Spaces:
Sleeping
Sleeping
docs: add test example using included JCVI Syn3.0 data
Browse filesCo-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- GETTING_STARTED.md +16 -0
GETTING_STARTED.md
CHANGED
|
@@ -145,6 +145,22 @@ cpr verify --check syn30 # Verify JCVI Syn3.0 result (39.6% annotation)
|
|
| 145 |
cpr verify --check all # Run all verification checks
|
| 146 |
```
|
| 147 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
---
|
| 149 |
|
| 150 |
## FDR/FNR Threshold Reference
|
|
|
|
| 145 |
cpr verify --check all # Run all verification checks
|
| 146 |
```
|
| 147 |
|
| 148 |
+
### Test with Included Data
|
| 149 |
+
|
| 150 |
+
The repo includes JCVI Syn3.0 sequences for testing:
|
| 151 |
+
|
| 152 |
+
```bash
|
| 153 |
+
# Test search with included FASTA (requires Zenodo data downloaded)
|
| 154 |
+
cpr search --input data/gene_unknown/unknown_aa_seqs.fasta --output test_results.csv --fdr 0.1
|
| 155 |
+
|
| 156 |
+
# Or use pre-computed embeddings (faster, no model weights needed)
|
| 157 |
+
cpr search --input data/gene_unknown/unknown_aa_seqs.npy \
|
| 158 |
+
--database data/lookup_embeddings.npy \
|
| 159 |
+
--output test_results.csv --fdr 0.1
|
| 160 |
+
|
| 161 |
+
# Expected: ~59 hits (39.6% of 149 sequences)
|
| 162 |
+
```
|
| 163 |
+
|
| 164 |
---
|
| 165 |
|
| 166 |
## FDR/FNR Threshold Reference
|