nanoget-1.16.1/0000755000175000017500000000000014135742676012600 5ustar nileshnileshnanoget-1.16.1/README.md0000644000175000017500000000271114135742676014060 0ustar nileshnilesh# nanoget This module provides functions to extract useful metrics from Oxford Nanopore sequencing reads and alignments. [![Twitter URL](https://img.shields.io/twitter/url/https/twitter.com/wouter_decoster.svg?style=social&label=Follow%20%40wouter_decoster)](https://twitter.com/wouter_decoster) [![install with conda](https://anaconda.org/bioconda/nanoget/badges/installer/conda.svg)](https://anaconda.org/bioconda/nanoget) [![Build Status](https://travis-ci.org/wdecoster/nanoget.svg?branch=master)](https://travis-ci.org/wdecoster/nanoget) ## FUNCTIONS Data can be presented in the following formats, using the following functions: - A sorted bam file `process_bam(bamfile, threads)` - A standard fastq file `process_fastq_plain(fastqfile, 'threads')` - A fastq file with metadata from MinKNOW or Albacore `process_fastq_rich(fastqfile)` - A sequencing_summary file generated by Albacore `process_summary(sequencing_summary.txt, 'readtype')` Fastq files can be compressed using gzip, bzip2 or bgzip. The data is returned as a pandas DataFrame with standardized headernames for convenient extraction. The functions perform logging while being called and extracting data. ## INSTALLATION ```bash pip install nanoget ``` or [![install with conda](https://anaconda.org/bioconda/nanoget/badges/installer/conda.svg)](https://anaconda.org/bioconda/nanoget) ``` conda install -c bioconda nanoget ``` Copyright: 2016-2020 Wouter De Coster nanoget-1.16.1/scripts/0000755000175000017500000000000014135742676014267 5ustar nileshnileshnanoget-1.16.1/scripts/test.py0000644000175000017500000000114314135742676015617 0ustar nileshnileshimport nanoget def run_tests(): """Test functions using testdata from the nanotest repo.""" nanoget.get_input("bam", ["nanotest/alignment.bam"]) nanoget.get_input("bam", ["nanotest/alignment.bam"], keep_supp=False) nanoget.get_input("fastq_rich", ["nanotest/reads.fastq.gz"]) nanoget.get_input("summary", ["nanotest/sequencing_summary.txt"], combine="track") nanoget.get_input("fastq_minimal", ["nanotest/reads.fastq.gz"]) nanoget.get_input("fastq", ["nanotest/reads.fastq.gz"]) nanoget.get_input("fasta", ["nanotest/reads.fa.gz"]) if __name__ == '__main__': run_tests() nanoget-1.16.1/scripts/create_feather.py0000644000175000017500000001160514135742676017605 0ustar nileshnilesh#! /usr/bin/env python # wdecoster from argparse import ArgumentParser from nanoget import get_input import os def main(): ''' Organization function -setups logging -gets inputdata -calls plotting function ''' args = get_args() sources = { "fastq": args.fastq, "bam": args.bam, "cram": args.cram, "fastq_rich": args.fastq_rich, "fastq_minimal": args.fastq_minimal, "summary": args.summary, "fasta": args.fasta, "ubam": args.ubam, } if os.path.isfile(args.output) and not args.force: print("Output file {} already exists.".format(args.output)) else: get_input( source=[n for n, s in sources.items() if s][0], files=[f for f in sources.values() if f][0], threads=args.threads, readtype=args.readtype, combine="simple", barcoded=args.barcoded, huge=args.huge, keep_supp=not(args.no_supplementary)) \ .to_feather(args.output) def get_args(): parser = ArgumentParser( description="Creates various plots for long read sequencing data.".upper(), add_help=False) general = parser.add_argument_group( title='General options') general.add_argument("-h", "--help", action="help", help="show the help and exit") general.add_argument("-t", "--threads", help="Set the allowed number of threads to be used by the script", default=4, type=int) general.add_argument("--huge", help="Input data is one very large file.", action="store_true") general.add_argument("-o", "--output", help="Specify name of feather file.", default="NanoPlot-data.feather") general.add_argument("--readtype", help="Which read type to extract information about from summary. \ Options are 1D, 2D, 1D2", default="1D", choices=['1D', '2D', '1D2']) general.add_argument("--barcoded", help="Use if you want to split the summary file by barcode", action="store_true") general.add_argument("--no_supplementary", help="Use if you want to remove supplementary alignments", action="store_true", default=False) general.add_argument("--force", help="Overwrite existing feather files", action="store_true", default=False) target = parser.add_argument_group( title="Input data sources, one of these is required.") mtarget = target.add_mutually_exclusive_group( required=True) mtarget.add_argument("--fastq", help="Data is in one or more default fastq file(s).", nargs='+', metavar="file") mtarget.add_argument("--fasta", help="Data is in one or more fasta file(s).", nargs='+', metavar="file") mtarget.add_argument("--fastq_rich", help="Data is in one or more fastq file(s) generated by albacore, \ MinKNOW or guppy with additional information \ concerning channel and time.", nargs='+', metavar="file") mtarget.add_argument("--fastq_minimal", help="Data is in one or more fastq file(s) generated by albacore, \ MinKNOW or guppy with additional information concerning channel \ and time. Is extracted swiftly without elaborate checks.", nargs='+', metavar="file") mtarget.add_argument("--summary", help="Data is in one or more summary file(s) generated by albacore \ or guppy.", nargs='+', metavar="file") mtarget.add_argument("--bam", help="Data is in one or more sorted bam file(s).", nargs='+', metavar="file") mtarget.add_argument("--ubam", help="Data is in one or more unmapped bam file(s).", nargs='+', metavar="file") mtarget.add_argument("--cram", help="Data is in one or more sorted cram file(s).", nargs='+', metavar="file") return parser.parse_args() if __name__ == '__main__': main() nanoget-1.16.1/scripts/test.sh0000644000175000017500000000012514135742676015600 0ustar nileshnileshset -ev git