Skip to content

Instantly share code, notes, and snippets.

@lindenb
Created February 7, 2019 10:07
Show Gist options
  • Select an option

  • Save lindenb/f05bef81cff7e9223a6493ae7fac4236 to your computer and use it in GitHub Desktop.

Select an option

Save lindenb/f05bef81cff7e9223a6493ae7fac4236 to your computer and use it in GitHub Desktop.
https://www.biostars.org/p/362495/ biostars filter blastp blast xslt xslt xml
<?xml version='1.0' encoding="UTF-8" ?>
<xsl:stylesheet
xmlns:xsl='http://www.w3.org/1999/XSL/Transform'
version='1.0'
>
<xsl:output method="xml" encoding="UTF-8"/>
<xsl:template match="*">
<xsl:copy>
<xsl:apply-templates select="@*|text()|*"/>
</xsl:copy>
</xsl:template>
<xsl:template match="Hsp">
<xsl:choose>
<xsl:when test="number(Hsp_identity/text()) &lt; 13">
<xsl:copy-of select="."/>
</xsl:when>
<xsl:otherwise>
<xsl:comment>Ignoring <xsl:value-of select="Hsp_identity"/></xsl:comment>
</xsl:otherwise>
</xsl:choose>
</xsl:template>
</xsl:stylesheet>
<?xml version="1.0"?>
<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">
<BlastOutput>
<BlastOutput_program>blastp</BlastOutput_program>
<BlastOutput_version>BLASTP 2.8.1+</BlastOutput_version>
<BlastOutput_reference>Stephen F. Altschul, Thomas L. Madden, Alejandro A. Sch&amp;auml;ffer, Jinghui Zhang, Zheng Zhang, Webb Miller, and David J. Lipman (1997), &quot;Gapped BLAST and PSI-BLAST: a new generation of protein database search programs&quot;, Nucleic Acids Res. 25:3389-3402.</BlastOutput_reference>
<BlastOutput_db>nr</BlastOutput_db>
<BlastOutput_query-ID>Query_316121</BlastOutput_query-ID>
<BlastOutput_query-def>unnamed protein product</BlastOutput_query-def>
<BlastOutput_query-len>16</BlastOutput_query-len>
<BlastOutput_param>
<Parameters>
<Parameters_matrix>PAM30</Parameters_matrix>
<Parameters_expect>200000</Parameters_expect>
<Parameters_gap-open>9</Parameters_gap-open>
<Parameters_gap-extend>1</Parameters_gap-extend>
<Parameters_filter>F</Parameters_filter>
</Parameters>
</BlastOutput_param>
<BlastOutput_iterations>
<Iteration>
<Iteration_iter-num>1</Iteration_iter-num>
<Iteration_query-ID>Query_316121</Iteration_query-ID>
<Iteration_query-def>unnamed protein product</Iteration_query-def>
<Iteration_query-len>16</Iteration_query-len>
<Iteration_hits>
<Hit>
<Hit_num>1</Hit_num>
<Hit_id>gi|1432231202|gb|AXF43121.1|</Hit_id>
<Hit_def>truncated NSP3 [Bovine rotavirus]</Hit_def>
<Hit_accession>AXF43121</Hit_accession>
<Hit_len>38</Hit_len>
<Hit_hsps>
<Hsp>
<Hsp_num>1</Hsp_num>
<Hsp_bit-score>49.8412</Hsp_bit-score>
<Hsp_score>110</Hsp_score>
<Hsp_evalue>3.16775e-06</Hsp_evalue>
<Hsp_query-from>1</Hsp_query-from>
<Hsp_query-to>16</Hsp_query-to>
<Hsp_hit-from>7</Hsp_hit-from>
<Hsp_hit-to>22</Hsp_hit-to>
<Hsp_query-frame>0</Hsp_query-frame>
<Hsp_hit-frame>0</Hsp_hit-frame>
<Hsp_identity>15</Hsp_identity>
<Hsp_positive>15</Hsp_positive>
<Hsp_gaps>0</Hsp_gaps>
<Hsp_align-len>16</Hsp_align-len>
<Hsp_qseq>TQQMASSIINTSFEAA</Hsp_qseq>
<Hsp_hseq>TQQMVSSIINTSFEAA</Hsp_hseq>
<Hsp_midline>TQQM SSIINTSFEAA</Hsp_midline>
</Hsp>
</Hit_hsps>
</Hit>
<Hit>
<Hit_num>2</Hit_num>
<Hit_id>gi|23198438|gb|AAN15755.1|</Hit_id>
<Hit_def>protein 7, partial [Human rotavirus]</Hit_def>
