¶

computeMarkerGraphVerticesCoverageData(self: shasta.Assembler, threadCount: int = 0) → None¶

computeReadGraphConnectedComponents(self: shasta.Assembler) → None¶

computeSortedMarkers(self: shasta.Assembler, threadCount: int = 0) → None¶

createAssemblyGraph2(self: shasta.Assembler, bubbleRemovalDiscordantRatioThreshold: float, bubbleRemovalAmbiguityThreshold: float, bubbleRemovalMaxPeriod: int, superbubbleRemovalEdgeLengthThreshold: int, phasingMinReadCount: int, suppressGfaOutput: bool, suppressFastaOutput: bool, suppressDetailedOutput: bool, suppressPhasedOutput: bool, suppressHaploidOutput: bool, threadCount: int = 0) → None¶

createAssemblyGraphEdges(self: shasta.Assembler) → None¶

createAssemblyGraphVertices(self: shasta.Assembler) → None¶

createCompressedAssemblyGraph(self: shasta.Assembler) → None¶

createMarkerGraphEdges(self: shasta.Assembler, threadCount: int = 0) → None¶

createMarkerGraphEdgesStrict(self: shasta.Assembler, minEdgeCoverage: int, minEdgeCoveragePerStrand: int, threadCount: int = 0) → None¶

createMarkerGraphSecondaryEdges(self: shasta.Assembler, secondaryEdgeMaxSkip: int, threadCount: int = 0) → None¶

createMarkerGraphVertices(self: shasta.Assembler, minCoverage: int, maxCoverage: int, minCoveragePerStrand: int, allowDuplicateMarkers: bool, peakFinderMinAreaFraction: float, peakFinderAreaStartIndex: int, threadCount: int = 0) → None¶

createReadGraph(self: shasta.Assembler, maxAlignmentCount: int, maxTrim: int) → None¶

createReadGraph2(self: shasta.Assembler, maxAlignmentCount: int, markerCountPercentile: float, alignedFractionPercentile: float, maxSkipPercentile: float, maxDriftPercentile: float, maxTrimPercentile: float) → None¶

createReadGraphMode1(self: shasta.Assembler, maxAlignmentCount: int) → None¶

createReadGraphUsingPseudoPaths(self: shasta.Assembler, matchScore: int, mismatchScore: int, gapScore: int, mismatchSquareFactor: float, minScore: float, maxAlignmentCount: int, threadCount: int = 1) → None¶

detangle(self: shasta.Assembler) → None¶

detangle2(self: shasta.Assembler, diagonalReadCountMin: int, offDiagonalReadCountMax: int, offDiagonalRatio: float) → None¶

findAlignmentCandidatesLowHash0(self: shasta.Assembler, m: int, hashFraction: float, minHashIterationCount: int, alignmentCandidatesPerRead: float, log2MinHashBucketCount: int = 0, minBucketSize: int, maxBucketSize: int, minFrequency: int, threadCount: int = 0) → None¶

findAlignmentCandidatesLowHash1(self: shasta.Assembler, m: int, hashFraction: float, minHashIterationCount: int, log2MinHashBucketCount: int = 0, minBucketSize: int, maxBucketSize: int, minFrequency: int, threadCount: int = 0) → None¶

findMarkerGraphReverseComplementEdges(self: shasta.Assembler, threadCount: int = 0) → None¶

findMarkerGraphReverseComplementVertices(self: shasta.Assembler, threadCount: int = 0) → None¶

findMarkers(self: shasta.Assembler, threadCount: int = 0) → None¶: Find markers in reads.

flagChimericReads(self: shasta.Assembler, maxChimericReadDistance: int, threadCount: int = 0) → None¶

flagCrossStrandReadGraphEdges1(self: shasta.Assembler, maxDistance: int, threadCount: int = 0) → None¶

flagCrossStrandReadGraphEdges2(self: shasta.Assembler) → None¶

flagInconsistentAlignments(self: shasta.Assembler, triangleErrorThreshold: int, leastSquareErrorThreshold: int, leastSquareMaxDistance: int, threadCount: int = 0) → None¶

flagPalindromicReads(self: shasta.Assembler, maxSkip: int, maxDrift: int, maxMarkerFrequency: int, alignedFractionThreshold: float, nearDiagonalFractionThreshold: float, deltaThreshold: int, writeTocsv: bool = False, threadCount: int = 0) → None¶

gatherOrientedReadsByAssemblyGraphEdge(self: shasta.Assembler, threadCount: int = 0) → None¶

getAlignmentCandidates(self: shasta.Assembler) → List[shasta.OrientedReadPair]¶

getGlobalMarkerGraphVertex(self: shasta.Assembler, readId: int, strand: int, ordinal: int) → int¶

getGlobalMarkerGraphVertexMarkers(self: shasta.Assembler, vertexId: int) → List[Tuple[int, int, int]]¶

getMarkerGraphMinCoverageUsed(self: shasta.Assembler) → int¶

getMarkers(self: shasta.Assembler, arg0: int, arg1: int) → List[int]¶

getReads(self: shasta.Assembler) → shasta.Reads¶

histogramReadLength(self: shasta.Assembler, fileName: str = 'ReadLengthHistogram.csv') → None¶: Create a histogram of read length and write it to a csv file.

