diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | python-bioinfo-tools.spec | 453 | ||||
| -rw-r--r-- | sources | 1 |
3 files changed, 455 insertions, 0 deletions
@@ -0,0 +1 @@ +/bioinfo_tools-0.3.1.tar.gz diff --git a/python-bioinfo-tools.spec b/python-bioinfo-tools.spec new file mode 100644 index 0000000..a816d30 --- /dev/null +++ b/python-bioinfo-tools.spec @@ -0,0 +1,453 @@ +%global _empty_manifest_terminate_build 0 +Name: python-bioinfo_tools +Version: 0.3.1 +Release: 1 +Summary: Python library that parses GFF, Fasta files into python classes +License: BSD +URL: https://github.com/sebriois/bioinfo_tools +Source0: https://mirrors.aliyun.com/pypi/web/packages/0b/79/69b6fa350d0f8074c64a53642ddcf6e8453f1c1ed9d06f636bd70efb5686/bioinfo_tools-0.3.1.tar.gz +BuildArch: noarch + + +%description +# bioinfo_tools 0.3.1 + +## Installation + +```bash +pip install bioinfo_tools +``` + +## Parsers + +*HEADS UP!* These parsers are still under development and usage is not consistent from one parser to another. + +### Fasta parser + +```python +from bioinfo_tools.parsers.fasta import FastaParser + +fasta_parser = FastaParser() + +# by default, sequence IDs are separated by the firstly found '|' or ':' +for seqid, sequence in fasta_parser.read("/path/to/file.fasta"): + print(seqid, sequence) + +# you may specify a specific separator for your sequence ID (e.g white space): +for seqid, sequence in fasta_parser.read("/path/to/file.fasta", id_separator=" "): + print(seqid, sequence) +``` + +### GFF parser + +```python +from bioinfo_tools.parsers.gff import Gff3 + +gff_parser = Gff3() +with open("/path/to/file.gff", "r") as fh: + for gene in gff_parser.read(fh): + print(gene) + +import gzip +with gzip.open("/path/to/file.gz", "rb") as fh: + for gene in gff_parser.read(fh): + print(gene) +``` + +### OBO parser + + +```python +from bioinfo_tools.parsers.obo import OboParser + +obo_parser = OboParser() +with open("/path/to/file.obo") as fh: + go_terms = obo_parser.read(fh) + +for go_term in go_terms.values(): + print(go_term) + + # you may also get the GO term parents via the parser + parents = obo_parser.get_parents(go_term) +``` + +## Usage Examples + +### Extract all introns sequences by parsing GFF and fasta files + +In this example, we focus on a genome assembly. We will first load a GFF file containing gene annotations for this +assembly, then load a fastA file containing the nucleic sequences of each chromosome in the genome. +We will then collect all transcript introns and extract their nucleic sequences. + +**__DISCLAIMER__**: for this example to work, your GFF file must expose at least the following feature types in column #3: + - `gene` + - one of `transcript|mRNA|RNA` (or lowercased version) + + +```python +from bioinfo_tools.genomic_features.chromosome import Chromosome +from bioinfo_tools.parsers.gff import Gff3 +from bioinfo_tools.parsers.fasta import FastaParser + +chromosomes = dict() # {<chromosome_id>: <bioinfo_tools.genomic_features.Chromosome>} + +# start with parsing a GFF file +gff_parser = Gff3() +with open("/path/to/gene_models.gff", "r") as fh: + for gene in gff_parser.read(fh): + chromosome = gene['seqid'] + + if chromosome not in chromosomes: + chromosomes[chromosome] = Chromosome(chromosome) # init a new Chromosome object + + chromosomes[chromosome].add_gene(gene) # add the current gene to our Chromosome object + +# load our chromosome sequences in memory +fasta_parser = FastaParser() +for chromosome, nucleic_sequence in fasta_parser.read("/path/to/genome_chromosomes.fasta"): + if chromosome not in chromosomes: + chromosomes[chromosome] = Chromosome(chromosome) + # attach parsed chromosome sequence to our Chromosome object + chromosomes[chromosome].attach_nucleic_sequence(nucleic_sequence) + +# now, collect introns and extact their nucleic sequence +introns_sequences = dict() # {<intron_id>: <intron_sequence>} +for chromosome in chromosomes.values(): + for gene in chromosome.genes: + for transcript in gene.transcripts: + for idx, intron in enumerate(transcript.introns): + intron_id = "%s_intron_%s" % (transcript.transcript_id, idx) + intron_seq = intron.extract(chromosome.nucleic_sequence) # that we attached above + introns_sequences[intron_id] = intron_seq + +# from here, you can do what you want with the intron sequences (eg. write them to a fasta file, etc) +# ... +``` + +__Note:__ when at the transcript level, you can grab its feature types as described in your GFF file by doing so: +```python +for feature in transcript._get_features("exon"): + print(feature) # I'm an exon +``` +For convenience and clarity, following properties are available on transcript objects: +```python +print(transcript.introns) # will call transcript._get_features('intron') behind the scenes +print(transcript.exons) # will call transcript._get_features('exon') behind the scenes +print(transcript.cds) # will call transcript._get_features('cds') behind the scenes +print(transcript.polypeptide) # will call transcript._get_features('polypeptide') behind the scenes +print(transcript.five_prime_utr) # will call transcript._get_features('five_prime_utr') behind the scenes +print(transcript.three_prime_utr) # will call transcript._get_features('three_prime_utr') behind the scenes +``` + +%package -n python3-bioinfo_tools +Summary: Python library that parses GFF, Fasta files into python classes +Provides: python-bioinfo_tools +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-bioinfo_tools +# bioinfo_tools 0.3.1 + +## Installation + +```bash +pip install bioinfo_tools +``` + +## Parsers + +*HEADS UP!