<Hit_accession>AAN15755</Hit_accession>
<Hit_len>58</Hit_len>
<Hit_hsps>
<Hsp>
<Hsp_num>1</Hsp_num>
<Hsp_bit-score>49.8412</Hsp_bit-score>
<Hsp_score>110</Hsp_score>
<Hsp_evalue>6.5624e-06</Hsp_evalue>
<Hsp_query-from>1</Hsp_query-from>
<Hsp_query-to>16</Hsp_query-to>
<Hsp_hit-from>4</Hsp_hit-from>
<Hsp_hit-to>19</Hsp_hit-to>
<Hsp_query-frame>0</Hsp_query-frame>
<Hsp_hit-frame>0</Hsp_hit-frame>
<Hsp_identity>15</Hsp_identity>
<Hsp_positive>15</Hsp_positive>
<Hsp_gaps>0</Hsp_gaps>
<Hsp_align-len>16</Hsp_align-len>
<Hsp_qseq>TQQMASSIINTSFEAA</Hsp_qseq>
<Hsp_hseq>TQQMVSSIINTSFEAA</Hsp_hseq>
<Hsp_midline>TQQM SSIINTSFEAA</Hsp_midline>
</Hsp>
</Hit_hsps>
</Hit>
<Hit>
<Hit_num>3</Hit_num>
<Hit_id>gi|30027639|gb|AAP13880.1|</Hit_id>
<Hit_def>gene 7 [Human rotavirus]</Hit_def>
<Hit_accession>AAP13880</Hit_accession>
<Hit_len>22</Hit_len>
<Hit_hsps>
<Hsp>
<Hsp_num>1</Hsp_num>
<Hsp_bit-score>40.0857</Hsp_bit-score>
<Hsp_score>87</Hsp_score>
<Hsp_evalue>0.00577974</Hsp_evalue>
<Hsp_query-from>4</Hsp_query-from>
<Hsp_query-to>16</Hsp_query-to>
<Hsp_hit-from>1</Hsp_hit-from>
<Hsp_hit-to>13</Hsp_hit-to>
<Hsp_query-frame>0</Hsp_query-frame>
<Hsp_hit-frame>0</Hsp_hit-frame>
<Hsp_identity>12</Hsp_identity>
<Hsp_positive>12</Hsp_positive>
<Hsp_gaps>0</Hsp_gaps>
<Hsp_align-len>13</Hsp_align-len>
<Hsp_qseq>MASSIINTSFEAA</Hsp_qseq>
<Hsp_hseq>MVSSIINTSFEAA</Hsp_hseq>
<Hsp_midline>M SSIINTSFEAA</Hsp_midline>
</Hsp>
</Hit_hsps>
</Hit>
<Hit>
<Hit_num>4</Hit_num>
<Hit_id>gi|1539474422|emb|VEB38454.1|</Hit_id>
<Hit_def>Uncharacterised protein [Legionella sainthelensi]</Hit_def>
<Hit_accession>VEB38454</Hit_accession>
<Hit_len>29</Hit_len>
<Hit_hsps>
<Hsp>
<Hsp_num>1</Hsp_num>
<Hsp_bit-score>22.6954</Hsp_bit-score>
<Hsp_score>46</Hsp_score>
<Hsp_evalue>27356.3</Hsp_evalue>
<Hsp_query-from>2</Hsp_query-from>
<Hsp_query-to>8</Hsp_query-to>
<Hsp_hit-from>9</Hsp_hit-from>
<Hsp_hit-to>15</Hsp_hit-to>
<Hsp_query-frame>0</Hsp_query-frame>
<Hsp_hit-frame>0</Hsp_hit-frame>
<Hsp_identity>6</Hsp_identity>
<Hsp_positive>7</Hsp_positive>
<Hsp_gaps>0</Hsp_gaps>
<Hsp_align-len>7</Hsp_align-len>
<Hsp_qseq>QQMASSI</Hsp_qseq>
<Hsp_hseq>EQMASSI</Hsp_hseq>
<Hsp_midline>+QMASSI</Hsp_midline>
</Hsp>
</Hit_hsps>
</Hit>
</Iteration_hits>
<Iteration_stat>
<Statistics>
<Statistics_db-num>187417574</Statistics_db-num>
<Statistics_db-len>68351197366</Statistics_db-len>
<Statistics_hsp-len>0</Statistics_hsp-len>
<Statistics_eff-space>0</Statistics_eff-space>
<Statistics_kappa>0.11</Statistics_kappa>
<Statistics_lambda>0.294</Statistics_lambda>
<Statistics_entropy>0.61</Statistics_entropy>
</Statistics>
</Iteration_stat>
</Iteration>
</BlastOutput_iterations>
</BlastOutput>
<?xml version="1.0" encoding="UTF-8"?>
<BlastOutput>
<BlastOutput_program>blastp</BlastOutput_program>
<BlastOutput_version>BLASTP 2.8.1+</BlastOutput_version>
<BlastOutput_reference>Stephen F. Altschul, Thomas L. Madden, Alejandro A. Sch&amp;auml;ffer, Jinghui Zhang, Zheng Zhang, Webb Miller, and David J. Lipman (1997), "Gapped BLAST and PSI-BLAST: a new generation of protein database search programs", Nucleic Acids Res. 25:3389-3402.</BlastOutput_reference>
<BlastOutput_db>nr</BlastOutput_db>
<BlastOutput_query-ID>Query_316121</BlastOutput_query-ID>
