- {"date":"06 February 2022, Sunday, 19:53:54","assembliesNames":["contig1","contig2"],"referenceName":"dataset_066b3cb5_c2ca_4ed5_b245_29eeab002f94","order":[0,1],"report":[["Genome statistics",[{"metricName":"Genome fraction (%)","quality":"More is better","values":["71.579","100.000"],"isMain":true},{"metricName":"Duplication ratio","quality":"Less is better","values":["1.000","1.000"],"isMain":true},{"metricName":"# genomic features","quality":"More is better","values":["7 + 7 part","13 + 1 part"],"isMain":true},{"metricName":"Largest alignment","quality":"More is better","values":[2030,6650],"isMain":true},{"metricName":"Total aligned length","quality":"More is better","values":[4760,6650],"isMain":true},{"metricName":"NG50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"NG75","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"NA50","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"NA75","quality":"More is better","values":[null,6650],"isMain":false},{"metricName":"NGA50","quality":"More is better","values":[1610,6650],"isMain":true},{"metricName":"NGA75","quality":"More is better","values":[null,6650],"isMain":false},{"metricName":"LG50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"LG75","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"LA50","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"LA75","quality":"Less is better","values":[null,1],"isMain":false},{"metricName":"LGA50","quality":"Less is better","values":[2,1],"isMain":true},{"metricName":"LGA75","quality":"Less is better","values":[null,1],"isMain":false}]],["Reads mapping",[]],["Misassemblies",[{"metricName":"# misassemblies","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":" # relocations","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # translocations","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # inversions","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# misassembled contigs","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Misassembled contigs length","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":"# local misassemblies","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# scaffold gap ext. mis.","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# scaffold gap loc. mis.","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# unaligned mis. contigs","quality":"Less is better","values":[0,0],"isMain":false}]],["Unaligned",[{"metricName":"# fully unaligned contigs","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Fully unaligned length","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# partially unaligned contigs","quality":"Less is better","values":[1,0],"isMain":false},{"metricName":"Partially unaligned length","quality":"Less is better","values":[1950,0],"isMain":false}]],["Mismatches",[{"metricName":"# mismatches","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# indels","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Indels length","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# mismatches per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# indels per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":" # indels (<= 5 bp)","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # indels (> 5 bp)","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# N's","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# N's per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true}]],["Statistics without reference",[{"metricName":"# contigs","quality":"Equal","values":[3,1],"isMain":true},{"metricName":"# contigs (>= 0 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"# contigs (>= 1000 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"Largest contig","quality":"More is better","values":[3980,6650],"isMain":true},{"metricName":"Total length","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"Total length (>= 0 bp)","quality":"More is better","values":[6710,6650],"isMain":false},{"metricName":"Total length (>= 1000 bp)","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"N50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"N75","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"L50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"L75","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"GC (%)","quality":"Equal","values":["51.28","52.00"],"isMain":false}]],["K-mer-based statistics",[{"metricName":"K-mer-based compl. (%)","quality":"More is better","values":["68.09","100.00"],"isMain":true},{"metricName":"K-mer-based cor. length (%)","quality":"More is better","values":["100.00","100.00"],"isMain":false},{"metricName":"K-mer-based mis. length (%)","quality":"Less is better","values":["0.00","0.00"],"isMain":false},{"metricName":"K-mer-based undef. length (%)","quality":"Less is better","values":["0.00","0.00"],"isMain":false},{"metricName":"# k-mer-based misjoins","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":" # k-mer-based translocations","quality":"Equal","values":[0,0],"isMain":false},{"metricName":" # k-mer-based 100kbp relocations","quality":"Equal","values":[0,0],"isMain":false}]],["Predicted genes",[{"metricName":"# predicted rRNA genes","quality":"More is better","values":["0 + 0 part","0 + 0 part"],"isMain":true}]],["Similarity statistics",[{"metricName":"# similar correct contigs","quality":"Equal","values":[0,0],"isMain":false},{"metricName":"# similar misassembled blocks","quality":"Equal","values":[0,0],"isMain":false}]],["Reference statistics",[{"metricName":"Reference length","quality":"Equal","values":[6650,6650],"isMain":false},{"metricName":"Reference fragments","quality":"Equal","values":[1,1],"isMain":false},{"metricName":"Reference GC (%)","quality":"Equal","values":["52.00","52.00"],"isMain":false},{"metricName":"Reference genomic features","quality":"Equal","values":[14,14],"isMain":false},{"metricName":"Reference operons","quality":"Equal","values":[0,0],"isMain":false}]]],"subreferences":[],"subreports":[],"minContig":500}
+ {"date":"07 July 2022, Thursday, 16:52:16","assembliesNames":["contig1","contig2"],"referenceName":"dataset_be05aefa-bbf2-47ec-ac87-32bf4b214023","order":[0,1],"report":[["Genome statistics",[{"metricName":"Genome fraction (%)","quality":"More is better","values":["71.579","100.000"],"isMain":true},{"metricName":"Duplication ratio","quality":"Less is better","values":["1.000","1.000"],"isMain":true},{"metricName":"# genomic features","quality":"More is better","values":["7 + 7 part","13 + 1 part"],"isMain":true},{"metricName":"Largest alignment","quality":"More is better","values":[2030,6650],"isMain":true},{"metricName":"Total aligned length","quality":"More is better","values":[4760,6650],"isMain":true},{"metricName":"NG50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"NG90","quality":"More is better","values":[1120,6650],"isMain":false},{"metricName":"auNG","quality":"More is better","values":["2960.4","6650.0"],"isMain":false},{"metricName":"NA50","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"NA90","quality":"More is better","values":[null,6650],"isMain":false},{"metricName":"auNA","quality":"More is better","values":["1187.4","6650.0"],"isMain":false},{"metricName":"NGA50","quality":"More is better","values":[1610,6650],"isMain":true},{"metricName":"NGA90","quality":"More is better","values":[null,6650],"isMain":false},{"metricName":"auNGA","quality":"More is better","values":["1198.1","6650.0"],"isMain":false},{"metricName":"LG50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"LG90","quality":"Less is better","values":[3,1],"isMain":false},{"metricName":"LA50","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"LA90","quality":"Less is better","values":[null,1],"isMain":false},{"metricName":"LGA50","quality":"Less is better","values":[2,1],"isMain":true},{"metricName":"LGA90","quality":"Less is better","values":[null,1],"isMain":false},{"metricName":"Complete BUSCO (%)","quality":"More is better","values":["0.00","0.00"],"isMain":true},{"metricName":"Partial BUSCO (%)","quality":"Less is better","values":["0.68","0.00"],"isMain":true}]],["Reads mapping",[]],["Misassemblies",[{"metricName":"# misassemblies","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":" # relocations","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # translocations","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # inversions","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# misassembled contigs","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Misassembled contigs length","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":"# local misassemblies","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# scaffold gap ext. mis.","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# scaffold gap loc. mis.","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# unaligned mis. contigs","quality":"Less is better","values":[0,0],"isMain":false}]],["Unaligned",[{"metricName":"# fully unaligned contigs","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Fully unaligned length","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# partially unaligned contigs","quality":"Less is better","values":[1,0],"isMain":false},{"metricName":"Partially unaligned length","quality":"Less is better","values":[1950,0],"isMain":false}]],["Mismatches",[{"metricName":"# mismatches per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# mismatches","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# indels per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# indels","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # indels (<= 5 bp)","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # indels (> 5 bp)","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Indels length","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# N's per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# N's","quality":"Less is better","values":[0,0],"isMain":false}]],["Statistics without reference",[{"metricName":"# contigs","quality":"Equal","values":[3,1],"isMain":true},{"metricName":"# contigs (>= 0 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"# contigs (>= 1000 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"Largest contig","quality":"More is better","values":[3980,6650],"isMain":true},{"metricName":"Total length","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"Total length (>= 0 bp)","quality":"More is better","values":[6710,6650],"isMain":false},{"metricName":"Total length (>= 1000 bp)","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"N50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"N90","quality":"More is better","values":[1120,6650],"isMain":false},{"metricName":"auN","quality":"More is better","values":["2934.0","6650.0"],"isMain":false},{"metricName":"L50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"L90","quality":"Less is better","values":[3,1],"isMain":false},{"metricName":"GC (%)","quality":"Equal","values":["51.28","52.00"],"isMain":false}]],["K-mer-based statistics",[{"metricName":"K-mer-based compl. (%)","quality":"More is better","values":["68.09","100.00"],"isMain":true},{"metricName":"K-mer-based cor. length (%)","quality":"More is better","values":["100.00","100.00"],"isMain":false},{"metricName":"K-mer-based mis. length (%)","quality":"Less is better","values":["0.00","0.00"],"isMain":false},{"metricName":"K-mer-based undef. length (%)","quality":"Less is better","values":["0.00","0.00"],"isMain":false},{"metricName":"# k-mer-based misjoins","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":" # k-mer-based translocations","quality":"Equal","values":[0,0],"isMain":false},{"metricName":" # k-mer-based 100kbp relocations","quality":"Equal","values":[0,0],"isMain":false}]],["Predicted genes",[{"metricName":"# predicted rRNA genes","quality":"More is better","values":["0 + 0 part","0 + 0 part"],"isMain":true}]],["Similarity statistics",[{"metricName":"# similar correct contigs","quality":"Equal","values":[0,0],"isMain":false},{"metricName":"# similar misassembled blocks","quality":"Equal","values":[0,0],"isMain":false}]],["Reference statistics",[{"metricName":"Reference length","quality":"Equal","values":[6650,6650],"isMain":false},{"metricName":"Reference fragments","quality":"Equal","values":[1,1],"isMain":false},{"metricName":"Reference GC (%)","quality":"Equal","values":["52.00","52.00"],"isMain":false},{"metricName":"Reference genomic features","quality":"Equal","values":[14,14],"isMain":false},{"metricName":"Reference operons","quality":"Equal","values":[0,0],"isMain":false}]]],"subreferences":[],"subreports":[],"minContig":500}
{{ qualities }}
@@ -4720,27 +4720,24 @@
"# contigs (>= 0 bp)" : "
is the total number of contigs in the assembly that have size greater than or equal to 0 bp.",
"Total length (>= 0 bp)" : "
is the total number of bases in the contigs having size greater than or equal to 0 bp.",
- "N50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the assembly. Usually there is no value that produces exactly 50%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 50% of the total assembly length.",
- "NG50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
- "N75" : "
is the contig length such that using longer or equal length contigs produces 75% of the bases of the assembly. Usually there is no value that produces exactly 75%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 75% of the total assembly length.",
- "NG75" : "
is the contig length such that using longer or equal length contigs produces 75% of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
-
- "L50" : "
is the minimum number of contigs that produce half (50%) of the bases of the assembly. In other words, it's the number of contigs of length at least N50.",
- "LG50" : "
is the minimum number of contigs that produce half (50%) of the bases of the reference genome. In other words, it's the number of contigs of length at least NG50. This metric is computed only if a reference genome is provided.",
- "L75" : "
