DAJIN2 0.4.2__zip → 0.4.3__zip

{DAJIN2-0.4.2/src/DAJIN2.egg-info → DAJIN2-0.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: DAJIN2
-Version: 0.4.2
+Version: 0.4.3
 Summary: One-step genotyping tools for targeted long-read sequencing
 Home-page: https://github.com/akikuno/DAJIN2
 Author: Akihiro Kuno
@@ -14,22 +14,22 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy>=1.20.0
-Requires-Dist: scipy>=1.6.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: scipy>=1.10.0
 Requires-Dist: pandas>=1.0.0
-Requires-Dist: openpyxl>=3.0.0
-Requires-Dist: rapidfuzz>=3.0.0
-Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: openpyxl>=3.1.0
+Requires-Dist: rapidfuzz>=3.6.0
+Requires-Dist: scikit-learn>=1.3.0
 Requires-Dist: mappy>=2.24
-Requires-Dist: pysam>=0.19.0
+Requires-Dist: pysam>=0.21.0
 Requires-Dist: Flask>=2.2.0
 Requires-Dist: waitress>=2.1.0
 Requires-Dist: Jinja2>=3.1.0
-Requires-Dist: plotly>=5.0.0
+Requires-Dist: plotly>=5.19.0
 Requires-Dist: kaleido>=0.2.0
 Requires-Dist: cstag>=1.0.0
-Requires-Dist: midsv>=0.10.1
-Requires-Dist: wslPath>=0.3.0
+Requires-Dist: midsv>=0.11.0
+Requires-Dist: wslPath>=0.4.1
 
 [![License](https://img.shields.io/badge/License-MIT-9cf.svg)](https://choosealicense.com/licenses/mit/)
 [![Test](https://img.shields.io/github/actions/workflow/status/akikuno/dajin2/pytest.yml?branch=main&label=Test&color=brightgreen)](https://github.com/akikuno/dajin2/actions)
@@ -78,6 +78,7 @@ conda activate env-dajin2
 > CONDA_SUBDIR=osx-64 conda create -n env-dajin2 -c conda-forge -c bioconda python=3.10 DAJIN2 -y
 > conda activate env-dajin2
 > conda config --env --set subdir osx-64
+> python -c "import platform; print(platform.machine())" # Confirm that the output is 'x86_64', not 'arm64'
 > ```
 
 ### From [PyPI](https://pypi.org/project/DAJIN2/)
@@ -164,12 +165,17 @@ Options:
 #### Example
 
 ```bash
+# Download example dataset
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_single.tar.gz
+tar -xf example_single.tar.gz
+
+# Run DAJIN2
 DAJIN2 \
-    --control example/barcode01 \
-    --sample example/barcode02 \
-    --allele example/design.fa \
-    --name IL6-knockin \
-    --genome hg38 \
+    --control example_single/control \
+    --sample example_single/sample \
+    --allele example_single/stx2_deletion.fa \
+    --name stx2_deletion \
+    --genome mm39 \
     --threads 4
 ```
 
@@ -206,7 +212,6 @@ DAJIN2 \
 
 By using the `batch` subcommand, you can process multiple FASTQ files simultaneously.  
 For this purpose, a CSV or Excel file consolidating the sample information is required.  
-<!-- For a specific example, please refer to [this link](https://github.com/akikuno/DAJIN2/blob/main/examples/example-batch/batch.csv). -->
 
 > [!NOTE]
 > For guidance on how to compile sample information, please refer to [this document](https://docs.google.com/presentation/d/e/2PACX-1vSMEmXJPG2TNjfT66XZJRzqJd82aAqO5gJrdEzyhn15YBBr_Li-j5puOgVChYf3jA/embed?start=false&loop=false&delayms=3000).
@@ -224,13 +229,18 @@ options:
 #### Example
 
 ```bash
-DAJIN2 --file batch.csv --threads 4
+# Donwload the example dataset
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_batch.tar.gz
+tar -xf example_batch.tar.gz
+
+# Run DAJIN2
+DAJIN2 batch --file example_batch/batch.csv --threads 4
 ```
 
 <!-- ```bash
 # Donwload the example dataset
-wget https://github.com/akikuno/DAJIN2/raw/main/examples/example-batch.tar.gz
-tar -xf example-batch.tar.gz
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_batch.tar.gz
+tar -xf example_batch.tar.gz
 
