orfdata 0.36.0__tar.gz → 0.37.0__tar.gz

{orfdata-0.36.0/orfdata.egg-info → orfdata-0.37.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orfdata
-Version: 0.36.0
+Version: 0.37.0
 Summary: Reference proteomes with evidence-backed noncanonical ORFs on PyEnsembl genomes
 Author: OpenVax
 License-Expression: Apache-2.0
@@ -130,11 +130,11 @@ immunopeptidomics: peptides eluted from HLA molecules.
 
 | Species | Noncanonical ORFs | Sources |
 | --- | ---: | --- |
-| Human | 7,264 bundled; 57,607 with `nc_orf_sources="all"` | GENCODE; optionally Chang et al. 2025 and Yang et al. 2024 Ribo-seq |
-| Mouse | 48,805 | Chang et al. and Yang et al. Ribo-seq, OpenProt 2.2 MS |
-| Zebrafish | 9,759 | Yang et al. Ribo-seq |
-| C. elegans | 2,849 | Yang et al. Ribo-seq |
-| Yeast | 1,128 | Yang et al. Ribo-seq |
+| Human | 7,264 bundled; 69,286 with `nc_orf_sources="all"` | GENCODE; optionally Chang et al. 2025 and Yang et al. 2024 Ribo-seq |
+| Mouse | 60,707 | Chang et al. and Yang et al. Ribo-seq, OpenProt 2.2 MS |
+| Zebrafish | 15,491 | Yang et al. Ribo-seq |
+| C. elegans | 4,035 | Yang et al. Ribo-seq |
+| Yeast | 1,369 | Yang et al. Ribo-seq |
 | Dog | none: no public dog Ribo-seq or ncORF MS exists | |
 
 Human's bundled catalogue needs no setup. For the others, `pip install
@@ -161,6 +161,11 @@ combined.save("human-all-proteins.proteome.json.gz")  # Complete provenance.
 
 nc_only = transcriptome.proteome(reference_cds=False, nc_orf_sources="all")
 nc_only.write_fasta("human-reference-ncorfs.fasta")
+
+# A peptide-search policy can exclude short products without deleting their ORF models.
+search_reference = transcriptome.proteome(
+    nc_orf_sources="all", min_protein_length=5
+)
 ```
 
 For sample-specific altered sequences, `DerivedProtein` records the supplied

{orfdata-0.36.0 → orfdata-0.37.0}/README.md

@@ -95,11 +95,11 @@ immunopeptidomics: peptides eluted from HLA molecules.
 
 | Species | Noncanonical ORFs | Sources |
 | --- | ---: | --- |
-| Human | 7,264 bundled; 57,607 with `nc_orf_sources="all"` | GENCODE; optionally Chang et al. 2025 and Yang et al. 2024 Ribo-seq |
-| Mouse | 48,805 | Chang et al. and Yang et al. Ribo-seq, OpenProt 2.2 MS |
-| Zebrafish | 9,759 | Yang et al. Ribo-seq |
-| C. elegans | 2,849 | Yang et al. Ribo-seq |
-| Yeast | 1,128 | Yang et al. Ribo-seq |
+| Human | 7,264 bundled; 69,286 with `nc_orf_sources="all"` | GENCODE; optionally Chang et al. 2025 and Yang et al. 2024 Ribo-seq |
+| Mouse | 60,707 | Chang et al. and Yang et al. Ribo-seq, OpenProt 2.2 MS |
+| Zebrafish | 15,491 | Yang et al. Ribo-seq |
+| C. elegans | 4,035 | Yang et al. Ribo-seq |
+| Yeast | 1,369 | Yang et al. Ribo-seq |
 | Dog | none: no public dog Ribo-seq or ncORF MS exists | |
 
 Human's bundled catalogue needs no setup. For the others, `pip install
@@ -126,6 +126,11 @@ combined.save("human-all-proteins.proteome.json.gz")  # Complete provenance.
 
 nc_only = transcriptome.proteome(reference_cds=False, nc_orf_sources="all")
 nc_only.write_fasta("human-reference-ncorfs.fasta")
+
+# A peptide-search policy can exclude short products without deleting their ORF models.
+search_reference = transcriptome.proteome(
+    nc_orf_sources="all", min_protein_length=5
+)
 ```
 
