pytransdecoder 0.2.1__py3-none-any.whl

pytransdecoder/presets/apicomplexan/kozak.tsv

@@ -0,0 +1,9 @@
+#position	A	C	G	T  (log2-odds in bits, start vs internal in-frame ATG; 437 training starts)
+-6	-0.142	-0.343	-0.885	0.897
+-5	-0.192	-0.661	-0.133	0.600
+-4	0.456	0.623	-0.195	-0.668
+-3	0.627	-1.721	-1.214	-0.661
+-2	-0.040	-0.007	0.214	0.026
+-1	0.909	-0.730	0.675	-0.898
++4	-0.120	-0.631	0.584	-0.235
++5	-0.188	0.214	0.367	0.147

pytransdecoder/presets/apicomplexan/preset.json

@@ -0,0 +1,20 @@
+{
+ "name": "apicomplexan",
+ "source": "pfalciparum benchmark annotation (TransDecoder paper 2026): complete coding transcripts + their fragments",
+ "genetic_code": "Universal",
+ "gc_pct": 22.0,
+ "auto_accept_nt": 519,
+ "strata": "len_tx_type",
+ "q_levels": [
+  0.001,
+  0.002,
+  0.005,
+  0.01,
+  0.02,
+  0.05,
+  0.1,
+  0.2,
+  0.3,
+  0.5
+ ]
+}

pytransdecoder/presets/ciliate/kozak.tsv

@@ -0,0 +1,9 @@
+#position	A	C	G	T  (log2-odds in bits, start vs internal in-frame ATG; 243 training starts)
+-6	0.206	-0.849	-1.159	0.453
+-5	-0.173	-0.767	0.824	0.160
+-4	0.366	-0.450	-0.552	-0.196
+-3	0.348	0.296	-1.012	-0.074
+-2	0.251	-0.738	0.199	-0.327
+-1	0.476	-0.780	-0.349	-0.331
++4	0.268	-0.610	-0.227	-0.039
++5	0.001	-0.015	0.802	-0.499

pytransdecoder/presets/ciliate/preset.json

@@ -0,0 +1,20 @@
+{
+ "name": "ciliate",
+ "source": "tthermophila benchmark annotation (TransDecoder paper 2026): complete coding transcripts + their fragments",
+ "genetic_code": "Tetrahymena",
+ "gc_pct": 25.85,
+ "auto_accept_nt": null,
+ "strata": "len_tx_type",
+ "q_levels": [
+  0.001,
+  0.002,
+  0.005,
+  0.01,
+  0.02,
+  0.05,
+  0.1,
+  0.2,
+  0.3,
+  0.5
+ ]
+}

pytransdecoder/presets/fungus/kozak.tsv

@@ -0,0 +1,9 @@
+#position	A	C	G	T  (log2-odds in bits, start vs internal in-frame ATG; 390 training starts)
+-6	0.132	-0.418	-0.897	0.772
+-5	-0.140	-0.526	0.067	0.438
+-4	0.222	0.473	-0.251	-0.303
+-3	0.781	-1.282	-0.406	-0.131
+-2	0.229	-0.309	-0.195	0.037
+-1	0.263	0.146	0.125	-0.461
++4	0.267	-0.834	0.207	-0.098
++5	-0.098	0.539	0.494	-0.922

pytransdecoder/presets/fungus/preset.json

@@ -0,0 +1,20 @@
+{
+ "name": "fungus",
+ "source": "spombe benchmark annotation (TransDecoder paper 2026): complete coding transcripts + their fragments",
+ "genetic_code": "Universal",
+ "gc_pct": 37.84,
+ "auto_accept_nt": 615,
+ "strata": "len_tx_type",
+ "q_levels": [
+  0.001,
+  0.002,
+  0.005,
+  0.01,
+  0.02,
+  0.05,
+  0.1,
+  0.2,
+  0.3,
+  0.5
+ ]
+}

pytransdecoder/presets/green_alga/kozak.tsv

@@ -0,0 +1,9 @@
+#position	A	C	G	T  (log2-odds in bits, start vs internal in-frame ATG; 368 training starts)
+-6	0.305	-0.214	-0.195	0.552
+-5	-0.102	-0.008	0.413	-0.474
+-4	2.066	-0.368	-0.991	0.566
+-3	1.420	-0.966	-0.440	-0.112
+-2	0.427	0.031	0.164	-0.919
+-1	2.432	-0.987	-0.650	1.273
++4	0.318	-0.661	0.243	0.105
++5	0.214	0.321	-0.069	-1.042

