-
Notifications
You must be signed in to change notification settings - Fork 4
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'dev' of https://github.com/bigbio/quantms.io into dev
- Loading branch information
Showing
12 changed files
with
675 additions
and
23 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -4,4 +4,5 @@ build | |
| .idea | ||
| data | ||
| docs/.vscode | ||
| __pycache__ | ||
| __pycache__ | ||
| .vscode | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,39 @@ | ||
| PSM_MAP = { | ||
| "sequence": "sequence", | ||
| "modifications": "modifications", | ||
|
|
||
| "opt_global_Posterior_Error_Probability_score": "posterior_error_probability", | ||
| "opt_global_q-value": "global_qvalue", | ||
| "opt_global_cv_MS:1002217_decoy_peptide": "is_decoy", | ||
| "calc_mass_to_charge": "calculated_mz", | ||
| "accession": "pg_accessions", | ||
| "unique": "unique", | ||
| "charge": "precursor_charge", | ||
| "exp_mass_to_charge": "observed_mz", | ||
| "retention_time": "rt", | ||
| } | ||
|
|
||
| PSM_USECOLS = list(PSM_MAP.keys()) + [ | ||
| "spectra_ref", | ||
| "start", | ||
| "end", | ||
| ] | ||
|
|
||
| ADDITIONS = [ | ||
| "peptidoform", | ||
| "modification_details", | ||
| "additional_scores", | ||
| "pg_positions", | ||
| "protein_global_qvalue", | ||
| "gg_accessions", | ||
| "gg_names", | ||
| "predicted_rt" | ||
| "reference_file_name" | ||
| "scan_number" | ||
| "ion_mobility" | ||
| "num_peaks" | ||
| "mz_array" | ||
| "intensity_array" | ||
| "rank" | ||
| "cv_params" | ||
| ] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,165 @@ | ||
| import pyarrow as pa | ||
| PEPTIDE_FIELDS = [ | ||
| pa.field( | ||
| "sequence", | ||
| pa.string(), | ||
| metadata={"description": "The peptide’s sequence corresponding to the PSM"}, | ||
| ), | ||
| pa.field( | ||
| "peptidoform", | ||
| pa.string(), | ||
| metadata={"description": "Peptide sequence with modifications: Read the specification for more details"}, | ||
| ), | ||
| pa.field( | ||
| "modifications", | ||
| pa.list_(pa.string()), | ||
| metadata={"description": "List of modifications as string array, easy for search and filter"}, | ||
| ), | ||
| pa.field( | ||
| "modification_details", | ||
| pa.list_(pa.string()), | ||
| metadata={"description": "List of alternative site probabilities for the modification format: read the specification for more details"}, | ||
| ), | ||
| pa.field( | ||
| "posterior_error_probability", | ||
| pa.float32(), | ||
| metadata={"description": "Posterior error probability for the given peptide spectrum match"}, | ||
| ), | ||
| pa.field("global_qvalue", pa.float32(), metadata={"description": "Global q-value of the peptide or psm at the level of the experiment"}), | ||
|
|
||
| pa.field( | ||
| "is_decoy", | ||
| pa.int32(), | ||
| metadata={"description": "Decoy indicator, 1 if the PSM is a decoy, 0 target"}, | ||
| ), | ||
| pa.field( | ||
| "calculated_mz", | ||
| pa.float32(), | ||
| metadata={"description": "Theoretical peptide mass-to-charge ratio based on identified sequence and modifications"}, | ||
| ), | ||
| pa.field( | ||
| "additional_scores", | ||
| pa.list_( | ||
| pa.struct([ | ||
| ("name", pa.string()), | ||
| ("value", pa.float32()) | ||
| ]) | ||
| ), | ||
| metadata={"description": "List of structures, each structure contains two fields: name and value"}, | ||