 For sample-specific altered sequences, `DerivedProtein` records the supplied

{orfdata-0.36.0 → orfdata-0.37.0}/docs/catalogs.md

@@ -21,11 +21,11 @@ The packaged registry builds each catalogue from its sources' own files:
 
 | Species | Catalogues | ORFs |
 | --- | --- | ---: |
-| Mouse | [OpenProt's MS-supported ORFs](#mouse-orfs-from-openprot), [Chang et al.'s](#mouse-ribo-seq-orfs-chang-et-al) and [Yang et al.'s](#mouse-riborf-orfs-yang-et-al) Ribo-seq ORFs | 48,805 merged |
-| Human | the bundled GENCODE set; optionally [Chang et al.'s and Yang et al.'s Ribo-seq ORFs](#human-ribo-seq-orfs-optional) | 7,264; 57,607 with both |
-| Zebrafish | [Yang et al.'s Ribo-seq ORFs](#zebrafish-c-elegans-and-yeast) | 9,759 |
-| C. elegans | [Yang et al.'s Ribo-seq ORFs](#zebrafish-c-elegans-and-yeast) | 2,849 |
-| Yeast | [Yang et al.'s Ribo-seq ORFs](#zebrafish-c-elegans-and-yeast) | 1,128 |
+| Mouse | [OpenProt's MS-supported ORFs](#mouse-orfs-from-openprot), [Chang et al.'s](#mouse-ribo-seq-orfs-chang-et-al) and [Yang et al.'s](#mouse-riborf-orfs-yang-et-al) Ribo-seq ORFs | 60,707 merged |
+| Human | the bundled GENCODE set; optionally [Chang et al.'s and Yang et al.'s Ribo-seq ORFs](#human-ribo-seq-orfs-optional) | 7,264; 69,286 with both |
+| Zebrafish | [Yang et al.'s Ribo-seq ORFs](#zebrafish-c-elegans-and-yeast) | 15,491 |
+| C. elegans | [Yang et al.'s Ribo-seq ORFs](#zebrafish-c-elegans-and-yeast) | 4,035 |
+| Yeast | [Yang et al.'s Ribo-seq ORFs](#zebrafish-c-elegans-and-yeast) | 1,369 |
 | Dog | [none exists](#dog) | 0 |
 
 `orfdata setup --species mouse` (or zebrafish, worm, yeast) installs a
@@ -88,8 +88,8 @@ already installed, repaired or skipped. If one fails, the rest are still
 installed and it exits with status 1, naming each failure; in Python,
 `install_species` raises `InstallError`, whose `result` holds the same
 report. `load_catalog(species="mouse")` then merges the three,
-in this order, into 48,805 ORFs: 2,976 MS-supported OpenProt ORFs, 16,484
-Ribo-seq ORFs of Chang et al. and 40,089 of Yang et al. 10,448 of Chang's and
+in this order, into 60,707 ORFs: 2,976 MS-supported OpenProt ORFs, 16,484
+Ribo-seq ORFs of Chang et al. and 51,991 of Yang et al. 10,448 of Chang's and
 Yang's ORFs are the same ORF (28 of them also in OpenProt), and 296 OpenProt
 ORFs have Ribo-seq support from one or both, 242 from Yang et al. alone. On
 Ensembl 115 (GRCm39):
@@ -97,11 +97,11 @@ Ensembl 115 (GRCm39):
 | Evidence | Selected | Added to the proteome |
 | --- | ---: | ---: |
 | `"ms"` (default) | 2,976 | 2,854 |
-| `RiboSeq()` | 46,207 | 46,094 |
+| `RiboSeq()` | 58,109 | 57,992 |
 | `RiboSeq() & MS()` | 378 | 371 |
-| `None` | 48,805 | 48,577 |
+| `None` | 60,707 | 60,475 |
 
-Loading the merged catalogue takes about 10 seconds and 0.9 GB of memory, once
+Loading the merged catalogue takes about 10 seconds and 1.1 GB of memory, once
 per process, whichever evidence is selected. On GRCm38 and NCBIM37 all three
 are [lifted automatically](#every-assembly-of-a-species).
 
