Updated Annotation tools using branch of this repo

LICENSE

@@ -0,0 +1,20 @@
+The MIT License (MIT)
+
+Copyright (c) 2022 Youpu-Chen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -0,0 +1,48 @@
+# plastidUtilis
+
+`plastidUtilis` is a collection utilities of module which could be applied in manual annotation of plastid genome.
+
+
+
+## How to get it?
+
+```shell
+# pip install biopython
+pip install plastidUtilis
+```
+
+
+
+## How to use it?
+
+Note: this toolkit is only compatible with TBtools, so be careful with other format in this version.
+
+```shell
+# main utilities
+python -m plastidUtilis.Sort -f <Geseq_out_seq> -o <name_of_output> --header <Input_header>
+python -m plastidUtilis.AbnormalDetect -a <input_fasta> -o <output_filename>
+python -m plastidUtilis.BLAST -d <tRNA_database> -t <sort_tRNA> -o <output.fasta>
+python -m plastidUtilis.Table2GBK -t <self-made table file> -o <.gb>
+python -m plastidUtilis.Filter -f <input_fasta> -i <minumum_length> -I <maximum_length> -o <output filename>
+python -m plastidUtilis.Longest -f <input.fasta> -d <delimiter> -o <output.fasta>
+
+# side utilities
+python -m plastidUtilis.Translate -i <sorted_CDS> -o <output_protein_sequence>
+python -m plastidUtilis.Stats -i <sorted_CDS>    # further it will be designed as tabular output 
+python -m plastidUtilis.SequenceAppend -f <input_assembly> -i <input_abnormal_bed> -n <the_number_of_extending_bp> -o <output>
+```
+
+
+
+# Pipeline
+
+
+
+# License
+
+MIT License
+Copyright (c) 2022 Zihao Huang, Youpu-Chen.
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "plastidUtilis"
+version = "0.0.5"
+authors = [
+  { name="Youpu Chen", email="[email protected]" }
+]
+description = "chloroplast/mitochondrion annotation toolkits"
+readme = "README.md"
+requires-python = ">=3.8"
+dependencies = [
+    "biopython"
+]
+classifiers = [  # Optional
+    # How mature is this project? Common values are
+    #   3 - 3
+    #   4 - Beta
+    #   5 - Production/Stable
+    'Development Status :: 3 - Alpha',
+
+    # Indicate who your project is intended for
+    'Intended Audience :: Information Technology',
+    'Topic :: Scientific/Engineering :: Bio-Informatics',
+
+    # Pick your license as you wish
+    'License :: OSI Approved :: MIT License',
+
+    # Specify the Python versions you support here. In particular, ensure
+    # that you indicate whether you support Python 2, Python 3 or both.
+    'Programming Language :: Python :: 3',
+    'Programming Language :: Python :: 3.8',
+]

src/plastidUtilis.egg-info/PKG-INFO

@@ -0,0 +1,65 @@
+Metadata-Version: 2.1
+Name: plastidUtilis
+Version: 0.0.5
+Summary: chloroplast/mitochondrion annotation toolkits
+Author-email: Youpu Chen <[email protected]>
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Information Technology
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# plastidUtilis
+
+`plastidUtilis` is a collection utilities of module which could be applied in manual annotation of plastid genome.
+
+
+
+## How to get it?
+
+```shell
+# pip install biopython
+pip install plastidUtilis
+```
+
+
+
+## How to use it?
+
+Note: this toolkit is only compatible with TBtools, so be careful with other format in this version.
+
+```shell
+# main utilities
+python -m plastidUtilis.Sort -f <Geseq_out_seq> -o <name_of_output> --header <Input_header>
+python -m plastidUtilis.AbnormalDetect -a <input_fasta> -o <output_filename>
+python -m plastidUtilis.BLAST -d <tRNA_database> -t <sort_tRNA> -o <output.fasta>
+python -m plastidUtilis.Table2GBK -t <self-made table file> -o <.gb>
+python -m plastidUtilis.Filter -f <input_fasta> -i <minumum_length> -I <maximum_length> -o <output filename>
+python -m plastidUtilis.Longest -f <input.fasta> -d <delimiter> -o <output.fasta>
+
+# side utilities
+python -m plastidUtilis.Translate -i <sorted_CDS> -o <output_protein_sequence>
+python -m plastidUtilis.Stats -i <sorted_CDS>    # further it will be designed as tabular output 
+python -m plastidUtilis.SequenceAppend -f <input_assembly> -i <input_abnormal_bed> -n <the_number_of_extending_bp> -o <output>
+```
+
+
+
+# Pipeline
+
+
+
+
+
+# License
+
+MIT License
+Copyright (c) 2022 Zihao Huang, Youpu-Chen.
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

