High Level Overview of the SMRT Link Secondary Analysis System

advanced-jobs.dot

digraph {

  subgraph cluster_0 {
  c0_Job [shape=hexagon, color=blue, label="Import DataSet Job"]
  c0_store [shape=cylinder, label="DataStore"]
  c0_ep1 [shape=diamond, label="Path /path/to/alpha_subreadset.xml"]
  c0_ep1 -> c0_Job
  c0_Job -> c0_store
  c0_dsf_02 [shape=tab, label="DataStoreFile (SubreadSet)"]
  c0_dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  c0_dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  c0_dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  c0_store -> c0_dsf_02
  c0_store -> c0_dsf_04
  c0_store -> c0_dsf_05
  c0_store -> c0_dsf_03
  c0_dsf_02 -> c0_dsf_04 [style=dotted]
  c0_dsf_02 -> c0_dsf_05 [style=dotted]
  }

  subgraph cluster_2 {
  c2_Job [shape=hexagon, color=blue, label="Import DataSet Job"]
  c2_store [shape=cylinder, label="DataStore"]
  c2_ep1 [shape=diamond, label="Path /path/to/beta_subreadset.xml"]
  c2_ep1 -> c2_Job
  c2_Job -> c2_store
  c2_dsf_02 [shape=tab, label="DataStoreFile (SubreadSet)"]
  c2_dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  c2_dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  c2_dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  c2_store -> c2_dsf_02
  c2_store -> c2_dsf_04
  c2_store -> c2_dsf_05
  c2_store -> c2_dsf_03
  c2_dsf_02 -> c2_dsf_04 [style=dotted]
  c2_dsf_02 -> c2_dsf_05 [style=dotted]
  }



    subgraph cluster_3 {
  c3_Job [shape=hexagon, color=blue, label="Merge DataSets Job"]
  c3_store [shape=cylinder, label="DataStore"]
  c3_ep1 [shape=diamond, label="Path /path/to/gamma_subreadset.xml"]
  c3_ep1 -> c3_Job
  c3_Job -> c3_store
  c3_dsf_02 [shape=tab, label="DataStoreFile (Merged SubreadSet)"]
  c3_dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  c3_dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  c3_dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  c3_store -> c3_dsf_02
  c3_store -> c3_dsf_04
  c3_store -> c3_dsf_05
  c3_store -> c3_dsf_03
  c3_dsf_02 -> c3_dsf_04 [style=dotted]
  c3_dsf_02 -> c3_dsf_05 [style=dotted]
  }



 subgraph cluster_4 {
  c4_Job [shape=hexagon, color=blue, label="Import DataSet Job"]
  c4_store [shape=cylinder, label="DataStore"]
  c4_ep1 [shape=diamond, label="Path /path/to/referenceset.xml"]
  c4_ep1 -> c4_Job
  c4_Job -> c4_store
  c4_dsf_02 [shape=tab, label="DataStoreFile (ReferenceSet)"]
  c4_dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  c4_store -> c4_dsf_02
  c4_store -> c4_dsf_03
  }

 subgraph cluster_5 {
  c5_Job [shape=hexagon, color=blue, label="Copy (and filter) DataSet"]
  c5_store [shape=cylinder, label="DataStore"]
  c5_ep1 [shape=diamond, label="DataSet UUID=X,filter=rq >= 0.7"]
  c5_ep1 -> c5_Job
  c5_Job -> c5_store
  c5_dsf_02 [shape=tab, label="DataStoreFile (SubreadSet)"]
  c5_dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  c5_dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  c5_dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  c5_store -> c5_dsf_02
  c5_store -> c5_dsf_04
  c5_store -> c5_dsf_05
  c5_store -> c5_dsf_03
  c5_dsf_02 -> c5_dsf_04 [style=dotted]
  c5_dsf_02 -> c5_dsf_05 [style=dotted]
  }

 subgraph cluster_6 {
  c6_Job [shape=hexagon, color=blue, label="Export DataSet(s) Zip Job"]
  c6_store [shape=cylinder, label="DataStore"]
  c6_ep1 [shape=diamond, label="DataSet UUIDs=X,Y,Z"]
  c6_ep1 -> c6_Job
  c6_Job -> c6_store
  c6_dsf_02 [shape=tab, label="DataStoreFile DataSet XML(s) Zip"]
  c6_dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  c6_store -> c6_dsf_02
  c6_store -> c6_dsf_03
  }