@@ -138,32 +138,39 @@ ATG, CTG, GTG or TTG. Its types are uORF (8,294), lncORF (3,576), uoORF
 `riborf-mouse` holds the mouse ORFs that RibORF 2.0 identified as translated in
 the Ribo-seq data of Yang et al. (Nat Commun 2024,
 [doi:10.1038/s41467-024-46240-9](https://doi.org/10.1038/s41467-024-46240-9);
-224 samples in 26 GEO series), of at least 5 residues: uORF (20,399), lncORF
-(6,954), dORF (4,075), uoORF (3,037), iORF (2,370), N-terminal truncation
-(2,047) and extension (575), and doORF (632). The source's ouORF, odORF and
+224 samples in 26 GEO series): uORF (26,052), lncORF (8,149), iORF (6,155),
+dORF (5,174), uoORF (3,157), N-terminal truncation (2,059), doORF (670) and
+extension (575). The source's ouORF, odORF and
 noncoding types take Chang et al.'s names, so `--biotype uoORF` finds both
 sources' overlapping uORFs. Annotated CDSs, likely sequencing errors,
-stop-codon readthrough and 12,222 ORFs shorter than Chang et al.'s shortest (5
-residues; 4,505 are a bare start and stop) are not imported.
+and stop-codon readthrough are not imported. Release 2 retains 11,902 valid
+ORFs shorter than five residues. Release 1, which applied a five-residue import
+floor, remains available explicitly as `--version 1`.
 
 - **Placement.** The source gives mm10 / GENCODE vM25 transcript coordinates
   (a 1-based start, an exclusive end) and no proteins. Rather than lift mm10
   through a restricted chain, each ORF is placed on the same transcript in
   Ensembl 107 GRCm39 and translated from that transcript's sequence. Of the
-  41,906 rows long enough, 40,089 resolve. Listed as unresolved, with the
-  reason: 1,393 rows on 633 transcripts that changed length since GENCODE
-  vM25, 338 on 216 TEC transcripts that Ensembl 107 has in its GTF but in
-  neither FASTA, 85 on 51 transcripts that are gone, and one whose
+  54,128 non-skipped source rows, 51,991 resolve. Listed as unresolved, with the
+  reason: 1,642 rows on transcripts that changed length since GENCODE
+  vM25, 399 on transcripts that Ensembl 107 has in its GTF but in
+  neither FASTA, 95 on transcripts that are gone, and one whose
   transcript's sequence changed at the same length. Placing through the
   transcript gives the same coding path as lifting the source's mm10 blocks
   through UCSC's chain for all but 2, in a duplicated region of chr14 where
-  the chain is ambiguous. 39,983 place on Ensembl 115.
+  the chain is ambiguous. Of the 12,222 source rows below five residues,
+  11,902 resolve and 320 carry one of the same explicit failures. In all,
+  51,881 place on Ensembl 115.
 - **Sources.** Supplementary Data 3 (CC BY 4.0) and Ensembl 107's GTF, cDNA
   and ncRNA FASTAs; about 115 MB, of which the 32 MB GTF is the one Chang et
   al.'s catalogue uses, so `orfdata setup` downloads it once. Building needs
   `orfdata[build-data]`.
 - **Evidence.** Presence in the source's set is aggregate Ribo-seq support:
   `RiboSeq()` selects every ORF, `RiboSeq(min_studies=2)` none.
+- **Length policy.** `catalog.query(min_protein_length=5)` and
+  `Proteome.build(..., min_protein_length=5)` reproduce a downstream
+  five-residue selection without removing short models from the catalogue.
+  Proteome layers record the threshold and number filtered.
 - **IDs.** `riborf_` and the GRCm39 start and stop, such as
   `riborf_4_120262600_120262620_+`, never a name Chang et al. use. Two paths
   with the same start and stop add their transcript (`…@ENSMUST00000226495.2`),
@@ -268,8 +275,8 @@ load_catalog(species="human", catalogs=["ncorf-mammals-human"])   # Just one
 such as `nc_orf_sources="ms"` also query every compatible dataset; use
 `nc_orf_sources="bundled"` for only the bundled set. They merge after the bundled
 catalogue, Chang et al.'s before Yang et al.'s as for mouse, so an ORF in
-several keeps the first one's ID. Together they give 57,607 ORFs, of which 57,485 place on Ensembl 115; that
-takes about a minute and 3.2 GB of memory, against about a second for the
+several keeps the first one's ID. Together they give 69,286 ORFs, of which 69,162 place on Ensembl 115; that
+takes about a minute and several GB of memory, against about a second for the
 bundled catalogue alone. Neither adds MS evidence, so `"ms"` selects the same
 ORFs either way.
 
@@ -282,10 +289,11 @@ ORFs either way.
 - **`riborf-human`:** the human ORFs of [Yang et
   al.](#mouse-riborf-orfs-yang-et-al), from 136 samples in 30 GEO series, on
   GENCODE V39, placed through the same Ensembl 105 transcripts (GENCODE V39
-  is Ensembl 105): 51,174 of the 51,275 rows long enough; 101 are on
-  transcripts with no sequence in Ensembl 105's FASTAs. Types: uORF (23,664),
-  lncORF (11,379), uoORF (4,548), dORF (3,747), N-terminal truncation (3,561),
-  iORF (2,547), extension (1,046) and doORF (682).
+  is Ensembl 105): 62,853 of 62,962 non-skipped rows; 109 are on transcripts
+  with no sequence in Ensembl 105's FASTAs. The catalogue includes 11,679
+  valid records below five residues. Types: uORF (28,981), lncORF (12,938),
+  iORF (5,990), dORF (4,907), uoORF (4,679), N-terminal truncation (3,574),
+  extension (1,046) and doORF (738).
 
 `catalogs` takes `None` (the species' default set), `"all"`, or catalogue
 names, `"bundled"` among them. `orfdata catalogs status` marks optional
@@ -298,25 +306,25 @@ orfdata setup --species zebrafish   # or worm, or yeast
 ```
 
 Yang et al.'s RibORF 2.0 ORFs of [the mouse catalogue's
-kind](#mouse-riborf-orfs-yang-et-al), at least 5 residues long, from each
-species' sheet of Supplementary Data 3, imported the same way:
+kind](#mouse-riborf-orfs-yang-et-al), including valid short source models, from
+each species' sheet of Supplementary Data 3, imported the same way:
 
-| Catalogue | Samples (GEO series) | Placed through | ORFs | On Ensembl 115 |
+| Catalogue | Samples (GEO series) | Placed through | ORFs | Below 5 aa |
 | --- | --- | --- | ---: | ---: |
-| `riborf-zebrafish` | 20 (2) | Ensembl 115 GRCz11 transcripts | 9,759 | 9,759 |
-| `riborf-worm` | 39 (1) | Ensembl 105 WBcel235 transcripts | 2,849 | 2,433 |
-| `riborf-yeast` | 5 (1) | the R64-1-1 genome (sacCer3) | 1,128 | 171 |
+| `riborf-zebrafish` | 20 (2) | Ensembl 115 GRCz11 transcripts | 15,491 | 5,732 |
+| `riborf-worm` | 39 (1) | Ensembl 105 WBcel235 transcripts | 4,035 | 1,186 |
+| `riborf-yeast` | 5 (1) | the R64-1-1 genome (sacCer3) | 1,369 | 241 |
 
 - **Zebrafish:** every source transcript has the same length in Ensembl 100
   to 115, so the catalogue uses 115. 18 rows have ambiguous bases in the ORF
-  and are left out. Types: N-terminal truncation (3,805), uORF (3,543), dORF
-  (771), iORF (605), lncORF (411), uoORF (304), extension (224) and doORF (96).
+  and are left out. Types: uORF (6,168), N-terminal truncation (3,816), iORF
+  (2,696), dORF (1,623), lncORF (501), uoORF (343), extension (224) and doORF
+  (120).
 - **C. elegans:** the source's transcripts match Ensembl 100 and 105, and
-  WormBase changed many models after, so the catalogue uses 105; all 2,849
-  place there, 2,433 on 115. Transcript names with dots of their own
-  (`F45H11.11.1`) are kept whole. Types: truncation (614), iORF (596),
-  extension (556), uORF (521), uoORF (217), lncORF (151), doORF (117) and dORF
-  (77).
+  WormBase changed many models after, so the catalogue uses 105; all 4,035
+  place there. Transcript names with dots of their own (`F45H11.11.1`) are
+  kept whole. Types: iORF (1,525), uORF (725), truncation (614), extension
+  (556), lncORF (158), uoORF (249), doORF (121) and dORF (87).
 - **Yeast:** the source's yeast transcripts carry UTRs, and some are unstable
   transcripts (CUTs, SUTs), none of which Ensembl's yeast annotation has; its
   transcripts span only the CDS. So each ORF is placed from its genomic span
@@ -330,8 +338,8 @@ species' sheet of Supplementary Data 3, imported the same way:
   Only the 171 ORFs on an Ensembl transcript, such as truncations and iORFs,
   place on a PyEnsembl genome; the rest (uORFs in 5′ UTRs, ORFs on CUTs) stay
   in the catalogue, queryable by region and gene, until ORFs on source-defined
-  RNAs are supported (#66). Types: uORF (321), lncORF (249), dORF (224),