src/plastidUtilis.egg-info/SOURCES.txt

@@ -0,0 +1,17 @@
+LICENSE
+README.md
+pyproject.toml
+src/plastidUtilis/AbnormalDetect.py
+src/plastidUtilis/BLAST.py
+src/plastidUtilis/Filter.py
+src/plastidUtilis/Longest.py
+src/plastidUtilis/SequenceAppend.py
+src/plastidUtilis/Sort.py
+src/plastidUtilis/Stats.py
+src/plastidUtilis/Table2GBK.py
+src/plastidUtilis/Translate.py
+src/plastidUtilis.egg-info/PKG-INFO
+src/plastidUtilis.egg-info/SOURCES.txt
+src/plastidUtilis.egg-info/dependency_links.txt
+src/plastidUtilis.egg-info/requires.txt
+src/plastidUtilis.egg-info/top_level.txt

src/plastidUtilis.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

src/plastidUtilis.egg-info/requires.txt

@@ -0,0 +1 @@
+biopython

src/plastidUtilis.egg-info/top_level.txt

@@ -0,0 +1 @@
+plastidUtilis

src/plastidUtilis/AbnormalDetect.py

@@ -0,0 +1,58 @@
+'''this module is used to detect the abnormal CDS sequence annotated by Geseq
+Note: input sequence should be in protein / amino acid format. 
+'''
+def AbnormalDetect(input, output):
+    aa_dict = {}
+    # aa_file = options.aa
+    aa_file = input
+    # out_file = options.output
+    out_file = output
+    with open(aa_file) as f:
+        data = f.readlines()
+        for line in data:
+            if line.startswith(">"):
+                aa_header = line.strip()
+                aa_dict[aa_header] = []
+            else:
+                aa_dict[aa_header].append(line.strip())
+
+    for k, v in aa_dict.items():
+        aa_dict[k] = "".join(v)
+
+    normal_dict = {}
+    abnormal_dict = {}
+
+    for k, v in aa_dict.items():
+        # normal
+        if v.endswith("*") and int(len(v.split("*"))) == 2:
+            normal_dict[k.split()[0][1:]] = v
+        else:
+            # abnormal
+            abnormal_dict[k.split()[0][1:]] = v
+    with open(out_file, "w") as out:
+        for k, v in abnormal_dict.items():
+            if k in normal_dict.keys():
+                # copy abnormal
+                out.write(k+ "\t" + "copy_abnormal" + "\n")
+            elif k not in normal_dict.keys():
+                out.write(k + "\n")
+    out.close()
+
+
+def main():
+    import optparse
+
+    usage = """python -m plastidUtilis.AbnormalDetect -a <input_fasta> -o <output_filename>
+                                                                                        --Joe"""
+    parser = optparse.OptionParser(usage)
+    parser.add_option("-a", dest="aa", help="input protein fasta",
+                    metavar="FILE", action="store", type="string")
+    parser.add_option("-o", dest="output", help="output filename",
+                    metavar="OUT", action="store", type="string")
+    (options, args) = parser.parse_args()
+
+    AbnormalDetect(options.aa, options.output)
+
+
+if __name__ == "__main__":
+    main()

