init new structure

pyproject.toml

@@ -33,10 +33,10 @@ documentation = "https://github.com/adamtaranto/tirmite"
 repository = "https://github.com/adamtaranto/tirmite"
 
 [project.scripts]
-#my-script = "package.module:function"
 tirmite = "tirmite.cmd_tirmite:main"
 tsplit-TIR = "tirmite.cmd_TIR:main"
 
+
 # ... other project metadata fields as specified in:
 # https://packaging.python.org/en/latest/specifications/declaring-project-metadata/
 # https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html

src/tirmite/modules/build.py

@@ -0,0 +1,48 @@
+"""
+
+timite build
+
+Cluster, align TIRs and build HMM
+
+
+Input: 
+- unaligned TIR sequences, or
+- TIR alignment
+
+Output:
+- TIR-HMM
+- Report alignment to screen
+- Report variation
+- Report TIR stats: length, variation, identity, duplicates
+- If high diversity suggest making sub-models
+
+"""
+
+import argparse
+import logging
+
+
+def mainArgs():
+    """Parse command line arguments."""
+    parser = argparse.ArgumentParser(
+        description="Build TIR-HMM from a collection of TIRsequences",
+        prog="tirmite build",
+    )
+    parser.add_argument(
+        "--loglevel",
+        default="INFO",
+        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
+        help="Set logging level.",
+    )
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = mainArgs()
+    logging.info("Running analysis")
+
+
+"""
+
+"""

src/tirmite/modules/classify.py

@@ -0,0 +1,50 @@
+"""
+tirmite classify
+
+cluster complete elements
+search for known transposase domains
+update gff with cluster labels
+
+
+Input:
+- Element json
+- or element fasta
+- Clustering identity threshold
+- Domain database
+
+Output:
+- Element JSON with cluster labels
+- GFF with cluster labels
+
+"""
+
+import argparse
+import logging
+
+
+def mainArgs():
+    """Parse command line arguments."""
+
+    parser = argparse.ArgumentParser(
+        description="Cluster elements on identity. Search for TPase domains. Apply Wicker classification.",
+        prog="tirmite classify",
+    )
+
+    parser.add_argument(
+        "--loglevel",
+        default="INFO",
+        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
+        help="Set logging level.",
+    )
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = mainArgs()
+    logging.info("Running analysis")
+
+
+"""
+
+"""

src/tirmite/modules/compare.py

@@ -0,0 +1,7 @@
+"""
+
+tirmite compare
+
+report unique hits in each set
+
+"""

src/tirmite/modules/extract.py

@@ -0,0 +1,48 @@
+"""
+tirmite extract
+
+Extract TIRs from list of elements
+
+
+Input:
+- TE sequence
+
+Output:
+- TIR sequences as fasta
+- Print sequences to screen
+- Print as proportion of input sequence
+- Report if TIRs are too short for meaningful HMM hits
+
+
+"""
+import argparse
+import logging
+
+
+def mainArgs():
+    """Parse command line arguments."""
+
+    parser = argparse.ArgumentParser(
+        description=" Identify and extract TIR sequences from one or more candidate transposon sequences.",
+        prog="tirmite extract",
+    )
+
+    parser.add_argument(
+        "--loglevel",
+        default="INFO",
+        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
+        help="Set logging level.",
+    )
+
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = mainArgs()
+    logging.info("Running analysis")
+
+
+"""
+
+"""

src/tirmite/modules/find.py

@@ -0,0 +1,49 @@
+"""
+tirmite find
+
+Query genome for HMM hits
+
+
+Input:
+- TIR HMM
+- Path to genome
+- Filtering options
+- Genome index
+
+Output:
+- Bedfile of hits coords with quality + strand
+- Optional collection of unique hit sequences
+- Optional add flanks to extraction
+
+"""
+
+import argparse
+import logging
+
+
+def mainArgs():
+    """Parse command line arguments."""
+
+    parser = argparse.ArgumentParser(
+        description="Find TIR model matches in a genome.",
+        prog="tirmite find",
+    )
+
+    parser.add_argument(
+        "--loglevel",
+        default="INFO",
+        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
+        help="Set logging level.",
+    )
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = mainArgs()
+    logging.info("Running analysis")
+
+
+"""
+
+"""

src/tirmite/modules/merge.py

@@ -0,0 +1,44 @@
+"""
+tirmite merge
+
+merge two sets of hits
+
+
+Input:
+- Multiple hit bedfiles (BLAST, HMM, other)
+
+Output:
+- Bedfile of merged hits
+
+"""
+
+import argparse
+import logging
+
+
+def mainArgs():
+    """Parse command line arguments."""
+
+    parser = argparse.ArgumentParser(
+        description="Merge TIR features from diff runs of search methods.",
+        prog="tirmite merge",
+    )
+
+    parser.add_argument(
+        "--loglevel",
+        default="INFO",
+        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
+        help="Set logging level.",
+    )
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = mainArgs()
+    logging.info("Running analysis")
+
+
+"""
+
+"""

src/tirmite/modules/pair.py

@@ -0,0 +1,46 @@
+"""
+tirmite pair
+
+Take list of hits (HMM or BLAST) and perform pairing.
+
+
+Input:
+- TIR hit file (BED)
+- Genome path
+- Index path
+
+Output:
+- GFF annotation
+- Element JSON file
+- TIRs of Paired elements only
+- FASTA of elements
+
+"""
+
+import argparse
+import logging
+
+
+def mainArgs():
+    """Parse command line arguments."""
+
+    parser = argparse.ArgumentParser(
+        description="Run pairing procedure on TIR hits",
+        prog="tirmite pair",
+    )
+
+    parser.add_argument(
+        "--loglevel",
+        default="INFO",
+        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
+        help="Set logging level.",
+    )
+    args = parser.parse_args()
+    return args
+
+
+logging.info("Running analysis")
+
+"""
+
+"""

src/tirmite/modules/report.py

@@ -0,0 +1,9 @@
+"""
+tirmite report
+
+Output gffs for elements and TIRs, 
+output fasta, 
+report length distribution, 
+stats on found elements
+
+"""