 # Run DAJIN2
 DAJIN2 batch --file example-batch/batch.csv --threads 3

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/README.md

@@ -45,6 +45,7 @@ conda activate env-dajin2
 > CONDA_SUBDIR=osx-64 conda create -n env-dajin2 -c conda-forge -c bioconda python=3.10 DAJIN2 -y
 > conda activate env-dajin2
 > conda config --env --set subdir osx-64
+> python -c "import platform; print(platform.machine())" # Confirm that the output is 'x86_64', not 'arm64'
 > ```
 
 ### From [PyPI](https://pypi.org/project/DAJIN2/)
@@ -131,12 +132,17 @@ Options:
 #### Example
 
 ```bash
+# Download example dataset
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_single.tar.gz
+tar -xf example_single.tar.gz
+
+# Run DAJIN2
 DAJIN2 \
-    --control example/barcode01 \
-    --sample example/barcode02 \
-    --allele example/design.fa \
-    --name IL6-knockin \
-    --genome hg38 \
+    --control example_single/control \
+    --sample example_single/sample \
+    --allele example_single/stx2_deletion.fa \
+    --name stx2_deletion \
+    --genome mm39 \
     --threads 4
 ```
 
@@ -173,7 +179,6 @@ DAJIN2 \
 
 By using the `batch` subcommand, you can process multiple FASTQ files simultaneously.  
 For this purpose, a CSV or Excel file consolidating the sample information is required.  
-<!-- For a specific example, please refer to [this link](https://github.com/akikuno/DAJIN2/blob/main/examples/example-batch/batch.csv). -->
 
 > [!NOTE]
 > For guidance on how to compile sample information, please refer to [this document](https://docs.google.com/presentation/d/e/2PACX-1vSMEmXJPG2TNjfT66XZJRzqJd82aAqO5gJrdEzyhn15YBBr_Li-j5puOgVChYf3jA/embed?start=false&loop=false&delayms=3000).
@@ -191,13 +196,18 @@ options:
 #### Example
 
 ```bash
-DAJIN2 --file batch.csv --threads 4
+# Donwload the example dataset
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_batch.tar.gz
+tar -xf example_batch.tar.gz
+
+# Run DAJIN2
+DAJIN2 batch --file example_batch/batch.csv --threads 4
 ```
 
 <!-- ```bash
 # Donwload the example dataset
-wget https://github.com/akikuno/DAJIN2/raw/main/examples/example-batch.tar.gz
-tar -xf example-batch.tar.gz
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_batch.tar.gz
+tar -xf example_batch.tar.gz
 
 # Run DAJIN2
 DAJIN2 batch --file example-batch/batch.csv --threads 3

DAJIN2-0.4.3/requirements.txt

@@ -0,0 +1,20 @@
+numpy >= 1.24.0
+scipy >= 1.10.0
+pandas >= 1.0.0
+openpyxl >= 3.1.0
+rapidfuzz >=3.6.0
+scikit-learn >= 1.3.0
+
+mappy >= 2.24
+pysam >= 0.21.0
+
+Flask >= 2.2.0
+waitress >= 2.1.0
+Jinja2 >= 3.1.0
+
+plotly >= 5.19.0
+kaleido >= 0.2.0
+
+cstag >= 1.0.0
+midsv >= 0.11.0
+wslPath >=0.4.1

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/setup.py

@@ -9,7 +9,7 @@ with open("requirements.txt") as requirements_file:
 
 setuptools.setup(
     name="DAJIN2",
-    version="0.4.2",
+    version="0.4.3",
     author="Akihiro Kuno",
     author_email="akuno@md.tsukuba.ac.jp",
     description="One-step genotyping tools for targeted long-read sequencing",

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/src/DAJIN2/core/clustering/label_merger.py

@@ -11,20 +11,6 @@ def calculate_label_percentages(labels: list[int]) -> dict[int, float]:
     return {label: (count / total_labels * 100) for label, count in label_counts.items()}
 
