Skip to content

Commit 975788d

Browse files
committed
adding retrieval of omim ids
1 parent 2d16e84 commit 975788d

2 files changed

Lines changed: 24 additions & 12 deletions

File tree

biojava3-genome/src/main/java/org/biojava3/genome/parsers/genename/GeneName.java

Lines changed: 15 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -49,6 +49,7 @@ public class GeneName implements Serializable, Comparable<GeneName>{
4949
String accessionNr;
5050
String refseqIds;
5151
String uniprot;
52+
String omimId;
5253

5354
public String getHgncId() {
5455
return hgncId;
@@ -116,18 +117,27 @@ public String getUniprot() {
116117
public void setUniprot(String uniprot) {
117118
this.uniprot = uniprot;
118119
}
119-
@Override
120-
public int compareTo(GeneName o) {
121-
return hgncId.compareTo(o.getHgncId());
122-
}
120+
121+
123122
@Override
124123
public String toString() {
125124
return "GeneName [hgncId=" + hgncId + ", approvedSymbol="
126125
+ approvedSymbol + ", approvedName=" + approvedName
127126
+ ", status=" + status + ", previousSymbols=" + previousSymbols
128127
+ ", previousNames=" + previousNames + ", synonyms=" + synonyms
129128
+ ", chromosome=" + chromosome + ", accessionNr=" + accessionNr
130-
+ ", refseqIds=" + refseqIds + ", uniprot=" + uniprot + "]";
129+
+ ", refseqIds=" + refseqIds + ", uniprot=" + uniprot
130+
+ ", omimId=" + omimId + "]";
131+
}
132+
public String getOmimId() {
133+
return omimId;
134+
}
135+
public void setOmimId(String omimId) {
136+
this.omimId = omimId;
137+
}
138+
@Override
139+
public int compareTo(GeneName o) {
140+
return hgncId.compareTo(o.getHgncId());
131141
}
132142

133143

biojava3-genome/src/main/java/org/biojava3/genome/parsers/genename/GeneNamesParser.java

Lines changed: 9 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -29,6 +29,7 @@
2929
import java.io.InputStreamReader;
3030
import java.net.URL;
3131
import java.util.ArrayList;
32+
import java.util.Arrays;
3233
import java.util.List;
3334

3435
import org.biojava3.core.util.InputStreamProvider;
@@ -39,7 +40,7 @@
3940
*
4041
*/
4142
public class GeneNamesParser {
42-
public static final String DEFAULT_GENENAMES_URL = "http://www.genenames.org/cgi-bin/download?title=HGNC+output+data&hgnc_dbtag=on&col=gd_hgnc_id&col=gd_app_sym&col=gd_app_name&col=gd_status&col=gd_prev_sym&col=gd_prev_name&col=gd_aliases&col=gd_pub_chrom_map&col=gd_pub_acc_ids&col=gd_pub_refseq_ids&col=md_prot_id&status=Approved&status_opt=2&where=((gd_pub_chrom_map%20not%20like%20%27%patch%%27%20and%20gd_pub_chrom_map%20not%20like%20%27%ALT_REF%%27)%20or%20gd_pub_chrom_map%20IS%20NULL)%20and%20gd_locus_group%20%3d%20%27protein-coding%20gene%27&order_by=gd_app_sym_sort&format=text&limit=&submit=submit&.cgifields=&.cgifields=chr&.cgifields=status&.cgifields=hgnc_dbtag";
43+
public static final String DEFAULT_GENENAMES_URL = "http://www.genenames.org/cgi-bin/download?title=HGNC+output+data&hgnc_dbtag=on&col=gd_hgnc_id&col=gd_app_sym&col=gd_app_name&col=gd_status&col=gd_prev_sym&col=gd_prev_name&col=gd_aliases&col=gd_pub_chrom_map&col=gd_pub_acc_ids&col=md_mim_id&col=gd_pub_refseq_ids&col=md_prot_id&status=Approved&status_opt=2&where=((gd_pub_chrom_map%20not%20like%20%27%patch%%27%20and%20gd_pub_chrom_map%20not%20like%20%27%ALT_REF%%27)%20or%20gd_pub_chrom_map%20IS%20NULL)%20and%20gd_locus_group%20%3d%20%27protein-coding%20gene%27&order_by=gd_app_sym_sort&format=text&limit=&submit=submit&.cgifields=&.cgifields=chr&.cgifields=status&.cgifields=hgnc_dbtag";
4344

4445
/** parses a file from the genenames website
4546
*
@@ -116,9 +117,9 @@ private static GeneName getGeneName(String line) {
116117

117118
String[] s = line.split("\t");
118119

119-
if ( s.length != 11) {
120-
System.err.println("WARNING line does not contain 11 data items but " + s.length+"." );
121-
System.err.println(line);
120+
if ( s.length != 12) {
121+
System.err.println("WARNING line does not contain 12 data items but " + s.length+"." );
122+
System.err.println(line.replaceAll("\t", "|---|"));
122123
return null;
123124
}
124125
GeneName gn = new GeneName();
@@ -132,9 +133,10 @@ private static GeneName getGeneName(String line) {
132133
gn.setSynonyms(s[6]);
133134
gn.setChromosome(s[7]);
134135
gn.setAccessionNr(s[8]);
135-
gn.setRefseqIds(s[9]);
136-
gn.setUniprot(s[10]);
137-
136+
gn.setOmimId(s[9]);
137+
gn.setRefseqIds(s[10]);
138+
gn.setUniprot(s[11]);
139+
138140

139141
return gn;
140142

0 commit comments

Comments
 (0)