  subgraph cluster_01 {
  c1_Job [shape=hexagon, color=blue, label="Analysis Job"]
  c1_store [shape=cylinder, label="DataStore"]
  c1_ep1 [shape=diamond, label="EntryPoint (SubreadSet)"]
  c1_ep2 [shape=diamond, label="EntryPoint (ReferenceSet)"]
  c1_ep1 -> c1_Job
  c1_ep2 -> c1_Job
  c1_Job -> c1_store
  c1_dsf_01 [shape=tab, label="DataStoreFile (Fasta)"]
  c1_dsf_02 [shape=tab, label="DataStoreFile (AlignmentSet)"]
  c1_dsf_03 [shape=tab, label="DataStoreFile (VCF)"]
  c1_dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  c1_dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  c1_dsf_06 [shape=tab, label="DataStoreFile (LOG)"]
  c1_store -> c1_dsf_01
  c1_store -> c1_dsf_02
  c1_store -> c1_dsf_03
  c1_store -> c1_dsf_04
  c1_store -> c1_dsf_05
  c1_store -> c1_dsf_06
  c1_ep1 -> c1_dsf_04 [style=dotted]
  c1_dsf_02 -> c1_dsf_05 [style=dotted]
  c1_ep2 -> c1_dsf_05 [style=dotted]
  }

  c3_dsf_02 -> c1_ep1
  c4_dsf_02 -> c1_ep2

  c0_dsf_02 -> c5_ep1

  c2_dsf_02 -> c3_ep1
  c5_dsf_02 -> c3_ep1

  c5_dsf_02 -> c6_ep1
} 

advanced-jobs.png

advanced-jobs.svg

ArchOverview.md

Arch Overview

Core Nouns of the PacBio System

1. Run (often created/edited from SMRT Link RunDesign, stored as XML)
2. CollectionMetadata a Run has a list of Collection (Primary Analysis will convert a CollectionMetadata to a SubreadSet)
3. PacBio DataSets SubreadSet, ReferenceSet, etc... These are thin-ish XML files that have general metadata as well as pointers to 'external resources' (e.g., BAM, Fasta files) and their companion index files.
4. SMRT Link Job A general (async) unit of work to perform operations on PacBio DataSets
5. ** DataStoreFile** a container for output files from a SMRT Link Job and contains metadata, such as file type, size, path. A list of DataStore Files is called a DataStore. This is the core output of SMRT Link Job.
6. ** Report** a Report is general model to capture Report metrics (also referred to as 'Attributes'), Report Tables and Report Plot Groups. A Report is a specific type of DataStoreFile and are used to communicate details of a SMRT Link Job to the SMRT Link UI (and webservices.)

Second tier models, such as Report View Rules, or Pipeline View Rules are not discussed here.

General Workflow starting from PA

ICS/PA takes a Run XML with a list of Collections, converts each CollectionMeta into a SubreadSet. The SubreadSet is copied from ICS/PA file system into the customer storage on NFS (accessible by the companion SMRT Link instance) and the SubreadSet XML is imported into SMRT Link using the import-dataset Job type in SMRT Link. The Reports for the SubreadSet XML emitted from the import-dataset job show up in RunQC as well as in DataManagement in SMRT Link.

Show below is a sketch of the dataflow.

General SMRT Link Job Model

Simplify, the general interface of a SMRT Link Job, for type T,

A Job takes T as input and produces a PB (T -> Job -> DataStore)

List of EntryPoint PB DataSet -> Job -> DataStore

A DataStore is a list of DataStore files.

Each DataStoreFile can be a different file types, such as, PB DataSet, VCF, ReportJSON, Fasta, etc... and also contains the specific ob id and UUID that generated the DataStoreFile.

During and after SMRT Link Job execution, the DataStoreFiles will be imorted into the db, the DataStoreFile. For a specific subset of file types (PB DataSet types), additional metadata will be stored in the SMRT Link database. Each DataSet has metadata about the specific dataset type as well as metadata about a possible 'parent' DataSet. The DataSet 'parentage' can be a result from copying, merging, analysis (the semantics are not consistent).

Report Details

Each ReportJson file type contains a list of PB Dataset UUIDs in the data model. This is used to communicate which DataSets are specific to the input(s) of a specific ReportJSON. Alternatively said, the EntryPoint PB DataSet(s) might not be directly used to compute the ReportJson* datastore file..

Example Jobs

NOTE, the dotted arrow represents the relation between the Report and the source input for the task at the Report JSON level. This is NOT captured at the SMRT Link Server level.

Import DataSet Job

Accessing the Reports and the source DataSet is clearly defined here by only depending on the Job Id.

I believe the Merge DataSet Job type is Similar.

Example Resequencing Job

Example: Larger Picture of DataFlow in SMRT Link using SMRT Link Jobs

Simple Example

To perform a standard Resequencing Job, the user can run two different import-dataset SMRT Link Jobs, then a pbsmrtpipe (i.e., 'Analysis') SMRT Link Job can be performed.

Steps:

1. Import SubreadSet
2. Import ReferenceSet
3. Run Analysis Job to run the Resequencing Analysis

(Each Job type is shown in its own box)

Advanced Example

To demonstrate a larger dataflow example, consider the following case. A user would like to import SubreadSet alpha and beta, perform filtering on beta, merge the datasets, perform a Resequencing analysis on the merged subreadset and export the filtered SubreadSet as a zip.

Steps:

1. Import ReferenceSet, SubreadSet alpha and Beta
2. Create a filtered SubreadSet from SubreadSet alpha
3. Create a Merged SubreadSet from SubreadSet Beta and the output of #2
4. Create an Analysis Job using #3 and ReferenceSet from #1
5. Create a DataSet XML(s) ZIP from the output of #3

This demonstrates graph nature of the design and composibility of different SMRT Link Job types. Note that data provenance is for free in the model.

connected-jobs.dot

digraph {

  subgraph cluster_0 {
  c0_Job [shape=hexagon, color=blue, label="Import DataSet"]
  c0_store [shape=cylinder, label="DataStore"]
  c0_ep1 [shape=diamond, label="Path /path/to/subreadset.xml"]
  c0_ep1 -> c0_Job
  c0_Job -> c0_store
  c0_dsf_02 [shape=tab, label="DataStoreFile (SubreadSet)"]
  c0_dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  c0_dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  c0_dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  c0_store -> c0_dsf_02
  c0_store -> c0_dsf_04
  c0_store -> c0_dsf_05
  c0_store -> c0_dsf_03
  c0_dsf_02 -> c0_dsf_04 [style=dotted]
  c0_dsf_02 -> c0_dsf_05 [style=dotted]
  }

 subgraph cluster_2 {
  c2_Job [shape=hexagon, color=blue, label="Import DataSet"]
  c2_store [shape=cylinder, label="DataStore"]
  c2_ep1 [shape=diamond, label="Path /path/to/referenceset.xml"]
  c2_ep1 -> c2_Job
  c2_Job -> c2_store
  c2_dsf_02 [shape=tab, label="DataStoreFile (ReferenceSet)"]
  c2_dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  c2_store -> c2_dsf_02
  c2_store -> c2_dsf_03
  }

  subgraph cluster_02 {
  c1_Job [shape=hexagon, color=blue, label="Analysis Job"]
  c1_store [shape=cylinder, label="DataStore"]
  c1_ep1 [shape=diamond, label="EntryPoint (SubreadSet)"]
  c1_ep2 [shape=diamond, label="EntryPoint (ReferenceSet)"]
  c1_ep1 -> c1_Job
  c1_ep2 -> c1_Job
  c1_Job -> c1_store
  c1_dsf_01 [shape=tab, label="DataStoreFile (Fasta)"]
  c1_dsf_02 [shape=tab, label="DataStoreFile (AlignmentSet)"]
  c1_dsf_03 [shape=tab, label="DataStoreFile (VCF)"]
  c1_dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  c1_dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  c1_dsf_06 [shape=tab, label="DataStoreFile (LOG)"]
  c1_store -> c1_dsf_01
  c1_store -> c1_dsf_02
  c1_store -> c1_dsf_03
  c1_store -> c1_dsf_04
  c1_store -> c1_dsf_05
  c1_store -> c1_dsf_06
  c1_ep1 -> c1_dsf_04 [style=dotted]
  c1_dsf_02 -> c1_dsf_05 [style=dotted]
  c1_ep2 -> c1_dsf_05 [style=dotted]
  }

  c2_dsf_02 -> c1_ep2
  c0_dsf_02 -> c1_ep1
  
} 

connected-jobs.png

connected-jobs.svg

DataSet-Job-Report-ScratchPad.md

Notes on SMRT Link DataSet, Job, DataStoreFile, Report models

Current Model for SMRT Link 'Job' model

Simplify, the general interface of a SMRT Link Job, for type T,

A Job takes T as input and produces a PB (T -> Job -> DataStore)

List of EntryPoint PB DataSet -> Job -> DataStore

A DataStore is a list of DataStore files.

Each DataStoreFile can be a different file types, such as, PB DataSet, VCF, ReportJSON, Fasta, etc... and also contains the specific ob id and UUID that generated the DataStoreFile.

During and after SMRT Link Job execution, the DataStoreFiles will be imorted into the db, the DataStoreFile. For a specific subset of file types (PB DataSet types), additional metadata will be stored in the SMRT Link database. Each DataSet has metadata about the specific dataset type as well as metadata about a possible 'parent' DataSet. The DataSet 'parentage' can be a result from copying, merging, analysis (the semantics are not consistent).

Report Details

Each ReportJson file type contains a list of PB Dataset UUIDs in the data model. This is used to communicate which DataSets are specific to the input(s) of a specific ReportJSON. Alternatively said, the EntryPoint PB DataSet(s) might not be directly used to compute the ReportJson* datastore file..

NOTE This is the core issue. Currently the system only communicates the DataSet Job Id

Example Jobs

NOTE, the dotted arrow represents the relation between the Report and the source input for the task at the Report JSON level. This is NOT captured at the SMRT Link Server level.

Import DataSet Job

Accessing the Reports and the source DataSet is clearly defined here by only depending on the Job Id.

I believe the Merge DataSet Job type is Similar.

Example Resequencing Job

The use case here is often to view all the output'ed Reports and links back to the source DataSet is not necessary.

However, viewing the AlignmentSet in DM will start yield unexpected results. This is why the SMRT Link has a workaround to filter all the Reports from the Job and only show the DataSets where for the AlignmentSet in interest. This works for small number of Reports, but DOES NOT work for an Job that outputs "many" reports (because of the explicit filtering necessary on the client side).

Example Demux Analysis Job

The model is more involved when N DataSets and N (or more) companion reports per DataSet are emitted.

The core issue is that a specific DataSet of the N will return

Job Output Access Points

From the file system access point, the DataStore* is accessible in the datastore.json file in the SMRT Link Job directory (the path of this is not consistent, but it's often in the root directory of the Job).

From the webservices, the datastore files are accessible from DM where DS-TYPE' is the DataSet type 'short name' (e.g., subreads) and DS-IDABLE is the DataSet (local) integer id, or (global) UUID.

smrt-link/datasets/<DS-TYPE>/<DS-IDABLE>/reports

NOTE The reports interface is the core issue because it assumes the Job Id link. I believe the SMRT Link UI is filtering to get around this, however, this is not scalable because the SMRT Link UI has to fetch the details of all the reports, then filter out based on the DataSet UUID in the report.

And from the Jobs context.

smrt-link/job-manager/jobs/<JOB-TYPE>/<JOB-IDABLE>/reports

The Job is not a problem and the interface does NOT need to be changed. Semantically, the interface captures exactly what is expected.

Possible Solution

Capture new Report -> DataSet(s) relation

• Add new table to capture DataStoreFile -> Set(DataStoreFile) relation
• On import parse Report and assign
• Update /smrt-link/<DS-TYPE>/<DS-IDABLE>/reports to also filter by 'parent' DataStore File UUID(s)

This is straight forward, but this now requires a join to get the reports for a specific DataSet.

Legacy Data

Need to handle legacy data, specifically for the smrt-link/datasets/<DS-TYPE>/<DS-IDABLE>/reports webservice endpoint.

Possible Solutions

1. During db migration on "start/upgrade", parse the Report JSON files and extract the DataSet UUID from the Report JSON file on disk and update the database.

   • BAD. This is expensive (could be parsing 1000's of report JSON files)
   • BAD. The dataset_uuids field might not be populated consistently. Not clear when that was added in the SMRT Link version.
   • GOOD. Potentially parsing the raw data removes guesswork at the job level (See #3 and the above issue is resolved)

2. Hide the details in the API and dispatch on lookup based on the Job Version. (i.e., if job > 6.0.0, do X else do Y to get reports)

   • BAD. Fundamentally has different semantic results.
   • This is probably very difficult to debug when it's not working as expected. The dispatch from different SL versions would requires an extra join to the engine_jobs table.
   • GOOD. Potentially least amount of db migration machinery

3. During db migration, attempt a thinner approach to migrate old data and assign Report -> DataSet relation based on the Job type

   • import-dataset (Look at the output DataStore file, get the (single) DataSet DataStoreFile, get the List of Reports, then update the DB
   • merge-datasets (Similar to import-dataset)
   • analysis job (Use the Entry Point(s) to get the UUID(s) and assign to all output Reports) (Note, this is not correct. The SL UI would still have to keep the legacy filtering model in place)
   • Other job types (Don't support?)

GOOD. Thin-ish migration BAD. Edge cases on capturing the

demux-pbsmrtpipe-job.dot

strict digraph {
  Job [shape=hexagon, color=blue, label="Demux Analysis Job"]
  store [shape=cylinder, label="DataStore"]
  ep1 [shape=diamond, label="EntryPoint (SubreadSet)"]
  ep2 [shape=diamond, label="EntryPoint (BarcodeSet)"]
  ep1 -> Job
  ep2 -> Job
  Job -> store
  s1 [shape=tab, label="DataStoreFile (SubreadSet_01)"]
  s2 [shape=tab, label="DataStoreFile (SubreadSet_02)"]
  s3 [shape=tab, label="DataStoreFile (SubreadSet_03)"]
  r1 [shape=tab, label="DataStoreFile (Report_01)"]
  r2 [shape=tab, label="DataStoreFile (Report_02)"]
  r3 [shape=tab, label="DataStoreFile (Report_03)"]
  dsf_01 [shape=tab, label="DataStoreFile (Log)"]
  store -> dsf_01
  store -> s1
  store -> s2
  store -> s3
  store -> r1
  store -> r2
  store -> r3
  s1 -> r1 [style=dotted]
  s2 -> r2 [style=dotted]
  s3 -> r3 [style=dotted]
} 

demux-pbsmrtpipe-job.png

demux-pbsmrtpipe-job.svg

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
 "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
 -->
<!-- Title: %3 Pages: 1 -->
<svg width="881pt" height="332pt"
 viewBox="0.00 0.00 881.24 332.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 328)">
<title>%3</title>
<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-328 877.2417,-328 877.2417,4 -4,4"/>
<!-- Job -->
<g id="node1" class="node">
<title>Job</title>
<polygon fill="none" stroke="#0000ff" points="564.0845,-234 515.8794,-252 419.4692,-252 371.2641,-234 419.4692,-216 515.8794,-216 564.0845,-234"/>
<text text-anchor="middle" x="467.6743" y="-229.8" font-family="Times,serif" font-size="14.00" fill="#000000">Demux Analysis Job</text>
</g>
<!-- store -->
<g id="node2" class="node">
<title>store</title>
<path fill="none" stroke="#000000" d="M503.6538,-176.7273C503.6538,-178.5331 487.5272,-180 467.6743,-180 447.8214,-180 431.6948,-178.5331 431.6948,-176.7273 431.6948,-176.7273 431.6948,-147.2727 431.6948,-147.2727 431.6948,-145.4669 447.8214,-144 467.6743,-144 487.5272,-144 503.6538,-145.4669 503.6538,-147.2727 503.6538,-147.2727 503.6538,-176.7273 503.6538,-176.7273"/>
<path fill="none" stroke="#000000" d="M503.6538,-176.7273C503.6538,-174.9214 487.5272,-173.4545 467.6743,-173.4545 447.8214,-173.4545 431.6948,-174.9214 431.6948,-176.7273"/>
<text text-anchor="middle" x="467.6743" y="-157.8" font-family="Times,serif" font-size="14.00" fill="#000000">DataStore</text>
</g>
<!-- Job&#45;&gt;store -->
<g id="edge3" class="edge">
<title>Job&#45;&gt;store</title>
<path fill="none" stroke="#000000" d="M467.6743,-215.8314C467.6743,-208.131 467.6743,-198.9743 467.6743,-190.4166"/>
<polygon fill="#000000" stroke="#000000" points="471.1744,-190.4132 467.6743,-180.4133 464.1744,-190.4133 471.1744,-190.4132"/>
</g>
<!-- s1 -->
<g id="node5" class="node">
<title>s1</title>
<polygon fill="none" stroke="#000000" points="191.5233,-108 11.8254,-108 11.8254,-112 -.1746,-112 -.1746,-72 191.5233,-72 191.5233,-108"/>
<polyline fill="none" stroke="#000000" points="-.1746,-108 11.8254,-108 "/>
<text text-anchor="middle" x="95.6743" y="-85.8" font-family="Times,serif" font-size="14.00" fill="#000000">DataStoreFile (SubreadSet_01)</text>
</g>
<!-- store&#45;&gt;s1 -->
<g id="edge5" class="edge">
<title>store&#45;&gt;s1</title>
<path fill="none" stroke="#000000" d="M431.6674,-155.0309C378.3349,-144.7085 276.2858,-124.9571 198.5858,-109.9183"/>
<polygon fill="#000000" stroke="#000000" points="199.2383,-106.4798 188.7554,-108.0157 197.9081,-113.3522 199.2383,-106.4798"/>
</g>
<!-- s2 -->
<g id="node6" class="node">
<title>s2</title>
<polygon fill="none" stroke="#000000" points="439.5233,-108 259.8254,-108 259.8254,-112 247.8254,-112 247.8254,-72 439.5233,-72 439.5233,-108"/>
<polyline fill="none" stroke="#000000" points="247.8254,-108 259.8254,-108 "/>
<text text-anchor="middle" x="343.6743" y="-85.8" font-family="Times,serif" font-size="14.00" fill="#000000">DataStoreFile (SubreadSet_02)</text>
</g>
<!-- store&#45;&gt;s2 -->
<g id="edge6" class="edge">
<title>store&#45;&gt;s2</title>
<path fill="none" stroke="#000000" d="M437.9732,-144.7542C421.7436,-135.3306 401.4173,-123.5282 383.7958,-113.2963"/>
<polygon fill="#000000" stroke="#000000" points="385.2688,-110.1045 374.8634,-108.1098 381.7539,-116.158 385.2688,-110.1045"/>
</g>
<!-- s3 -->
<g id="node7" class="node">
<title>s3</title>
<polygon fill="none" stroke="#000000" points="687.5233,-108 507.8254,-108 507.8254,-112 495.8254,-112 495.8254,-72 687.5233,-72 687.5233,-108"/>
<polyline fill="none" stroke="#000000" points="495.8254,-108 507.8254,-108 "/>
<text text-anchor="middle" x="591.6743" y="-85.8" font-family="Times,serif" font-size="14.00" fill="#000000">DataStoreFile (SubreadSet_03)</text>
</g>
<!-- store&#45;&gt;s3 -->
<g id="edge7" class="edge">
<title>store&#45;&gt;s3</title>
<path fill="none" stroke="#000000" d="M497.3754,-144.7542C513.605,-135.3306 533.9313,-123.5282 551.5528,-113.2963"/>
<polygon fill="#000000" stroke="#000000" points="553.5948,-116.158 560.4852,-108.1098 550.0798,-110.1045 553.5948,-116.158"/>
</g>
<!-- r1 -->
<g id="node8" class="node">
<title>r1</title>
<polygon fill="none" stroke="#000000" points="242.3611,-36 88.9875,-36 88.9875,-40 76.9875,-40 76.9875,0 242.3611,0 242.3611,-36"/>
<polyline fill="none" stroke="#000000" points="76.9875,-36 88.9875,-36 "/>
<text text-anchor="middle" x="159.6743" y="-13.8" font-family="Times,serif" font-size="14.00" fill="#000000">DataStoreFile (Report_01)</text>
</g>
<!-- store&#45;&gt;r1 -->
<g id="edge8" class="edge">
<title>store&#45;&gt;r1</title>
<path fill="none" stroke="#000000" d="M431.4011,-160.2268C383.9791,-156.4624 299.7744,-144.7072 238.6743,-108 224.6453,-99.5718 197.9929,-67.4709 179.5495,-44.002"/>
<polygon fill="#000000" stroke="#000000" points="182.3099,-41.8501 173.4024,-36.1137 176.7884,-46.1529 182.3099,-41.8501"/>
</g>
<!-- r2 -->
<g id="node9" class="node">
<title>r2</title>
<polygon fill="none" stroke="#000000" points="458.3611,-36 304.9875,-36 304.9875,-40 292.9875,-40 292.9875,0 458.3611,0 458.3611,-36"/>
<polyline fill="none" stroke="#000000" points="292.9875,-36 304.9875,-36 "/>
<text text-anchor="middle" x="375.6743" y="-13.8" font-family="Times,serif" font-size="14.00" fill="#000000">DataStoreFile (Report_02)</text>
</g>
<!-- store&#45;&gt;r2 -->
<g id="edge9" class="edge">
<title>store&#45;&gt;r2</title>
<path fill="none" stroke="#000000" d="M467.5435,-143.6681C466.5985,-124.3994 462.7425,-93.901 448.6743,-72 441.1382,-60.2679 430.0948,-50.1965 418.8675,-42.0387"/>
<polygon fill="#000000" stroke="#000000" points="420.5306,-38.9358 410.3011,-36.1776 416.5779,-44.713 420.5306,-38.9358"/>
</g>
<!-- r3 -->
<g id="node10" class="node">
<title>r3</title>
<polygon fill="none" stroke="#000000" points="736.3611,-36 582.9875,-36 582.9875,-40 570.9875,-40 570.9875,0 736.3611,0 736.3611,-36"/>
<polyline fill="none" stroke="#000000" points="570.9875,-36 582.9875,-36 "/>
<text text-anchor="middle" x="653.6743" y="-13.8" font-family="Times,serif" font-size="14.00" fill="#000000">DataStoreFile (Report_03)</text>
</g>
<!-- store&#45;&gt;r3 -->
<g id="edge10" class="edge">
<title>store&#45;&gt;r3</title>
<path fill="none" stroke="#000000" d="M503.917,-158.8245C562.2992,-152.8755 673.0325,-137.8651 696.6743,-108 712.0723,-88.5487 696.7701,-62.6826 680.3061,-43.6729"/>
<polygon fill="#000000" stroke="#000000" points="682.8425,-41.2601 673.5121,-36.2408 677.6759,-45.9831 682.8425,-41.2601"/>
</g>
<!-- dsf_01 -->
<g id="node11" class="node">
<title>dsf_01</title>
<polygon fill="none" stroke="#000000" points="873.3092,-108 756.0395,-108 756.0395,-112 744.0395,-112 744.0395,-72 873.3092,-72 873.3092,-108"/>
<polyline fill="none" stroke="#000000" points="744.0395,-108 756.0395,-108 "/>
<text text-anchor="middle" x="808.6743" y="-85.8" font-family="Times,serif" font-size="14.00" fill="#000000">DataStoreFile (Log)</text>
</g>
<!-- store&#45;&gt;dsf_01 -->
<g id="edge4" class="edge">
<title>store&#45;&gt;dsf_01</title>
<path fill="none" stroke="#000000" d="M503.7472,-154.8116C554.3121,-144.6792 649.1136,-125.4779 729.6743,-108 731.1349,-107.6831 732.6104,-107.3615 734.0969,-107.0362"/>
<polygon fill="#000000" stroke="#000000" points="735.0186,-110.4171 744.0293,-104.8441 733.51,-103.5816 735.0186,-110.4171"/>
</g>
<!-- ep1 -->
<g id="node3" class="node">
<title>ep1</title>
<polygon fill="none" stroke="#000000" points="321.6743,-324 184.8544,-306 321.6743,-288 458.4942,-306 321.6743,-324"/>
<text text-anchor="middle" x="321.6743" y="-301.8" font-family="Times,serif" font-size="14.00" fill="#000000">EntryPoint (SubreadSet)</text>
</g>
<!-- ep1&#45;&gt;Job -->
<g id="edge1" class="edge">
<title>ep1&#45;&gt;Job</title>
<path fill="none" stroke="#000000" d="M350.5192,-291.7751C370.9146,-281.7171 398.6756,-268.0267 422.0549,-256.4973"/>
<polygon fill="#000000" stroke="#000000" points="423.6854,-259.5957 431.1061,-252.0336 420.5893,-253.3176 423.6854,-259.5957"/>
</g>
<!-- ep2 -->
<g id="node4" class="node">
<title>ep2</title>
<polygon fill="none" stroke="#000000" points="614.6743,-324 476.9865,-306 614.6743,-288 752.3621,-306 614.6743,-324"/>
<text text-anchor="middle" x="614.6743" y="-301.8" font-family="Times,serif" font-size="14.00" fill="#000000">EntryPoint (BarcodeSet)</text>
</g>
<!-- ep2&#45;&gt;Job -->
<g id="edge2" class="edge">
<title>ep2&#45;&gt;Job</title>
<path fill="none" stroke="#000000" d="M585.6318,-291.7751C565.0968,-281.7171 537.1456,-268.0267 513.6062,-256.4973"/>
<polygon fill="#000000" stroke="#000000" points="515.0132,-253.2891 504.493,-252.0336 511.9341,-259.5756 515.0132,-253.2891"/>
</g>
<!-- s1&#45;&gt;r1 -->
<g id="edge11" class="edge">
<title>s1&#45;&gt;r1</title>
<path fill="none" stroke="#000000" stroke-dasharray="1,5" d="M111.8242,-71.8314C119.346,-63.3694 128.4308,-53.1489 136.6547,-43.8971"/>
<polygon fill="#000000" stroke="#000000" points="139.2792,-46.2127 143.307,-36.4133 134.0474,-41.5621 139.2792,-46.2127"/>
</g>
<!-- s2&#45;&gt;r2 -->
<g id="edge12" class="edge">
<title>s2&#45;&gt;r2</title>
<path fill="none" stroke="#000000" stroke-dasharray="1,5" d="M351.7493,-71.8314C355.2845,-63.8771 359.5103,-54.369 363.42,-45.5723"/>
<polygon fill="#000000" stroke="#000000" points="366.6275,-46.9729 367.4906,-36.4133 360.2309,-44.1299 366.6275,-46.9729"/>
</g>
<!-- s3&#45;&gt;r3 -->
<g id="edge13" class="edge">
<title>s3&#45;&gt;r3</title>
<path fill="none" stroke="#000000" stroke-dasharray="1,5" d="M607.3195,-71.8314C614.5334,-63.454 623.2313,-53.3531 631.1348,-44.1749"/>
<polygon fill="#000000" stroke="#000000" points="633.9454,-46.2748 637.8184,-36.4133 628.641,-41.7071 633.9454,-46.2748"/>
</g>
</g>
</svg>