 
-def merge_mixed_cluster(labels_control: list[int], labels_sample: list[int], threshold: float = 0.5) -> list[int]:
-    """Merge labels in sample if they appear more than 'threshold' percentage in control."""
-    labels_merged = labels_sample.copy()
-    label_percentages_control = calculate_label_percentages(labels_control)
-    mixed_labels = {label for label, percent in label_percentages_control.items() if percent > threshold}
-
-    new_label = max(labels_merged) + 1
-    for i, label in enumerate(labels_sample):
-        if label in mixed_labels:
-            labels_merged[i] = new_label
-
-    return labels_merged
-
-
 def map_clusters_to_previous(labels_sample: list[int], labels_previous: list[int]) -> dict[int, int]:
     """
     Determine which cluster in labels_previous corresponds to each cluster in labels_sample.
@@ -63,6 +49,8 @@ def merge_minor_cluster(
     minor_labels_percentage = {label for label, percent in label_percentages.items() if percent < threshold_percentage}
     minor_labels_readnumber = {label for label, num in Counter(labels_sample).items() if num <= threshold_readnumber}
     minor_labels = minor_labels_percentage | minor_labels_readnumber
+    if minor_labels == set():
+        return labels_sample
 
     correspondence = map_clusters_to_previous(labels_sample, labels_previous)
     update_required_labels = get_update_required_labels(correspondence)
@@ -70,7 +58,23 @@ def merge_minor_cluster(
     labels_merged = labels_sample.copy()
     for m in minor_labels:
         new_label = max(labels_merged) + 1
-        labels_merged = [new_label if label in update_required_labels[correspondence[m]] else label for label in labels_merged]
+        labels_merged = [
+            new_label if label in update_required_labels[correspondence[m]] else label for label in labels_merged
+        ]
+
+    return labels_merged
+
+
+def merge_mixed_cluster(labels_control: list[int], labels_sample: list[int], threshold: float = 0.5) -> list[int]:
+    """Merge labels in sample if they appear more than 'threshold' percentage in control."""
+    labels_merged = labels_sample.copy()
+    label_percentages_control = calculate_label_percentages(labels_control)
+    mixed_labels = {label for label, percent in label_percentages_control.items() if percent > threshold}
+
+    new_label = max(labels_merged) + 1
+    for i, label in enumerate(labels_sample):
+        if label in mixed_labels:
+            labels_merged[i] = new_label
 
     return labels_merged
 
@@ -82,7 +86,7 @@ def merge_minor_cluster(
 
 def merge_labels(labels_control: list[int], labels_sample: list[int], labels_previous: list[int]) -> list[int]:
     labels_merged = merge_minor_cluster(
-        labels_sample, labels_previous, threshold_percentage=0.5, threshold_readnumber=10
+        labels_sample, labels_previous, threshold_percentage=0.5, threshold_readnumber=5
     )
     labels_merged = merge_mixed_cluster(labels_control, labels_merged)
     return labels_merged

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/src/DAJIN2/core/core.py

@@ -70,8 +70,8 @@ def execute_control(arguments: dict):
     # Output BAM files
     ###########################################################
     logger.info(f"Output BAM files of {arguments['control']}...")
-    report.report_bam.export_to_bam(
-        ARGS.tempdir, ARGS.control_name, ARGS.genome_coordinates, ARGS.threads, is_control=True
+    report.bam_exporter.export_to_bam(
+        ARGS.tempdir, ARGS.control_name, ARGS.genome_coordinates, ARGS.threads, ARGS.uuid, is_control=True
     )
     ###########################################################
     # Finish call
@@ -204,15 +204,15 @@ def execute_sample(arguments: dict):
     # RESULT
     io.write_jsonl(RESULT_SAMPLE, Path(ARGS.tempdir, "result", f"{ARGS.sample_name}.jsonl"))
     # FASTA
-    report.report_files.export_to_fasta(ARGS.tempdir, ARGS.sample_name, cons_sequence)
-    report.report_files.export_reference_to_fasta(ARGS.tempdir, ARGS.sample_name)
+    report.sequence_exporter.export_to_fasta(ARGS.tempdir, ARGS.sample_name, cons_sequence)
+    report.sequence_exporter.export_reference_to_fasta(ARGS.tempdir, ARGS.sample_name)
     # HTML
-    report.report_files.export_to_html(ARGS.tempdir, ARGS.sample_name, cons_percentage)
+    report.sequence_exporter.export_to_html(ARGS.tempdir, ARGS.sample_name, cons_percentage)
     # CSV (Allele Info)
-    report.report_mutation.export_to_csv(ARGS.tempdir, ARGS.sample_name, ARGS.genome_coordinates, cons_percentage)
+    report.mutation_exporter.export_to_csv(ARGS.tempdir, ARGS.sample_name, ARGS.genome_coordinates, cons_percentage)
     # BAM
-    report.report_bam.export_to_bam(
-        ARGS.tempdir, ARGS.sample_name, ARGS.genome_coordinates, ARGS.threads, RESULT_SAMPLE
+    report.bam_exporter.export_to_bam(
+        ARGS.tempdir, ARGS.sample_name, ARGS.genome_coordinates, ARGS.threads, ARGS.uuid, RESULT_SAMPLE
     )
     for path_bam_igvjs in Path(ARGS.tempdir, "cache", ".igvjs").glob(f"{ARGS.control_name}_control.bam*"):
         shutil.copy(path_bam_igvjs, Path(ARGS.tempdir, "report", ".igvjs", ARGS.sample_name))