is the minimum number of contigs that produce 75% of the bases of the assembly. In other words, it's the number of contigs of length at least N75.",
- "LG75" : "
is the minimum number of contigs that produce 75% of the bases of the reference genome. In other words, it's the number of contigs of length at least NG75. This metric is computed only if a reference genome is provided.",
-
- "NA50" : "
is N50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NGA50" : "
is NG50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NA75" : "
is N75 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NGA75" : "
is NG75 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
-
- "LA50" : "
is L50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LGA50" : "
is LG50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LA75" : "
is L75 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LGA75" : "
is LG75 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
-
- "Average %IDY" : "
is the average of alignment identity percent (Nucmer measure of alignment accuracy) among all contigs.",
+ "N50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the assembly. Usually there is no value that produces exactly 50%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 50% of the total assembly length. Similarly, Nx for any x between 0 and 100 could be computed (x% of assembly).",
+ "NG50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the reference genome. This metric is computed only if a reference genome is provided. Similarly, NGx for any x between 0 and 100 could be computed (x% of the reference).",
+
+ "L50" : "
is the minimum number of contigs that produce half (50%) of the bases of the assembly. In other words, it's the number of contigs of length at least N50. Similarly, Lx for any x between 0 and 100 could be computed.",
+ "LG50" : "
is the minimum number of contigs that produce half (50%) of the bases of the reference genome. In other words, it's the number of contigs of length at least NG50. This metric is computed only if a reference genome is provided. Similarly, LGx for any x between 0 and 100 could be computed.",
+
+ "NA50" : "
is N50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided. Similarly, NAx for any x between 0 and 100 could be computed.",
+ "NGA50" : "
is NG50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided. Similarly, NGAx for any x between 0 and 100 could be computed.",
+
+ "LA50" : "
is L50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. Similarly, LAx for any x between 0 and 100 could be computed.",
+ "LGA50" : "
is LG50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. Similarly, LGAx for any x between 0 and 100 could be computed.",
+
+ "auN" : "
is the area under the Nx curve.",
+ "auNG" : "
is the area under the NGx curve.",
+ "auNA" : "
is the area under the NAx curve.",
+ "auNGA" : "
is the area under the NGAx curve.",
+
+ "Average %IDY" : "
is the average of alignment identity percent (alignment accuracy) among all contigs.",
"# misassemblies" : "
is the number of positions in the assembled contigs where the left flanking sequence aligns over 1 kbp away from the right flanking sequence on the reference (relocation) or they overlap on more than 1 kbp (relocation) or flanking sequences align on different strands (inversion) or different chromosomes (translocation).",
"# large block misassemblies" : "
is the number of misassemblies between alignments with length greater than or equal to 3 kbp and with the misassembly threshold equal to 5 kbp (instead of default 1 kbp for regular misassemblies).",
"# misassembled contigs" : "
is the number of contigs that contain misassembly events.",
@@ -4762,11 +4759,11 @@
"# intergenomic misassemblies" : "
is the number of all found and putative (possible) interspecies translocations.",
"# structural variations" : "
is the number of misassemblies matched with structural variations.",
"# possible TEs" : "
is the number of misassemblies possibly caused by transposable elements (TEs). We define a possible TE as an event that satisfies these conditions: - There are two misassembly breakpoints of the same type around a short alignment (less than 7 kbp by default)
- The gap between two long flanking sequences on the sides of the short alignment is less than 7 kbp.
- The long flanking sequences both are on the same strand of the same chromosome of the reference genome.
",
- "# unaligned mis. contigs" : "
is the number of contigs that have the number of unaligned bases more than 50% of contig length and a misassembly event in their aligned fragment. Note that such misassemblies are not counted in # misassemblies and other misassemblies statistics.",
+ "# unaligned mis. contigs" : "
is the number of contigs that have the number of unaligned bases more than 50% of the contig length and a misassembly event in their aligned fragment. Note that such misassemblies are not counted in # misassemblies and other misassemblies statistics.",
"# fully unaligned contigs" : "
is the number of contigs that have no alignment to the reference sequence.",
"Fully unaligned length" : "
is the total number of bases contained in all fully unaligned contigs. Uncalled bases (N's) are not counted.",
- "# partially unaligned contigs" : "
is the number of contigs that have at least one alignment to the reference sequence but also have at least one unaligned fragment of length ≥ unaligned-part-size threshold.",
+ "# partially unaligned contigs" : "
is the number of contigs that have at least one alignment to the reference sequence but also have at least one unaligned fragment of length ≥ unaligned-part-size threshold (uncalled bases (N's) are not counted towards the fragment length).",
"Partially unaligned length" : "
is the total number of unaligned bases in all partially unaligned contigs. Uncalled bases (N's) are not counted.",
"# ambiguous contigs" : "
is the number of contigs that have reference alignments of equal quality in multiple locations on the reference.",
@@ -4776,13 +4773,13 @@
"GC (%)" : "
is the total number of G and C nucleotides in the assembly, divided by the total length of the assembly.",
"Reference GC (%)" : "
is the total number of G and C nucleotides in the reference, divided by the total length of the reference.",
- "# mismatches per 100 kbp" : "
is the average number of mismatches per 100000 aligned bases.",
- "# mismatches" : "
is the number of mismatches in all aligned bases.",
- "# indels per 100 kbp" : "
is the average number of indels per 100000 aligned bases.",
- "# indels" : "
is the number of indels in all aligned bases",
- "# indels (<= 5 bp)" : "
is the number of indels of length less than or equal to 5 bp",
- "# indels (> 5 bp)" : "
is the number of indels of length greater than 5 bp",
- "Indels length" : "
is the number of total bases contained in all indels",
+ "# mismatches per 100 kbp" : "
is the average number of mismatches per 100,000 aligned bases in the assembly.",
+ "# mismatches" : "
is the number of mismatches in all aligned bases in the assembly.",
+ "# indels per 100 kbp" : "
is the average number of indels per 100,000 aligned bases in the assembly.",
+ "# indels" : "
is the number of indels in all aligned bases in the assembly.",
+ "# indels (<= 5 bp)" : "
is the number of indels of length less than or equal to 5 bp.",
+ "# indels (> 5 bp)" : "
is the number of indels of length greater than 5 bp.",
+ "Indels length" : "
is the number of total bases contained in all indels.",
"# genomic features" : "
is the number of genomic features (genes, transcripts, CDS) in the assembly (complete and partial), based on a user-provided annotated list of gene positions in the reference genome. A feature counts as 'partially covered' if the assembly contains at least 100 bp of this feature but not the whole feature.",
"# operons" : "
is the number of operons in the assembly (complete and partial), based on a user-provided annotated list of operon positions in the reference genome. An operon counts as 'partially covered' if the assembly contains at least 100 bp of this operon but not the whole operon.",
@@ -4799,13 +4796,13 @@
"NGAx" : "
plot shows the NGAx metric value as x varies from 0 to 100.NGAx is computed similarly to NGx, but based on lengths of aligned blocks instead of contig lengths. Contigs are broken at misassembly breakpoints. NGAx is the minimum block length y such that using blocks of length at least y accounts for at least x% of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
"GC content" : "
plot shows the distribution of GC percentage among the contigs, i.e., the total number of bases in contigs with such GC content. Typically, the distribution is approximately Gaussian. However, for some genomes it is not Gaussian. For assembly projects with contaminants, the GC distribution of the contaminants often differs from the reference genome and may give a superposition of multiple curves with different peaks.",
- "Duplication ratio" : "
is the total number of aligned bases in the assembly (i.e. Total length - Fully unaligned length - Partially unaligned length), divided by the total number of aligned bases in the reference (see the Genome fraction (%) metric). If the assembly contains many contigs that cover the same regions of the reference, its Duplication ratio may be much larger than 1. This may occur due to overestimating repeat multiplicities and due to small overlaps between contigs, among other reasons.",
+ "Duplication ratio" : "
is the total number of aligned bases in the assembly, divided by the total number of aligned bases in the reference (see the Genome fraction (%) metric). If the assembly contains many contigs that cover the same regions of the reference, its Duplication ratio may be much larger than 1. This may occur due to overestimating repeat multiplicities and due to small overlaps between contigs, among other reasons.",
"Largest alignment" : "
is the length of the largest continuous alignment in the assembly. This metric is always equal to the Largest contig metric but it can be smaller if the largest contig of the assembly contains a misassembly event.",
"Total aligned length" : "
is the total number of aligned bases in the assembly.",
"Avg contig read support" : "
is the average coverage of contigs that have large unique alignments to the reference. Read coverage is extracted from contig names (SPAdes/Velvet naming scheme only).",
"# N's" : "
is the total number of uncalled bases (N's) in the assembly.",
- "# N's per 100 kbp" : "
is the average number of uncalled bases (N's) per 100000 assembly bases.",
+ "# N's per 100 kbp" : "
is the average number of uncalled bases (N's) per 100,000 assembly bases.",
"# mapped" : "
is the number of reads that mapped to the assembly.",
"Mapped (%)" : "
is the percent of reads that mapped to the assembly.",
diff -r 675488238c96 -r 3061c8b029e5 test-data/test2.log
--- a/test-data/test2.log Fri Mar 25 17:36:59 2022 +0000
+++ b/test-data/test2.log Fri Aug 05 15:21:27 2022 +0000
@@ -1,199 +1,199 @@
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/bin/quast --labels contig1,contig2 -o outputdir -r /tmp/tmpmqu3v_ze/files/f/2/0/dataset_f20bc8a3-6ab5-43f7-a0a3-42dcc6408039.dat --features /tmp/tmpmqu3v_ze/files/2/a/f/dataset_2afd5bcc-2ff5-46bc-83cd-0690bcbd9c67.dat --operons /tmp/tmpmqu3v_ze/files/f/f/a/dataset_ffa07559-8af9-4a08-8719-807dc3575dc8.dat --circos --k-mer-stats --k-mer-size 101 --min-contig 500 --min-alignment 65 --min-identity 95.0 --ambiguity-usage one --ambiguity-score 0.99 --contig-thresholds 0,1000 --extensive-mis-size 1000 --scaffold-gap-max-size 1000 --unaligned-part-size 500 /tmp/tmpmqu3v_ze/files/a/e/3/dataset_ae3fd171-9eb4-40d1-a8c8-d896fef3f293.dat /tmp/tmpmqu3v_ze/files/f/c/b/dataset_fcbec1fc-e7c4-42db-b9e4-7c32ac9882dd.dat --threads 1
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/bin/quast --labels contig1,contig2 -o outputdir -r /tmp/tmphjbhe4x0/files/a/d/a/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat --features /tmp/tmphjbhe4x0/files/3/1/a/dataset_31a7a886-1c84-4423-8fc9-cdfda1537f40.dat --operons /tmp/tmphjbhe4x0/files/2/9/8/dataset_29831cd9-b20d-4b69-af42-19aa1c84bbbb.dat --circos --k-mer-stats --k-mer-size 101 --min-identity 95.0 --min-contig 500 --min-alignment 65 --ambiguity-usage one --ambiguity-score 0.99 --local-mis-size 200 --contig-thresholds 0,1000 --extensive-mis-size 1000 --scaffold-gap-max-size 1000 --unaligned-part-size 500 --x-for-Nx 90 /tmp/tmphjbhe4x0/files/d/f/0/dataset_df0f2e39-68eb-4a15-949f-d6678854d50e.dat /tmp/tmphjbhe4x0/files/3/4/7/dataset_34703c25-26f5-4dc0-9211-fc1217c11724.dat --threads 1
-Version: 5.0.2
+Version: 5.2.0
System information:
- OS: Linux-5.13.0-28-generic-x86_64-with-debian-bullseye-sid (linux_64)
- Python version: 3.7.12
+ OS: Linux-5.13.0-51-generic-x86_64-with-glibc2.31 (linux_64)
+ Python version: 3.9.13
CPUs number: 8
-Started: 2022-02-06 19:54:35
+Started: 2022-07-07 16:53:46
-Logging to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/quast.log
-NOTICE: --ambiguity-usage was set to 'all' because not default --ambiguity-score was specified
+Logging to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/quast.log
+WARNING: --ambiguity-usage was set to 'all' because not default --ambiguity-score was specified
-CWD: /tmp/tmpmqu3v_ze/job_working_directory/000/12/working
+CWD: /tmp/tmphjbhe4x0/job_working_directory/000/12/working
Main parameters:
- MODE: default, threads: 1, minimum contig length: 500, minimum alignment length: 65, \
- ambiguity: all, threshold for extensive misassembly size: 1000
+ MODE: default, threads: 1, min contig length: 500, min alignment length: 65, min alignment IDY: 95.0, \
+ ambiguity: all, min local misassembly length: 200, min extensive misassembly length: 1000
Reference:
- /tmp/tmpmqu3v_ze/files/f/2/0/dataset_f20bc8a3-6ab5-43f7-a0a3-42dcc6408039.dat ==> dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039
+ /tmp/tmphjbhe4x0/files/a/d/a/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat ==> dataset_adad470c-d758-46ef-afd5-390f178fb362
Contigs:
Pre-processing...
