update benchmark results

shenwei356 · Aug 15, 2024 · 12045c3 · 12045c3
1 parent 09d3e4d
commit 12045c3
Show file tree

Hide file tree

Showing 5 changed files with 72 additions and 71 deletions.
diff --git a/index.html b/index.html
@@ -444,28 +444,28 @@ <h1></h1>
 </thead>
 <tbody>
 <tr>
-<td style="text-align:left">A 1.3-kb marker gene</td>
+<td style="text-align:left">A 1.3-kb        gene</td>
 <td style="text-align:right">37,164</td>
-<td style="text-align:right">52s</td>
-<td style="text-align:right">4.1 GB</td>
+<td style="text-align:right">36s</td>
+<td style="text-align:right">4.1GB</td>
 </tr>
 <tr>
 <td style="text-align:left">A 1.5-kb 16S rRNA</td>
 <td style="text-align:right">1,949,496</td>
-<td style="text-align:right">13m53s</td>
-<td style="text-align:right">13.1 GB</td>
+<td style="text-align:right">10m41s</td>
+<td style="text-align:right">14.1GB</td>
 </tr>
 <tr>
 <td style="text-align:left">A 52.8-kb plasmid</td>
 <td style="text-align:right">544,619</td>
-<td style="text-align:right">23m30s</td>
-<td style="text-align:right">17.5 GB</td>
+<td style="text-align:right">19m20s</td>
+<td style="text-align:right">19.3GB</td>
 </tr>
 <tr>
 <td style="text-align:left">1003 AMR genes</td>
 <td style="text-align:right">25,702,419</td>
-<td style="text-align:right">4h02m</td>
-<td style="text-align:right">41.3 GB</td>
+<td style="text-align:right">187m40s</td>
+<td style="text-align:right">55.4GB</td>
 </tr>
 </tbody>
 </table> </div>

