Changeset 5773 for trunk/config/dist/raw-data-types.xml

Timestamp:

Sep 29, 2011, 3:14:56 PM (10 years ago)

Author:

Nicklas Nordborg

Message:

References #1152: Handling short read transcript sequence data

• Adds a 'Cufflinks' raw data type with five columns: coverage, fpkm, fpkm_lo, fpkm_hi and status
• Define FPKM_TRACKING file type and MIME type.
• Adds left(string, index) as a JEP formula so that we can parse out the chromosome from the 'locus' column in the tracking files.
• Define two new configurations for the raw data importer that parses cufflinks isoform files.

File:

• trunk/config/dist/raw-data-types.xml (modified) (1 diff)

trunk/config/dist/raw-data-types.xml

@@ -3536 +3536 @@
     </intensity-formula>
   </raw-data-type>
+  <raw-data-type
+    id="cufflinks" 
+    channels="1" 
+    name="Cufflinks" 
+    table="RawDataCufflinks"
+    description="Cufflinks isoforms/gene-level expression values in FPKM tracking format">
+    <property
+      name="coverage"
+      title="Coverage"
+      description="Estimate for the absolute depth of read coverage across the object."
+      column="coverage"
+      type="float"
+      averagemethod="arithmetic_mean"
+    />
+    <property
+      name="fpkm"
+      title="FPKM"
+      description="Fragments Per Kilobase of exon per Million fragments mapped."
+      column="fpkm"
+      type="float"
+      averagemethod="geometric_mean"
+    />
+    <property
+      name="fpkm_lo"
+      title="FPKM lo"
+      description="The lower bound of the 95% confidence interval on the FPKM."
+      column="fpkm_lo"
+      type="float"
+      averagemethod="geometric_mean"
+    />
+    <property
+      name="fpkm_hi"
+      title="FPKM hi"
+      description="The upper bound of the 95% confidence interval on the FPKM."
+      column="fpkm_hi"
+      type="float"
+      averagemethod="geometric_mean"
+    />
+    <property
+      name="status"
+      title="Status"
+      description="Quantification status. Can be one of OK (deconvolution successful), LOWDATA (too complex or shallowly sequenced), HIDATA (too many fragments in locus), or FAIL, when an ill-conditioned covariance matrix or other numerical exception prevents deconvolution."
+      column="status"
+      type="string"
+      length="255"
+      averagemethod="none"
+    />
+    <intensity-formula
+      name="fpkm"
+      title="FPKM"
+      description="Fragments Per Kilobase of exon per Million fragments mapped."
+      >
+      <formula 
+        channel="1"
+        expression="raw('fpkm')"
+      />
+    </intensity-formula>
+  
+  </raw-data-type>
 </raw-data-types>