- 1 /tmp/tmpmqu3v_ze/files/a/e/3/dataset_ae3fd171-9eb4-40d1-a8c8-d896fef3f293.dat ==> contig1
- 2 /tmp/tmpmqu3v_ze/files/f/c/b/dataset_fcbec1fc-e7c4-42db-b9e4-7c32ac9882dd.dat ==> contig2
+ 1 /tmp/tmphjbhe4x0/files/d/f/0/dataset_df0f2e39-68eb-4a15-949f-d6678854d50e.dat ==> contig1
+ 2 /tmp/tmphjbhe4x0/files/3/4/7/dataset_34703c25-26f5-4dc0-9211-fc1217c11724.dat ==> contig2
-2022-02-06 19:54:39
+2022-07-07 16:53:55
Running Basic statistics processor...
Reference genome:
- dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat, length = 6650, num fragments = 1, GC % = 52.00
+ dataset_adad470c-d758-46ef-afd5-390f178fb362.dat, length = 6650, num fragments = 1, GC % = 52.00
Contig files:
1 contig1
2 contig2
Calculating N50 and L50...
- 1 contig1, N50 = 3980, L50 = 1, Total length = 6710, GC % = 51.28, # N's per 100 kbp = 0.00
- 2 contig2, N50 = 6650, L50 = 1, Total length = 6650, GC % = 52.00, # N's per 100 kbp = 0.00
+ 1 contig1, N50 = 3980, L50 = 1, auN = 2934.0, Total length = 6710, GC % = 51.28, # N's per 100 kbp = 0.00
+ 2 contig2, N50 = 6650, L50 = 1, auN = 6650.0, Total length = 6650, GC % = 52.00, # N's per 100 kbp = 0.00
Drawing Nx plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/basic_stats/Nx_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/basic_stats/Nx_plot.pdf
Drawing NGx plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/basic_stats/NGx_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/basic_stats/NGx_plot.pdf
Drawing cumulative plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/basic_stats/cumulative_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/basic_stats/cumulative_plot.pdf
Drawing GC content plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/basic_stats/GC_content_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/basic_stats/GC_content_plot.pdf
Drawing contig1 GC content plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/basic_stats/contig1_GC_content_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/basic_stats/contig1_GC_content_plot.pdf
Drawing contig2 GC content plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/basic_stats/contig2_GC_content_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/basic_stats/contig2_GC_content_plot.pdf
Done.
-2022-02-06 19:54:40
+2022-07-07 16:53:58
Running analysis based on unique 101-mers...
Running KMC on reference...
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc \
--t1 -hp -m2 -n128 -k101 -fm -cx1 -ci1 outputdir/quast_corrected_input/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat \
-outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat.kmc outputdir/k_mer_stats/tmp \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc \
+-t1 -hp -m2 -n128 -k101 -fm -cx1 -ci1 outputdir/quast_corrected_input/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat \
+outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat.kmc outputdir/k_mer_stats/tmp \
>> outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc_tools \
--t1 -hp histogram outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat.kmc \
-outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat.kmc.histo.txt \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc_tools \
+-t1 -hp histogram outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat.kmc \
+outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat.kmc.histo.txt \
>> outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
Analyzing assemblies completeness...
1 contig1
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc \
-t1 -hp -m2 -n128 -k101 -fm -cx1 -ci1 outputdir/quast_corrected_input/contig1 outputdir/k_mer_stats/tmp/contig1.kmc \
outputdir/k_mer_stats/tmp >> outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc_tools \
--t1 -hp simple outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat.kmc \
-outputdir/k_mer_stats/tmp/contig1.kmc intersect outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a_contig1.kmc \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc_tools \
+-t1 -hp simple outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat.kmc \
+outputdir/k_mer_stats/tmp/contig1.kmc intersect outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd_contig1.kmc \
>> outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc_tools \
--t1 -hp histogram outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a_contig1.kmc \
-outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a_contig1.kmc.histo.txt >> \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc_tools \
+-t1 -hp histogram outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd_contig1.kmc \
+outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd_contig1.kmc.histo.txt >> \
outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
2 contig2
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc \
-t1 -hp -m2 -n128 -k101 -fm -cx1 -ci1 outputdir/quast_corrected_input/contig2 outputdir/k_mer_stats/tmp/contig2.kmc \
outputdir/k_mer_stats/tmp >> outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc_tools \
--t1 -hp simple outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat.kmc \
-outputdir/k_mer_stats/tmp/contig2.kmc intersect outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a_contig2.kmc \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc_tools \
+-t1 -hp simple outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat.kmc \
+outputdir/k_mer_stats/tmp/contig2.kmc intersect outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd_contig2.kmc \
>> outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc_tools \
--t1 -hp histogram outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a_contig2.kmc \
-outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a_contig2.kmc.histo.txt >> \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc_tools \
+-t1 -hp histogram outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd_contig2.kmc \
+outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd_contig2.kmc.histo.txt >> \
outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
Analyzing assemblies correctness...
Downsampling k-mers...
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/lib/python3.7/site-packages/quast_libs/kmc/kmc_tools \
--t1 -hp filter outputdir/k_mer_stats/tmp/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat.kmc \
-outputdir/k_mer_stats/tmp/kmers_NC_000913.3_1_6650.fasta -ci1 -fa outputdir/k_mer_stats/tmp/kmers_NC_000913.3_1_6650.filtered.fasta \
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/lib/python3.9/site-packages/quast_libs/kmc/kmc_tools \
+-t1 -hp filter outputdir/k_mer_stats/tmp/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat.kmc \
+outputdir/k_mer_stats/tmp/kmers_NC_000913.3_1-6650.fasta -ci1 -fa outputdir/k_mer_stats/tmp/kmers_NC_000913.3_1-6650.filtered.fasta \
>> outputdir/k_mer_stats/kmc.log 2>> outputdir/k_mer_stats/kmc.err
1 contig1
- /home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/bin/minimap2 \
+ /home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/bin/minimap2 \
-cx sr -s202 --frag=no -t 1 outputdir/quast_corrected_input/contig1 outputdir/k_mer_stats/tmp/kmc.downsampled.txt \
> outputdir/k_mer_stats/tmp/kmers.coords 2>> outputdir/k_mer_stats/kmc.err
2 contig2
- /home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/bin/minimap2 \
+ /home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/bin/minimap2 \
-cx sr -s202 --frag=no -t 1 outputdir/quast_corrected_input/contig2 outputdir/k_mer_stats/tmp/kmc.downsampled.txt \
> outputdir/k_mer_stats/tmp/kmers.coords 2>> outputdir/k_mer_stats/kmc.err
Creating total report...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/k_mer_stats/kmers_report.txt, kmers_report.tsv, and kmers_report.tex
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/k_mer_stats/kmers_report.txt, kmers_report.tsv, and kmers_report.tex
Done.
-2022-02-06 19:54:41
+2022-07-07 16:54:01
Running Contig analyzer...
1 contig1
- 1 Logging to files /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/contigs_reports/contigs_report_contig1.stdout and contigs_report_contig1.stderr...
+ 1 Logging to files /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/contigs_reports/contigs_report_contig1.stdout and contigs_report_contig1.stderr...
1 Aligning contigs to the reference
- 1 /home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/bin/minimap2 \
- -c -x asm5 -B5 -O4,16 --no-long-join -r 85 -N 50 -s 65 -z 200 --mask-level 0.9 \
- --min-occ 200 -g 2500 --score-N 2 --cs -t 1 outputdir/quast_corrected_input/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat \
+ 1 /home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/bin/minimap2 \
+ -c -x asm10 -B5 -O4,16 --no-long-join -r 200 -N 50 -s 65 -z 200 --mask-level \
+ 0.9 --min-occ 200 -g 2500 --score-N 2 --cs -t 1 outputdir/quast_corrected_input/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat \
outputdir/quast_corrected_input/contig1 > outputdir/contigs_reports/minimap_output/contig1.coords_tmp \
2>> outputdir/contigs_reports/contigs_report_contig1.stderr
1 Analysis is finished.
2 contig2
- 2 Logging to files /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/contigs_reports/contigs_report_contig2.stdout and contigs_report_contig2.stderr...