-  truncation (137), extension (67), uoORF (55), doORF (40) and iORF (35).
+  RNAs are supported (#66). Types: uORF (393), dORF (267), lncORF (260), iORF
+  (139), truncation (138), extension (67), uoORF (58) and doORF (47).
 
 ## Dog
 
@@ -381,9 +389,7 @@ With evidence `None` (every catalogue ORF), each assembly gets:
 | Human Ensembl 75, GRCh37 | lifted, 1 hop | 7,247 | 6,857 | 270 transcripts absent, 108 paths changed, 1 on a transcript with a different protein |
 | Human Ensembl 54, NCBI36 | lifted, 1 hop | 7,253 | 4,195 | 2,708 transcripts absent, 2 on a transcript with a different protein |
 | Human Ensembl rapid 2022_07, T2T-CHM13v2.0 | lifted, 1 hop | 7,208 | 6,767 | 383 on a transcript with a different protein, 58 on no transcript, 56 not lifted |
-| Mouse Ensembl 115, GRCm39 | OpenProt, Chang et al. and Yang et al. | 48,805 | 48,577 | 110 transcripts absent, 109 without sequence |
-| Mouse Ensembl 102, GRCm38 | all three lifted, 1 hop | 48,800 | 48,169 | 434 transcripts absent, 5 not lifted |
-| Mouse Ensembl 67, NCBIM37 | all three lifted, 2 hops | 48,642 | 38,105 | 9,217 transcripts absent, 163 not lifted |
+| Mouse Ensembl 115, GRCm39 | OpenProt, Chang et al. and Yang et al. | 60,707 | 60,475 | 232 fail transcript/path/sequence binding checks |
 
 Older annotations lack many of the transcripts the sources name, so fewer ORFs
 place; the rest, and any that didn't lift, are listed with the reason, never

{orfdata-0.36.0 → orfdata-0.37.0}/docs/coverage.md

@@ -48,10 +48,10 @@ Calibration and uncertainty remain attached to observations:
 ## ORF evidence and ribosome profiling
 
 The separate existence-evidence catalogue contains 7,264 human noncanonical
-ORFs, including 2,186 with reported MS support. Mouse has 48,805 ORFs: Ribo-seq ORFs
+ORFs, including 2,186 with reported MS support. Mouse has 60,707 ORFs: Ribo-seq ORFs
 from Chang et al. and Yang et al., and 2,976 OpenProt 2.2 ORFs with at least
 two unique MS peptides, built from their sources' files. Yang et al.'s Ribo-seq ORFs
-cover zebrafish (9,759), C. elegans (2,849) and yeast (1,128), and with Chang et al.'s
+cover zebrafish (15,491), C. elegans (4,035) and yeast (1,369), and with Chang et al.'s
 are optional human catalogues; dog has no experimental ncORF catalogue, because no
 dog Ribo-seq or ncORF MS search is public ([details](catalogs.md#dog)). Its
 ribosome evidence and pooled PSM counts are not sample-level ribosome

{orfdata-0.36.0 → orfdata-0.37.0}/docs/downstream.md

@@ -103,6 +103,11 @@ That writes `ncorfs/annotation.gtf`, `ncorfs/transcripts.fasta` and
 gene, with the spliced coding sequence and the translation. In Python the same
 is `proteome.write_annotation("ncorfs")`.
 
+Catalogue imports preserve short translated ORFs for variant annotation. If a
+particular peptide-search workflow requires a length floor, add
+`--min-protein-length 5`; the generated proteome records the explicit policy and
+its omitted count, while the underlying catalogue remains complete.
+
 ```python
 from pyensembl import Genome
 

{orfdata-0.36.0 → orfdata-0.37.0}/docs/index.md

@@ -67,17 +67,20 @@ orfdata proteome --species human --release 115 --nc-orf-sources ms --output huma
 
 | `nc_orf_sources=` | Selects ORFs with | Human ORFs | Encoded in Ensembl 115 |
 | --- | --- | ---: | ---: |
-| `"ribosome"` or `"riboseq"` | Ribosome profiling across all datasets | 57,607 | 57,485 |
+| `"ribosome"` or `"riboseq"` | Ribosome profiling across all datasets | 69,286 | 69,162 |
 | `"ms"` | Any supporting MS peptide | 2,186 | 2,181 |
 | `"immunopeptidomics"` | Peptides eluted from MHC (in human, HLA) molecules | 1,881 | 1,879 |
 | `"proteomics"` | Peptides from digested cellular proteins | 73 | 72 |
-| `"all"` | Every compatible dataset | 57,607 | 57,485 |
+| `"all"` | Every compatible dataset | 69,286 | 69,162 |
 
 Use `nc_orf_sources="bundled"` for the bundled dataset alone, or a list of
 names such as `["bundled", "ncorf-mammals-human"]` for a subset. Evidence presets
 and `"all"` require all compatible datasets; install human's optional datasets
 once with `orfdata setup --species human --catalogs all`. Missing resources
 produce installation instructions. The defaults still add no ncORFs.
+RibORF source catalogues include valid 1–4-residue ORFs. Apply a downstream
+policy explicitly with `min_protein_length=5`, or CLI
+`--min-protein-length 5`, when a peptide-search reference should omit them.
 
 Most MS support in the bundled human catalogue comes from
 immunopeptidomics. A presented peptide shows that the ORF was translated; it
@@ -116,11 +119,11 @@ transcript alongside them.
 
 | Species | Annotated proteins | Noncanonical ORFs |
 | --- | --- | --- |
-| Human | From PyEnsembl; T2T-CHM13 from a pinned Ensembl annotation | 7,264 GRCh38 ORFs, bundled; lifted to GRCh37, NCBI36 and [T2T-CHM13](catalogs.md#t2t-chm13). 57,607 with the [optional Ribo-seq catalogues](catalogs.md#human-ribo-seq-orfs-optional) of Chang et al. and Yang et al. (`nc_orf_sources="all"`) |
-| Mouse | From PyEnsembl | 48,805 ORFs on GRCm39: Ribo-seq ORFs of Chang et al. and Yang et al., and 2,976 MS-supported ones (OpenProt 2.2), [built locally](catalogs.md#mouse) with `orfdata setup --species mouse`; lifted to GRCm38 and NCBIM37 |
-| Zebrafish | From PyEnsembl | 9,759 GRCz11 Ribo-seq ORFs of Yang et al., [built locally](catalogs.md#zebrafish-c-elegans-and-yeast) |
-| C. elegans | From PyEnsembl | 2,849 WBcel235 Ribo-seq ORFs of Yang et al., built locally |
-| Budding yeast | From PyEnsembl | 1,128 R64-1-1 Ribo-seq ORFs of Yang et al., built locally; 171 lie on Ensembl's transcripts |
+| Human | From PyEnsembl; T2T-CHM13 from a pinned Ensembl annotation | 7,264 GRCh38 ORFs, bundled; lifted to GRCh37, NCBI36 and [T2T-CHM13](catalogs.md#t2t-chm13). 69,286 with the [optional Ribo-seq catalogues](catalogs.md#human-ribo-seq-orfs-optional) of Chang et al. and Yang et al. (`nc_orf_sources="all"`) |
+| Mouse | From PyEnsembl | 60,707 ORFs on GRCm39: Ribo-seq ORFs of Chang et al. and Yang et al., and 2,976 MS-supported ones (OpenProt 2.2), [built locally](catalogs.md#mouse) with `orfdata setup --species mouse`; lifted to GRCm38 and NCBIM37 |
+| Zebrafish | From PyEnsembl | 15,491 GRCz11 Ribo-seq ORFs of Yang et al., [built locally](catalogs.md#zebrafish-c-elegans-and-yeast) |
+| C. elegans | From PyEnsembl | 4,035 WBcel235 Ribo-seq ORFs of Yang et al., built locally |
+| Budding yeast | From PyEnsembl | 1,369 R64-1-1 Ribo-seq ORFs of Yang et al., built locally; 171 lie on Ensembl's transcripts |
 | Dog | From PyEnsembl | None: [no public dog Ribo-seq or ncORF MS exists](catalogs.md#dog) |
 
 Other assemblies use a catalogue lifted to them once `orfdata chains download`

{orfdata-0.36.0 → orfdata-0.37.0}/docs/proteome.md

@@ -146,6 +146,22 @@ A list of evidence names selects ORFs with any of them:
 MS peptide, unlike `"ms"`, which also counts unclassified MS. For ORFs that
 need two kinds of evidence at once, combine rules with `&`, below.
 