* These parsers are still under development and usage is not consistent from one parser to another. + +### Fasta parser + +```python +from bioinfo_tools.parsers.fasta import FastaParser + +fasta_parser = FastaParser() + +# by default, sequence IDs are separated by the firstly found '|' or ':' +for seqid, sequence in fasta_parser.read("/path/to/file.fasta"): + print(seqid, sequence) + +# you may specify a specific separator for your sequence ID (e.g white space): +for seqid, sequence in fasta_parser.read("/path/to/file.fasta", id_separator=" "): + print(seqid, sequence) +``` + +### GFF parser + +```python +from bioinfo_tools.parsers.gff import Gff3 + +gff_parser = Gff3() +with open("/path/to/file.gff", "r") as fh: + for gene in gff_parser.read(fh): + print(gene) + +import gzip +with gzip.open("/path/to/file.gz", "rb") as fh: + for gene in gff_parser.read(fh): + print(gene) +``` + +### OBO parser + + +```python +from bioinfo_tools.parsers.obo import OboParser + +obo_parser = OboParser() +with open("/path/to/file.obo") as fh: + go_terms = obo_parser.read(fh) + +for go_term in go_terms.values(): + print(go_term) + + # you may also get the GO term parents via the parser + parents = obo_parser.get_parents(go_term) +``` + +## Usage Examples + +### Extract all introns sequences by parsing GFF and fasta files + +In this example, we focus on a genome assembly. We will first load a GFF file containing gene annotations for this +assembly, then load a fastA file containing the nucleic sequences of each chromosome in the genome. +We will then collect all transcript introns and extract their nucleic sequences. + +**__DISCLAIMER__**: for this example to work, your GFF file must expose at least the following feature types in column #3: + - `gene` + - one of `transcript|mRNA|RNA` (or lowercased version) + + +```python +from bioinfo_tools.genomic_features.chromosome import Chromosome +from bioinfo_tools.parsers.gff import Gff3 +from bioinfo_tools.parsers.fasta import FastaParser + +chromosomes = dict() # {<chromosome_id>: <bioinfo_tools.genomic_features.Chromosome>} + +# start with parsing a GFF file +gff_parser = Gff3() +with open("/path/to/gene_models.gff", "r") as fh: + for gene in gff_parser.read(fh): + chromosome = gene['seqid'] + + if chromosome not in chromosomes: + chromosomes[chromosome] = Chromosome(chromosome) # init a new Chromosome object + + chromosomes[chromosome].add_gene(gene) # add the current gene to our Chromosome object + +# load our chromosome sequences in memory +fasta_parser = FastaParser() +for chromosome, nucleic_sequence in fasta_parser.read("/path/to/genome_chromosomes.fasta"): + if chromosome not in chromosomes: + chromosomes[chromosome] = Chromosome(chromosome) + # attach parsed chromosome sequence to our Chromosome object + chromosomes[chromosome].attach_nucleic_sequence(nucleic_sequence) + +# now, collect introns and extact their nucleic sequence +introns_sequences = dict() # {<intron_id>: <intron_sequence>} +for chromosome in chromosomes.values(): + for gene in chromosome.genes: + for transcript in gene.transcripts: + for idx, intron in enumerate(transcript.introns): + intron_id = "%s_intron_%s" % (transcript.transcript_id, idx) + intron_seq = intron.extract(chromosome.nucleic_sequence) # that we attached above + introns_sequences[intron_id] = intron_seq + +# from here, you can do what you want with the intron sequences (eg. write them to a fasta file, etc) +# ... +``` + +__Note:__ when at the transcript level, you can grab its feature types as described in your GFF file by doing so: +```python +for feature in transcript._get_features("exon"): + print(feature) # I'm an exon +``` +For convenience and clarity, following properties are available on transcript objects: +```python +print(transcript.introns) # will call transcript._get_features('intron') behind the scenes +print(transcript.exons) # will call transcript._get_features('exon') behind the scenes +print(transcript.cds) # will call transcript._get_features('cds') behind the scenes +print(transcript.polypeptide) # will call transcript._get_features('polypeptide') behind the scenes +print(transcript.five_prime_utr) # will call transcript._get_features('five_prime_utr') behind the scenes +print(transcript.three_prime_utr) # will call transcript._get_features('three_prime_utr') behind the scenes +``` + +%package help +Summary: Development documents and examples for bioinfo_tools +Provides: python3-bioinfo_tools-doc +%description help +# bioinfo_tools 0.3.1 + +## Installation + +```bash +pip install bioinfo_tools +``` + +## Parsers + +*HEADS UP!