+ 2 Logging to files /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/contigs_reports/contigs_report_contig2.stdout and contigs_report_contig2.stderr...
2 Aligning contigs to the reference
- 2 /home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/bin/minimap2 \
- -c -x asm5 -B5 -O4,16 --no-long-join -r 85 -N 50 -s 65 -z 200 --mask-level 0.9 \
- --min-occ 200 -g 2500 --score-N 2 --cs -t 1 outputdir/quast_corrected_input/dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039.dat \
+ 2 /home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/bin/minimap2 \
+ -c -x asm10 -B5 -O4,16 --no-long-join -r 200 -N 50 -s 65 -z 200 --mask-level \
+ 0.9 --min-occ 200 -g 2500 --score-N 2 --cs -t 1 outputdir/quast_corrected_input/dataset_adad470c-d758-46ef-afd5-390f178fb362.dat \
outputdir/quast_corrected_input/contig2 > outputdir/contigs_reports/minimap_output/contig2.coords_tmp \
2>> outputdir/contigs_reports/contigs_report_contig2.stderr
2 Analysis is finished.
Creating total report...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/contigs_reports/misassemblies_report.txt, misassemblies_report.tsv, and misassemblies_report.tex
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/contigs_reports/misassemblies_report.txt, misassemblies_report.tsv, and misassemblies_report.tex
Transposed version of total report...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/contigs_reports/transposed_report_misassemblies.txt, transposed_report_misassemblies.tsv, and transposed_report_misassemblies.tex
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/contigs_reports/transposed_report_misassemblies.txt, transposed_report_misassemblies.tsv, and transposed_report_misassemblies.tex
Creating total report...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/contigs_reports/unaligned_report.txt, unaligned_report.tsv, and unaligned_report.tex
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/contigs_reports/unaligned_report.txt, unaligned_report.tsv, and unaligned_report.tex
Drawing misassemblies by types plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/contigs_reports/misassemblies_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/contigs_reports/misassemblies_plot.pdf
Drawing misassemblies FRCurve plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/contigs_reports/misassemblies_frcurve_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/contigs_reports/misassemblies_frcurve_plot.pdf
Done.
-2022-02-06 19:54:41
+2022-07-07 16:54:01
Running NA-NGA calculation...
1 contig1, Largest alignment = 2030, NA50 = 1610, NGA50 = 1610, LA50 = 2, LGA50 = 2
2 contig2, Largest alignment = 6650, NA50 = 6650, NGA50 = 6650, LA50 = 1, LGA50 = 1
Drawing cumulative plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/aligned_stats/cumulative_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/aligned_stats/cumulative_plot.pdf
Drawing NAx plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/aligned_stats/NAx_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/aligned_stats/NAx_plot.pdf
Drawing NGAx plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/aligned_stats/NGAx_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/aligned_stats/NGAx_plot.pdf
Done.
-2022-02-06 19:54:42
+2022-07-07 16:54:02
Running Genome analyzer...
Loaded 14 genomic features of type "ANY"
- NOTICE: Reference name in file with genomic features of type "ANY" (NC_000913.3) does not match the name in the reference file (NC_000913.3_1_6650). QUAST will ignore this issue and count as if they match.
+ NOTICE: Reference name in file with genomic features of type "ANY" (NC_000913.3) does not match the name in the reference file (NC_000913.3_1-6650). QUAST will ignore this issue and count as if they match.
WARNING: Incorrect format of operon's file! GFF, NCBI and the plain TXT format accepted. See manual.
-WARNING: /tmp/tmpmqu3v_ze/files/f/f/a/dataset_ffa07559-8af9-4a08-8719-807dc3575dc8.dat was skipped
+WARNING: /tmp/tmphjbhe4x0/files/2/9/8/dataset_29831cd9-b20d-4b69-af42-19aa1c84bbbb.dat was skipped
WARNING: No genomic features of type "operon" were loaded.
1 contig1
1 Analysis is finished.
2 contig2
2 Analysis is finished.
Drawing genomic features cumulative plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/genome_stats/features_cumulative_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/genome_stats/features_cumulative_plot.pdf
Drawing genomic features FRCurve plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/genome_stats/features_frcurve_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/genome_stats/features_frcurve_plot.pdf
Drawing # complete genomic features histogram...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/genome_stats/complete_features_histogram.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/genome_stats/complete_features_histogram.pdf
Drawing Genome fraction, % histogram...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/genome_stats/genome_fraction_histogram.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/genome_stats/genome_fraction_histogram.pdf
Done.
NOTICE: Genes are not predicted by default. Use --gene-finding or --glimmer option to enable it.
-2022-02-06 19:54:42
+2022-07-07 16:54:04
Creating large visual summaries...
This may take a while: press Ctrl-C to skip this step..
- 1 of 3: Creating Icarus viewers...
- 2 of 3: Creating Circos plot...
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/bin/circos \
+ 1 of 3: Creating PDF with all tables and plots...
+ 2 of 3: Creating Icarus viewers...
+ 3 of 3: Creating Circos plot...
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/bin/circos \
-conf outputdir/circos/circos.conf > outputdir/circos/circos.log 2> outputdir/circos/circos.err
- 3 of 3: Creating PDF with all tables and plots...
Done
-2022-02-06 19:54:46
+2022-07-07 16:54:16
RESULTS:
- Text versions of total report are saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/report.txt, report.tsv, and report.tex
- Text versions of transposed total report are saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/transposed_report.txt, transposed_report.tsv, and transposed_report.tex
- HTML version (interactive tables and plots) is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/report.html
- PDF version (tables and plots) is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/report.pdf
- Circos plot is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/circos/circos.png (legend is in legend.txt, configuration file is in circos.conf)
- Icarus (contig browser) is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/icarus.html
- Log is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/12/working/outputdir/quast.log
+ Text versions of total report are saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/report.txt, report.tsv, and report.tex
+ Text versions of transposed total report are saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/transposed_report.txt, transposed_report.tsv, and transposed_report.tex
+ HTML version (interactive tables and plots) is saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/report.html
+ PDF version (tables and plots) is saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/report.pdf
+ Circos plot is saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/circos/circos.png (legend is in legend.txt, configuration file is in circos.conf)
+ Icarus (contig browser) is saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/icarus.html
+ Log is saved to /tmp/tmphjbhe4x0/job_working_directory/000/12/working/outputdir/quast.log
-Finished: 2022-02-06 19:54:46
-Elapsed time: 0:00:11.313989
-NOTICEs: 3; WARNINGs: 3; non-fatal ERRORs: 0
+Finished: 2022-07-07 16:54:16
+Elapsed time: 0:00:30.044753
+NOTICEs: 2; WARNINGs: 4; non-fatal ERRORs: 0
Thank you for using QUAST!
diff -r 675488238c96 -r 3061c8b029e5 test-data/test2_report.html
--- a/test-data/test2_report.html Fri Mar 25 17:36:59 2022 +0000
+++ b/test-data/test2_report.html Fri Aug 05 15:21:27 2022 +0000
@@ -4639,7 +4639,7 @@
- {"date":"06 February 2022, Sunday, 19:54:46","assembliesNames":["contig1","contig2"],"referenceName":"dataset_f20bc8a3_6ab5_43f7_a0a3_42dcc6408039","order":[0,1],"report":[["Genome statistics",[{"metricName":"Genome fraction (%)","quality":"More is better","values":["71.579","100.000"],"isMain":true},{"metricName":"Duplication ratio","quality":"Less is better","values":["1.000","1.000"],"isMain":true},{"metricName":"# genomic features","quality":"More is better","values":["7 + 7 part","13 + 1 part"],"isMain":true},{"metricName":"Largest alignment","quality":"More is better","values":[2030,6650],"isMain":true},{"metricName":"Total aligned length","quality":"More is better","values":[4760,6650],"isMain":true},{"metricName":"NG50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"NG75","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"NA50","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"NA75","quality":"More is better","values":[null,6650],"isMain":false},{"metricName":"NGA50","quality":"More is better","values":[1610,6650],"isMain":true},{"metricName":"NGA75","quality":"More is better","values":[null,6650],"isMain":false},{"metricName":"LG50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"LG75","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"LA50","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"LA75","quality":"Less is better","values":[null,1],"isMain":false},{"metricName":"LGA50","quality":"Less is better","values":[2,1],"isMain":true},{"metricName":"LGA75","quality":"Less is better","values":[null,1],"isMain":false}]],["Reads mapping",[]],["Misassemblies",[{"metricName":"# misassemblies","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":" # relocations","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # translocations","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # inversions","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# misassembled contigs","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Misassembled contigs length","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":"# local misassemblies","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# scaffold gap ext. mis.","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# scaffold gap loc. mis.","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# unaligned mis. contigs","quality":"Less is better","values":[0,0],"isMain":false}]],["Unaligned",[{"metricName":"# fully unaligned contigs","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Fully unaligned length","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# partially unaligned contigs","quality":"Less is better","values":[1,0],"isMain":false},{"metricName":"Partially unaligned length","quality":"Less is better","values":[1950,0],"isMain":false}]],["Mismatches",[{"metricName":"# mismatches","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# indels","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Indels length","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# mismatches per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# indels per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":" # indels (<= 5 bp)","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # indels (> 5 bp)","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# N's","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# N's per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true}]],["Statistics without reference",[{"metricName":"# contigs","quality":"Equal","values":[3,1],"isMain":true},{"metricName":"# contigs (>= 0 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"# contigs (>= 1000 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"Largest contig","quality":"More is better","values":[3980,6650],"isMain":true},{"metricName":"Total length","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"Total length (>= 0 bp)","quality":"More is better","values":[6710,6650],"isMain":false},{"metricName":"Total length (>= 1000 bp)","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"N50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"N75","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"L50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"L75","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"GC (%)","quality":"Equal","values":["51.28","52.00"],"isMain":false}]],["K-mer-based statistics",[{"metricName":"K-mer-based compl. (%)","quality":"More is better","values":["68.09","100.00"],"isMain":true},{"metricName":"K-mer-based cor. length (%)","quality":"More is better","values":["100.00","100.00"],"isMain":false},{"metricName":"K-mer-based mis. length (%)","quality":"Less is better","values":["0.00","0.00"],"isMain":false},{"metricName":"K-mer-based undef. length (%)","quality":"Less is better","values":["0.00","0.00"],"isMain":false},{"metricName":"# k-mer-based misjoins","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":" # k-mer-based translocations","quality":"Equal","values":[0,0],"isMain":false},{"metricName":" # k-mer-based 100kbp relocations","quality":"Equal","values":[0,0],"isMain":false}]],["Predicted genes",[]],["Similarity statistics",[{"metricName":"# similar correct contigs","quality":"Equal","values":[0,0],"isMain":false},{"metricName":"# similar misassembled blocks","quality":"Equal","values":[0,0],"isMain":false}]],["Reference statistics",[{"metricName":"Reference length","quality":"Equal","values":[6650,6650],"isMain":false},{"metricName":"Reference fragments","quality":"Equal","values":[1,1],"isMain":false},{"metricName":"Reference GC (%)","quality":"Equal","values":["52.00","52.00"],"isMain":false},{"metricName":"Reference genomic features","quality":"Equal","values":[14,14],"isMain":false},{"metricName":"Reference operons","quality":"Equal","values":[0,0],"isMain":false}]]],"subreferences":[],"subreports":[],"minContig":500}