pytransdecoder/presets/green_alga/preset.json

@@ -0,0 +1,20 @@
+{
+ "name": "green_alga",
+ "source": "creinhardtii benchmark annotation (TransDecoder paper 2026): complete coding transcripts + their fragments",
+ "genetic_code": "Universal",
+ "gc_pct": 68.17,
+ "auto_accept_nt": 1347,
+ "strata": "len_tx_type",
+ "q_levels": [
+  0.001,
+  0.002,
+  0.005,
+  0.01,
+  0.02,
+  0.05,
+  0.1,
+  0.2,
+  0.3,
+  0.5
+ ]
+}

pytransdecoder/presets/insect/kozak.tsv

@@ -0,0 +1,9 @@
+#position	A	C	G	T  (log2-odds in bits, start vs internal in-frame ATG; 446 training starts)
+-6	0.252	-0.258	-0.273	0.339
+-5	-0.407	0.232	0.450	-0.145
+-4	0.745	0.430	-1.021	-0.313
+-3	1.210	-2.084	-0.227	-1.356
+-2	0.280	0.264	-0.361	-0.654
+-1	0.726	-0.137	-0.450	-0.259
++4	0.187	-0.572	0.061	0.376
++5	-0.160	0.397	0.114	-0.398

pytransdecoder/presets/insect/preset.json

@@ -0,0 +1,20 @@
+{
+ "name": "insect",
+ "source": "dmel benchmark annotation (TransDecoder paper 2026): complete coding transcripts + their fragments",
+ "genetic_code": "Universal",
+ "gc_pct": 50.84,
+ "auto_accept_nt": 804,
+ "strata": "len_tx_type",
+ "q_levels": [
+  0.001,
+  0.002,
+  0.005,
+  0.01,
+  0.02,
+  0.05,
+  0.1,
+  0.2,
+  0.3,
+  0.5
+ ]
+}

pytransdecoder/presets/mammal/kozak.tsv

@@ -0,0 +1,9 @@
+#position	A	C	G	T  (log2-odds in bits, start vs internal in-frame ATG; 308 training starts)
+-6	-0.613	-0.312	0.298	0.538
+-5	-0.828	0.169	0.640	0.117
+-4	0.217	0.544	-0.191	-0.976
+-3	0.877	-2.042	0.095	-1.261
+-2	-0.095	0.594	0.179	-0.845
+-1	-0.280	0.254	0.258	-0.979
++4	-0.180	-0.969	0.483	0.043
++5	-0.283	0.624	0.270	-0.780

pytransdecoder/presets/mammal/preset.json

@@ -0,0 +1,20 @@
+{
+ "name": "mammal",
+ "source": "human benchmark annotation (TransDecoder paper 2026): complete coding transcripts + their fragments + GENCODE lncRNAs",
+ "genetic_code": "Universal",
+ "gc_pct": 49.81,
+ "auto_accept_nt": 726,
+ "strata": "len_tx_type",
+ "q_levels": [
+  0.001,
+  0.002,
+  0.005,
+  0.01,
+  0.02,
+  0.05,
+  0.1,
+  0.2,
+  0.3,
+  0.5
+ ]
+}

pytransdecoder/presets/plant/kozak.tsv

@@ -0,0 +1,9 @@
+#position	A	C	G	T  (log2-odds in bits, start vs internal in-frame ATG; 396 training starts)
+-6	-0.201	-0.071	-0.466	0.816
+-5	-0.126	0.031	-0.070	0.168
+-4	0.509	-0.252	0.120	-0.606
+-3	0.469	-0.673	-0.175	-0.018
+-2	0.179	0.331	-0.633	-0.237
+-1	0.578	-0.113	-0.026	-0.969
++4	-0.607	-1.330	0.880	-0.792
++5	-0.115	0.833	-0.098	-0.828

pytransdecoder/presets/plant/preset.json

@@ -0,0 +1,20 @@
+{
+ "name": "plant",
+ "source": "athal benchmark annotation (TransDecoder paper 2026): complete coding transcripts + their fragments",
+ "genetic_code": "Universal",
+ "gc_pct": 42.1,
+ "auto_accept_nt": 663,
+ "strata": "len_tx_type",
+ "q_levels": [
+  0.001,
+  0.002,
+  0.005,
+  0.01,
+  0.02,
+  0.05,
+  0.1,
+  0.2,
+  0.3,
+  0.5
+ ]
+}