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/src/DAJIN2/core/preprocess/genome_fetcher.py

@@ -5,11 +5,19 @@ from urllib.request import urlopen
 
 def fetch_seq_coordinates(genome: str, blat_url: str, seq: str) -> dict:
     url = f"{blat_url}?db={genome}&type=BLAT&userSeq={seq}"
-    response = urlopen(url).read().decode("utf8").split("\n")
-    matches = [x for x in response if "100.0%" in x]
+    records = urlopen(url).read().decode("utf8").split("\n")
+    matches = []
+    for record in records:
+        if "100.0%" not in record:
+            continue
+        record_trim = [r for r in record.split(" ") if r]
+        if record_trim[-1] == str(len(seq)):
+            matches = record_trim
+
     if not matches:
         raise ValueError(f"{seq[:60]}... is not found in {genome}")
-    chrom, strand, start, end, _ = matches[0].split()[-5:]
+
+    chrom, strand, start, end, _ = matches[-5:]
     return {"chrom": chrom, "strand": strand, "start": int(start), "end": int(end)}
 
 

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/src/DAJIN2/core/preprocess/midsv_caller.py

@@ -8,8 +8,7 @@ from itertools import chain, groupby
 
 from collections import Counter
 
-from DAJIN2.utils import sam_handler
-from DAJIN2.utils import cssplits_handler
+from DAJIN2.utils import io, sam_handler, cssplits_handler
 
 
 def has_inversion_in_splice(CIGAR: str) -> bool:
@@ -215,8 +214,8 @@ def generate_midsv(ARGS, is_control: bool = False, is_insertion: bool = False) -
             path_splice = Path(ARGS.tempdir, name, "sam", f"splice_{allele}.sam")
             path_output_midsv = Path(ARGS.tempdir, name, "midsv", f"{allele}.json")
 
-        sam_ont = sam_handler.remove_overlapped_reads(list(sam_handler.read_sam(path_ont)))
-        sam_splice = sam_handler.remove_overlapped_reads(list(sam_handler.read_sam(path_splice)))
+        sam_ont = sam_handler.remove_overlapped_reads(list(io.read_sam(path_ont)))
+        sam_splice = sam_handler.remove_overlapped_reads(list(io.read_sam(path_splice)))
         qname_of_map_ont = extract_qname_of_map_ont(sam_ont, sam_splice)
         sam_of_map_ont = filter_sam_by_preset(sam_ont, qname_of_map_ont, preset="map-ont")
         sam_of_splice = filter_sam_by_preset(sam_splice, qname_of_map_ont, preset="splice")

DAJIN2-0.4.3/src/DAJIN2/core/report/__init__.py

@@ -0,0 +1,3 @@
+from DAJIN2.core.report import bam_exporter
+from DAJIN2.core.report import sequence_exporter
+from DAJIN2.core.report import mutation_exporter

DAJIN2-0.4.2/src/DAJIN2/core/report/report_bam.py → DAJIN2-0.4.3/src/DAJIN2/core/report/bam_exporter.py

@@ -1,17 +1,16 @@
 from __future__ import annotations
 
-import random
 from collections import defaultdict
 from itertools import groupby
 from pathlib import Path
 
-import midsv
 import pysam
 
-from DAJIN2.utils import sam_handler
+from DAJIN2.utils import io, sam_handler
 
 
-def realign(sam: list[list[str]], GENOME_COODINATES: dict) -> list[str]:
+def recalculate_sam_coodinates_to_reference(sam: list[list[str]], GENOME_COODINATES: dict) -> list[str]:
+    """Recalculate SAM genomic coordinates with the reference genome, not with the FASTA_ALLELE"""
     sam_headers = [s for s in sam if s[0].startswith("@")]
     sam_contents = [s for s in sam if not s[0].startswith("@")]
     for s in sam_headers:
@@ -29,31 +28,44 @@ def realign(sam: list[list[str]], GENOME_COODINATES: dict) -> list[str]:
     return sam_headers + sam_contents
 