+ {"date":"07 July 2022, Thursday, 16:54:16","assembliesNames":["contig1","contig2"],"referenceName":"dataset_adad470c-d758-46ef-afd5-390f178fb362","order":[0,1],"report":[["Genome statistics",[{"metricName":"Genome fraction (%)","quality":"More is better","values":["71.579","100.000"],"isMain":true},{"metricName":"Duplication ratio","quality":"Less is better","values":["1.000","1.000"],"isMain":true},{"metricName":"# genomic features","quality":"More is better","values":["7 + 7 part","13 + 1 part"],"isMain":true},{"metricName":"Largest alignment","quality":"More is better","values":[2030,6650],"isMain":true},{"metricName":"Total aligned length","quality":"More is better","values":[4760,6650],"isMain":true},{"metricName":"NG50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"NG90","quality":"More is better","values":[1120,6650],"isMain":false},{"metricName":"auNG","quality":"More is better","values":["2960.4","6650.0"],"isMain":false},{"metricName":"NA50","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"NA90","quality":"More is better","values":[null,6650],"isMain":false},{"metricName":"auNA","quality":"More is better","values":["1187.4","6650.0"],"isMain":false},{"metricName":"NGA50","quality":"More is better","values":[1610,6650],"isMain":true},{"metricName":"NGA90","quality":"More is better","values":[null,6650],"isMain":false},{"metricName":"auNGA","quality":"More is better","values":["1198.1","6650.0"],"isMain":false},{"metricName":"LG50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"LG90","quality":"Less is better","values":[3,1],"isMain":false},{"metricName":"LA50","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"LA90","quality":"Less is better","values":[null,1],"isMain":false},{"metricName":"LGA50","quality":"Less is better","values":[2,1],"isMain":true},{"metricName":"LGA90","quality":"Less is better","values":[null,1],"isMain":false}]],["Reads mapping",[]],["Misassemblies",[{"metricName":"# misassemblies","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":" # relocations","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # translocations","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # inversions","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# misassembled contigs","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Misassembled contigs length","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":"# local misassemblies","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# scaffold gap ext. mis.","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# scaffold gap loc. mis.","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# unaligned mis. contigs","quality":"Less is better","values":[0,0],"isMain":false}]],["Unaligned",[{"metricName":"# fully unaligned contigs","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Fully unaligned length","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# partially unaligned contigs","quality":"Less is better","values":[1,0],"isMain":false},{"metricName":"Partially unaligned length","quality":"Less is better","values":[1950,0],"isMain":false}]],["Mismatches",[{"metricName":"# mismatches per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# mismatches","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# indels per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# indels","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # indels (<= 5 bp)","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":" # indels (> 5 bp)","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"Indels length","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# N's per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# N's","quality":"Less is better","values":[0,0],"isMain":false}]],["Statistics without reference",[{"metricName":"# contigs","quality":"Equal","values":[3,1],"isMain":true},{"metricName":"# contigs (>= 0 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"# contigs (>= 1000 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"Largest contig","quality":"More is better","values":[3980,6650],"isMain":true},{"metricName":"Total length","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"Total length (>= 0 bp)","quality":"More is better","values":[6710,6650],"isMain":false},{"metricName":"Total length (>= 1000 bp)","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"N50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"N90","quality":"More is better","values":[1120,6650],"isMain":false},{"metricName":"auN","quality":"More is better","values":["2934.0","6650.0"],"isMain":false},{"metricName":"L50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"L90","quality":"Less is better","values":[3,1],"isMain":false},{"metricName":"GC (%)","quality":"Equal","values":["51.28","52.00"],"isMain":false}]],["K-mer-based statistics",[{"metricName":"K-mer-based compl. (%)","quality":"More is better","values":["68.09","100.00"],"isMain":true},{"metricName":"K-mer-based cor. length (%)","quality":"More is better","values":["100.00","100.00"],"isMain":false},{"metricName":"K-mer-based mis. length (%)","quality":"Less is better","values":["0.00","0.00"],"isMain":false},{"metricName":"K-mer-based undef. length (%)","quality":"Less is better","values":["0.00","0.00"],"isMain":false},{"metricName":"# k-mer-based misjoins","quality":"Less is better","values":[0,0],"isMain":true},{"metricName":" # k-mer-based translocations","quality":"Equal","values":[0,0],"isMain":false},{"metricName":" # k-mer-based 100kbp relocations","quality":"Equal","values":[0,0],"isMain":false}]],["Predicted genes",[]],["Similarity statistics",[{"metricName":"# similar correct contigs","quality":"Equal","values":[0,0],"isMain":false},{"metricName":"# similar misassembled blocks","quality":"Equal","values":[0,0],"isMain":false}]],["Reference statistics",[{"metricName":"Reference length","quality":"Equal","values":[6650,6650],"isMain":false},{"metricName":"Reference fragments","quality":"Equal","values":[1,1],"isMain":false},{"metricName":"Reference GC (%)","quality":"Equal","values":["52.00","52.00"],"isMain":false},{"metricName":"Reference genomic features","quality":"Equal","values":[14,14],"isMain":false},{"metricName":"Reference operons","quality":"Equal","values":[0,0],"isMain":false}]]],"subreferences":[],"subreports":[],"minContig":500}
{{ qualities }}
@@ -4720,27 +4720,24 @@
"# contigs (>= 0 bp)" : "
is the total number of contigs in the assembly that have size greater than or equal to 0 bp.",
"Total length (>= 0 bp)" : "
is the total number of bases in the contigs having size greater than or equal to 0 bp.",
- "N50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the assembly. Usually there is no value that produces exactly 50%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 50% of the total assembly length.",
- "NG50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
- "N75" : "
is the contig length such that using longer or equal length contigs produces 75% of the bases of the assembly. Usually there is no value that produces exactly 75%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 75% of the total assembly length.",
- "NG75" : "
is the contig length such that using longer or equal length contigs produces 75% of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
-
- "L50" : "
is the minimum number of contigs that produce half (50%) of the bases of the assembly. In other words, it's the number of contigs of length at least N50.",
- "LG50" : "
is the minimum number of contigs that produce half (50%) of the bases of the reference genome. In other words, it's the number of contigs of length at least NG50. This metric is computed only if a reference genome is provided.",
- "L75" : "
is the minimum number of contigs that produce 75% of the bases of the assembly. In other words, it's the number of contigs of length at least N75.",
- "LG75" : "
is the minimum number of contigs that produce 75% of the bases of the reference genome. In other words, it's the number of contigs of length at least NG75. This metric is computed only if a reference genome is provided.",
-
- "NA50" : "
is N50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NGA50" : "
is NG50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NA75" : "
is N75 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NGA75" : "
is NG75 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
-
- "LA50" : "
is L50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LGA50" : "
is LG50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LA75" : "
is L75 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LGA75" : "
is LG75 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
-
- "Average %IDY" : "
is the average of alignment identity percent (Nucmer measure of alignment accuracy) among all contigs.",
+ "N50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the assembly. Usually there is no value that produces exactly 50%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 50% of the total assembly length. Similarly, Nx for any x between 0 and 100 could be computed (x% of assembly).",
+ "NG50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the reference genome. This metric is computed only if a reference genome is provided. Similarly, NGx for any x between 0 and 100 could be computed (x% of the reference).",
+
+ "L50" : "
is the minimum number of contigs that produce half (50%) of the bases of the assembly. In other words, it's the number of contigs of length at least N50. Similarly, Lx for any x between 0 and 100 could be computed.",
+ "LG50" : "
is the minimum number of contigs that produce half (50%) of the bases of the reference genome. In other words, it's the number of contigs of length at least NG50. This metric is computed only if a reference genome is provided. Similarly, LGx for any x between 0 and 100 could be computed.",
+
+ "NA50" : "
is N50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided. Similarly, NAx for any x between 0 and 100 could be computed.",
+ "NGA50" : "
is NG50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided. Similarly, NGAx for any x between 0 and 100 could be computed.",
+
+ "LA50" : "
is L50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. Similarly, LAx for any x between 0 and 100 could be computed.",
+ "LGA50" : "
is LG50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. Similarly, LGAx for any x between 0 and 100 could be computed.",
+
+ "auN" : "
is the area under the Nx curve.",
+ "auNG" : "
is the area under the NGx curve.",
+ "auNA" : "
is the area under the NAx curve.",
+ "auNGA" : "
is the area under the NGAx curve.",
+
+ "Average %IDY" : "
is the average of alignment identity percent (alignment accuracy) among all contigs.",
"# misassemblies" : "
is the number of positions in the assembled contigs where the left flanking sequence aligns over 1 kbp away from the right flanking sequence on the reference (relocation) or they overlap on more than 1 kbp (relocation) or flanking sequences align on different strands (inversion) or different chromosomes (translocation).",
"# large block misassemblies" : "
is the number of misassemblies between alignments with length greater than or equal to 3 kbp and with the misassembly threshold equal to 5 kbp (instead of default 1 kbp for regular misassemblies).",
"# misassembled contigs" : "
is the number of contigs that contain misassembly events.",
@@ -4762,11 +4759,11 @@
"# intergenomic misassemblies" : "
is the number of all found and putative (possible) interspecies translocations.",
"# structural variations" : "
is the number of misassemblies matched with structural variations.",
"# possible TEs" : "
is the number of misassemblies possibly caused by transposable elements (TEs). We define a possible TE as an event that satisfies these conditions: - There are two misassembly breakpoints of the same type around a short alignment (less than 7 kbp by default)
- The gap between two long flanking sequences on the sides of the short alignment is less than 7 kbp.
- The long flanking sequences both are on the same strand of the same chromosome of the reference genome.
",
- "# unaligned mis. contigs" : "
is the number of contigs that have the number of unaligned bases more than 50% of contig length and a misassembly event in their aligned fragment. Note that such misassemblies are not counted in # misassemblies and other misassemblies statistics.",
+ "# unaligned mis. contigs" : "
is the number of contigs that have the number of unaligned bases more than 50% of the contig length and a misassembly event in their aligned fragment. Note that such misassemblies are not counted in # misassemblies and other misassemblies statistics.",
"# fully unaligned contigs" : "
is the number of contigs that have no alignment to the reference sequence.",
"Fully unaligned length" : "
is the total number of bases contained in all fully unaligned contigs. Uncalled bases (N's) are not counted.",
- "# partially unaligned contigs" : "
is the number of contigs that have at least one alignment to the reference sequence but also have at least one unaligned fragment of length ≥ unaligned-part-size threshold.",
+ "# partially unaligned contigs" : "
is the number of contigs that have at least one alignment to the reference sequence but also have at least one unaligned fragment of length ≥ unaligned-part-size threshold (uncalled bases (N's) are not counted towards the fragment length).",
"Partially unaligned length" : "
is the total number of unaligned bases in all partially unaligned contigs. Uncalled bases (N's) are not counted.",
"# ambiguous contigs" : "
is the number of contigs that have reference alignments of equal quality in multiple locations on the reference.",
@@ -4776,13 +4773,13 @@
"GC (%)" : "
is the total number of G and C nucleotides in the assembly, divided by the total length of the assembly.",
"Reference GC (%)" : "
is the total number of G and C nucleotides in the reference, divided by the total length of the reference.",
- "# mismatches per 100 kbp" : "
is the average number of mismatches per 100000 aligned bases.",
- "# mismatches" : "
is the number of mismatches in all aligned bases.",
- "# indels per 100 kbp" : "
is the average number of indels per 100000 aligned bases.",
- "# indels" : "
is the number of indels in all aligned bases",
- "# indels (<= 5 bp)" : "
is the number of indels of length less than or equal to 5 bp",
- "# indels (> 5 bp)" : "
is the number of indels of length greater than 5 bp",
- "Indels length" : "
is the number of total bases contained in all indels",
+ "# mismatches per 100 kbp" : "
is the average number of mismatches per 100,000 aligned bases in the assembly.",
+ "# mismatches" : "
is the number of mismatches in all aligned bases in the assembly.",
+ "# indels per 100 kbp" : "
is the average number of indels per 100,000 aligned bases in the assembly.",
+ "# indels" : "
is the number of indels in all aligned bases in the assembly.",
+ "# indels (<= 5 bp)" : "
is the number of indels of length less than or equal to 5 bp.",
+ "# indels (> 5 bp)" : "
is the number of indels of length greater than 5 bp.",
+ "Indels length" : "
is the number of total bases contained in all indels.",
"# genomic features" : "
is the number of genomic features (genes, transcripts, CDS) in the assembly (complete and partial), based on a user-provided annotated list of gene positions in the reference genome. A feature counts as 'partially covered' if the assembly contains at least 100 bp of this feature but not the whole feature.",
"# operons" : "
is the number of operons in the assembly (complete and partial), based on a user-provided annotated list of operon positions in the reference genome. An operon counts as 'partially covered' if the assembly contains at least 100 bp of this operon but not the whole operon.",
@@ -4799,13 +4796,13 @@
"NGAx" : "
plot shows the NGAx metric value as x varies from 0 to 100.NGAx is computed similarly to NGx, but based on lengths of aligned blocks instead of contig lengths. Contigs are broken at misassembly breakpoints. NGAx is the minimum block length y such that using blocks of length at least y accounts for at least x% of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
"GC content" : "
plot shows the distribution of GC percentage among the contigs, i.e., the total number of bases in contigs with such GC content. Typically, the distribution is approximately Gaussian. However, for some genomes it is not Gaussian. For assembly projects with contaminants, the GC distribution of the contaminants often differs from the reference genome and may give a superposition of multiple curves with different peaks.",
- "Duplication ratio" : "
is the total number of aligned bases in the assembly (i.e. Total length - Fully unaligned length - Partially unaligned length), divided by the total number of aligned bases in the reference (see the Genome fraction (%) metric). If the assembly contains many contigs that cover the same regions of the reference, its Duplication ratio may be much larger than 1. This may occur due to overestimating repeat multiplicities and due to small overlaps between contigs, among other reasons.",
+ "Duplication ratio" : "
is the total number of aligned bases in the assembly, divided by the total number of aligned bases in the reference (see the Genome fraction (%) metric). If the assembly contains many contigs that cover the same regions of the reference, its Duplication ratio may be much larger than 1. This may occur due to overestimating repeat multiplicities and due to small overlaps between contigs, among other reasons.",
"Largest alignment" : "
is the length of the largest continuous alignment in the assembly. This metric is always equal to the Largest contig metric but it can be smaller if the largest contig of the assembly contains a misassembly event.",
"Total aligned length" : "
is the total number of aligned bases in the assembly.",
"Avg contig read support" : "
is the average coverage of contigs that have large unique alignments to the reference. Read coverage is extracted from contig names (SPAdes/Velvet naming scheme only).",
"# N's" : "
is the total number of uncalled bases (N's) in the assembly.",
- "# N's per 100 kbp" : "
is the average number of uncalled bases (N's) per 100000 assembly bases.",
+ "# N's per 100 kbp" : "
is the average number of uncalled bases (N's) per 100,000 assembly bases.",
"# mapped" : "
is the number of reads that mapped to the assembly.",
"Mapped (%)" : "
is the percent of reads that mapped to the assembly.",
diff -r 675488238c96 -r 3061c8b029e5 test-data/test2_report.pdf
Binary file test-data/test2_report.pdf has changed
diff -r 675488238c96 -r 3061c8b029e5 test-data/test2_report.tab
--- a/test-data/test2_report.tab Fri Mar 25 17:36:59 2022 +0000
+++ b/test-data/test2_report.tab Fri Aug 05 15:21:27 2022 +0000
@@ -11,12 +11,14 @@
Reference GC (%) 52.00 52.00
N50 3980 6650
NG50 3980 6650
-N75 1610 6650
-NG75 1610 6650
+N90 1120 6650
+NG90 1120 6650
+auN 2934.0 6650.0
+auNG 2960.4 6650.0
L50 1 1
LG50 1 1
-L75 2 1
-LG75 2 1
+L90 3 1
+LG90 3 1
# misassemblies 0 0
# misassembled contigs 0 0
Misassembled contigs length 0 0
@@ -36,12 +38,14 @@
Total aligned length 4760 6650
NA50 1610 6650
NGA50 1610 6650
-NA75 - 6650
-NGA75 - 6650
+NA90 - 6650
+NGA90 - 6650
+auNA 1187.4 6650.0
+auNGA 1198.1 6650.0
LA50 2 1
LGA50 2 1
-LA75 - 1
-LGA75 - 1
+LA90 - 1
+LGA90 - 1
K-mer-based compl. (%) 68.09 100.00
K-mer-based cor. length (%) 100.00 100.00
K-mer-based mis. length (%) 0.00 0.00
diff -r 675488238c96 -r 3061c8b029e5 test-data/test3.log
--- a/test-data/test3.log Fri Mar 25 17:36:59 2022 +0000
+++ b/test-data/test3.log Fri Aug 05 15:21:27 2022 +0000
@@ -1,67 +1,67 @@
-/home/laptop/miniconda3/envs/mulled-v1-77a890c6a67835ab995adc5c8cf65f55886a6cbedc27599b62f1d6a231bcca56/bin/quast --labels contigs1_fna,contigs2_fna -o outputdir --eukaryote --min-contig 500 --min-alignment 65 --min-identity 95.0 --ambiguity-usage one --ambiguity-score 0.99 --contig-thresholds 0,1000,500 --extensive-mis-size 1000 --scaffold-gap-max-size 1000 --unaligned-part-size 500 --skip-unaligned-mis-contigs /tmp/tmpmqu3v_ze/files/c/a/f/dataset_cafcd90b-16e7-46aa-8617-cdefd1766b23.dat /tmp/tmpmqu3v_ze/files/6/4/e/dataset_64ec6db4-a92f-4ec5-b641-96e96830b6b5.dat --threads 1
+/home/laptop/miniconda3/envs/mulled-v1-92b15e9954bc988dbc8d54298d41c8a76a5ff384441fcf564162dec5c1c0faf0/bin/quast --labels contigs1_fna,contigs2_fna -o outputdir --eukaryote --min-identity 95.0 --min-contig 500 --min-alignment 65 --ambiguity-usage one --ambiguity-score 0.99 --local-mis-size 200 --contig-thresholds 0,1000,500 --extensive-mis-size 1000 --scaffold-gap-max-size 1000 --unaligned-part-size 500 --skip-unaligned-mis-contigs --x-for-Nx 90 /tmp/tmphjbhe4x0/files/0/2/b/dataset_02bce539-33f0-4693-bfe9-a92ebf1615f8.dat /tmp/tmphjbhe4x0/files/6/0/2/dataset_60253425-26a2-4019-bae6-07285864be68.dat --threads 1
-Version: 5.0.2
+Version: 5.2.0
System information:
- OS: Linux-5.13.0-28-generic-x86_64-with-debian-bullseye-sid (linux_64)
- Python version: 3.7.12
+ OS: Linux-5.13.0-51-generic-x86_64-with-glibc2.31 (linux_64)
+ Python version: 3.9.13
CPUs number: 8
-Started: 2022-02-06 19:55:07
+Started: 2022-07-07 16:55:02
-Logging to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/quast.log
-NOTICE: --ambiguity-usage was set to 'all' because not default --ambiguity-score was specified
+Logging to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/quast.log
+WARNING: --ambiguity-usage was set to 'all' because not default --ambiguity-score was specified
-CWD: /tmp/tmpmqu3v_ze/job_working_directory/000/15/working
+CWD: /tmp/tmphjbhe4x0/job_working_directory/000/15/working
Main parameters:
- MODE: default, threads: 1, eukaryotic: true, minimum contig length: 500, minimum alignment length: 65, \
- ambiguity: all, threshold for extensive misassembly size: 1000
+ MODE: default, threads: 1, eukaryotic: true, min contig length: 500, min alignment length: 65, \
+ min alignment IDY: 95.0, ambiguity: all, min local misassembly length: 200, min extensive misassembly length: 1000
Contigs:
Pre-processing...