pytransdecoder-0.2.1.dist-info/METADATA

@@ -0,0 +1,307 @@
+Metadata-Version: 2.4
+Name: pytransdecoder
+Version: 0.2.1
+Summary: TransDecoder, the original Perl version ported to Python by AI/LLMs with new features integrated
+Author: Brian Haas, ported to python by AI/LLMs
+License: BSD-3-Clause
+Project-URL: Homepage, https://github.com/TransDecoder/PyTransDecoder
+Project-URL: Repository, https://github.com/TransDecoder/PyTransDecoder
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython>=1.81
+Requires-Dist: tqdm>=4.65
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4; extra == "dev"
+Requires-Dist: pytest-cov>=4.1; extra == "dev"
+Requires-Dist: black>=23.0; extra == "dev"
+Requires-Dist: mypy>=1.0; extra == "dev"
+Dynamic: license-file
+
+# PyTransDecoder
+
+Python port of [TransDecoder](https://github.com/TransDecoder/TransDecoder) - identify candidate coding regions within transcript sequences.
+
+## Installation
+
+```bash
+pip install pytransdecoder
+```
+
+or from a clone of this repository:
+
+```bash
+cd PyTransDecoder
+pip install -e .
+```
+
+## Quick Start
+
+Use `pyTransdecoder` as the primary interface when you want the standard end-to-end pipeline:
+
+```bash
+pyTransdecoder -t transcripts.fasta
+```
+
+This runs LongOrfs followed by Predict and writes the usual `*.transdecoder.{gff3,bed,pep,cds}` outputs.
+
+You can also have the pipeline run homology support searches directly:
+
+```bash
+pyTransdecoder -t transcripts.fasta \
+    --blast-search-pep uniprot_sprot.pep \
+    --pfam-search-db Pfam-A.hmm
+```
+
+## Phase-Specific Commands
+
+If you want to run the phases separately, use the subcommand CLI:
+
+### Phase 1: Extract Long ORFs
+
+```bash
+pytransdecoder longorfs -t transcripts.fasta
+```
+
+This creates a directory `transcripts.fasta.transdecoder_dir/` with:
+- `longest_orfs.pep` - Protein sequences
+- `longest_orfs.cds` - CDS sequences  
+- `longest_orfs.gff3` - ORF annotations
+- `base_freqs.dat` - Nucleotide frequencies
+
+### Options
+
+```
+-t, --transcripts PATH          Input transcripts FASTA file [required]
+-m, --min-protein-length INT    Minimum protein length (default: 50 aa; Predict's target-decoy
+                                test, not this cutoff, controls chance ORFs)
+-G, --genetic-code TEXT         Genetic code (default: Standard)
+-S, --strand-specific           Only analyze top strand
+-O, --output-dir PATH           Output directory
+--gene-trans-map PATH           Gene-to-transcript mapping file
+--complete-orfs-only            Only output complete ORFs
+-v, --verbose                   Verbose output
+```
+
+## CLI Compatibility
+
+PyTransDecoder's CLI accepts **both underscore and dash formats** for option names, ensuring compatibility with existing Perl TransDecoder workflows:
+
+```bash
+# Both of these work identically:
+pytransdecoder predict -t transcripts.fasta --retain-pfam-hits pfam.domtblout
+pytransdecoder predict -t transcripts.fasta --retain_pfam_hits pfam.domtblout
+```
+
+This means you can use existing scripts and Makefiles without modification.
+
+Legacy compatibility wrappers for `TransDecoder.LongOrfs` and `TransDecoder.Predict` now live under [`util/`](https://github.com/TransDecoder/PyTransDecoder/tree/main/util) instead of the repository root.
+
+## Supported Genetic Codes
+
+- universal/standard
+- vertebrate_mitochondrial
+- yeast_mitochondrial
+- invertebrate_mitochondrial
+- ciliate/tetrahymena/dasycladacean
+- euplotid
+- bacterial
+- candida
+- And 15+ more...
+
+## Phase 2: Predict Likely Coding Regions
+
+### Basic Usage
+
+```bash
+pytransdecoder predict -t transcripts.fasta
+```
+
+This creates final output files in the same directory as your transcripts:
+- `transcripts.fasta.transdecoder.gff3` - Gene predictions
+- `transcripts.fasta.transdecoder.bed` - BED format
+- `transcripts.fasta.transdecoder.pep` - Protein sequences
+- `transcripts.fasta.transdecoder.cds` - CDS sequences
+
+### With Homology Support
+
+```bash
+# Run BLASTP against UniProt
+blastp -query transcripts.fasta.transdecoder_dir/longest_orfs.pep \
+       -db uniprot_sprot.pep -max_target_seqs 1 \
+       -outfmt 6 -evalue 1e-5 -num_threads 4 > blastp.outfmt6
+
+# Run Pfam domain search
+hmmscan --cpu 4 --domtblout pfam.domtblout Pfam-A.hmm \
+        transcripts.fasta.transdecoder_dir/longest_orfs.pep
+
+# Run predict with homology data
+pytransdecoder predict -t transcripts.fasta \
+    --retain-blastp-hits blastp.outfmt6 \
+    --retain-pfam-hits pfam.domtblout
+```
+
+ORFs with a hit are kept even when their coding signal alone would not keep them. Hits to
+transposable-element proteins (or to host proteins with a TE-derived segment) can therefore keep
+short ORFs in TE-containing transcripts. These are kept on purpose; to find and remove them by
+best-hit protein or by repeat overlap, see
+[docs/homology_te_screen.md](https://github.com/TransDecoder/PyTransDecoder/blob/main/docs/homology_te_screen.md).
+
+For the full pipeline entrypoint, you can skip the separate Pfam step and let
+`pyTransdecoder` prepare and search the HMM database for you:
+
+```bash
+pyTransdecoder -t transcripts.fasta --pfam-search-db Pfam-A.hmm
+```
+
+### Options
+
+```
+-t, --transcripts PATH            Input transcripts FASTA file [required]
+-O, --output-dir PATH             Output directory
+-T, --top-orfs-train INT          Training ORFs (default: 500)
+--retain-long-orfs-mode           'dynamic' or 'strict' (default: dynamic)
+--retain-pfam-hits PATH           Pfam domain hits (domtblout format)
+--retain-blastp-hits PATH         BLAST hits (outfmt 6 format)
+--retain-multiple-orfs            Report all non-overlapping ORFs passing selection
+                                  (default: the best ORF per transcript)
+--no-refine-starts                Skip start codon refinement
+--no-homology-start-assist        Do not let BLASTP/Pfam hits decide 5'-partial vs trimmed starts
+                                  (default: they do whenever hits are supplied)
+--start-contrast-alpha FLOAT      Start refinement: UTR score per base of upstream segment (default: 0.4)
+--start-kozak-weight FLOAT        Start refinement: bases of coding signal per bit of Kozak score (default: 17)
+--max-qvalue FLOAT                Keep ORFs (without homology) with target-decoy q-value <= this
+                                  (default: 0.05)
+--precise                         Same as --max-qvalue 0.01: fewer calls on noncoding sequence
+--sensitive                       Same as --max-qvalue 0.2: more short and partial ORFs
+--decoy-shuffles INT              Shuffled copies per transcript (default: 0 = automatic)
+--decoy-seed INT                  Seed of the decoy shuffles (default: 42)
+--preset NAME|DIR                 Models and thresholds from a preset instead of the input
+                                  (recommended below ~1,000 transcripts or for mostly partial sets)
+-G, --genetic-code TEXT           Genetic code (default: Standard)
+-v, --verbose                     Verbose output
+```
+
+### How It Works
+
+1. **Training**: Selects top longest unique ORFs to train hexamer scoring model
+2. **Scoring**: Scores all ORFs using Markov chain model (hexamer composition)
+3. **Selection**: Chooses best ORFs based on:
+   - Homology support (BLAST/Pfam hits)
+   - Coding potential score
+   - ORF length
+   - GC content-based thresholds (ORFs long enough to be unlikely in random sequence of the
+     transcriptome's GC content are kept regardless of score; applied only when the genetic
+     code's stop codons are TAA/TAG/TGA, the set the thresholds were simulated with)
+   - A false discovery rate against decoys: each input transcript is shuffled keeping its
+     dinucleotide counts (so length and base composition are kept), decoy ORFs are found in the
+     shuffles with the LongOrfs settings and genetic code, and scored with the same model. Within
+     strata of ORF length, transcript length and ORF type (complete or partial), an ORF's q-value
+     is the lowest estimated FDR (decoys / targets at or above its frame contrast) of any cutoff
+     that accepts it. Without homology support an ORF needs in-frame score > 0, a higher score
+     than the shifted frames, and q <= `--max-qvalue` (0.05; `--precise` 0.01, `--sensitive` 0.2).
+     Short ORFs, which are far more frequent by chance, therefore need more coding evidence, with
+     no fixed length cutoff. The decoys are reproducible (`--decoy-seed`) and identical in
+     TransDecoder (Perl).
+   - Translated noncanonical ORFs (Ribo-seq ORFs) mostly lack codon-usage signal, so finding
+     them needs translation evidence.
+   - **Small inputs**: below ~1,000 transcripts the coding model and the decoy statistics learned
+     from the input are unreliable. `--preset NAME` uses a coding model, start model and q-value
+     thresholds learned from a reference transcriptome instead (bundled: see `--help`;
+     `pytransdecoder build-preset` makes one from a Predict run on a related species).
+4. **Start refinement**: an ORF that runs to the 5' end of its transcript (no start codon) is
+   either a truncated (5'-partial) ORF or one that extends into the 5' UTR. For the segment
+   before its first in-frame ATG, two scores are compared, both in bases' worth of typical coding
+   signal (the training ORFs' median per-base frame contrast):
+   - **coding score**: the segment's frame contrast (coding score in frame minus the better
+     shifted frame) divided by that typical per-base value;
+   - **UTR score**: `--start-contrast-alpha` (0.4) x segment length + `--start-kozak-weight` (17)
+     x the ATG's Kozak score in bits (log2-odds of -6..-1, +4..+5 against in-frame ATGs inside
+     the training ORFs).
+   If the UTR score is higher, the ORF is trimmed to start at the ATG; otherwise it stays 5'
+   partial. Each bit of Kozak score lets the ATG overrule 17 bases of coding signal. See
+   [docs/start_codon_refinement.md](https://github.com/TransDecoder/PyTransDecoder/blob/main/docs/start_codon_refinement.md) for a step-by-step
+   walkthrough with examples and advice on choosing alpha. The Kozak model is written to the
+   work directory as `start_refinement.kozak.tsv` (bits), `.kozak.counts.tsv` and a sequence
+   logo, `.kozak.logo.svg`.
+   **With homology hits** (`--retain-blastp-hits` and/or `--retain-pfam-hits`), the hits of the
+   ORF's longest-ORF peptide decide first (PyTransDecoder only; turn off with
+   `--no-homology-start-assist`):
+   - BLASTP, trim: the best hit's subject N-terminus (subject start <= 3) aligns within 5 aa of the
+     first ATG;
+   - BLASTP, keep 5' partial: the alignment starts >= 5 aa upstream of the ATG and the subject
+     continues further N-terminal (subject start > 1);
+   - Pfam, keep 5' partial: a domain envelope starts upstream of the ATG.
+   Where no rule fires, or a trim and a keep call conflict, the coding-vs-UTR rule above decides.
+   Each rule is used only if its hits file was given. Per-ORF evidence and decisions are written
+   to `start_refinement.homology.tsv` in the work directory, and ORFs trimmed by homology carry
+   `start_homology=R2` in the GFF3. See [docs/start_codon_refinement.md](https://github.com/TransDecoder/PyTransDecoder/blob/main/docs/start_codon_refinement.md).
+5. **Output**: Generates final predictions in multiple formats
+
+## Annotating a Genome from Transcript Structures
+
+Transcripts reconstructed from RNA-seq (StringTie, LRAA, Cufflinks, PASA, or Trinity aligned to
+the genome) can be annotated with coding regions on the genome: ORFs predicted on the transcript
+sequences are propagated through each transcript's exon structure, giving gene / mRNA / exon /
+CDS / five_prime_UTR / three_prime_UTR models in GFF3.
+
+From a genome and a GTF (transcript sequences are extracted with gffread):
+
+```bash
+pyTransdecoder --genome genome.fa --gtf stringtie.gtf -O out
+# -> out/stringtie.cDNA.fasta.transdecoder.genome.gff3 (and .genome.bed)
+```
+
+From transcript sequences and their structures (GTF, alignment GFF3 from GMAP/PASA with
+`Target=`, or minimap2 SAM/BAM spliced alignments):
+
+```bash
+pyTransdecoder -t Trinity.fasta --structures Trinity.minimap2.bam -O out
+# or, after LongOrfs + Predict:
+pytransdecoder genome-map --orfs Trinity.fasta.transdecoder.gff3 --structures Trinity.minimap2.bam \
+    -t Trinity.fasta -o Trinity.fasta.transdecoder.genome.gff3
+```
+
+Notes:
+- ORFs on the opposite strand of a spliced transcript are not propagated; single-exon
+  transcripts take the ORF's orientation.
+- Alignment blocks carry transcript coordinates (GFF3 `Target`, SAM CIGAR), so transcripts with
+  indels or clipped ends map base-accurately; an ORF whose CDS is not within the aligned part of
+  its transcript is not propagated. Only primary SAM/BAM alignments are used.
+- GTF transcripts with strand `.` are taken as `+`, as gffread extracts them; use
+  `--unstranded-as minus` for sequences extracted with TransDecoder's
+  `util/gtf_genome_to_cdna_fasta.pl`.
+- Isoforms are grouped by the GTF `gene_id` (or the TransDecoder gene id, e.g. with
+  `--gene-trans-map`), with the chromosome and strand appended.
+
+## Development Status
+
+- ✅ Phase 1 (LongOrfs): Implemented and validated
+- ✅ Phase 2 (Predict): Implemented and tested
+- ⏳ Performance benchmarking on large datasets
+
+## Testing Against Perl Version
+
+To validate output matches the Perl version:
+
+```bash
+# Run Perl version
+cd ../TransDecoder
+./TransDecoder.LongOrfs -t test.fasta
+
+# Run Python version
+cd ../PyTransDecoder  
+pytransdecoder longorfs -t test.fasta
+
+# Compare outputs
+diff ../TransDecoder/test.fasta.transdecoder_dir/longest_orfs.pep \
+     test.fasta.transdecoder_dir/longest_orfs.pep
+```
+
+## Requirements
+
+- Python 3.8+
+- BioPython >= 1.81
+- tqdm >= 4.65
+
+**Note**: Ported by Claude.io Sonnet 4.5 under guidance by bhaas. Jan 24, 2026.