<BlastOutput_query-def>unnamed protein product</BlastOutput_query-def>
<BlastOutput_query-len>16</BlastOutput_query-len>
<BlastOutput_param>
<Parameters>
<Parameters_matrix>PAM30</Parameters_matrix>
<Parameters_expect>200000</Parameters_expect>
<Parameters_gap-open>9</Parameters_gap-open>
<Parameters_gap-extend>1</Parameters_gap-extend>
<Parameters_filter>F</Parameters_filter>
</Parameters>
</BlastOutput_param>
<BlastOutput_iterations>
<Iteration>
<Iteration_iter-num>1</Iteration_iter-num>
<Iteration_query-ID>Query_316121</Iteration_query-ID>
<Iteration_query-def>unnamed protein product</Iteration_query-def>
<Iteration_query-len>16</Iteration_query-len>
<Iteration_hits>
<Hit>
<Hit_num>1</Hit_num>
<Hit_id>gi|1432231202|gb|AXF43121.1|</Hit_id>
<Hit_def>truncated NSP3 [Bovine rotavirus]</Hit_def>
<Hit_accession>AXF43121</Hit_accession>
<Hit_len>38</Hit_len>
<Hit_hsps>
<!--Ignoring 15-->
</Hit_hsps>
</Hit>
<Hit>
<Hit_num>2</Hit_num>
<Hit_id>gi|23198438|gb|AAN15755.1|</Hit_id>
<Hit_def>protein 7, partial [Human rotavirus]</Hit_def>
<Hit_accession>AAN15755</Hit_accession>
<Hit_len>58</Hit_len>
<Hit_hsps>
<!--Ignoring 15-->
</Hit_hsps>
</Hit>
<Hit>
<Hit_num>3</Hit_num>
<Hit_id>gi|30027639|gb|AAP13880.1|</Hit_id>
<Hit_def>gene 7 [Human rotavirus]</Hit_def>
<Hit_accession>AAP13880</Hit_accession>
<Hit_len>22</Hit_len>
<Hit_hsps>
<Hsp>
<Hsp_num>1</Hsp_num>
<Hsp_bit-score>40.0857</Hsp_bit-score>
<Hsp_score>87</Hsp_score>
<Hsp_evalue>0.00577974</Hsp_evalue>
<Hsp_query-from>4</Hsp_query-from>
<Hsp_query-to>16</Hsp_query-to>
<Hsp_hit-from>1</Hsp_hit-from>
<Hsp_hit-to>13</Hsp_hit-to>
<Hsp_query-frame>0</Hsp_query-frame>
<Hsp_hit-frame>0</Hsp_hit-frame>
<Hsp_identity>12</Hsp_identity>
<Hsp_positive>12</Hsp_positive>
<Hsp_gaps>0</Hsp_gaps>
<Hsp_align-len>13</Hsp_align-len>
<Hsp_qseq>MASSIINTSFEAA</Hsp_qseq>
<Hsp_hseq>MVSSIINTSFEAA</Hsp_hseq>
<Hsp_midline>M SSIINTSFEAA</Hsp_midline>
</Hsp>
</Hit_hsps>
</Hit>
<Hit>
<Hit_num>4</Hit_num>
<Hit_id>gi|1539474422|emb|VEB38454.1|</Hit_id>
<Hit_def>Uncharacterised protein [Legionella sainthelensi]</Hit_def>
<Hit_accession>VEB38454</Hit_accession>
<Hit_len>29</Hit_len>
<Hit_hsps>
<Hsp>
<Hsp_num>1</Hsp_num>
<Hsp_bit-score>22.6954</Hsp_bit-score>
<Hsp_score>46</Hsp_score>
<Hsp_evalue>27356.3</Hsp_evalue>
<Hsp_query-from>2</Hsp_query-from>
<Hsp_query-to>8</Hsp_query-to>
<Hsp_hit-from>9</Hsp_hit-from>
<Hsp_hit-to>15</Hsp_hit-to>
<Hsp_query-frame>0</Hsp_query-frame>
<Hsp_hit-frame>0</Hsp_hit-frame>
<Hsp_identity>6</Hsp_identity>
<Hsp_positive>7</Hsp_positive>
<Hsp_gaps>0</Hsp_gaps>
<Hsp_align-len>7</Hsp_align-len>
<Hsp_qseq>QQMASSI</Hsp_qseq>
<Hsp_hseq>EQMASSI</Hsp_hseq>
<Hsp_midline>+QMASSI</Hsp_midline>
</Hsp>
</Hit_hsps>
</Hit>
</Iteration_hits>
<Iteration_stat>
<Statistics>
<Statistics_db-num>187417574</Statistics_db-num>
<Statistics_db-len>68351197366</Statistics_db-len>
<Statistics_hsp-len>0</Statistics_hsp-len>
<Statistics_eff-space>0</Statistics_eff-space>
<Statistics_kappa>0.11</Statistics_kappa>
<Statistics_lambda>0.294</Statistics_lambda>
<Statistics_entropy>0.61</Statistics_entropy>
</Statistics>
</Iteration_stat>
</Iteration>
</BlastOutput_iterations>
</BlastOutput>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment