Skip to content

[WIP] Comparison fdr #30

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
benpullman wants to merge 22 commits into
base: main
Choose a base branch
from
Open

[WIP] Comparison fdr #30

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
22 commits
Select commit Hold shift + click to select a range
8427e7f
update mappings to separate contaminants
benpullman Jul 1, 2022
e56b10a
use variants
benpullman Jul 6, 2022
77c17b9
add non-numeric filter to PE column
benpullman Jul 6, 2022
3bfa14b
update variant definition to be sum of integer mod masses
benpullman Jul 6, 2022
f8120fe
find best cosine over all sequences matching
benpullman Jul 7, 2022
bc5b98f
update to only calculate precursor FDR for spectra that pass PSM FDR
benpullman Jul 7, 2022
43412e1
properly account for PSM quality filters
benpullman Jul 7, 2022
33f22c8
use EI as tie breaker when PSM scores are the same
benpullman Jul 7, 2022
7b99f7f
keep track of num PSMs
benpullman Jul 7, 2022
b3b16da
keep track of overall best PSM score
benpullman Jul 7, 2022
5180540
keep track of num_precursors per variant
benpullman Jul 7, 2022
4698e08
add variant number, option to run with peptidoforms and not variants
benpullman Jul 7, 2022
5dab5cd
assume TMT
benpullman Jul 7, 2022
0a24e54
fix variant aggregation
benpullman Jul 7, 2022
256b7ff
cosine updates
benpullman Jul 7, 2022
e0e0e38
update variant grouping
benpullman Jul 7, 2022
bdb0d1f
update PSM counting
benpullman Jul 8, 2022
baf1bcc
update outputs to be better named
benpullman Jul 10, 2022
4b8aab5
update to fix bug in EI representative
benpullman Jul 12, 2022
f9c160d
update peptide protein cosine
benpullman Jul 15, 2022
8738847
changes for window filters
benpullman Aug 5, 2022
9c5e60f
changes to add FDR to comparison, should be discarded
benpullman Aug 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions peptide_statistics_hpp/binding.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,9 @@
<download port="fastadb" type="folder">
<query name="resource" value="fastadb"/>
</download>
<download port="con_fastadb" type="folder">
<query name="resource" value="con_fastadb"/>
</download>
<download port="dna" type="folder">
<query name="resource" value="dna"/>
</download>
Expand All @@ -54,13 +57,15 @@
<bind action="download_latest_kb" tool="download_latest_kb">
<inputAsRequirement port="params" requirement="params"/>
<inputAsRequirement port="fastadb" requirement="fastadb"/>
<inputAsRequirement port="con_fastadb" requirement="con_fastadb"/>
<inputAsRequirement port="peptide_coverage_comparisons" requirement="peptide_coverage_comparisons"/>
<productionToOutput port="kb_pep" production="kb_pep"/>
</bind>

<bind action="map_peptides" tool="map_peptides">
<inputAsRequirement port="peptide_list" requirement="peptide_list"/>
<inputAsRequirement port="fastadb" requirement="fastadb"/>
<inputAsRequirement port="con_fastadb" requirement="con_fastadb"/>
<inputAsRequirement port="exon_fasta" requirement="exon_fasta"/>
<productionToOutput port="peptide_coverage" production="peptide_coverage"/>
</bind>
Expand All @@ -87,7 +92,9 @@

<bind action="peptide_protein_cosine" tool="peptide_protein_cosine">
<inputAsRequirement port="kb_pep" requirement="kb_pep"/>
<inputAsRequirement port="peptide_coverage_merged_external_compare" requirement="peptide_coverage_merged_external_compare"/>
<inputAsRequirement port="fastadb" requirement="fastadb"/>
<inputAsRequirement port="con_fastadb" requirement="con_fastadb"/>
<inputAsRequirement port="novel_psms_w_cosine" requirement="novel_psms_w_cosine"/>
<inputAsRequirement port="peptide_coverage" requirement="peptide_coverage"/>
<inputAsRequirement port="novel_psms_w_cosine_external" requirement="novel_psms_w_cosine_external"/>
Expand Down
16 changes: 12 additions & 4 deletions peptide_statistics_hpp/flow.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
<object name="kb_pep"/>

<collection name="fastadb"/>
<collection name="con_fastadb"/>

<collection name="parallel_params"/>
<collection name="intermediate_protein_coverage"/>
Expand Down Expand Up @@ -41,6 +42,8 @@
<output port="mztab" collection="mztab"/>
<output port="spec_on_server" collection="spec_on_server"/>
<output port="fastadb" collection="fastadb"/>
<output port="con_fastadb" collection="con_fastadb"/>

<output port="synthetics" collection="synthetics"/>
<output port="params" object="workflowParameters"/>
<output port="peptide_coverage_merged_external" collection="peptide_coverage_merged_external"/>
Expand All @@ -60,16 +63,19 @@

<action name="download_latest_kb">
<input port="params" object="workflowParameters"/>
<input port="fastadb" object="fastadb"/>
<input port="fastadb" collection="fastadb"/>
<input port="con_fastadb" collection="con_fastadb"/>

<input port="peptide_coverage_comparisons" collection="peptide_coverage_comparisons"/>
<output port="kb_pep" object="kb_pep"/>
</action>

<collection name="intermediate_peptide_coverage"/>
<action name="map_peptides" multiplicity="multiple" type="parallel">
<input port="peptide_list" collection="peptide_list" transformation="unfolding"/>
<input port="fastadb" object="fastadb"/>
<input port="exon_fasta" object="exon_fasta"/>
<input port="fastadb" collection="fastadb"/>
<input port="con_fastadb" collection="con_fastadb"/>
<input port="exon_fasta" object="exon_fasta"/>
<output port="peptide_coverage" collection="peptide_coverage"/>
</action>

Expand Down Expand Up @@ -111,8 +117,10 @@

<action name="peptide_protein_cosine">
<input port="kb_pep" object="kb_pep"/>
<input port="peptide_coverage_merged_external_compare" collection="peptide_coverage_comparisons"/>
<input port="novel_psms_w_cosine" collection="novel_psms_w_cosine"/>
<input port="fastadb" object="fastadb"/>
<input port="fastadb" collection="fastadb"/>
<input port="con_fastadb" collection="con_fastadb"/>
<input port="peptide_coverage" collection="peptide_coverage"/>
<input port="novel_psms_w_cosine_external" collection="novel_psms_w_cosine_external"/>
<input port="peptide_coverage_merged_external" collection="peptide_coverage_merged_external"/>
Expand Down
70 changes: 60 additions & 10 deletions peptide_statistics_hpp/input.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,10 @@
<parameter name="fastadb" label="Proteome DB">
<fileGenerator type="upload" purpose="fasta" target="fastadb"/>
</parameter>
<!-- Search file parameters -->
<parameter name="con_fastadb" label="Proteome DB - Contaminants">
<fileGenerator type="upload" purpose="con_fasta" target="con_fastadb"/>
</parameter>

<parameter name="mztab" label="Search mzTab Files">
<fileGenerator type="upload" purpose="mztab" target="mztab"/>
Expand Down Expand Up @@ -41,8 +45,8 @@
<validator type="float" minimum="0"/>
</parameter>

<parameter name="annotated_ions_threshold" label="Annotated Ions Threshold">
<default value="6"/>
<parameter name="annotated_ions_threshold" label="Peptide Breaks Threshold">
<default value="5"/>
<validator type="integer" minimum="0"/>
</parameter>

Expand Down Expand Up @@ -80,22 +84,40 @@

<parameter name="main_fdr" label="FDR for HPP proteins">
<options>
<option label="Common HPP" value="common_hpp" />
<option label="Picked HPP" value="picked_hpp" />
<option label="Traditional" value="traditional" />
<option label="Traditional" value="common_hpp" />
<option label="Picked" value="picked_hpp" />
</options>
<default value="common_hpp" />
<validator type="set" />
</parameter>

<parameter name="leftover_fdr" label="FDR for leftover proteins (if using non-traditional FDR for HPP stage)">
<!--<parameter name="leftover_fdr" label="FDR for leftover proteins">
<options>
<option label="Common" value="common_leftover" />
<option label="Traditional" value="common_leftover" />
<option label="Picked" value="picked_leftover" />
</options>
<default value="picked_leftover" />
<validator type="set" />
</parameter>-->

<parameter name="use_variants" label="Variant-level analysis">
<options>
<option label="Peptidoforms" value="0" />
<option label="Variants" value="1" />
</options>
<default value="0" />
<validator type="set" />
</parameter>

<parameter name="hpp_aggregation_function" label="Sequence-level HPP Aggregation">
<options>
<option label="Sum of variants" value="sum" />
<option label="Max of variants" value="max" />
</options>
<default value="sum" />
<validator type="set" />
</parameter>


<parameter name="parallel_cosine.parallel_cosine" label="Parallelism (For Cosine Calculations)">
<default value="10"/>
Expand All @@ -113,7 +135,7 @@
</parameter>

<parameter name="min_mz" label="Minimum m/z">
<default value="232"/>
<default value="0"/>
<validator type="float" minimum="0"/>
</parameter>

Expand Down Expand Up @@ -227,6 +249,16 @@
<module id="fastadb" type="fileSelector">
<property name="label">Proteome DB</property>
</module>
</cell>
<cell>
<label>
<content parameter="con_fastadb"/>
</label>
</cell>
<cell colspan="3">
<module id="con_fastadb" type="fileSelector">
<property name="label">Proteome DB - Contaminants</property>
</module>
</cell>
</row>

Expand Down Expand Up @@ -363,14 +395,14 @@
<cell colspan="3">
<input type="select" parameter="main_fdr"/>
</cell>
<cell>
<!-- <cell>
<label>
<content parameter="leftover_fdr"/>
</label>
</cell>
<cell colspan="3">
<input type="select" parameter="leftover_fdr"/>
</cell>
</cell> -->
</row>
<row>
<cell>
Expand All @@ -382,6 +414,24 @@
<input type="select" parameter="synthetic_filters"/>
</cell>
</row>
<row>
<cell>
<label>
<content parameter="use_variants"/>
</label>
</cell>
<cell colspan="2">
<input type="select" parameter="use_variants"/>
</cell>
<cell>
<label>
<content parameter="hpp_aggregation_function"/>
</label>
</cell>
<cell colspan="2">
<input type="select" parameter="hpp_aggregation_function"/>
</cell>
</row>

</block>
<block label="Comparison">
Expand Down
Loading