pytransdecoder-0.2.1.dist-info/RECORD

@@ -0,0 +1,63 @@
+pytransdecoder/__init__.py,sha256=7PHDZ23rYyc7hO6w0-rnwB1E7UMng2uLrbNqWdo_LUA,150
+pytransdecoder/__main__.py,sha256=37cCIfD-m7brRwI36e7id3gNzCLeTdVL7itGvtNl1Yk,107
+pytransdecoder/cli.py,sha256=Av_9mVceZVTATM-dqs6wE2vWHB7pjPyCAIpMnLgtLRI,34862
+pytransdecoder/genome.py,sha256=2lfCaGgJHZzQOVWbUSaZ2-UWjpwZNsqmKGOG1x-Pvew,14631
+pytransdecoder/longorfs.py,sha256=qly1nCGW6q862HLywmNnaX-zZOfUwIBKeTUaU1nlwbA,6509
+pytransdecoder/predict.py,sha256=YPrCFDxbWDzYWllp8J6UlI-m2OcpFR42s4w4dpy-OLc,75446
+pytransdecoder/core/__init__.py,sha256=SezWMpPUMx_7qoZwMVX9vUVg8Y3xarsXLvJOH1z68z0,38
+pytransdecoder/core/base_freqs.py,sha256=QiEbFiMJ71kFU1DanZWSVS55YctJtfxu9VS_FcW2nU0,2617
+pytransdecoder/core/decoys.py,sha256=Bg94NCdTjR3NmhyJKPPABF0Ee2y5u-kx9LGN4UGaNqU,4203
+pytransdecoder/core/fasta.py,sha256=3rGfQGINDDsm90s4lIlhGnOOebzUJjnrs3aRYAUFtgI,1987
+pytransdecoder/core/gene_model.py,sha256=xDUqXPF7QUA3YgcRFLnz7H2fAC_f5XIpeKogjxdMAAk,6301
+pytransdecoder/core/gff3_parser.py,sha256=M5jVtY4uS74bUL73k4Ye6Zhnqatm7X6Y9OFrPgCAj9M,1603
+pytransdecoder/core/homology_starts.py,sha256=sVpSwuzEv_caG9PAh5I5Ihb7qVatOPJS6q0yfO1PEpM,2476
+pytransdecoder/core/kozak.py,sha256=WGMDbfFbp7WnDwj2PNZnm8cx1QSQ-V_WMb07Y2kWQaI,7857
+pytransdecoder/core/models.py,sha256=r9ns5RND7QVVLffk1_d9bz8oo9R357CqHkBu7NQaS7g,3948
+pytransdecoder/core/orf_finder.py,sha256=aws4D8Yx45fBnWMj_xNvAAvOus5VfJ0XC0HcyXG5wiM,12617
+pytransdecoder/core/presets.py,sha256=rX6YHQ3cju--5b8A9FqVg6CQ7lSh8uLdSuuITAcZ9lU,6937
+pytransdecoder/core/prng.py,sha256=uZwc4GLY9gtBoglC35u1k0fDQzRCvm65DAhuwRHehUw,1504
+pytransdecoder/core/pwm.py,sha256=q9KKZiPpKsom5csNm2iB5y-XyMxDONrvo-PbEtahcxA,5926
+pytransdecoder/core/sequence.py,sha256=TwwSKhzTJzZssntm1jf7DNakgVgKj7rhjwg-qbbEF9A,345
+pytransdecoder/core/translator.py,sha256=FVi8SvZCJG5HKDdFTZng1Agrcih2zxqTWpJx4wfa470,4808
+pytransdecoder/core/writers.py,sha256=lkTs1-GgAe42XMFgylG7RJomaAhvwQZeJ7ncbPBqdSw,1799
+pytransdecoder/presets/apicomplexan/hexamer.scores.gz,sha256=xKN4Vsv1Yuh-h7HtVG9OYT6FXYP89LG2tFvtaEh0tKk,225383
+pytransdecoder/presets/apicomplexan/kozak.tsv,sha256=cxw1xx_GE34HUQNhrPIzlQrVrdTgItazqWrXe4lJLqk,327
+pytransdecoder/presets/apicomplexan/preset.json,sha256=jF9cOLWlnaw6nfEFFfYt-64ekCXvPgV4Pz-z0qy4ATg,342
+pytransdecoder/presets/apicomplexan/thresholds.tsv.gz,sha256=sm9s_PrHR_gjbEfh5Yz856rOumjB3W9QAl-8aylu9QY,5309
+pytransdecoder/presets/apicomplexan/training_orfs.cds.gz,sha256=7uSFXrnac29oZpe9iz0jZIQ3ghdOyA-kr2WocVGmAGM,577154
+pytransdecoder/presets/ciliate/hexamer.scores.gz,sha256=Mr2lHaLTRijRC9yxH0z6ADusA63qoMX38a8QlvJK5A4,239964
+pytransdecoder/presets/ciliate/kozak.tsv,sha256=Cs4Rh5JsvLsZAByLucDnMNIzfk-FqgRpdUNUnkwSL_M,327
+pytransdecoder/presets/ciliate/preset.json,sha256=zokziLnP3B-wVHvIQK_xChLV9iz69fcSg1aNV-vLAcs,342
+pytransdecoder/presets/ciliate/thresholds.tsv.gz,sha256=UnX42pnHskdt4JrQWLLrjerjjOi32CU7RT6zyAOpM0E,8424
+pytransdecoder/presets/ciliate/training_orfs.cds.gz,sha256=XC17RtAuw2AzBrBCQkoI2DmnCA2SrDgxm-rXzvUgHrk,691838
+pytransdecoder/presets/fungus/hexamer.scores.gz,sha256=NUXEHB5J_pWHbhUYhU3lbNFFvgI9nigvS8SFOxD-JRM,239943
+pytransdecoder/presets/fungus/kozak.tsv,sha256=Z4QaicJeq86NYJDZUWox3gsjPLDQbrWzIAJhp1Sqky8,324
+pytransdecoder/presets/fungus/preset.json,sha256=IyTfTyj5ASR_I4yV-eQPnt_-Jn2cuAaWSk-D6R0NP3A,332
+pytransdecoder/presets/fungus/thresholds.tsv.gz,sha256=rDsJRn_oKDYcbjGQ8JJYrf2_InLMhUjDAqixYj1qOfg,4776
+pytransdecoder/presets/fungus/training_orfs.cds.gz,sha256=NJpb6zf7P4YqTuyW7cjdMPz_5sFh8igo8HrCI6nvRnA,512609
+pytransdecoder/presets/green_alga/hexamer.scores.gz,sha256=7OFF9HJzr_aHLlQuNEsXxcGi8Gx-dlIdE8BQJ56mav0,236464
+pytransdecoder/presets/green_alga/kozak.tsv,sha256=3EKtFePS46IQcuhNnihCEPe9zw6kV51aQ873hwVGNWQ,324
+pytransdecoder/presets/green_alga/preset.json,sha256=_6hWzjglcPMnQlCCFodEPS5rnAr1tHuqzCZIjrclbfQ,343
+pytransdecoder/presets/green_alga/thresholds.tsv.gz,sha256=3YFq0LY_dsBlsNkJLfS6LR4vDxxNCY3leS9bFvdnnes,7367
+pytransdecoder/presets/green_alga/training_orfs.cds.gz,sha256=QMHhQAolZvg6ow9qFYgniWAyhppsaah3Qgd2SCr63eQ,671531
+pytransdecoder/presets/insect/hexamer.scores.gz,sha256=qAWdadv_lSgBw9lYVbsYlJQW8ZD5UFD_-W39KG6Knuo,242916
+pytransdecoder/presets/insect/kozak.tsv,sha256=8Msh50-V5sJrikX5GErT-9XO2pAqbogy54T-E4eOwqQ,325
+pytransdecoder/presets/insect/preset.json,sha256=FkJa0CZgIG13TiPY0NqCIIfR22gQV0mL45BgFttBjIo,330
+pytransdecoder/presets/insect/thresholds.tsv.gz,sha256=e0H5PcKjAq5yvO93zdjahZTNM5_pdZFYo-eKy9Ae5pc,6498
+pytransdecoder/presets/insect/training_orfs.cds.gz,sha256=HRI1oUOQyu687qIwShIJtoYoEm9NX42fIm3vyHWRUmA,658717
+pytransdecoder/presets/mammal/hexamer.scores.gz,sha256=bG8Wthh4APN0KuIZ1wdw19qFY_lR7shFcwAEFxTba28,242860
+pytransdecoder/presets/mammal/kozak.tsv,sha256=6zK_8P5kSuASO-tI2sBV4dk97I4tdj9cC4K6V2QIxEg,323
+pytransdecoder/presets/mammal/preset.json,sha256=TKceOyby8fK8yy-rw0Zl9CCFgLm3OJ_P3Dk6QqarvwQ,349
+pytransdecoder/presets/mammal/thresholds.tsv.gz,sha256=aDUXYMKnT-VRLf4WmSMRfYWqDC9FOB101ny9EsM2As4,11649
+pytransdecoder/presets/mammal/training_orfs.cds.gz,sha256=sOGgQoh21iKV6ctLIuXxN9HBMl4JTAhfEOpSSgTgidI,683504
+pytransdecoder/presets/plant/hexamer.scores.gz,sha256=TRhP3u6aYjeEC8MVG57s-CuIwIlmz-9ZuOqgIUVg39I,241915
+pytransdecoder/presets/plant/kozak.tsv,sha256=mAY8AE43JkTuR4IsqoZ21vu5EPzXcDVnuyLtbVemt1Q,329
+pytransdecoder/presets/plant/preset.json,sha256=hAwps6Q75lNH8igNtX88vC0DpoZvD2N8jtEeWpxcqF4,329
+pytransdecoder/presets/plant/thresholds.tsv.gz,sha256=dfmrgwcjueLvXiXLIPVOAgIg4JyH-Plc_bxkI7MuzQY,6001
+pytransdecoder/presets/plant/training_orfs.cds.gz,sha256=fWPK8a_hf8SwA6rNZM7dbuTU1HsAvBD28vkrGx61RVM,606972
+pytransdecoder-0.2.1.dist-info/licenses/LICENSE,sha256=TfCmyKcCtNlN1xsUNTkG6T3HV6F6k9Bi-2H_n4cIUZQ,1499
+pytransdecoder-0.2.1.dist-info/METADATA,sha256=uYr9n_bGuTA0H7Q0SiQi2zupM5-AQVOHTVG678JUB3U,13643
+pytransdecoder-0.2.1.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+pytransdecoder-0.2.1.dist-info/entry_points.txt,sha256=SM3IHQANJP3OIJh9jsVLoICwHQ6ydbI0dnjwFNwHImo,108
+pytransdecoder-0.2.1.dist-info/top_level.txt,sha256=PYGdqaVT__0vywRq0EO8CgHQP8cHtuPqhryslKZh9Xc,15
+pytransdecoder-0.2.1.dist-info/RECORD,,

pytransdecoder-0.2.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.2.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

pytransdecoder-0.2.1.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+pyTransdecoder = pytransdecoder.cli:pipeline_main
+pytransdecoder = pytransdecoder.cli:cli