speconsense 0.7.3__py3-none-any.whl → 0.7.5__py3-none-any.whl

speconsense/__init__.py

@@ -5,7 +5,7 @@ A Python tool for experimental clustering and consensus generation as an alterna
 in the fungal DNA barcoding pipeline.
 """
 
-__version__ = "0.7.3"
+__version__ = "0.7.5"
 __author__ = "Josh Walker"
 __email__ = "joshowalker@yahoo.com"
 

speconsense/profiles/__init__.py

@@ -103,6 +103,7 @@ VALID_SUMMARIZE_KEYS = {
     "select-max-groups",
     "select-max-variants",
     "select-strategy",
+    "select-min-size-ratio",
     "enable-full-consensus",
     # Processing
     "scale-threshold",

speconsense/profiles/compressed.yaml

@@ -23,5 +23,6 @@ speconsense-summarize:
   merge-indel-length: 5         # Merge indels up to 5bp
   merge-position-count: 10      # Allow up to 10 variant positions in a merge
   merge-min-size-ratio: 0.2     # Match 20% calling threshold
+  select-min-size-ratio: 0.2    # Match 20% calling threshold
   min-merge-overlap: 0          # Disable partial overlap merging
   enable-full-consensus: true   # Include full IUPAC consensus per group

speconsense/profiles/example.yaml

@@ -91,6 +91,7 @@ speconsense-summarize:
   # select-max-groups: -1         # Max groups to output (-1 = no limit)
   # select-max-variants: -1       # Max variants per group (-1 = no limit)
   # select-strategy: size         # Selection strategy: size or diversity
+  # select-min-size-ratio: 0    # Min size ratio to include variant (0 = disabled)
 
   # --- Processing ---
   # threads: 0                    # Max threads (0 = auto-detect)

speconsense/summarize/cli.py

@@ -169,6 +169,9 @@ def parse_arguments():
     selection_group.add_argument("--select-strategy", "--variant-selection",
                                  dest="select_strategy", choices=["size", "diversity"], default="size",
                                  help="Variant selection strategy: size or diversity (default: size)")
+    selection_group.add_argument("--select-min-size-ratio", type=float, default=0,
+                                 help="Minimum size ratio (variant/largest) to include in output "
+                                      "(default: 0 = disabled, e.g. 0.2 for 20%% cutoff)")
     selection_group.add_argument("--enable-full-consensus", action="store_true",
                                  help="Generate a full consensus per variant group representing all variation "
                                       "from pre-merge variants (gaps never win)")
@@ -359,6 +362,18 @@ def process_single_specimen(file_consensuses: List[ConsensusInfo],
     for group_idx, (group_id, group_members) in enumerate(sorted_groups):
         final_group_name = group_idx + 1
 
+        # Apply select-min-size-ratio filter
+        if args.select_min_size_ratio > 0 and len(group_members) > 1:
+            largest_size = max(v.size for v in group_members)
+            filtered = [v for v in group_members
+                        if (v.size / largest_size) >= args.select_min_size_ratio]
+            if len(filtered) < len(group_members):
+                filtered_count = len(group_members) - len(filtered)
+                logging.debug(f"Group {group_idx + 1}: filtered out {filtered_count} "
+                              f"variants with size ratio < {args.select_min_size_ratio} "
+                              f"relative to largest (size={largest_size})")
+                group_members = filtered
+
         # Select variants for this group
         selected_variants = select_variants(group_members, args.select_max_variants, args.select_strategy, group_number=final_group_name)
 
@@ -377,9 +392,20 @@ def process_single_specimen(file_consensuses: List[ConsensusInfo],
             final_consensus.append(renamed_variant)
             group_naming.append((variant.sample_name, new_name))
 
-        # Generate full consensus from PRE-MERGE variants
+        # Generate full consensus from PRE-MERGE variants that contributed
+        # to surviving post-merge variants (after select-min-size-ratio)
         if getattr(args, 'enable_full_consensus', False):
-            pre_merge_variants = variant_groups[group_id]
+            # Collect original cluster names from surviving post-merge variants
+            surviving_originals = set()
+            for v in group_members:
+                if v.sample_name in all_merge_traceability:
+                    surviving_originals.update(all_merge_traceability[v.sample_name])
+                else:
+                    surviving_originals.add(v.sample_name)
+
+            pre_merge_variants = [v for v in variant_groups[group_id]
+                                  if v.sample_name in surviving_originals]
+
             specimen_base = selected_variants[0].sample_name.rsplit('-c', 1)[0]
             full_name = f"{specimen_base}-{group_idx + 1}.full"
 
@@ -450,6 +476,7 @@ def main():
     logging.info(f"  --select-max-variants: {args.select_max_variants}")
     logging.info(f"  --select-max-groups: {args.select_max_groups}")
     logging.info(f"  --select-strategy: {args.select_strategy}")
+    logging.info(f"  --select-min-size-ratio: {args.select_min_size_ratio}")
     logging.info(f"  --enable-full-consensus: {args.enable_full_consensus}")
     logging.info(f"  --log-level: {args.log_level}")
     logging.info("")

{speconsense-0.7.3.dist-info → speconsense-0.7.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: speconsense
-Version: 0.7.3
+Version: 0.7.5
 Summary: High-quality clustering and consensus generation for Oxford Nanopore amplicon reads
 Author-email: Josh Walker <joshowalker@yahoo.com>
 License: BSD-3-Clause
@@ -171,7 +171,7 @@ speconsense input.fastq -p herbarium --min-size 10
 ```
 
 **Bundled profiles:**
-- `compressed` — Compress variants into minimal IUPAC consensus sequences (aggressive merging with indels, 20% thresholds, full consensus)
+- `compressed` — Compress variants into minimal IUPAC consensus sequences (aggressive merging with indels, 20% thresholds, full consensus, 20% selection size ratio)
 - `herbarium` — High-recall for degraded DNA/type specimens
 - `largedata` — Experimental settings for large input files
 - `nostalgia` — Simulate older bioinformatics pipelines
@@ -295,14 +295,14 @@ When using `speconsense-summarize` for post-processing, creates `__Summary__/` d
 |---------------|-------------|------------|-------------|
 | **Original** | Source `cluster_debug/` | `-c1`, `-c2`, `-c3` | Preserves speconsense clustering results |
 | **Summarization** | `__Summary__/`, `FASTQ Files/`, `variants/` | `-1.v1`, `-1.v2`, `-2.v1`, `.raw1` | Post-processing groups and variants |
-| **Full consensus** | `__Summary__/` | `-1.full` | IUPAC consensus from all pre-merge variants in a group |
+| **Full consensus** | `__Summary__/` | `-1.full` | IUPAC consensus from pre-merge components of surviving variants |
 
 ### Example Directory Structure
 ```
 __Summary__/
 ├── sample-1.v1-RiC45.fasta                  # Primary variant (group 1, merged)
 ├── sample-1.v2-RiC23.fasta                  # Additional variant (not merged)
-├── sample-1.full-RiC68.fasta                # Full IUPAC consensus for group 1 (all pre-merge variants)
+├── sample-1.full-RiC68.fasta                # Full IUPAC consensus for group 1 (surviving variants' components)
 ├── sample-2.v1-RiC30.fasta                  # Second organism group, primary variant
 ├── summary.fasta                            # All final consensus sequences (excludes .raw)
 ├── summary.txt                              # Statistics
@@ -678,6 +678,18 @@ speconsense-summarize --select-strategy diversity --select-max-variants 2
    - Output up to select_max_variants per group
 3. Final output contains representatives from all groups, ensuring both biological diversity (between groups) and appropriate sampling within each biological entity (within groups)
 
+**Selection Size Ratio Filtering:**
+```bash
+speconsense-summarize --select-min-size-ratio 0.2
+```
+- Filters out post-merge variants whose size is too small relative to the largest variant in their group
+- Ratio calculated as `variant_size / largest_size` — must be ≥ threshold to keep
+- Example: `--select-min-size-ratio 0.2` means a variant must have ≥20% the reads of the largest variant in its group
+- Default is 0 (disabled) — all post-merge variants pass through to selection
+- Applied after merging but before variant selection
+- Useful for suppressing noise variants that survived merging but are too small to be meaningful
+- Set to 0.2 in the `compressed` profile to match the 20% calling threshold theme
+
 This two-stage process ensures that distinct biological sequences are preserved as separate groups, while providing control over variant complexity within each group.
 
 ### Customizing FASTA Header Fields
@@ -817,7 +829,7 @@ For high-throughput workflows (e.g., 100K sequences/year), this prioritization e
 ```bash
 speconsense-summarize --enable-full-consensus
 ```
-- Generates a full IUPAC consensus sequence per variant group from all pre-merge variants
+- Generates a full IUPAC consensus sequence per variant group from pre-merge variants that contributed to surviving post-merge variants
 - Output named `{specimen}-{group}.full-RiC{reads}.fasta` in the `__Summary__/` directory
 - Uses majority voting across all variants in the group; **gaps never win** — at each alignment column, the most common non-gap base is chosen, with IUPAC codes for ties among bases
 - Useful when you want a single representative sequence that captures all variation within a group as IUPAC ambiguity codes
@@ -1059,9 +1071,10 @@ The complete speconsense-summarize workflow operates in this order:
 2. **HAC variant grouping** by sequence identity to separate dissimilar sequences (`--group-identity`); uses single-linkage when overlap merging is enabled
 3. **Group filtering** to limit output groups (`--select-max-groups`)
 4. **Homopolymer-aware MSA-based variant merging** within each group, including **overlap merging** for different-length sequences (`--disable-merging`, `--merge-effort`, `--merge-position-count`, `--merge-indel-length`, `--min-merge-overlap`, `--merge-snp`, `--merge-min-size-ratio`, `--disable-homopolymer-equivalence`)
-5. **Variant selection** within each group (`--select-max-variants`, `--select-strategy`)
-6. **Full consensus generation** (optional) — IUPAC consensus from all pre-merge variants per group (`--enable-full-consensus`)
-7. **Output generation** with customizable header fields (`--fasta-fields`) and full traceability
+5. **Selection size ratio filtering** to remove tiny post-merge variants (`--select-min-size-ratio`)
+6. **Variant selection** within each group (`--select-max-variants`, `--select-strategy`)
+7. **Full consensus generation** (optional) — IUPAC consensus from pre-merge components of surviving post-merge variants (`--enable-full-consensus`)
+8. **Output generation** with customizable header fields (`--fasta-fields`) and full traceability
 
 **Key architectural features**:
 - HAC grouping occurs BEFORE merging to prevent inappropriate merging of dissimilar sequences (e.g., contaminants with primary targets)
@@ -1273,6 +1286,7 @@ usage: speconsense-summarize [-h] [--source SOURCE]
                              [--select-max-groups SELECT_MAX_GROUPS]
                              [--select-max-variants SELECT_MAX_VARIANTS]
                              [--select-strategy {size,diversity}]
+                             [--select-min-size-ratio SELECT_MIN_SIZE_RATIO]
                              [--enable-full-consensus]
                              [--disable-full-consensus]
                              [--scale-threshold SCALE_THRESHOLD] [--threads N]
@@ -1357,6 +1371,10 @@ Selection:
   --select-strategy {size,diversity}, --variant-selection {size,diversity}
                         Variant selection strategy: size or diversity
                         (default: size)
+  --select-min-size-ratio SELECT_MIN_SIZE_RATIO
+                        Minimum size ratio (variant/largest) to include in
+                        output (default: 0 = disabled, e.g. 0.2 for 20%
+                        cutoff)
   --enable-full-consensus
                         Generate a full consensus per variant group
                         representing all variation from pre-merge variants

{speconsense-0.7.3.dist-info → speconsense-0.7.5.dist-info}/RECORD

@@ -1,4 +1,4 @@
-speconsense/__init__.py,sha256=kKZUeH8GW0eHErdEOPuDsMEF9qqfUQjy3wntewndiO8,537
+speconsense/__init__.py,sha256=qxithGom21C3MjbApvgOzVSIRFqw4jReMKZqipfY-Kk,537
 speconsense/cli.py,sha256=Kqb2da0IuazocAz72iqTnw71jI7UaQgxsHfb9CwiolU,85
 speconsense/msa.py,sha256=t1uDb-Tj5tDnB17QnNZPslpAiLXgAMIlnmMKBbwBKzs,31661
 speconsense/quality_report.py,sha256=Byrc115T03ybi7mpA0Bw8-gc83nhKPzDY0tyH1IIAMQ,19803
@@ -9,9 +9,9 @@ speconsense/core/__main__.py,sha256=dCfyQkVxxwlP6QqcWw9y5zp5iLzkG-fQsLmFHHEUlbI,
 speconsense/core/cli.py,sha256=iepQMK0ZUhZvQShVZY_6WaHneR8ZIRKZ_b6NvVwaRwU,17186
 speconsense/core/clusterer.py,sha256=UFK5Ec0oMQ7l3GsFJOAhTFk7r90eOOdOBXRskm79Fwk,72093
 speconsense/core/workers.py,sha256=6pUyt-W9KxkillJ6TU1RjRh-_L-zRIwWqzIcBSeiOSc,25811
-speconsense/profiles/__init__.py,sha256=SPQ_Xh5QTC-HV0hYyHyJ_oEIWREz74Zmx_vcRTIJwIA,16353
-speconsense/profiles/compressed.yaml,sha256=UZx7hgu9SQQ2fvId8B60NlQmpDkrJakC45vWpIfVh_4,1165
-speconsense/profiles/example.yaml,sha256=FGCsSAVtZL_m8PHWVLVrxaVCCwQkIk8wR7N7I2ZyxX0,4463
+speconsense/profiles/__init__.py,sha256=5UWj6VyUIXTzQ1kBZ4mJ2olZ_ADMK85rwr7KEmRfZfk,16382
+speconsense/profiles/compressed.yaml,sha256=LKtBm6nj8cpF2xeFcA7vzzNzaXdEo0JknnmcDDmdFj8,1227
+speconsense/profiles/example.yaml,sha256=UGHoVvFiB6iQ-lUU4rwInL6oE1eAd7Fo5qp14vfXJvA,4546
 speconsense/profiles/herbarium.yaml,sha256=1OyAPvBZmJ0eWHejfTU_NLd1_08F9n5WbeE686mzYGE,1125
 speconsense/profiles/largedata.yaml,sha256=7qwl5CHA7BiFcznycUoprOX_A-qrsZzV5fBLnA3QmcE,884
 speconsense/profiles/nostalgia.yaml,sha256=Hy20M88FiCmDvscyIKbwfNSusiHptmBm4pIWPiSFmp0,661
@@ -23,15 +23,15 @@ speconsense/scalability/vsearch.py,sha256=I1IzTeRzEFn9bi8mNbBRvtcHvUBzBFdE7D5yf-
 speconsense/summarize/__init__.py,sha256=PE6W9hytDxhkw7W6Fz8X3jd92N2VdhuxiQ72Nqm1xC0,3181
 speconsense/summarize/__main__.py,sha256=_hzLNqNtv4PirL1oMic37GW2QmjWquoznzNtld_3FiQ,117
 speconsense/summarize/analysis.py,sha256=1MXtKMpX1bgKEtI-JN6BwTQj99qyt1eQLqNg51EgPiE,31560
-speconsense/summarize/cli.py,sha256=ts-N8i7fGTkB-qsvR-HX4egaxambHGq43Z_hjSZ8znU,25327
+speconsense/summarize/cli.py,sha256=JDgLQl8zFlbkH-Oa_n68lbUTB-cLBWzl3dphn041ph0,26961
 speconsense/summarize/clustering.py,sha256=kk-FdFCea8KRocowN_4dt_aoqZNVJMmEu7CVKPfYgK8,28346
 speconsense/summarize/fields.py,sha256=a6aK9hkPJ-sDRRSqM_7IkyqCki99KSMnsQMV-U7r2zY,8687
 speconsense/summarize/io.py,sha256=FdHLbcj0NOL3WE1e5OL85DRdJaHpyXPMcmlNg9mG3tM,32732
 speconsense/summarize/iupac.py,sha256=Y6KqELmnGy4Eya4C_4ldXY8uek0ReuSUgITLI3NW0-A,11042
 speconsense/summarize/merging.py,sha256=FakBey3qpu7ULPIsc2GDo9WG8jNU1L6q2pgQ2HrOKXk,28454
-speconsense-0.7.3.dist-info/licenses/LICENSE,sha256=T_VYPNbu9NSWjdQunfk4jqUGND_kYWe_An18s6N492o,1498
-speconsense-0.7.3.dist-info/METADATA,sha256=GdljwvAiXAA27Ei6dSE4PXcC1CH6WdKPCVVuYnd9x08,78804
-speconsense-0.7.3.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-speconsense-0.7.3.dist-info/entry_points.txt,sha256=C0zFp5EYA8_KCb04uOyb4JNkxNH7bli1eU-XYrSX3BU,147
-speconsense-0.7.3.dist-info/top_level.txt,sha256=nYUJOHrqeX-OOxOYQKvpp7Iv8-Bed18wN1DBwWfJKnQ,12
-speconsense-0.7.3.dist-info/RECORD,,
+speconsense-0.7.5.dist-info/licenses/LICENSE,sha256=T_VYPNbu9NSWjdQunfk4jqUGND_kYWe_An18s6N492o,1498
+speconsense-0.7.5.dist-info/METADATA,sha256=JiEg26k5JEJUFSR5hw4FHHysL4ei9PPyvVXsGBRBZVc,80041
+speconsense-0.7.5.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+speconsense-0.7.5.dist-info/entry_points.txt,sha256=C0zFp5EYA8_KCb04uOyb4JNkxNH7bli1eU-XYrSX3BU,147
+speconsense-0.7.5.dist-info/top_level.txt,sha256=nYUJOHrqeX-OOxOYQKvpp7Iv8-Bed18wN1DBwWfJKnQ,12
+speconsense-0.7.5.dist-info/RECORD,,