From: Jim Procter <jprocter@issues.jalview.org>
Date: Mon, 2 Nov 2015 15:01:50 +0000 (+0000)
Subject: JAL-1950 structuring methods and note on parsing flat-files
X-Git-Url: http://source.jalview.org/gitweb/?a=commitdiff_plain;h=ecdc8f7020e2fe1b510e03635801528a08480ec8;hp=b919fa3374d70132c50e4c87270461c1be795206;p=jalview.git

JAL-1950 structuring methods and note on parsing flat-files
---

diff --git a/src/jalview/ws/ebi/hmmerClient.java b/src/jalview/ws/ebi/hmmerClient.java
index 3db35be..c29d355 100644
--- a/src/jalview/ws/ebi/hmmerClient.java
+++ b/src/jalview/ws/ebi/hmmerClient.java
@@ -1,6 +1,14 @@
 package jalview.ws.ebi;
 
+import jalview.datamodel.AlignmentI;
+import jalview.io.AppletFormatAdapter;
+import jalview.io.FileParse;
+import jalview.io.FormatAdapter;
+
+import java.io.BufferedReader;
 import java.io.File;
+import java.io.IOException;
+import java.util.StringTokenizer;
 import java.util.regex.Matcher;
 
 import org.apache.axis.transport.http.HTTPConstants;
@@ -219,4 +227,76 @@ public class hmmerClient
      * results......
      */
   }
+
+  /**
+   * retrieve an alignment annotated with scores from JackHmmer
+   * 
+   * @param jobid
+   * @param dataset
+   * @return
+   */
+  AlignmentI retrieveJackhmmerResult(String jobid, AlignmentI dataset)
+          throws OutOfMemoryError, IOException
+  {
+    AlignmentI searchResult = null;
+
+    // get results
+
+    searchResult = new AppletFormatAdapter().readFile(baseUrl
+            + "/download/" + jobid
+                    + "/score?format=afa&t=.gz", FormatAdapter.URL, "FASTA");
+
+    // match up to dataset.
+
+    // and do scores
+
+    FileParse csvsource = new FileParse(baseUrl + "/download/" + jobid
+            + "/score?format=csv", FormatAdapter.URL);
+    if (!csvsource.isValid())
+    {
+      throw new IOException("Couldn't access scores for Jackhammer results");
+    }
+    readJackhmmerScores(searchResult, csvsource);
+    return searchResult;
+  }
+
+  private void readJackhmmerScores(AlignmentI searchResult,
+          FileParse csvsource)
+          throws IOException
+  {
+    String line;
+    BufferedReader rl = new BufferedReader(csvsource.getReader());
+    while ((line = rl.readLine()) != null)
+    {
+      StringTokenizer st = new StringTokenizer(line, "\t");
+
+    }
+    // http://www.ebi.ac.uk/Tools/hmmer/download/60048B38-7CEC-11E5-A230-CED6D26C98AD.5/score?format=csv
+    // 1gri_A 1gri_A 217 jackhmmer - 163 4.7e-62 212.4 0.1 1 2 4.4e-46 2.1e-43
+    // each line scores a fragment
+    // so for a combined score ?
+
+    /**
+     * for a sequence q sort any t against q according to overallScore(q,t)
+     * maxFragment(q,t) in sequence features parlance: for alignment
+     * s.getFeature("overallScore",q) -> range on q and range on s
+     * 
+     * 
+     */
+
+    // 151.758316040039 0.04 11 151 3 139 1 150 0.94 GROWTH FACTOR BOUND PROTEIN
+    // 2 1cj1_J 1gri_B
+    // 1gri_A 1gri_A 217 jackhmmer - 163 4.7e-62 212.4 0.1 2 2 1.6e-17 7.9e-15
+    // 58.8796501159668 0.01 7 66 157 215 153 216 0.95 GROWTH FACTOR BOUND
+    // PROTEIN 2 1cj1_J 1gri_B
+    // 4h1o_A 4h1o_A 560 jackhmmer - 163 2.1e-57 197.3 0.0 1 2 7.5e-28 3.6e-25
+    // 92.4921493530273 0.00 65 161 20 122 17 124 0.95 Tyrosine-protein
+    // phosphatase non-receptor typ 4h1o_A
+    //
+    // 4h1o_A 4h1o_A 560 jackhmmer - 163 2.1e-57 197.3 0.0 2 2 7.6e-31 3.7e-28
+    // 102.219146728516 0.03 66 161 127 236 124 238 0.94 Tyrosine-protein
+    // phosphatase non-receptor typ 4h1o_A
+
+  }
+
 }