diff --git a/introduction/index.html b/introduction/index.html
@@ -62,7 +62,7 @@
       "url" : "https://bioinf.shenwei.me/LexicMap/introduction/",
       "headline": "Introduction",
       "description": "LexicMap is a nucleotide sequence alignment tool for efficiently querying gene, plasmid, viral, or long-read sequences against up to millions of prokaryotic genomes.\nTable of contents Table of contents Features Introduction Quick start Performance Indexing Searching Installation Algorithm overview Related projects Support License Features LexicMap is scalable to up to millions of prokaryotic genomes. The sensitivity of LexicMap is comparable with Blastn. The alignment is fast and memory-efficient. LexicMap is easy to install, we provide binary files with no dependencies for Linux, Windows, MacOS (x86 and arm CPUs).",
-      "wordCount" : "1604",
+      "wordCount" : "1614",
       "inLanguage": "en",
       "isFamilyFriendly": "true",
       "mainEntityOfPage": {
@@ -1583,26 +1583,26 @@ <h1>Introduction</h1>
 <tr>
 <td style="text-align:left">A 1.3-kb marker gene</td>
 <td style="text-align:right">37,164</td>
-<td style="text-align:right">52s</td>
+<td style="text-align:right">36 s</td>
 <td style="text-align:right">4.1 GB</td>
 </tr>
 <tr>
 <td style="text-align:left">A 1.5-kb 16S rRNA</td>
 <td style="text-align:right">1,949,496</td>
-<td style="text-align:right">13m53s</td>
-<td style="text-align:right">13.1 GB</td>
+<td style="text-align:right">10 m 41 s</td>
+<td style="text-align:right">14.1 GB</td>
 </tr>
 <tr>
 <td style="text-align:left">A 52.8-kb plasmid</td>
 <td style="text-align:right">544,619</td>
-<td style="text-align:right">23m30s</td>
-<td style="text-align:right">17.5 GB</td>
+<td style="text-align:right">19 m 20 s</td>
+<td style="text-align:right">19.3 GB</td>
 </tr>
 <tr>
 <td style="text-align:left">1003 AMR genes</td>
 <td style="text-align:right">25,702,419</td>
-<td style="text-align:right">4h02m</td>
-<td style="text-align:right">41.3 GB</td>
+<td style="text-align:right">187 m 40 s</td>
+<td style="text-align:right">55.4 GB</td>
 </tr>
 </tbody>
 </table> </div>
@@ -1845,7 +1845,7 @@ <h1>Introduction</h1>
 <thead>
 <tr>
 <th style="text-align:left">query</th>
-<th style="text-align:left">query_len</th>
+<th style="text-align:right">query_len</th>
 <th style="text-align:left">tool</th>
 <th style="text-align:right">genome_hits</th>
 <th style="text-align:right">genome_hits(qcov&gt;50)</th>
@@ -1856,16 +1856,16 @@ <h1>Introduction</h1>
 <tbody>
 <tr>
 <td style="text-align:left">a marker gene</td>
-<td style="text-align:left">1,299 bp</td>
+<td style="text-align:right">1,299 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">5,170</td>
 <td style="text-align:right">5,143</td>
-<td style="text-align:right">3.0 s</td>
+<td style="text-align:right">17 s</td>
 <td style="text-align:right">1.4 GB</td>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Blastn</td>
 <td style="text-align:right">7,121</td>
 <td style="text-align:right">6,177</td>
@@ -1874,16 +1874,16 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left">a 16S rRNA gene</td>
-<td style="text-align:left">1,542 bp</td>
+<td style="text-align:right">1,542 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">303,925</td>
 <td style="text-align:right">278,141</td>
-<td style="text-align:right">92 s</td>
-<td style="text-align:right">4.9 GB</td>
+<td style="text-align:right">235 s</td>
+<td style="text-align:right">4.4 GB</td>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Blastn</td>
 <td style="text-align:right">301,197</td>
 <td style="text-align:right">277,042</td>
@@ -1892,16 +1892,16 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left">a plasmid</td>
-<td style="text-align:left">52,830 bp</td>
+<td style="text-align:right">52,830 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">63,108</td>
 <td style="text-align:right">1,190</td>
-<td style="text-align:right">87 s</td>
-<td style="text-align:right">4.8 GB</td>
+<td style="text-align:right">499 s</td>
+<td style="text-align:right">4.6 GB</td>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Blastn</td>
 <td style="text-align:right">69,311</td>
 <td style="text-align:right">2,308</td>
@@ -1910,16 +1910,16 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left">1033 AMR genes</td>
-<td style="text-align:left">1 kb (median)</td>
+<td style="text-align:right">1 kb (median)</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">3,867,003</td>
 <td style="text-align:right">2,228,339</td>
-<td style="text-align:right">1,254 s</td>
-<td style="text-align:right">21.4 GB</td>
+<td style="text-align:right">4,350 s</td>
+<td style="text-align:right">16.3 GB</td>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Blastn</td>
 <td style="text-align:right">5,357,772</td>
 <td style="text-align:right">2,240,766</td>
@@ -1933,7 +1933,7 @@ <h1>Introduction</h1>
 <thead>
 <tr>
 <th style="text-align:left">query</th>
-<th style="text-align:left">query_len</th>
+<th style="text-align:right">query_len</th>
 <th style="text-align:left">tool</th>
 <th style="text-align:right">genome_hits</th>
 <th style="text-align:right">genome_hits(qcov&gt;50)</th>
@@ -1944,16 +1944,16 @@ <h1>Introduction</h1>
 <tbody>
 <tr>
 <td style="text-align:left">a marker gene</td>
-<td style="text-align:left">1,299 bp</td>
+<td style="text-align:right">1,299 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">27,963</td>
 <td style="text-align:right">27,953</td>
-<td style="text-align:right">41.7 s</td>
+<td style="text-align:right">31 s</td>
 <td style="text-align:right">3.4 GB</td>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Phylign_local</td>
 <td style="text-align:right">7,936</td>
 <td style="text-align:right"></td>
@@ -1962,7 +1962,7 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Phylign_cluster</td>
 <td style="text-align:right">7,936</td>
 <td style="text-align:right"></td>
@@ -1971,16 +1971,16 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left">a 16S rRNA gene</td>
-<td style="text-align:left">1,542 bp</td>
+<td style="text-align:right">1,542 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">1,857,761</td>
 <td style="text-align:right">1,740,000</td>
-<td style="text-align:right">13 m 24 s</td>
-<td style="text-align:right">13.7 GB</td>
+<td style="text-align:right">9 m 36 s</td>
+<td style="text-align:right">14.9 GB</td>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Phylign_local</td>
 <td style="text-align:right">1,017,765</td>
 <td style="text-align:right"></td>
@@ -1989,7 +1989,7 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Phylign_cluster</td>
 <td style="text-align:right">1,017,765</td>
 <td style="text-align:right"></td>
@@ -1998,16 +1998,16 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left">a plasmid</td>
-<td style="text-align:left">52,830 bp</td>
+<td style="text-align:right">52,830 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">468,821</td>
 <td style="text-align:right">3,618</td>
-<td style="text-align:right">20 m 48 s</td>
-<td style="text-align:right">15.9 GB</td>
+<td style="text-align:right">15 m 55 s</td>
+<td style="text-align:right">15.7 GB</td>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Phylign_local</td>
 <td style="text-align:right">46,822</td>
 <td style="text-align:right"></td>
@@ -2016,7 +2016,7 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Phylign_cluster</td>
 <td style="text-align:right">46,822</td>
 <td style="text-align:right"></td>
@@ -2025,16 +2025,16 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left">1033 AMR genes</td>
-<td style="text-align:left">1 kb (median)</td>
+<td style="text-align:right">1 kb (median)</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">21,288,000</td>
 <td style="text-align:right">12,148,642</td>
-<td style="text-align:right">168 m 48 s</td>
-<td style="text-align:right">49.2 GB</td>
+<td style="text-align:right">138 m 55 s</td>
+<td style="text-align:right">49.9 GB</td>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Phylign_local</td>
 <td style="text-align:right">1,135,215</td>
 <td style="text-align:right"></td>
@@ -2043,7 +2043,7 @@ <h1>Introduction</h1>
 </tr>
 <tr>
 <td style="text-align:left"></td>
-<td style="text-align:left"></td>
+<td style="text-align:right"></td>
 <td style="text-align:left">Phylign_cluster</td>
 <td style="text-align:right">1,135,215</td>
 <td style="text-align:right"></td>
@@ -2057,7 +2057,7 @@ <h1>Introduction</h1>
 <thead>
 <tr>
 <th style="text-align:left">query</th>
-<th style="text-align:left">query_len</th>
+<th style="text-align:right">query_len</th>
 <th style="text-align:left">tool</th>
 <th style="text-align:right">genome_hits</th>
 <th style="text-align:right">genome_hits(qcov&gt;50)</th>
@@ -2068,39 +2068,39 @@ <h1>Introduction</h1>
 <tbody>
 <tr>
 <td style="text-align:left">a marker gene</td>
-<td style="text-align:left">1,299 bp</td>
+<td style="text-align:right">1,299 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">37,164</td>
 <td style="text-align:right">37,082</td>
-<td style="text-align:right">51.9 s</td>
+<td style="text-align:right">36 s</td>
 <td style="text-align:right">4.1 GB</td>
 </tr>
 <tr>
 <td style="text-align:left">a 16S rRNA gene</td>
-<td style="text-align:left">1,542 bp</td>
+<td style="text-align:right">1,542 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">1,949,496</td>
 <td style="text-align:right">1,381,974</td>
-<td style="text-align:right">13 m 53 s</td>
-<td style="text-align:right">13.1 GB</td>
+<td style="text-align:right">10 m 41 s</td>
+<td style="text-align:right">14.1 GB</td>
 </tr>
 <tr>
 <td style="text-align:left">a plasmid</td>
-<td style="text-align:left">52,830 bp</td>
+<td style="text-align:right">52,830 bp</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">544,619</td>
 <td style="text-align:right">6,563</td>
-<td style="text-align:right">23 m 30 s</td>
-<td style="text-align:right">17.5 GB</td>
+<td style="text-align:right">19 m 20 s</td>
+<td style="text-align:right">19.3 GB</td>
 </tr>
 <tr>
 <td style="text-align:left">1033 AMR genes</td>
-<td style="text-align:left">1 kb (median)</td>
+<td style="text-align:right">1 kb (median)</td>
 <td style="text-align:left">LexicMap</td>
 <td style="text-align:right">25,702,419</td>
 <td style="text-align:right">14,692,624</td>
-<td style="text-align:right">242 m 25 s</td>
-<td style="text-align:right">56.2 GB</td>
+<td style="text-align:right">187 m 40 s</td>
+<td style="text-align:right">55.4 GB</td>
 </tr>
 </tbody>
 </table> </div>

diff --git a/[email protected] b/[email protected]
@@ -1,5 +1,5 @@
 Query	Genome hits	Time	RAM
-A 1.3-kb marker gene	37,164	52s	4.1 GB
-A 1.5-kb 16S rRNA	1,949,496	13m53s	13.1 GB
-A 52.8-kb plasmid	544,619	23m30s	17.5 GB
-1003 AMR genes	25,702,419	4h02m	41.3 GB
+A 1.3-kb marker gene	37,164	36 s	4.1 GB
+A 1.5-kb 16S rRNA	1,949,496	10 m 41 s	14.1 GB
+A 52.8-kb plasmid	544,619	19 m 20 s	19.3 GB
+1003 AMR genes	25,702,419	187 m 40 s	55.4 GB
diff --git a/releases/index.html b/releases/index.html
@@ -59,7 +59,7 @@
       "url" : "https://bioinf.shenwei.me/LexicMap/releases/",
       "headline": "Releases",
       "description": "Latest version v0.4.0 v0.4.0 - 2024-07-xx New commands: lexicmap utils 2blast: Convert the default search output to blast-style format. lexicmap index: Support suffix matching of seeds, now seeds are immune to any single SNP!!!, at the cost of doubled seed data. Better sketching desert filling for highly-repetitive regions. Change the default value of --seed-max-desert from 900 to 200 to increase alignment sensitivity. Mask gap regions (N’s). Fix skipping interval regions by further including the last k-1 bases of contigs.",
-      "wordCount" : "609",
+      "wordCount" : "616",
       "inLanguage": "en",
       "isFamilyFriendly": "true",
       "mainEntityOfPage": {
@@ -1465,6 +1465,7 @@ <h1>Releases</h1>
   class="gdoc-markdown__link"
   href="https://github.com/shenwei356/wfa"
 >WFA</a></strong>.</li>
+<li>Use buffered reader for seeds file reading.</li>
 <li>Fix object recycling and reduce memory usage.</li>
 <li>Fix alignment against genomes with many short contigs.</li>
 <li>Fix early quit when meeting a sequence shorter than k.</li>

diff --git a/search/en.data.min.json b/search/en.data.min.json