 
+def convert_pos_to_one_indexed(sam_lines: list[list[str]]) -> list[list[str]]:
+    """Convert SAM POS from 0-indexed to 1-indexed"""
+
+    def convert_line(line: list[str]) -> list[str]:
+        if not line[0].startswith("@") and line[3] == "0":
+            line[3] = "1"
+        return line
+
+    return [convert_line(line) for line in sam_lines]
+
+
 def group_by_name(sam_contents: list[str], clust_sample: list[dict]) -> dict[list]:
+    """Group alignments in map-ont.sam by allele name (NAME)"""
     sam_contents.sort()
-    clust_sample_qname = sorted(clust_sample, key=lambda x: x["QNAME"])
-    clust_sample_qname_set = set()
-    for qnames in clust_sample_qname:
-        qname = qnames["QNAME"]
-        clust_sample_qname_set.add(qname)
+    clust_sample_sorted = sorted(clust_sample, key=lambda x: x["QNAME"])
+
+    qnames: set[str] = {c["QNAME"] for c in clust_sample_sorted}
+
     sam_groups = defaultdict(list)
-    idx_left = 0
-    idx_right = 0
-    while idx_left < len(sam_contents) and idx_right < len(clust_sample_qname):
-        read_left = sam_contents[idx_left][:-1]
-        read_right = clust_sample_qname[idx_right]
-        qname_left = read_left[0]
-        qname_right = read_right["QNAME"]
-        if qname_left not in clust_sample_qname_set:
-            idx_left += 1
+    idx_sam_contents = 0
+    idx_clust_sample = 0
+    while idx_sam_contents < len(sam_contents) and idx_clust_sample < len(clust_sample_sorted):
+        alignments_sam = sam_contents[idx_sam_contents][:-1]  # Discard CS tags to reduce file size
+        alignments_clsut_sample = clust_sample_sorted[idx_clust_sample]
+        qname_sam = alignments_sam[0]
+
+        if qname_sam not in qnames:
+            idx_sam_contents += 1
             continue
-        if qname_left == qname_right:
-            key = read_right["NAME"]
-            sam_groups[key].append(read_left)
-            idx_left += 1
+
+        if qname_sam == alignments_clsut_sample["QNAME"]:
+            key = alignments_clsut_sample["NAME"]
+            sam_groups[key].append(alignments_sam)
+            idx_sam_contents += 1
         else:
-            idx_right += 1
-    return sam_groups
+            idx_clust_sample += 1
+
+    return dict(sam_groups)
 
 
 ###############################################################################
@@ -67,13 +79,11 @@ def subset_qnames(RESULT_SAMPLE, readnum: int = 100) -> dict[set[str]]:
         group = list(group)
         qnames = [res["QNAME"] for res in group[:readnum]]
         qnames_by_name[name] = set(qnames)
-    return qnames_by_name
+    return dict(qnames_by_name)
 
 
-def subset_reads(name, sam_content, qnames_by_name):
-    qnames = qnames_by_name[name]
-    sam_subset = [sam for sam in sam_content if sam[0] in qnames]
-    return sam_subset
+def subset_reads(sam_content: list[str], qnames: set[str]) -> list[str]:
+    return [sam for sam in sam_content if sam[0] in qnames]
 
 
 ###############################################################################
@@ -89,31 +99,34 @@ def write_sam_to_bam(sam: list[list[str]], path_sam: str | Path, path_bam: str |
 
 
 def update_sam(sam: list, GENOME_COODINATES: dict = {}) -> list:
-    sam_update = sam.copy()
-    sam_update = sam_handler.remove_overlapped_reads(sam_update)
-    sam_update = sam_handler.remove_microhomology(sam_update)
-    if "genome" in GENOME_COODINATES:
-        sam_update = realign(sam_update, GENOME_COODINATES)
-    return sam_update
+    sam_records = sam.copy()
+    sam_records = sam_handler.remove_overlapped_reads(sam_records)
+    sam_records = sam_handler.remove_microhomology(sam_records)
+    if GENOME_COODINATES["genome"]:
+        return recalculate_sam_coodinates_to_reference(sam_records, GENOME_COODINATES)
+    else:
+        return convert_pos_to_one_indexed(sam_records)
 