pruneMarkerGraphStrongSubgraph(self: shasta.Assembler, iterationCount: int) → None¶

randomlySelectKmers(self: shasta.Assembler, k: int, probability: float, seed: int = 231) → None¶

readGraphClustering(self: shasta.Assembler) → None¶

refineMarkerGraph(self: shasta.Assembler, refineThreshold: int, threadCount: int = 0) → None¶

removeAssemblyGraph(self: shasta.Assembler) → None¶

removeMarkerGraph(self: shasta.Assembler) → None¶

removeReadGraphBridges(self: shasta.Assembler, maxDistance: int) → None¶

reverseTransitiveReduction(self: shasta.Assembler, lowCoverageThreshold: int, highCoverageThreshold: int, maxDistance: int) → None¶

selectKmers2(self: shasta.Assembler, k: int, markerDensity: float, seed: int = 231, enrichmentThreshold: float, threadCount: int = 0) → None¶

selectKmers4(self: shasta.Assembler, k: int, markerDensity: float, seed: int = 231, distanceThreshold: int, threadCount: int = 0) → None¶

selectKmersBasedOnFrequency(self: shasta.Assembler, k: int, markerDensity: float, seed: int = 231, enrichmentThreshold: float, threadCount: int = 0) → None¶

setMarkerGraphEdgeFlags(self: shasta.Assembler, wasRemovedByTransitiveReduction: int, wasPruned: int, isSuperBubbleEdge: int, isLowCoverageCrossEdge: int, wasAssembled: int) → None¶

setupConsensusCaller(self: shasta.Assembler, arg0: str) → None¶

simplifyMarkerGraph(self: shasta.Assembler, maxLength: List[int], debug: bool = False) → None¶

test(self: shasta.Assembler) → None¶

transitiveReduction(self: shasta.Assembler, lowCoverageThreshold: int, highCoverageThreshold: int, maxDistance: int, edgeMarkerSkipThreshold: int) → None¶

vertexCoverageStatisticsByKmerId(self: shasta.Assembler) → None¶

writeAlignmentCandidates(self: shasta.Assembler, useReadName: bool = False, verbose: bool = False) → None¶

writeAlignmentDetails(self: shasta.Assembler) → None¶

writeAssemblyGraph(self: shasta.Assembler, arg0: str) → None¶

writeBadMarkerGraphVertices(self: shasta.Assembler) → None¶

writeFasta(self: shasta.Assembler, fileName: str) → None¶

writeGfa1(self: shasta.Assembler, fileName: str) → None¶

writeGfa1BothStrands(self: shasta.Assembler, fileName: str) → None¶

writeKmers(self: shasta.Assembler, fileName: str = 'Kmers.csv') → None¶

writeLocalAlignmentCandidateReads(self: shasta.Assembler, readId: int, strand: int, maxDistance: int, allowChimericReads: bool, allowCrossStrandEdges: bool, allowInconsistentAlignmentEdges: bool) → None¶

writeLocalReadGraphReads(self: shasta.Assembler, readId: int, strand: int, maxDistance: int, allowChimericReads: bool, allowCrossStrandEdges: bool, allowInconsistentAlignmentEdges: bool) → None¶

writeMarkerFrequency(self: shasta.Assembler) → None¶

writeMarkers(self: shasta.Assembler, readId: int, strand: int, fileName: str) → None¶: Write the markers of an oriented read.

writeOrientedReadPath(self: shasta.Assembler, readId: int, strand: int, fileName: str = 'OrientedReadPath.csv') → None¶

writeOrientedReadsByAssemblyGraphEdge(self: shasta.Assembler) → None¶

writeOverlappingReads(self: shasta.Assembler, readId: int, strand: int, fileName: str = 'OverlappingReads.fasta') → None¶: Write in fasta format the reads that overlap a given read.

writeParallelMarkerGraphEdges(self: shasta.Assembler) → None¶

writePseudoPath(self: shasta.Assembler, readId: int, strand: int) → None¶

writeReadGraphEdges(self: shasta.Assembler, useReadName: bool = False) → None¶