- 1 /tmp/tmpmqu3v_ze/files/c/a/f/dataset_cafcd90b-16e7-46aa-8617-cdefd1766b23.dat ==> contigs1_fna
- 2 /tmp/tmpmqu3v_ze/files/6/4/e/dataset_64ec6db4-a92f-4ec5-b641-96e96830b6b5.dat ==> contigs2_fna
+ 1 /tmp/tmphjbhe4x0/files/0/2/b/dataset_02bce539-33f0-4693-bfe9-a92ebf1615f8.dat ==> contigs1_fna
+ 2 /tmp/tmphjbhe4x0/files/6/0/2/dataset_60253425-26a2-4019-bae6-07285864be68.dat ==> contigs2_fna
-2022-02-06 19:55:10
+2022-07-07 16:55:11
Running Basic statistics processor...
Contig files:
1 contigs1_fna
2 contigs2_fna
Calculating N50 and L50...
- 1 contigs1_fna, N50 = 3980, L50 = 1, Total length = 6710, GC % = 51.28, # N's per 100 kbp = 0.00
- 2 contigs2_fna, N50 = 6650, L50 = 1, Total length = 6650, GC % = 52.00, # N's per 100 kbp = 0.00
+ 1 contigs1_fna, N50 = 3980, L50 = 1, auN = 2934.0, Total length = 6710, GC % = 51.28, # N's per 100 kbp = 0.00
+ 2 contigs2_fna, N50 = 6650, L50 = 1, auN = 6650.0, Total length = 6650, GC % = 52.00, # N's per 100 kbp = 0.00
Drawing Nx plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/basic_stats/Nx_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/basic_stats/Nx_plot.pdf
Drawing cumulative plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/basic_stats/cumulative_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/basic_stats/cumulative_plot.pdf
Drawing GC content plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/basic_stats/GC_content_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/basic_stats/GC_content_plot.pdf
Drawing contigs1_fna GC content plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/basic_stats/contigs1_fna_GC_content_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/basic_stats/contigs1_fna_GC_content_plot.pdf
Drawing contigs2_fna GC content plot...
- saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/basic_stats/contigs2_fna_GC_content_plot.pdf
+ saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/basic_stats/contigs2_fna_GC_content_plot.pdf
Done.
NOTICE: Genes are not predicted by default. Use --gene-finding or --glimmer option to enable it.
-2022-02-06 19:55:11
+2022-07-07 16:55:13
Creating large visual summaries...
This may take a while: press Ctrl-C to skip this step..
- 1 of 2: Creating Icarus viewers...
- 2 of 2: Creating PDF with all tables and plots...
+ 1 of 2: Creating PDF with all tables and plots...
+ 2 of 2: Creating Icarus viewers...
Done
-2022-02-06 19:55:12
+2022-07-07 16:55:14
RESULTS:
- Text versions of total report are saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/report.txt, report.tsv, and report.tex
- Text versions of transposed total report are saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/transposed_report.txt, transposed_report.tsv, and transposed_report.tex
- HTML version (interactive tables and plots) is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/report.html
- PDF version (tables and plots) is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/report.pdf
- Icarus (contig browser) is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/icarus.html
- Log is saved to /tmp/tmpmqu3v_ze/job_working_directory/000/15/working/outputdir/quast.log
+ Text versions of total report are saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/report.txt, report.tsv, and report.tex
+ Text versions of transposed total report are saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/transposed_report.txt, transposed_report.tsv, and transposed_report.tex
+ HTML version (interactive tables and plots) is saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/report.html
+ PDF version (tables and plots) is saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/report.pdf
+ Icarus (contig browser) is saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/icarus.html
+ Log is saved to /tmp/tmphjbhe4x0/job_working_directory/000/15/working/outputdir/quast.log
-Finished: 2022-02-06 19:55:12
-Elapsed time: 0:00:04.673393
-NOTICEs: 2; WARNINGs: 0; non-fatal ERRORs: 0
+Finished: 2022-07-07 16:55:14
+Elapsed time: 0:00:11.737584
+NOTICEs: 1; WARNINGs: 1; non-fatal ERRORs: 0
Thank you for using QUAST!
diff -r 675488238c96 -r 3061c8b029e5 test-data/test3_report.html
--- a/test-data/test3_report.html Fri Mar 25 17:36:59 2022 +0000
+++ b/test-data/test3_report.html Fri Aug 05 15:21:27 2022 +0000
@@ -4639,7 +4639,7 @@
- {"date":"06 February 2022, Sunday, 19:55:12","assembliesNames":["contigs1_fna","contigs2_fna"],"referenceName":"","order":[0,1],"report":[["Genome statistics",[]],["Reads mapping",[]],["Misassemblies",[]],["Unaligned",[]],["Mismatches",[{"metricName":"# N's","quality":"Less is better","values":[0,0],"isMain":false},{"metricName":"# N's per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true}]],["Statistics without reference",[{"metricName":"# contigs","quality":"Equal","values":[3,1],"isMain":true},{"metricName":"# contigs (>= 0 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"# contigs (>= 1000 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"# contigs (>= 500 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"Largest contig","quality":"More is better","values":[3980,6650],"isMain":true},{"metricName":"Total length","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"Total length (>= 0 bp)","quality":"More is better","values":[6710,6650],"isMain":false},{"metricName":"Total length (>= 1000 bp)","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"Total length (>= 500 bp)","quality":"More is better","values":[6710,6650],"isMain":false},{"metricName":"N50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"N75","quality":"More is better","values":[1610,6650],"isMain":false},{"metricName":"L50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"L75","quality":"Less is better","values":[2,1],"isMain":false},{"metricName":"GC (%)","quality":"Equal","values":["51.28","52.00"],"isMain":false}]],["K-mer-based statistics",[]],["Predicted genes",[]],["Similarity statistics",[]],["Reference statistics",[]]],"subreferences":[],"subreports":[],"minContig":500}
+ {"date":"07 July 2022, Thursday, 16:55:14","assembliesNames":["contigs1_fna","contigs2_fna"],"referenceName":"","order":[0,1],"report":[["Genome statistics",[]],["Reads mapping",[]],["Misassemblies",[]],["Unaligned",[]],["Mismatches",[{"metricName":"# N's per 100 kbp","quality":"Less is better","values":["0.00","0.00"],"isMain":true},{"metricName":"# N's","quality":"Less is better","values":[0,0],"isMain":false}]],["Statistics without reference",[{"metricName":"# contigs","quality":"Equal","values":[3,1],"isMain":true},{"metricName":"# contigs (>= 0 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"# contigs (>= 1000 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"# contigs (>= 500 bp)","quality":"Equal","values":[3,1],"isMain":false},{"metricName":"Largest contig","quality":"More is better","values":[3980,6650],"isMain":true},{"metricName":"Total length","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"Total length (>= 0 bp)","quality":"More is better","values":[6710,6650],"isMain":false},{"metricName":"Total length (>= 1000 bp)","quality":"More is better","values":[6710,6650],"isMain":true},{"metricName":"Total length (>= 500 bp)","quality":"More is better","values":[6710,6650],"isMain":false},{"metricName":"N50","quality":"More is better","values":[3980,6650],"isMain":false},{"metricName":"N90","quality":"More is better","values":[1120,6650],"isMain":false},{"metricName":"auN","quality":"More is better","values":["2934.0","6650.0"],"isMain":false},{"metricName":"L50","quality":"Less is better","values":[1,1],"isMain":false},{"metricName":"L90","quality":"Less is better","values":[3,1],"isMain":false},{"metricName":"GC (%)","quality":"Equal","values":["51.28","52.00"],"isMain":false}]],["K-mer-based statistics",[]],["Predicted genes",[]],["Similarity statistics",[]],["Reference statistics",[]]],"subreferences":[],"subreports":[],"minContig":500}
{{ qualities }}
@@ -4720,27 +4720,24 @@
"# contigs (>= 0 bp)" : "
is the total number of contigs in the assembly that have size greater than or equal to 0 bp.",
"Total length (>= 0 bp)" : "
is the total number of bases in the contigs having size greater than or equal to 0 bp.",
- "N50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the assembly. Usually there is no value that produces exactly 50%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 50% of the total assembly length.",
- "NG50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
- "N75" : "
is the contig length such that using longer or equal length contigs produces 75% of the bases of the assembly. Usually there is no value that produces exactly 75%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 75% of the total assembly length.",
- "NG75" : "
is the contig length such that using longer or equal length contigs produces 75% of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
-
- "L50" : "
is the minimum number of contigs that produce half (50%) of the bases of the assembly. In other words, it's the number of contigs of length at least N50.",
- "LG50" : "
is the minimum number of contigs that produce half (50%) of the bases of the reference genome. In other words, it's the number of contigs of length at least NG50. This metric is computed only if a reference genome is provided.",
- "L75" : "
is the minimum number of contigs that produce 75% of the bases of the assembly. In other words, it's the number of contigs of length at least N75.",
- "LG75" : "
is the minimum number of contigs that produce 75% of the bases of the reference genome. In other words, it's the number of contigs of length at least NG75. This metric is computed only if a reference genome is provided.",
-
- "NA50" : "
is N50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NGA50" : "
is NG50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NA75" : "
is N75 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
- "NGA75" : "
is NG75 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided.",
-
- "LA50" : "
is L50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LGA50" : "
is LG50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LA75" : "
is L75 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
- "LGA75" : "
is LG75 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces.",
-
- "Average %IDY" : "
is the average of alignment identity percent (Nucmer measure of alignment accuracy) among all contigs.",
+ "N50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the assembly. Usually there is no value that produces exactly 50%, so the technical definition is the maximum length x such that using contigs of length at least x accounts for at least 50% of the total assembly length. Similarly, Nx for any x between 0 and 100 could be computed (x% of assembly).",
+ "NG50" : "
is the contig length such that using longer or equal length contigs produces half (50%) of the bases of the reference genome. This metric is computed only if a reference genome is provided. Similarly, NGx for any x between 0 and 100 could be computed (x% of the reference).",
+
+ "L50" : "
is the minimum number of contigs that produce half (50%) of the bases of the assembly. In other words, it's the number of contigs of length at least N50. Similarly, Lx for any x between 0 and 100 could be computed.",
+ "LG50" : "
is the minimum number of contigs that produce half (50%) of the bases of the reference genome. In other words, it's the number of contigs of length at least NG50. This metric is computed only if a reference genome is provided. Similarly, LGx for any x between 0 and 100 could be computed.",
+
+ "NA50" : "
is N50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided. Similarly, NAx for any x between 0 and 100 could be computed.",
+ "NGA50" : "
is NG50 where the lengths of aligned blocks are counted instead of contig lengths. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. This metric is computed only if a reference genome is provided. Similarly, NGAx for any x between 0 and 100 could be computed.",
+
+ "LA50" : "
is L50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. Similarly, LAx for any x between 0 and 100 could be computed.",
+ "LGA50" : "
is LG50 where aligned blocks are counted instead of contigs. I.e., if a contig has a misassembly with respect to the reference, the contig is broken into smaller pieces. Similarly, LGAx for any x between 0 and 100 could be computed.",
+
+ "auN" : "
is the area under the Nx curve.",
+ "auNG" : "
is the area under the NGx curve.",
+ "auNA" : "
is the area under the NAx curve.",
+ "auNGA" : "
is the area under the NGAx curve.",
+
+ "Average %IDY" : "
is the average of alignment identity percent (alignment accuracy) among all contigs.",
"# misassemblies" : "
is the number of positions in the assembled contigs where the left flanking sequence aligns over 1 kbp away from the right flanking sequence on the reference (relocation) or they overlap on more than 1 kbp (relocation) or flanking sequences align on different strands (inversion) or different chromosomes (translocation).",
"# large block misassemblies" : "
is the number of misassemblies between alignments with length greater than or equal to 3 kbp and with the misassembly threshold equal to 5 kbp (instead of default 1 kbp for regular misassemblies).",
"# misassembled contigs" : "
is the number of contigs that contain misassembly events.",
@@ -4762,11 +4759,11 @@
"# intergenomic misassemblies" : "
is the number of all found and putative (possible) interspecies translocations.",
"# structural variations" : "
is the number of misassemblies matched with structural variations.",
"# possible TEs" : "
is the number of misassemblies possibly caused by transposable elements (TEs). We define a possible TE as an event that satisfies these conditions: - There are two misassembly breakpoints of the same type around a short alignment (less than 7 kbp by default)
- The gap between two long flanking sequences on the sides of the short alignment is less than 7 kbp.