+Length is a separate consumer policy, never an import rule. RibORF catalogues
+retain valid short source ORFs because they can matter for variant annotation
+even when they are unsuitable for a peptide search. Use
+`catalog.query(min_protein_length=5)`, `extra_orfs(...,
+min_protein_length=5)`, or:
+
+```python
+search_reference = transcriptome.proteome(
+    nc_orf_sources="ribosome", min_protein_length=5
+)
+```
+
+The corresponding CLI option is `--min-protein-length 5`. A proteome snapshot's
+ncORF layer records both the threshold and `length_filtered`, so the omission is
+auditable and changes the cache identity. Reference CDS proteins are unaffected.
+
 ### Separate Ribo-seq and MS stringency
 
 For more control, pass a rule. `RiboSeq(min_studies=n)` needs ribosome

{orfdata-0.36.0 → orfdata-0.37.0}/orfdata/catalog.py

@@ -588,6 +588,7 @@ class ORFCatalog:
         require_reviewed=False,
         require_resolved=False,
         biotype=None,
+        min_protein_length=None,
         include_initiation_context=False,
     ):
         """Filter records; genomic intervals are 1-based inclusive and spliced.
@@ -602,6 +603,8 @@ class ORFCatalog:
         scope, not unique in every normal human proteome.
         ``require_resolved`` excludes aggregate-only support: MS needs a peptide
         observation and ribosome evidence needs a named study.
+        ``min_protein_length`` is an explicit consumer selection in amino acids;
+        the catalogue itself retains every representable source ORF.
         ``include_initiation_context`` also intersects placed spliced start
         flanks, for example an upstream Kozak SNV. The default remains coding
         blocks only. It does not include introns between context bases.
@@ -619,6 +622,8 @@ class ORFCatalog:
             raise ValueError(f"Expected genome build {self.genome_build}, got {genome_build}")
         rule = evidence_rule(evidence, require_unique=require_unique, require_reviewed=require_reviewed,
                              require_resolved=require_resolved)
+        if min_protein_length is not None:
+            _positive_integer(min_protein_length, "min_protein_length")
 
         return tuple(
             r
@@ -642,6 +647,7 @@ class ORFCatalog:
                 )
             )
             and (biotype is None or any(m.biotype == biotype for m in r.members or (r,)))
+            and (min_protein_length is None or len(r.protein_sequence) >= min_protein_length)
             and (rule is None or rule.matches(r.evidence))
         )
 

{orfdata-0.36.0 → orfdata-0.37.0}/orfdata/catalogs.py

@@ -53,11 +53,11 @@ def _builder(manifest):
         from .sources.ncorf_mammals import import_orfs
 
         return lambda inputs, output: import_orfs(inputs, output, manifest)
-    if importer == "riborf-v1":
+    if importer in ("riborf-v1", "riborf-v2"):
         from .sources.riborf import import_orfs
 
         return lambda inputs, output: import_orfs(inputs, output, manifest)
-    if importer == "riborf-genome-v1":
+    if importer in ("riborf-genome-v1", "riborf-genome-v2"):
         from .sources.riborf import import_genome_orfs
 
         return lambda inputs, output: import_genome_orfs(inputs, output, manifest)

{orfdata-0.36.0 → orfdata-0.37.0}/orfdata/cli.py

@@ -120,6 +120,8 @@ def _add_query_arguments(parser, *, catalog_path=True):
     parser.add_argument("--biotype", help="Source ORF class, as each source labels it: uORF, lncRNA, intORF, dORF "
                                           "(GENCODE, human); uORF, uoORF, iORF, dORF, doORF, lncORF (mouse Ribo-seq; "
                                           "RibORF also truncation, extension); AltProt, Isoform (OpenProt)")
+    parser.add_argument("--min-protein-length", type=int, metavar="AA",
+                        help="Select ORFs with at least this many amino acids; source catalogues stay unfiltered")
     parser.add_argument("--region", help="1-based inclusive interval: chr7:66205483-66205522")
     parser.add_argument(
         "--position", help="Map a 1-based variant position: chr7:66205483 (JSON only)"
@@ -228,6 +230,7 @@ def _query(args, parser, catalog_loader):
             "transcript_id": args.transcript,
             "evidence": _rule(args, args.evidence, "--evidence"),
             "biotype": args.biotype,
+            "min_protein_length": args.min_protein_length,
             "genome_build": args.genome_build,
             "include_initiation_context": args.include_initiation_context or bool(args.ref),
         }