Merge pull request #107 from tripal/v2-issue201-blastForms

Some substantial fixes to blast forms but NOT COMPLETELY Fixed

Author: laceysanderson

Diff for: mkdocs/docs/admin/blast-databases.md

@@ -5,3 +5,66 @@
 
     This documentation is still being developed as this module is being upgraded.
 
+## How do I format my blast databases for use with Tripal BLAST?
+
+NCBI Blast+ comes with a program names `makeblastdb` which we will use to format a fasta file into a blast database.
+
+Arguements for makeblastdb command:
+
+- `-dbtype` indicates the type of sequence in the fasta file. It can be either `nucl` or `prot`
+- `-parse_seqids` indicates that you want to parse the fasta headers to be used by the blast query program
+- `-hash_index` creates an index for faster blast searches
+- `-in FASTAFILE` indicates that the fasta file you replace the token FASTAFILE with should be the input (i.e. the source for the blast database). Note: gzipped fasta is not a supported type for your input file.
+- `-input_type` indicates the type of file you provided to `-in` and it can be either `fasta` or `blastdb`.
+- `-title` should be a human-readable title describing this blast database. I recommend using the full name of the assembly including the version and the accession if known.
+- `-out GENOMEASSEMBLY` will be the filename of the blast database produced not including any file type suffix. The token GENOMEASSEMBLY should be replaced with an alphanumeric string uniquely describing the genome assembly that is the source for the blast database.
+
+### Nucleotide
+
+The command template to create a blast database from a nucleotide fasta file is:
+
+```
+makeblastdb -dbtype nucl -parse_seqids -hash_index -in FASTAFILE -input_type fasta -title "Genome Assembly Title with version" -out GENOMEASSEMBLY
+```
+
+An example which is actually how the demonstration blast database distributed with this module was created is:
+
+```
+makeblastdb -dbtype nucl -parse_seqids -hash_index -in Creinhardtii_281_v5.0.fa -input_type fasta -title "Chlamydomonas reinhardtii v5.6" -out Chlamydomonas_reinhardtii_v5.6
+```
+
+and the output of the command was
+
+> Building a new DB, current time: 03/31/2024 22:10:54
+> New DB name:   Chlamydomonas_reinhardtii_v5.6
+> New DB title:  Chlamydomonas reinhardtii v5.6
+> Sequence type: Nucleotide
+> Keep Linkouts: T
+> Keep MBits: T
+> Maximum file size: 1000000000B
+> Adding sequences from FASTA; added 54 sequences in 1.82259 seconds.
+
+## Protein
+
+The command template to create a blast database from a protein fasta file is:
+
+```
+makeblastdb -dbtype prot -parse_seqids -hash_index -in FASTAFILE -input_type fasta -title "Genome Assembly Title with version" -out GENOMEASSEMBLY
+```
+
+An example which is actually how the demonstration blast database distributed with this module was created is:
+
+```
+makeblastdb -dbtype nucl -parse_seqids -hash_index -in Creinhardtii_281_v5.5.protein.fa -input_type fasta -title "Chlamydomonas reinhardtii v5.6 Protein" -out Chlamydomonas_reinhardtii_v5.6_protein
+```
+
+and the output of the command was
+
+> Building a new DB, current time: 03/31/2024 22:38:57
+> New DB name:   Chlamydomonas_reinhardtii_v5.6_protein
+> New DB title:  Chlamydomonas reinhardtii v5.6 Protein
+> Sequence type: Nucleotide
+> Keep Linkouts: T
+> Keep MBits: T
+> Maximum file size: 1000000000B
+> Adding sequences from FASTA; added 19526 sequences in 4.40205 seconds.