* These parsers are still under development and usage is not consistent from one parser to another. + +### Fasta parser + +```python +from bioinfo_tools.parsers.fasta import FastaParser + +fasta_parser = FastaParser() + +# by default, sequence IDs are separated by the firstly found '|' or ':' +for seqid, sequence in fasta_parser.read("/path/to/file.fasta"): + print(seqid, sequence) + +# you may specify a specific separator for your sequence ID (e.g white space): +for seqid, sequence in fasta_parser.read("/path/to/file.fasta", id_separator=" "): + print(seqid, sequence) +``` + +### GFF parser + +```python +from bioinfo_tools.parsers.gff import Gff3 + +gff_parser = Gff3() +with open("/path/to/file.gff", "r") as fh: + for gene in gff_parser.read(fh): + print(gene) + +import gzip +with gzip.open("/path/to/file.gz", "rb") as fh: + for gene in gff_parser.read(fh): + print(gene) +``` + +### OBO parser + + +```python +from bioinfo_tools.parsers.obo import OboParser + +obo_parser = OboParser() +with open("/path/to/file.obo") as fh: + go_terms = obo_parser.read(fh) + +for go_term in go_terms.values(): + print(go_term) + + # you may also get the GO term parents via the parser + parents = obo_parser.get_parents(go_term) +``` + +## Usage Examples + +### Extract all introns sequences by parsing GFF and fasta files + +In this example, we focus on a genome assembly. We will first load a GFF file containing gene annotations for this +assembly, then load a fastA file containing the nucleic sequences of each chromosome in the genome. +We will then collect all transcript introns and extract their nucleic sequences. + +**__DISCLAIMER__**: for this example to work, your GFF file must expose at least the following feature types in column #3: + - `gene` + - one of `transcript|mRNA|RNA` (or lowercased version) + + +```python +from bioinfo_tools.genomic_features.chromosome import Chromosome +from bioinfo_tools.parsers.gff import Gff3 +from bioinfo_tools.parsers.fasta import FastaParser + +chromosomes = dict() # {<chromosome_id>: <bioinfo_tools.genomic_features.Chromosome>} + +# start with parsing a GFF file +gff_parser = Gff3() +with open("/path/to/gene_models.gff", "r") as fh: + for gene in gff_parser.read(fh): + chromosome = gene['seqid'] + + if chromosome not in chromosomes: + chromosomes[chromosome] = Chromosome(chromosome) # init a new Chromosome object + + chromosomes[chromosome].add_gene(gene) # add the current gene to our Chromosome object + +# load our chromosome sequences in memory +fasta_parser = FastaParser() +for chromosome, nucleic_sequence in fasta_parser.read("/path/to/genome_chromosomes.fasta"): + if chromosome not in chromosomes: + chromosomes[chromosome] = Chromosome(chromosome) + # attach parsed chromosome sequence to our Chromosome object + chromosomes[chromosome].attach_nucleic_sequence(nucleic_sequence) + +# now, collect introns and extact their nucleic sequence +introns_sequences = dict() # {<intron_id>: <intron_sequence>} +for chromosome in chromosomes.values(): + for gene in chromosome.genes: + for transcript in gene.transcripts: + for idx, intron in enumerate(transcript.introns): + intron_id = "%s_intron_%s" % (transcript.transcript_id, idx) + intron_seq = intron.extract(chromosome.nucleic_sequence) # that we attached above + introns_sequences[intron_id] = intron_seq + +# from here, you can do what you want with the intron sequences (eg. write them to a fasta file, etc) +# ... +``` + +__Note:__ when at the transcript level, you can grab its feature types as described in your GFF file by doing so: +```python +for feature in transcript._get_features("exon"): + print(feature) # I'm an exon +``` +For convenience and clarity, following properties are available on transcript objects: +```python +print(transcript.introns) # will call transcript._get_features('intron') behind the scenes +print(transcript.exons) # will call transcript._get_features('exon') behind the scenes +print(transcript.cds) # will call transcript._get_features('cds') behind the scenes +print(transcript.polypeptide) # will call transcript._get_features('polypeptide') behind the scenes +print(transcript.five_prime_utr) # will call transcript._get_features('five_prime_utr') behind the scenes +print(transcript.three_prime_utr) # will call transcript._get_features('three_prime_utr') behind the scenes +``` + +%prep +%autosetup -n bioinfo_tools-0.3.1 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "\"/%h/%f\"\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "\"/%h/%f\"\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "\"/%h/%f\"\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "\"/%h/%f\"\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "\"/%h/%f.gz\"\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-bioinfo_tools -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Tue Jun 20 2023 Python_Bot <Python_Bot@openeuler.org> - 0.3.1-1 +- Package Spec generated @@ -0,0 +1 @@ +79029c907c72764db0974acd8d9cf02a bioinfo_tools-0.3.1.tar.gz |