ics.dot

strict digraph {

  Run [shape=component, label="PacBio Run (XML)"]

  c1 [shape=box, label="CollectionMetadata 1"]
  c2 [shape=box, label="CollectionMetadata 2"]
  c3 [shape=box, label="CollectionMetadata 3"]
  c4 [shape=box, label="CollectionMetadata 4"]

  Run -> c1
  Run -> c2
  Run -> c3
  Run -> c4

  p [shape=parallelogram, color=blue, label="Primary Analysis: Convert CollectionMeta to SubreadSet)"]

  f1 [shape=tab, label="PA File (SubreadSet XML) on PA file system"]

  copy_job [shape=parallelogram, color=blue, label="Primary Analysis: Copy to Customer FileSystem"]
  customer_subreadset [shape=tab, label="SubreadSet XML on Customer FileSystem"]
  import_job [shape=parallelogram, color=blue, label="Primary Analysis: Import SubreadSet XML into SMRT Link using import-dataset Job"]

  c1 -> p
  p -> f1

  f1 -> copy_job
  copy_job -> customer_subreadset
  customer_subreadset -> import_job

} 

ics.png

import-dataset-job.dot

strict digraph {
  Job [shape=hexagon, color=blue, label="Import DataSet"]
  store [shape=cylinder, label="DataStore"]
  ep1 [shape=diamond, label="Path /path/to/subreadset.xml"]
  ep1 -> Job
  Job -> store
  dsf_02 [shape=tab, label="DataStoreFile (SubreadSet)"]
  dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  dsf_03 [shape=tab, label="DataStoreFile (Log)"]
  store -> dsf_02
  store -> dsf_04
  store -> dsf_05
  store -> dsf_03
  dsf_02 -> dsf_04 [style=dotted]
  dsf_02 -> dsf_05 [style=dotted]
} 

import-dataset-job.png

import-dataset-job.svg

Makefile

default: convert

convert:
	dot -Tpng demux-pbsmrtpipe-job.dot  -o demux-pbsmrtpipe-job.png
	dot -Tsvg demux-pbsmrtpipe-job.dot  -o demux-pbsmrtpipe-job.svg
	dot -Tpng import-dataset-job.dot -o import-dataset-job.png
	dot -Tsvg import-dataset-job.dot -o import-dataset-job.svg
	dot -Tpng pbsmrtpipe-job.dot -o pbsmrtpipe-job.png
	dot -Tsvg pbsmrtpipe-job.dot -o pbsmrtpipe-job.svg
	dot -Tpng connected-jobs.dot -o connected-jobs.png
	dot -Tsvg connected-jobs.dot -o connected-jobs.svg
	dot -Tpng advanced-jobs.dot -o advanced-jobs.png
	dot -Tsvg advanced-jobs.dot -o advanced-jobs.svg
	dot -Tpng ics.dot -o ics.png
	dot -Tsvg system-job-running.dot -o system-job-running.svg
	dot -Tpng system-job-running.dot -o system-job-running.png


clean:
	rm *.png

pbsmrtpipe-job.dot

strict digraph {
  Job [shape=hexagon, color=blue, label="Analysis Job"]
  store [shape=cylinder, label="DataStore"]
  ep1 [shape=diamond, label="EntryPoint (SubreadSet)"]
  ep2 [shape=diamond, label="EntryPoint (ReferenceSet)"]
  ep1 -> Job
  ep2 -> Job
  Job -> store
  dsf_01 [shape=tab, label="DataStoreFile (Fasta)"]
  dsf_02 [shape=tab, label="DataStoreFile (AlignmentSet)"]
  dsf_03 [shape=tab, label="DataStoreFile (VCF)"]
  dsf_04 [shape=tab, label="DataStoreFile (Report_01)"]
  dsf_05 [shape=tab, label="DataStoreFile (Report_02)"]
  dsf_06 [shape=tab, label="DataStoreFile (LOG)"]
  store -> dsf_01
  store -> dsf_02
  store -> dsf_03
  store -> dsf_04
  store -> dsf_05
  store -> dsf_06
  ep1 -> dsf_04 [style=dotted]
  dsf_02 -> dsf_05 [style=dotted]
  ep2 -> dsf_05 [style=dotted]
} 

pbsmrtpipe-job.png

pbsmrtpipe-job.svg

system-job-running.dot

digraph {
        postgres_db [shape=cylinder];
        WorkerA [shape=diamond, color=blue];
        WorkerB [shape=diamond, color=blue];
        WorkerC [shape=diamond, color=blue];
        WorkerD [shape=pentagon, color=green];
        WorkerE [shape=pentagon, color=orange];

        pbsmrtpipeJobA [shape=rectangle];
        pbsmrtpipeJobB [shape=rectangle]
        pbsmrtpipeJobC [shape=rectangle]

        postgres_db -> SL_Services
        SL_Services -> WorkerA
        SL_Services -> WorkerB
        SL_Services -> WorkerC
        SL_Services -> WorkerD
        SL_Services -> WorkerE

        WorkerA -> pbsmrtpipeJobA
        WorkerB -> pbsmrtpipeJobB
        WorkerC -> pbsmrtpipeJobC
        WorkerD -> backup_db
        WorkerE -> import_dataset


        pbsmrtpipeJobA -> taskA_01
        pbsmrtpipeJobA -> taskA_02
        pbsmrtpipeJobA -> taskA_03
        pbsmrtpipeJobA -> taskA_04
        pbsmrtpipeJobA -> taskA_05

        taskA_01 -> sge_sync_job_A_01
        taskA_02 -> sge_sync_job_A_02
        taskA_03 -> sge_sync_job_A_03
        taskA_04 -> sge_sync_job_A_04
        taskA_05 -> sge_sync_job_A_05


        pbsmrtpipeJobB -> taskB_01
        pbsmrtpipeJobB -> taskB_02

        taskB_01 -> sge_sync_job_B_01
        taskB_02 -> sge_sync_job_B_02

        pbsmrtpipeJobC -> taskC_01
        pbsmrtpipeJobC -> taskC_02

        taskC_01 -> sge_sync_job_C_01
        taskC_02 -> sge_sync_job_C_02


}

system-job-running.png

system-job-running.svg