Diff for: mkdocs/docs/install/docker-demo.md

@@ -42,12 +42,12 @@ git checkout -b my-feature-or-fix
 ```
 4. Build the docker demonstration image.
 ```
-docker build --tag=tripalBlast:local ./
+docker build --tag=tripalblast:local ./
 ```
 5. Create a container from the previous image in your current directory. The `--volume` part of this command will mount your current directory to the appropriate place inside the container.
 ```
-docker run --publish=80:80 -tid --name=tripalBlast --volume=`pwd`:/var/www/drupal/web/modules/contrib/tripal_blast tripalBlast:local
-docker exec tripalBlast service postgresql restart
+docker run --publish=80:80 -tid --name=tripalblast --volume=`pwd`:/var/www/drupal/web/modules/contrib/tripal_blast tripalblast:local
+docker exec tripalblast service postgresql restart
 ```
 
 Now you can interact with the Tripal site in your browser in all the same ways you would a regular Tripal site by going to https://localhost and logging in using the [Administrative username and password for the Tripal Docker](https://tripaldoc.readthedocs.io/en/latest/install/docker.html#development-site-information).

Diff for: src/Form/TripalBlastForm.php

@@ -210,8 +210,9 @@ public function buildForm(array $form, FormStateInterface $form_state, $query =
         $config_query_upload = \Drupal::config('tripal_blast.settings')
           ->get('tripal_blast_config_upload.allow_query');
 
+        // We don't current support this well so disabling for now.
         $is_query_upload_true = $config_query_upload ?? TRUE;
-        if ($is_query_upload_true) {
+        if (FALSE) {
           // Upload a file as an alternative to enter a query sequence.
           $form['#attributes']['enctype'] = 'multipart/form-data';
 
@@ -263,8 +264,9 @@ public function buildForm(array $form, FormStateInterface $form_state, $query =
             '#default_value' => $defaults['SELECT_DB'],
           ];
 
+          // We don't currently support this well so its being disabled for now.
           // Allow target upload - allow target configuration set to TRUE.
-          if ($config_query_upload) {
+          if (FALSE) {
             $form['#attributes']['enctype'] = 'multipart/form-data';
 
             //

Diff for: src/Services/TripalBlastJobService.php

@@ -247,6 +247,7 @@ public function jobsGetJobByJobId($job_id) {
       $config = \Drupal::service('tripal_blast.database_service')
         ->getDatabaseConfig($blastjob->target_blastdb);
 
+      $job->blastdb = new \stdClass();
       $job->blastdb->db_name = $config['name'];
       $job->blastdb->db_path = $config['path'];
       $job->blastdb->linkout = new \stdClass();

Diff for: src/Services/TripalBlastProgramBlastp.php

@@ -0,0 +1,63 @@
+<?php
+/**
+ * @file
+ * Form definition of BLASTp program.
+ */
+
+namespace Drupal\tripal_blast\Services;
+
+use Drupal\tripal_blast\Services\TripalBlastProgramHelper;
+
+/**
+ * BLASTp program class.
+ */
+class TripalBlastProgramBlastp {
+  const BLASTp = 'blastp';
+
+  /**
+   * Advanced field names used - refer to this value when
+   * validating and submitting fields under advanced options.
+   */
+  public function formFieldNames() {
+    // Keys match field names used in form definition below.
+    $field_name_validator = [];
+    return $field_name_validator;
+  }
+
+  /**
+   * Adds the BLASTp Advanced Options to the passed in form.
+   * This form function is meant to be called within another form definition.
+   *
+   * @param $blast_cache
+   *   BLAST job history to reference information information contained.
+   *
+   * @return array
+   *   Additional form field definitions.
+   */
+  public function formOptions($blast_cache) {
+    $blast = self::BLASTp;
+
+    // Edit and Resubmit functionality.
+    // We want to pull up the details from a previous blast and fill them in as defaults
+    // for this blast.
+    $options = (isset($blast_cache)) ? $blast_cache : [];
+    $defaults = TripalBlastProgramHelper::programGetDefaultValues($options, $blast);
+
+    $form_alter = [];
+
+    return $form_alter;
+  }
+
+  /**
+   * Map advanced options specific to this program to BLAST keywords.
+   *
+   * @param $advanced_field_names
+   *   Values set from form ($form_state).
+   *
+   * @return array
+   *   Form values mapped to BLAST keywords.
+   */
+  public function formFieldBlastKey($advanced_field_values) {
