seqstatx 0.1.0__py3-none-any.whl

seqstats/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

seqstats/cli.py

@@ -0,0 +1,84 @@
+"""Command-line interface for seqstats."""
+
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+from seqstats.core import SeqStats, parse_file
+from seqstats import __version__
+
+_COLS = ["file", "seqs", "total_bp", "gc%", "mean_len", "min_len", "max_len", "N50", "N90"]
+_COL_W = [30, 8, 12, 7, 10, 8, 8, 10, 10]
+
+
+def _fmt(stats: SeqStats) -> list[str]:
+    return [
+        stats.name[:29],
+        str(stats.n_seqs),
+        str(stats.total_bases),
+        f"{stats.gc_pct:.2f}",
+        f"{stats.mean_len:.1f}",
+        str(stats.min_len),
+        str(stats.max_len),
+        str(stats.n50),
+        str(stats.n90),
+    ]
+
+
+def _header() -> str:
+    return "  ".join(c.ljust(w) for c, w in zip(_COLS, _COL_W))
+
+
+def _row(stats: SeqStats) -> str:
+    return "  ".join(v.ljust(w) for v, w in zip(_fmt(stats), _COL_W))
+
+
+def _tsv_header() -> str:
+    return "\t".join(_COLS)
+
+
+def _tsv_row(stats: SeqStats) -> str:
+    return "\t".join(_fmt(stats))
+
+
+def main(argv: list[str] | None = None) -> None:
+    parser = argparse.ArgumentParser(
+        prog="seqstatx",
+        description="Compute sequence statistics for FASTA/FASTQ files.",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""examples:
+  seqstatx genome.fa
+  seqstatx *.fastq.gz
+  seqstatx --tsv reads.fq.gz > stats.tsv
+  seqstatx --tsv sample1.fa sample2.fa | column -t""",
+    )
+    parser.add_argument("files", nargs="+", type=Path, metavar="FILE")
+    parser.add_argument("--tsv", action="store_true", help="output tab-separated values")
+    parser.add_argument("--version", action="version", version=f"seqstatx {__version__}")
+
+    args = parser.parse_args(argv)
+
+    missing = [f for f in args.files if not f.exists()]
+    if missing:
+        for f in missing:
+            print(f"[seqstats] file not found: {f}", file=sys.stderr)
+        sys.exit(1)
+
+    if args.tsv:
+        print(_tsv_header())
+    else:
+        print(_header())
+        print("-" * sum(_COL_W) + "-" * (2 * (len(_COL_W) - 1)))
+
+    for path in args.files:
+        stats = parse_file(path)
+        if args.tsv:
+            print(_tsv_row(stats))
+        else:
+            print(_row(stats))
+
+
+if __name__ == "__main__":
+    main()

seqstats/core.py

@@ -0,0 +1,125 @@
+"""Core sequence statistics logic."""
+
+from __future__ import annotations
+
+import gzip
+import sys
+from dataclasses import dataclass, field
+from pathlib import Path
+
+
+@dataclass
+class SeqStats:
+    name: str
+    n_seqs: int = 0
+    total_bases: int = 0
+    gc_count: int = 0
+    _lengths: list[int] = field(default_factory=list, repr=False)
+
+    def add(self, seq: str) -> None:
+        n = len(seq)
+        self.n_seqs += 1
+        self.total_bases += n
+        self.gc_count += seq.count("G") + seq.count("C") + seq.count("g") + seq.count("c")
+        self._lengths.append(n)
+
+    @property
+    def gc_pct(self) -> float:
+        return 100.0 * self.gc_count / self.total_bases if self.total_bases else 0.0
+
+    @property
+    def mean_len(self) -> float:
+        return self.total_bases / self.n_seqs if self.n_seqs else 0.0
+
+    @property
+    def min_len(self) -> int:
+        return min(self._lengths) if self._lengths else 0
+
+    @property
+    def max_len(self) -> int:
+        return max(self._lengths) if self._lengths else 0
+
+    @property
+    def n50(self) -> int:
+        if not self._lengths:
+            return 0
+        sorted_lens = sorted(self._lengths, reverse=True)
+        threshold = self.total_bases / 2
+        cumsum = 0
+        for length in sorted_lens:
+            cumsum += length
+            if cumsum >= threshold:
+                return length
+        return 0
+
+    @property
+    def n90(self) -> int:
+        if not self._lengths:
+            return 0
+        sorted_lens = sorted(self._lengths, reverse=True)
+        threshold = self.total_bases * 0.9
+        cumsum = 0
+        for length in sorted_lens:
+            cumsum += length
+            if cumsum >= threshold:
+                return length
+        return 0
+
+
+def _open(path: Path):
+    """Open plain or gzipped file."""
+    if path.suffix in (".gz", ".gzip"):
+        return gzip.open(path, "rt")
+    return open(path, "r")
+
+
+def parse_fasta(path: Path) -> SeqStats:
+    stats = SeqStats(name=path.name)
+    current: list[str] = []
+
+    def flush():
+        if current:
+            stats.add("".join(current))
+            current.clear()
+
+    with _open(path) as fh:
+        for line in fh:
+            line = line.rstrip()
+            if not line:
+                continue
+            if line.startswith(">"):
+                flush()
+            else:
+                current.append(line)
+    flush()
+    return stats
+
+
+def parse_fastq(path: Path) -> SeqStats:
+    stats = SeqStats(name=path.name)
+    with _open(path) as fh:
+        while True:
+            header = fh.readline()
+            if not header:
+                break
+            seq = fh.readline().rstrip()
+            fh.readline()  # +
+            fh.readline()  # quality
+            if seq:
+                stats.add(seq)
+    return stats
+
+
+def parse_file(path: Path) -> SeqStats:
+    """Detect format by extension and parse."""
+    name = path.name.lower()
+    if any(name.endswith(ext) for ext in (".fa", ".fna", ".fasta", ".fa.gz", ".fna.gz", ".fasta.gz")):
+        return parse_fasta(path)
+    if any(name.endswith(ext) for ext in (".fq", ".fastq", ".fq.gz", ".fastq.gz")):
+        return parse_fastq(path)
+    # fallback: try FASTA
+    try:
+        return parse_fasta(path)
+    except Exception:
+        print(f"[seqstats] could not detect format for {path.name}", file=sys.stderr)
+        sys.exit(1)

seqstatx-0.1.0.dist-info/METADATA

@@ -0,0 +1,90 @@
+Metadata-Version: 2.4
+Name: seqstatx
+Version: 0.1.0
+Summary: Fast sequence statistics for FASTA/FASTQ files — N50, GC%, length distributions and more
+Author-email: Wendy Bui <wendybuinta@gmail.com>
+License: MIT
+Keywords: bioinformatics,genomics,fasta,fastq,sequence,qc
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+
+# seqstats
+
+[![CI](https://github.com/perhapsstrawberries/seqstats/actions/workflows/ci.yml/badge.svg)](https://github.com/perhapsstrawberries/seqstats/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/seqstatx)](https://pypi.org/project/seqstatx/)
+![Python](https://img.shields.io/badge/python-3.10%2B-blue)
+![License](https://img.shields.io/badge/license-MIT-green)
+
+Fast sequence statistics for FASTA and FASTQ files — works on plain or gzipped inputs, no dependencies.
+
+```
+file                            seqs      total_bp      gc%      mean_len    min_len   max_len   N50         N90
+-----------------------------------------------------------------------------------------------------------------
+GRCh38.primary_assembly.fa      194       3,088,286,401  40.93   15,918,992  970       248,956,422  153,373,213  40,103,529
+SRR10045678_1.fastq.gz          10000000  1,510,000,000  50.21   151.0       151       151          151          151
+```
+
+## Install
+
+```bash
+pip install seqstatx
+```
+
+Or for development:
+
+```bash
+git clone https://github.com/perhapsstrawberries/seqstats.git
+cd seqstats
+pip install -e .
+```
+
+## Usage
+
+```bash
+# single file
+seqstatx genome.fa
+
+# multiple files, gzipped FASTQ
+seqstatx sample1.fastq.gz sample2.fastq.gz
+
+# TSV output for downstream parsing
+seqstatx --tsv *.fa > stats.tsv
+
+# pipe to column for alignment
+seqstatx --tsv *.fastq.gz | column -t
+```
+
+## Metrics
+
+| Column | Description |
+|--------|-------------|
+| `seqs` | Number of sequences / reads |
+| `total_bp` | Total base pairs |
+| `gc%` | GC content (%) |
+| `mean_len` | Mean sequence length |
+| `min_len` / `max_len` | Shortest / longest sequence |
+| `N50` | 50% of total assembly is in sequences ≥ this length |
+| `N90` | 90% of total assembly is in sequences ≥ this length |
+
+## Supported formats
+
+| Extension | Format |
+|-----------|--------|
+| `.fa` `.fna` `.fasta` | FASTA |
+| `.fq` `.fastq` | FASTQ |
+| `.fa.gz` `.fastq.gz` etc. | gzipped variants |
+
+## Why
+
+Existing tools (seqkit, seqtk) are great but require installation of compiled binaries.  
+`seqstats` is pure Python 3.10+, zero dependencies, pip-installable from any HPC or Conda environment.
+
+## License
+
+MIT

seqstatx-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+seqstats/__init__.py,sha256=kUR5RAFc7HCeiqdlX36dZOHkUI5wI6V_43RpEcD8b-0,22
+seqstats/cli.py,sha256=G1j416HXic3FElg_v6JraqdRuUpHNwmOq9-Sv3UOtoE,2234
+seqstats/core.py,sha256=JMA1Ynrk41igrGYReqXv02wjVdpi3XBv5hs4GrYtyvk,3367
+seqstatx-0.1.0.dist-info/METADATA,sha256=TQ5gGX89VHJ6bQ42z1cPfkv-n_vOFGSXUg-rN6DIDBY,2796
+seqstatx-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+seqstatx-0.1.0.dist-info/entry_points.txt,sha256=hltTdEO16NlBN8dFELLix6DGhq6E8TSrFnGAjfqTMu4,47
+seqstatx-0.1.0.dist-info/top_level.txt,sha256=pu4R79NmGkId0R2KIUWXSCVKLiTPU5mgKR37uyRr5P0,9
+seqstatx-0.1.0.dist-info/RECORD,,

seqstatx-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

seqstatx-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+seqstatx = seqstats.cli:main

seqstatx-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+seqstats