- The long flanking sequences both are on the same strand of the same chromosome of the reference genome.
",
- "# unaligned mis. contigs" : "
is the number of contigs that have the number of unaligned bases more than 50% of contig length and a misassembly event in their aligned fragment. Note that such misassemblies are not counted in # misassemblies and other misassemblies statistics.",
+ "# unaligned mis. contigs" : "
is the number of contigs that have the number of unaligned bases more than 50% of the contig length and a misassembly event in their aligned fragment. Note that such misassemblies are not counted in # misassemblies and other misassemblies statistics.",
"# fully unaligned contigs" : "
is the number of contigs that have no alignment to the reference sequence.",
"Fully unaligned length" : "
is the total number of bases contained in all fully unaligned contigs. Uncalled bases (N's) are not counted.",
- "# partially unaligned contigs" : "
is the number of contigs that have at least one alignment to the reference sequence but also have at least one unaligned fragment of length ≥ unaligned-part-size threshold.",
+ "# partially unaligned contigs" : "
is the number of contigs that have at least one alignment to the reference sequence but also have at least one unaligned fragment of length ≥ unaligned-part-size threshold (uncalled bases (N's) are not counted towards the fragment length).",
"Partially unaligned length" : "
is the total number of unaligned bases in all partially unaligned contigs. Uncalled bases (N's) are not counted.",
"# ambiguous contigs" : "
is the number of contigs that have reference alignments of equal quality in multiple locations on the reference.",
@@ -4776,13 +4773,13 @@
"GC (%)" : "
is the total number of G and C nucleotides in the assembly, divided by the total length of the assembly.",
"Reference GC (%)" : "
is the total number of G and C nucleotides in the reference, divided by the total length of the reference.",
- "# mismatches per 100 kbp" : "
is the average number of mismatches per 100000 aligned bases.",
- "# mismatches" : "
is the number of mismatches in all aligned bases.",
- "# indels per 100 kbp" : "
is the average number of indels per 100000 aligned bases.",
- "# indels" : "
is the number of indels in all aligned bases",
- "# indels (<= 5 bp)" : "
is the number of indels of length less than or equal to 5 bp",
- "# indels (> 5 bp)" : "
is the number of indels of length greater than 5 bp",
- "Indels length" : "
is the number of total bases contained in all indels",
+ "# mismatches per 100 kbp" : "
is the average number of mismatches per 100,000 aligned bases in the assembly.",
+ "# mismatches" : "
is the number of mismatches in all aligned bases in the assembly.",
+ "# indels per 100 kbp" : "
is the average number of indels per 100,000 aligned bases in the assembly.",
+ "# indels" : "
is the number of indels in all aligned bases in the assembly.",
+ "# indels (<= 5 bp)" : "
is the number of indels of length less than or equal to 5 bp.",
+ "# indels (> 5 bp)" : "
is the number of indels of length greater than 5 bp.",
+ "Indels length" : "
is the number of total bases contained in all indels.",
"# genomic features" : "
is the number of genomic features (genes, transcripts, CDS) in the assembly (complete and partial), based on a user-provided annotated list of gene positions in the reference genome. A feature counts as 'partially covered' if the assembly contains at least 100 bp of this feature but not the whole feature.",
"# operons" : "
is the number of operons in the assembly (complete and partial), based on a user-provided annotated list of operon positions in the reference genome. An operon counts as 'partially covered' if the assembly contains at least 100 bp of this operon but not the whole operon.",
@@ -4799,13 +4796,13 @@
"NGAx" : "
plot shows the NGAx metric value as x varies from 0 to 100.NGAx is computed similarly to NGx, but based on lengths of aligned blocks instead of contig lengths. Contigs are broken at misassembly breakpoints. NGAx is the minimum block length y such that using blocks of length at least y accounts for at least x% of the bases of the reference genome. This metric is computed only if a reference genome is provided.",
"GC content" : "
plot shows the distribution of GC percentage among the contigs, i.e., the total number of bases in contigs with such GC content. Typically, the distribution is approximately Gaussian. However, for some genomes it is not Gaussian. For assembly projects with contaminants, the GC distribution of the contaminants often differs from the reference genome and may give a superposition of multiple curves with different peaks.",
- "Duplication ratio" : "
is the total number of aligned bases in the assembly (i.e. Total length - Fully unaligned length - Partially unaligned length), divided by the total number of aligned bases in the reference (see the Genome fraction (%) metric). If the assembly contains many contigs that cover the same regions of the reference, its Duplication ratio may be much larger than 1. This may occur due to overestimating repeat multiplicities and due to small overlaps between contigs, among other reasons.",
+ "Duplication ratio" : "
is the total number of aligned bases in the assembly, divided by the total number of aligned bases in the reference (see the Genome fraction (%) metric). If the assembly contains many contigs that cover the same regions of the reference, its Duplication ratio may be much larger than 1. This may occur due to overestimating repeat multiplicities and due to small overlaps between contigs, among other reasons.",
"Largest alignment" : "
is the length of the largest continuous alignment in the assembly. This metric is always equal to the Largest contig metric but it can be smaller if the largest contig of the assembly contains a misassembly event.",
"Total aligned length" : "
is the total number of aligned bases in the assembly.",
"Avg contig read support" : "
is the average coverage of contigs that have large unique alignments to the reference. Read coverage is extracted from contig names (SPAdes/Velvet naming scheme only).",
"# N's" : "
is the total number of uncalled bases (N's) in the assembly.",
- "# N's per 100 kbp" : "
is the average number of uncalled bases (N's) per 100000 assembly bases.",
+ "# N's per 100 kbp" : "
is the average number of uncalled bases (N's) per 100,000 assembly bases.",
"# mapped" : "
is the number of reads that mapped to the assembly.",
"Mapped (%)" : "
is the percent of reads that mapped to the assembly.",
diff -r 675488238c96 -r 3061c8b029e5 test-data/test3_report.pdf
Binary file test-data/test3_report.pdf has changed
diff -r 675488238c96 -r 3061c8b029e5 test-data/test5.tab
--- a/test-data/test5.tab Fri Mar 25 17:36:59 2022 +0000
+++ b/test-data/test5.tab Fri Aug 05 15:21:27 2022 +0000
@@ -11,16 +11,18 @@
Reference GC (%) 52.00 52.00
N50 3980 6650
NG50 3980 6650
-N75 1610 6650
-NG75 1610 6650
+N90 1120 6650
+NG90 1120 6650
+auN 2934.0 6650.0
+auNG 2960.4 6650.0
L50 1 1
LG50 1 1
-L75 2 1
-LG75 2 1
-# total reads 331 331
+L90 3 1
+LG90 3 1
+# total reads 330 330
# left 0 0
# right 0 0
-Mapped (%) 2.72 2.42
+Mapped (%) 2.73 2.42
Reference mapped (%) 2.42 2.42
Properly paired (%) 0.0 0.0
Reference properly paired (%) 0.0 0.0
@@ -46,9 +48,11 @@
Total aligned length 4760 6650
NA50 1610 6650
NGA50 1610 6650
-NA75 - 6650
-NGA75 - 6650
+NA90 - 6650
+NGA90 - 6650
+auNA 1187.4 6650.0
+auNGA 1198.1 6650.0
LA50 2 1
LGA50 2 1
-LA75 - 1
-LGA75 - 1
+LA90 - 1
+LGA90 - 1
diff -r 675488238c96 -r 3061c8b029e5 test-data/test6.tab
--- a/test-data/test6.tab Fri Mar 25 17:36:59 2022 +0000
+++ b/test-data/test6.tab Fri Aug 05 15:21:27 2022 +0000
@@ -8,9 +8,10 @@
Total length 6710 6650
GC (%) 51.28 52.00
N50 3980 6650
-N75 1610 6650
+N90 1120 6650
+auN 2934.0 6650.0
L50 1 1
-L75 2 1
+L90 3 1
# total reads 167 167
# left 0 0
# right 0 0
diff -r 675488238c96 -r 3061c8b029e5 test-data/test7.tab
--- a/test-data/test7.tab Fri Mar 25 17:36:59 2022 +0000
+++ b/test-data/test7.tab Fri Aug 05 15:21:27 2022 +0000
@@ -8,9 +8,10 @@
Total length 6710 6650
GC (%) 51.28 52.00
N50 3980 6650
-N75 1610 6650
+N90 1120 6650
+auN 2934.0 6650.0
L50 1 1
-L75 2 1
+L90 3 1
# total reads 167 167
# left 0 0
# right 0 0