| ), | ||
|
|
||
| pa.field( | ||
| "pg_accessions", | ||
| pa.list_(pa.string()), | ||
| metadata={"description": "Protein group accessions of all the proteins that the peptide maps to"}, | ||
| ), | ||
| pa.field( | ||
| "pg_positions", | ||
| pa.list_(pa.string()), | ||
| metadata={"description": "Protein start and end positions written as start_post:end_post"}, | ||
| ), | ||
| pa.field( | ||
| "unique", | ||
| pa.int32(), | ||
| metadata={"description": "Unique peptide indicator, if the peptide maps to a single protein, the value is 1, otherwise 0"}, | ||
| ), | ||
| pa.field( | ||
| "protein_global_qvalue", | ||
| pa.float32(), | ||
| metadata={"description": "Global q-value of the protein group at the experiment level"}, | ||
| ), | ||
| pa.field( | ||
| "gg_accessions", | ||
| pa.list_(pa.string()), | ||
| metadata={"description": "Gene accessions, as string array"}, | ||
| ), | ||
| pa.field( | ||
| "gg_names", | ||
| pa.list_(pa.string()), | ||
| metadata={"description": "Gene names, as string array"}, | ||
| ), | ||
|
|
||
| pa.field( | ||
| "precursor_charge", | ||
| pa.int32(), | ||
| metadata={"description": "Precursor charge"}, | ||
| ), | ||
| pa.field( | ||
| "observed_mz", | ||
| pa.float32(), | ||
| metadata={"description": "Experimental peptide mass-to-charge ratio of identified peptide (in Da)"}, | ||
| ), | ||
| pa.field( | ||
| "rt", | ||
| pa.float32(), | ||
| metadata={"description": "MS2 scan’s precursor retention time (in seconds)"}, | ||
| ), | ||
| pa.field( | ||
| "predicted_rt", | ||
| pa.float32(), | ||
| metadata={"description": "Predicted retention time of the peptide (in seconds)"}, | ||
| ), | ||
| pa.field( | ||
| "quantmsio_version", | ||
| pa.string(), | ||
| metadata={"description": "The version of quantms.io"}, | ||
| ) | ||
| ] | ||
|
|
||
| PSM_UNIQUE_FIELDS = [ | ||
| pa.field( | ||
| "reference_file_name", | ||
| pa.string(), | ||
| metadata={"description": "Spectrum file name with no path information and not including the file extension"}, | ||
| ), | ||
| pa.field( | ||
| "scan_number", | ||
| pa.string(), | ||
| metadata={"description": "Scan number of the spectrum"}, | ||
| ), | ||
| pa.field( | ||
| "ion_mobility", | ||
| pa.float32(), | ||
| metadata={"description": "Ion mobility value for the precursor ion"}, | ||
| ), | ||
| pa.field("num_peaks", pa.int32(), metadata={"description": "Number of peaks in the spectrum used for the peptide spectrum match"}), | ||
| pa.field( | ||
| "mz_array", | ||
| pa.list_(pa.float32()), | ||
| metadata={"description": "Array of m/z values for the spectrum used for the peptide spectrum match"}, | ||
| ), | ||
| pa.field( | ||
| "intensity_array", | ||
| pa.list_(pa.float32()), | ||
| metadata={"description": "Array of intensity values for the spectrum used for the peptide spectrum match"}, | ||
| ), | ||
| pa.field("rank", pa.int32(), metadata={"description": "Rank of the peptide spectrum match in the search engine output"}), | ||
|
|
||
| pa.field( | ||
| "cv_params", | ||
| pa.list_( | ||
| pa.struct([ | ||
| ("name", pa.string()), | ||
| ("value", pa.string()) | ||
| ]) | ||
| ), | ||
| metadata={"description": "Optional list of CV parameters for additional metadata"}, | ||
| ), | ||
| ] | ||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
| PSM_FIELDS = PEPTIDE_FIELDS + PSM_UNIQUE_FIELDS |
Oops, something went wrong.