+    return [];
+  }
+}

Diff for: src/Services/TripalBlastProgramBlastx.php

@@ -0,0 +1,62 @@
+<?php
+/**
+ * @file
+ * Form definition of BLASTx program.
+ */
+
+namespace Drupal\tripal_blast\Services;
+
+use Drupal\tripal_blast\Services\TripalBlastProgramHelper;
+
+/**
+ * BLASTx program class.
+ */
+class TripalBlastProgramBlastx {
+  const BLASTx = 'blastx';
+
+  /**
+   * Advanced field names used - refer to this value when
+   * validating and submitting fields under advanced options.
+   */
+  public function formFieldNames() {
+    // Keys match field names used in form definition below.
+    $field_name_validator = [];
+    return $field_name_validator;
+  }
+
+  /**
+   * Adds the BLASTx Advanced Options to the passed in form.
+   * This form function is meant to be called within another form definition.
+   *
+   * @param $blast_cache
+   *   BLAST job history to reference information information contained.
+   *
+   * @return array
+   *   Additional form field definitions.
+   */
+  public function formOptions($blast_cache) {
+    $blast = self::BLASTx;
+
+    // Edit and Resubmit functionality.
+    // We want to pull up the details from a previous blast and fill them in as defaults
+    // for this blast.
+    $options = (isset($blast_cache)) ? $blast_cache : [];
+    $defaults = TripalBlastProgramHelper::programGetDefaultValues($options, $blast);
+
+    $form_alter = [];
+    return $form_alter;
+  }
+
+  /**
+   * Map advanced options specific to this program to BLAST keywords.
+   *
+   * @param $advanced_field_names
+   *   Values set from form ($form_state).
+   *
+   * @return array
+   *   Form values mapped to BLAST keywords.
+   */
+  public function formFieldBlastKey($advanced_field_values) {
+    return [];
+  }
+}

Diff for: src/Services/TripalBlastProgramTblastn.php

@@ -0,0 +1,63 @@
+<?php
+/**
+ * @file
+ * Form definition of tBLASTn program.
+ */
+
+namespace Drupal\tripal_blast\Services;
+
+use Drupal\tripal_blast\Services\TripalBlastProgramHelper;
+
+/**
+ * tBLASTn program class.
+ */
+class TripalBlastProgramTblastn {
+  const tBLASTn = 'tblastn';
+
+  /**
+   * Advanced field names used - refer to this value when
+   * validating and submitting fields under advanced options.
+   */
+  public function formFieldNames() {
+    // Keys match field names used in form definition below.
+    $field_name_validator = [];
+    return $field_name_validator;
+  }
+
+  /**
+   * Adds the tBLASTn Advanced Options to the passed in form.
+   * This form function is meant to be called within another form definition.
+   *
+   * @param $blast_cache
+   *   BLAST job history to reference information information contained.
+   *
+   * @return array
+   *   Additional form field definitions.
+   */
+  public function formOptions($blast_cache) {
+    $blast = self::tBLASTn;
+
+    // Edit and Resubmit functionality.
+    // We want to pull up the details from a previous blast and fill them in as defaults
+    // for this blast.
+    $options = (isset($blast_cache)) ? $blast_cache : [];
+    $defaults = TripalBlastProgramHelper::programGetDefaultValues($options, $blast);
+
+    $form_alter = [];
+
+    return $form_alter;
+  }
+
+  /**
+   * Map advanced options specific to this program to BLAST keywords.
+   *
+   * @param $advanced_field_names
+   *   Values set from form ($form_state).
+   *
+   * @return array
+   *   Form values mapped to BLAST keywords.
+   */
+  public function formFieldBlastKey($advanced_field_values) {
+    return [];
+  }
+}

Diff for: tests/fixtures/Chlamydomonas_reinhardtii_v5.6/Chlamydomonas_reinhardtii_v5.6.nhd

@@ -0,0 +1,54 @@
+10108755045
+106631889149
+11680583722
+122348076936
+123157600146
+133201802923
+133495088526
+13388237823
+141955375240
+14436416117
+14687958800
+148257954821
+14972553776
+159893002343
+17272891335
+176626450533
+180334159331
+192257222211
+202836436513
+209573540437
+21471786988
+21930322904
+220749827215
+222648923514
+249497081312
+253753000153
+254996107652
+271782184127
+278570533441
+282813072951
+286405721439
+287847679634
+29827764759
+316168056929
+317436949018
+32350981650
+32526932432
+325350046620
+340419494324
+35518735411
+35770766810
+367450593917
+36831123715
+368561127048
+374024658030
+380330989942
+403246447016
+411547853319
+420767001647
+47385183422
+63887213144
+73359789128
+83902513038
+85684198425