 
-def export_to_bam(TEMPDIR, NAME, GENOME_COODINATES, THREADS, RESULT_SAMPLE=None, is_control=False) -> None:
-    randomnum = random.randint(100_000, 999_999)
+def export_to_bam(TEMPDIR, NAME, GENOME_COODINATES, THREADS, UUID, RESULT_SAMPLE=None, is_control=False) -> None:
     path_sam_input = Path(TEMPDIR, NAME, "sam", "map-ont_control.sam")
-    sam = list(midsv.read_sam(path_sam_input))
+    sam_records = list(io.read_sam(path_sam_input))
+
     # Update sam
-    sam_update = update_sam(sam, GENOME_COODINATES)
+    sam_updated = update_sam(sam_records, GENOME_COODINATES)
+
     # Output SAM and BAM
-    path_sam_output = Path(TEMPDIR, "report", "BAM", f"tmp{randomnum}_{NAME}_control.sam")
+    path_sam_output = Path(TEMPDIR, "report", "BAM", f"temp_{UUID}_{NAME}_control.sam")
     path_bam_output = Path(TEMPDIR, "report", "BAM", NAME, f"{NAME}.bam")
-    write_sam_to_bam(sam_update, path_sam_output, path_bam_output, THREADS)
+    write_sam_to_bam(sam_updated, path_sam_output, path_bam_output, THREADS)
+
     # Prepare SAM headers and contents
-    sam_headers = [s for s in sam_update if s[0].startswith("@")]
-    sam_contents = [s for s in sam_update if not s[0].startswith("@")]
+    sam_headers = [s for s in sam_updated if s[0].startswith("@")]
+    sam_contents = [s for s in sam_updated if not s[0].startswith("@")]
     if is_control:
-        qnames = set(list(set(s[0] for s in sam_contents[:10000]))[:100])
-        sam_subset = [s for s in sam_update if s[0] in qnames]
-        path_sam_output = Path(TEMPDIR, "report", "BAM", f"tmp{randomnum}_{NAME}_control_cache.sam")
+        qnames: set[str] = set(list(set(s[0] for s in sam_contents[:10000]))[:100])
+        sam_subset = [s for s in sam_updated if s[0] in qnames]
+        path_sam_output = Path(TEMPDIR, "report", "BAM", f"temp_{UUID}_{NAME}_control_cache.sam")
         path_bam_output = Path(TEMPDIR, "cache", ".igvjs", NAME, "control.bam")
         write_sam_to_bam(sam_headers + sam_subset, path_sam_output, path_bam_output, THREADS)
     else:
@@ -122,14 +135,15 @@ def export_to_bam(TEMPDIR, NAME, GENOME_COODINATES, THREADS, RESULT_SAMPLE=None,
         # Output SAM and BAM
         for name, sam_content in sam_groups.items():
             # BAM
-            path_sam_output = Path(TEMPDIR, "report", "bam", f"tmp{randomnum}_{name}.sam")
+            path_sam_output = Path(TEMPDIR, "report", "BAM", f"temp_{UUID}_{name}.sam")
             path_bam_output = Path(TEMPDIR, "report", "BAM", NAME, f"{NAME}_{name}.bam")
             write_sam_to_bam(sam_headers + sam_content, path_sam_output, path_bam_output, THREADS)
             # igvjs
-            sam_subset = subset_reads(name, sam_content, qnames_by_name)
-            path_sam_output = Path(TEMPDIR, "report", "bam", f"tmp{randomnum}_{name}_subset.sam")
+            sam_subset = subset_reads(sam_content, qnames_by_name[name])
+            path_sam_output = Path(TEMPDIR, "report", "BAM", f"temp_{UUID}_{name}_subset.sam")
             path_bam_output = Path(TEMPDIR, "report", ".igvjs", NAME, f"{name}.bam")
             write_sam_to_bam(sam_headers + sam_subset, path_sam_output, path_bam_output, THREADS)
+
     # Remove temporary files
-    sam_temp = Path(TEMPDIR, "report", "BAM").glob(f"tmp{randomnum}*.sam")
+    sam_temp = Path(TEMPDIR, "report", "BAM").glob(f"temp_{UUID}*.sam")
     [s.unlink() for s in sam_temp]

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/src/DAJIN2/main.py

@@ -20,7 +20,7 @@ from DAJIN2.core import core
 from DAJIN2.utils import io, config, report_generator, input_validator, multiprocess
 
 
-DAJIN_VERSION = "0.4.2"
+DAJIN_VERSION = "0.4.3"
 
 
 def generate_report(name: str) -> None:

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/src/DAJIN2/utils/io.py

@@ -19,6 +19,12 @@ from openpyxl import load_workbook, Workbook
 ###########################################################
 
 
+def read_sam(path_of_sam: str | Path) -> Generator[list]:
+    with open(path_of_sam) as f:
+        for line in f:
+            yield line.strip().split("\t")
+
+
 def load_pickle(file_path: Path):
     with open(file_path, "rb") as f:
         return pickle.load(f)

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/src/DAJIN2/utils/sam_handler.py

@@ -2,8 +2,6 @@ from __future__ import annotations
 
 import re
 
-from pathlib import Path
-from typing import Generator
 from itertools import groupby
 from DAJIN2.utils.dna_handler import revcomp
 
@@ -25,17 +23,6 @@ def is_mapped(s: list[str]) -> bool:
     return not s[0].startswith("@") and s[9] != "*"
 
 
-###########################################################
-# Read sam
-###########################################################
-
-
-def read_sam(path_of_sam: str | Path) -> Generator[list]:
-    with open(path_of_sam) as f:
-        for line in f:
-            yield line.strip().split("\t")
-
-
 ###########################################################
 # remove_overlapped_reads
 ###########################################################

{DAJIN2-0.4.2 → DAJIN2-0.4.3/src/DAJIN2.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: DAJIN2
-Version: 0.4.2
+Version: 0.4.3
 Summary: One-step genotyping tools for targeted long-read sequencing
 Home-page: https://github.com/akikuno/DAJIN2
 Author: Akihiro Kuno
@@ -14,22 +14,22 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy>=1.20.0
-Requires-Dist: scipy>=1.6.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: scipy>=1.10.0
 Requires-Dist: pandas>=1.0.0
-Requires-Dist: openpyxl>=3.0.0
-Requires-Dist: rapidfuzz>=3.0.0
-Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: openpyxl>=3.1.0
+Requires-Dist: rapidfuzz>=3.6.0
+Requires-Dist: scikit-learn>=1.3.0
 Requires-Dist: mappy>=2.24
-Requires-Dist: pysam>=0.19.0
+Requires-Dist: pysam>=0.21.0
 Requires-Dist: Flask>=2.2.0
 Requires-Dist: waitress>=2.1.0
 Requires-Dist: Jinja2>=3.1.0
-Requires-Dist: plotly>=5.0.0
+Requires-Dist: plotly>=5.19.0
 Requires-Dist: kaleido>=0.2.0
 Requires-Dist: cstag>=1.0.0
-Requires-Dist: midsv>=0.10.1
-Requires-Dist: wslPath>=0.3.0
+Requires-Dist: midsv>=0.11.0
+Requires-Dist: wslPath>=0.4.1
 
 [![License](https://img.shields.io/badge/License-MIT-9cf.svg)](https://choosealicense.com/licenses/mit/)
 [![Test](https://img.shields.io/github/actions/workflow/status/akikuno/dajin2/pytest.yml?branch=main&label=Test&color=brightgreen)](https://github.com/akikuno/dajin2/actions)
@@ -78,6 +78,7 @@ conda activate env-dajin2
 > CONDA_SUBDIR=osx-64 conda create -n env-dajin2 -c conda-forge -c bioconda python=3.10 DAJIN2 -y
 > conda activate env-dajin2
 > conda config --env --set subdir osx-64
+> python -c "import platform; print(platform.machine())" # Confirm that the output is 'x86_64', not 'arm64'
 > ```
 
 ### From [PyPI](https://pypi.org/project/DAJIN2/)
@@ -164,12 +165,17 @@ Options:
 #### Example
 
 ```bash
+# Download example dataset
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_single.tar.gz
+tar -xf example_single.tar.gz
+
+# Run DAJIN2
 DAJIN2 \
-    --control example/barcode01 \
-    --sample example/barcode02 \
-    --allele example/design.fa \
-    --name IL6-knockin \
-    --genome hg38 \
+    --control example_single/control \
+    --sample example_single/sample \
+    --allele example_single/stx2_deletion.fa \
+    --name stx2_deletion \
+    --genome mm39 \
     --threads 4
 ```
 
@@ -206,7 +212,6 @@ DAJIN2 \
 
 By using the `batch` subcommand, you can process multiple FASTQ files simultaneously.  
 For this purpose, a CSV or Excel file consolidating the sample information is required.  
-<!-- For a specific example, please refer to [this link](https://github.com/akikuno/DAJIN2/blob/main/examples/example-batch/batch.csv). -->
 
 > [!NOTE]
 > For guidance on how to compile sample information, please refer to [this document](https://docs.google.com/presentation/d/e/2PACX-1vSMEmXJPG2TNjfT66XZJRzqJd82aAqO5gJrdEzyhn15YBBr_Li-j5puOgVChYf3jA/embed?start=false&loop=false&delayms=3000).
@@ -224,13 +229,18 @@ options:
 #### Example
 
 ```bash
-DAJIN2 --file batch.csv --threads 4
+# Donwload the example dataset
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_batch.tar.gz
+tar -xf example_batch.tar.gz
+
+# Run DAJIN2
+DAJIN2 batch --file example_batch/batch.csv --threads 4
 ```
 
 <!-- ```bash
 # Donwload the example dataset
-wget https://github.com/akikuno/DAJIN2/raw/main/examples/example-batch.tar.gz
-tar -xf example-batch.tar.gz
+wget https://github.com/akikuno/DAJIN2/raw/main/examples/example_batch.tar.gz
+tar -xf example_batch.tar.gz
 
 # Run DAJIN2
 DAJIN2 batch --file example-batch/batch.csv --threads 3

{DAJIN2-0.4.2 → DAJIN2-0.4.3}/src/DAJIN2.egg-info/SOURCES.txt

@@ -46,10 +46,10 @@ src/DAJIN2/core/preprocess/mapping.py
 src/DAJIN2/core/preprocess/midsv_caller.py
 src/DAJIN2/core/preprocess/mutation_extractor.py
 src/DAJIN2/core/report/__init__.py
+src/DAJIN2/core/report/bam_exporter.py
 src/DAJIN2/core/report/insertion_reflector.py
-src/DAJIN2/core/report/report_bam.py
-src/DAJIN2/core/report/report_files.py
-src/DAJIN2/core/report/report_mutation.py
+src/DAJIN2/core/report/mutation_exporter.py
+src/DAJIN2/core/report/sequence_exporter.py
 src/DAJIN2/static/css/style.css
 src/DAJIN2/templates/index.html
 src/DAJIN2/utils/config.py

DAJIN2-0.4.3/src/DAJIN2.egg-info/requires.txt

@@ -0,0 +1,16 @@
+numpy>=1.24.0
+scipy>=1.10.0
+pandas>=1.0.0
+openpyxl>=3.1.0
+rapidfuzz>=3.6.0
+scikit-learn>=1.3.0
+mappy>=2.24
+pysam>=0.21.0
+Flask>=2.2.0
+waitress>=2.1.0
+Jinja2>=3.1.0
+plotly>=5.19.0
+kaleido>=0.2.0
+cstag>=1.0.0
+midsv>=0.11.0
+wslPath>=0.4.1

DAJIN2-0.4.2/requirements.txt

@@ -1,20 +0,0 @@
-numpy >= 1.20.0
-scipy >= 1.6.0
-pandas >= 1.0.0
-openpyxl >= 3.0.0
-rapidfuzz >=3.0.0
-scikit-learn >= 1.0.0
-
-mappy >= 2.24
-pysam >= 0.19.0
-
-Flask >= 2.2.0
-waitress >= 2.1.0
-Jinja2 >= 3.1.0
-
-plotly >= 5.0.0
-kaleido >= 0.2.0
-
-cstag >= 1.0.0
-midsv >= 0.10.1
-wslPath >=0.3.0

DAJIN2-0.4.2/src/DAJIN2/core/report/__init__.py

@@ -1,3 +0,0 @@
-from DAJIN2.core.report import report_bam
-from DAJIN2.core.report import report_files
-from DAJIN2.core.report import report_mutation

DAJIN2-0.4.2/src/DAJIN2.egg-info/requires.txt

@@ -1,16 +0,0 @@
-numpy>=1.20.0
-scipy>=1.6.0
-pandas>=1.0.0
-openpyxl>=3.0.0
-rapidfuzz>=3.0.0
-scikit-learn>=1.0.0
-mappy>=2.24
-pysam>=0.19.0
-Flask>=2.2.0
-waitress>=2.1.0
-Jinja2>=3.1.0
-plotly>=5.0.0
-kaleido>=0.2.0
-cstag>=1.0.0
-midsv>=0.10.1
-wslPath>=0.3.0