src/plastidUtilis/BLAST.py

@@ -0,0 +1,91 @@
+'''this module is able to execute local-installed BLAST to conduct sequence alignemnt analysis with preset parameters'''
+import optparse
+import os
+
+
+def RunBLAST(INPUT, BLASTDATABASE, OUTPUT):
+    trn_dict = {}
+    # with open(tRNA_file) as f:
+    with open(INPUT) as f:
+        data = f.readlines()
+        trn_dict["trash"] = []
+        for line in data:
+            if line.startswith(">"):
+                seqname = line.strip().replace("\t", "@")[1:]
+                if seqname not in trn_dict.keys():
+                    trn_dict[seqname] = []
+                elif seqname in trn_dict.keys():
+                    seqname = "trash"
+            else:
+                trn_dict[seqname].append(line.strip())
+
+    del trn_dict['trash']
+    with open("temp_tRNA.fasta", "w") as t:
+        for k, v in trn_dict.items():
+            t.write(">" + k + "\n")
+            t.write("".join(v) + "\n")
+    t.close()
+
+    print(len(trn_dict.keys()))
+    os.system("makeblastdb -in %s -dbtype nucl -out %s" % (BLASTDATABASE, BLASTDATABASE))
+    os.system(
+        "blastn -query temp_tRNA.fasta -db %s -out blast.txt -perc_identity 90 -max_target_seqs 1 -subject_besthit  -num_threads 6 -outfmt  '6 qseqid qlen sseqid slen pident length score' " % database_file)
+    os.system("rm temp_tRNA.fasta")
+
+    blast_dict = {}
+    with open("blast.txt") as b:
+        data = b.readlines()
+        for line in data:
+            qseqid = line.split()[0]
+            qlen = line.split()[1]
+            sseqid = line.split()[2]
+            slen = line.split()[3]
+            pident = line.split()[4]
+            length = line.split()[5]
+            score = line.split()[6].strip()
+            # length constrain
+            if float(int(qlen) / int(slen)) > 0.9 and float(int(qlen) / int(slen)) < 1.1:
+                # alignment length constrain
+                if float(int(length) / int(slen)) > 0.9 and float(pident) > 0.90:
+                    blast_dict[qseqid] = sseqid.split("-")[1] + "-" + sseqid.split("-")[2][:3]
+
+    with open(OUTPUT, "w") as out:
+        for k, v in blast_dict.items():
+            old_id = k.split("@")[0]
+            chr = k.split("@")[1]
+            start = k.split("@")[2]
+            end = k.split("@")[3]
+            chain = k.split("@")[4]
+            length = k.split("@")[5]
+            new_id = v
+            # intron
+            if int(end) - int(start) + 1 == int(length):
+                info = [new_id, chr, start, end, chain, length]
+            else:
+                info = [new_id, chr, start, end, chain, length, "intron"]
+            out.write(">" + "\t".join(info) + "\n")
+            out.write("".join(trn_dict[k]) + "\n")
+    out.close()
+
+
+def main():
+    usage = """python -m plastidUtilis -d <tRNA_database> -t <sort_tRNA> -o <output.fasta>
+                                                                                    --Joe"""
+    parser = optparse.OptionParser(usage)
+    parser.add_option("-d", dest="tRNA_database", help="tRNA blast database",
+                    metavar="FILE", action="store", type="string")
+    parser.add_option("-t", dest="sort_tRNA", help="sort_tRNA.fasta",
+                    metavar="OUT", action="store", type="string")
+    parser.add_option("-o", dest="output", help="output file name",
+                    metavar="OUT", action="store", type="string")
+    (options, args) = parser.parse_args()
+
+    database_file = options.tRNA_database
+    tRNA_file = options.sort_tRNA
+    out_file = options.output
+
+    RunBLAST(tRNA_file, database_file, out_file)
+
+
+if __name__ == "__main__":
+    main()

src/plastidUtilis/Filter.py

@@ -0,0 +1,44 @@
+'''
+Description: filter the unvaluable tRNA sequences of given .fa file
+Note: set "-i 64" in general case.
+'''
+import optparse
+
+usage = """python -m plastidUtilis.Filter -f <input.fasta> -i <minumum_length> -I <maximum_length> -o <output filename>
+                                                                                                                    --Joe"""
+
+parser = optparse.OptionParser(usage)
+parser.add_option("-f", dest="input_file", help="fasta",
+                  metavar="FILE", action="store", type="string")
+parser.add_option("-i", dest="min", help="minimum length",
+                  metavar="STRING", action="store", type="string")
+parser.add_option("-I", dest="max", help="maximum length",
+                  metavar="STRING", action="store", type="string")
+parser.add_option("-o", dest="output", help="output file",
+                  metavar="FILE", action="store", type="string")
+(options, args) = parser.parse_args()
+
+fa_dict = {}
+fa_dict["dump"] = []
+with open(options.input_file) as f:
+    for line in f.readlines():
+        if line.startswith(">"):
+            header = line.strip()
+            if header not in fa_dict.keys():
+                fa_dict[header] = []
+            elif header in fa_dict.keys():
+                header = "dump"
+        else:
+            fa_dict[header].append(line.strip())
+del fa_dict["dump"] 
+
+with open(options.output, "w") as out:
+    for k, v in fa_dict.items():
+        fa_dict[k] = "".join(v)
+        if len(fa_dict[k]) > int(options.min) and len(fa_dict[k]) < int(options.max):
+            out.write(k + "\n")
+            out.write(fa_dict[k] + "\n")
+out.close()
+
+
+