clone https://github.com/wdecoster/nanotest.git python scripts/test.py nanoget-1.16.1/setup.py0000644000175000017500000000267614135742676014325 0ustar nileshnilesh# Always prefer setuptools over distutils from setuptools import setup, find_packages # To use a consistent encoding from codecs import open from os import path here = path.abspath(path.dirname(__file__)) exec(open('nanoget/version.py').read()) setup( name='nanoget', version=__version__, description='Functions to extract information from Oxford Nanopore sequencing data and alignments.', long_description=open(path.join(here, "README.md")).read(), long_description_content_type="text/markdown", url='https://github.com/wdecoster/nanoget', author='Wouter De Coster', author_email='decosterwouter@gmail.com', license='GPLv3', classifiers=[ 'Development Status :: 4 - Beta', 'Intended Audience :: Science/Research', 'Topic :: Scientific/Engineering :: Bio-Informatics', 'License :: OSI Approved :: GNU General Public License v3 (GPLv3)', 'Programming Language :: Python :: 3', 'Programming Language :: Python :: 3.3', 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', ], keywords='nanopore sequencing plotting quality control', python_requires='>=3', packages=find_packages() + ['scripts'], install_requires=['pandas>=0.22.0', 'numpy', 'biopython', 'pysam>0.10.0.0'], package_dir={'nanoget': 'nanoget'}, data_files=[("", ["LICENSE"])]) nanoget-1.16.1/setup.cfg0000644000175000017500000000003514135742676014417 0ustar nileshnilesh[flake8] max-line-length=100 nanoget-1.16.1/.gitignore0000644000175000017500000000011214135742676014562 0ustar nileshnilesh.remote-sync.json README.rst dist/ nanoget.egg-info/ nanoget/__pycache__/ nanoget-1.16.1/LICENSE0000644000175000017500000010451314135742676013611 0ustar nileshnilesh GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Copyright (C) 2007 Free Software Foundation, Inc. Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The GNU General Public License is a free, copyleft license for software and other kinds of works. The licenses for most software and other practical works are designed to take away your freedom to share and change the works. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users. We, the Free Software Foundation, use the GNU General Public License for most of our software; it applies also to any other work released this way by its authors. You can apply it to your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things. To protect your rights, we need to prevent others from denying you these rights or asking you to surrender the rights. Therefore, you have certain responsibilities if you distribute copies of the software, or if you modify it: responsibilities to respect the freedom of others. For example, if you distribute copies of such a program, whether gratis or for a fee, you must pass on to the recipients the same freedoms that you received. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights. Developers that use the GNU GPL protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License giving you legal permission to copy, distribute and/or modify it. For the developers' and authors' protection, the GPL clearly explains that there is no warranty for this free software. For both users' and authors' sake, the GPL requires that modified versions be marked as changed, so that their problems will not be attributed erroneously to authors of previous versions. Some devices are designed to deny users access to install or run modified versions of the software inside them, although the manufacturer can do so. This is fundamentally incompatible with the aim of protecting users' freedom to change the software. The systematic pattern of such abuse occurs in the area of products for individuals to use, which is precisely where it is most unacceptable. Therefore, we have designed this version of the GPL to prohibit the practice for those products. If such problems arise substantially in other domains, we stand ready to extend this provision to those domains in future versions of the GPL, as needed to protect the freedom of users. Finally, every program is threatened constantly by software patents. States should not allow patents to restrict development and use of software on general-purpose computers, but in those that do, we wish to avoid the special danger that patents applied to a free program could make it effectively proprietary. To prevent this, the GPL assures that patents cannot be used to render the program non-free. The precise terms and conditions for copying, distribution and modification follow. TERMS AND CONDITIONS 0. Definitions. "This License" refers to version 3 of the GNU General Public License. "Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks. "The Program" refers to any copyrightable work licensed under this License. Each licensee is addressed as "you". "Licensees" and "recipients" may be individuals or organizations. To "modify" a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy. The resulting work is called a "modified version" of the earlier work or a work "based on" the earlier work. A "covered work" means either the unmodified Program or a work based on the Program. To "propagate" a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy. Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well. To "convey" a work means any kind of propagation that enables other parties to make or receive copies. Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying. An interactive user interface displays "Appropriate Legal Notices" to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License. If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion. 1. Source Code. The "source code" for a work means the preferred form of the work for making modifications to it. "Object code" means any non-source form of a work. A "Standard Interface" means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language. The "System Libraries" of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form. A "Major Component", in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it. The "Corresponding Source" for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities. However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work. For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those subprograms and other parts of the work. The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source. The Corresponding Source for a work in source code form is that same work. 2. Basic Permissions. All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met. This License explicitly affirms your unlimited permission to run the unmodified Program. The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work. This License acknowledges your rights of fair use or other equivalent, as provided by copyright law. You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force. You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright. Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you. Conveying under any other circumstances is permitted solely under the conditions stated below. Sublicensing is not allowed; section 10 makes it unnecessary. 3. Protecting Users' Legal Rights From Anti-Circumvention Law. No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures. When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures. 4. Conveying Verbatim Copies. You may convey verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program. You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee. 5. Conveying Modified Source Versions. You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions: a) The work must carry prominent notices stating that you modified it, and giving a relevant date. b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7. This requirement modifies the requirement in section 4 to "keep intact all notices". c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy. This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged. This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it. d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so. A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an "aggregate" if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit. Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate. 6. Conveying Non-Source Forms. You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways: a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange. b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge. c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source. This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b. d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge. You need not require recipients to copy the Corresponding Source along with the object code. If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source. Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements. e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d. A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work. A "User Product" is either (1) a "consumer product", which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling. In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage. For a particular product received by a particular user, "normally used" refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product. A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product. "Installation Information" for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source. The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made. If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information. But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM). The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed. Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network. Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying. 7. Additional Terms. "Additional permissions" are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law. If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions. When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it. (Additional permissions may be written to require their own removal in certain cases when you modify the work.) You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission. Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms: a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or d) Limiting the use for publicity purposes of names of licensors or authors of the material; or e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors. All other non-permissive additional terms are considered "further restrictions" within the meaning of section 10. If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term. If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying. If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms. Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way. 8. Termination. You may not propagate or modify a covered work except as expressly provided under this License. Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11). However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation. Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice. Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License. If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10. 9. Acceptance Not Required for Having Copies. You are not required to accept this License in order to receive or run a copy of the Program. Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance. However, nothing other than this License grants you permission to propagate or modify any covered work. These actions infringe copyright if you do not accept this License. Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so. 10. Automatic Licensing of Downstream Recipients. Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License. You are not responsible for enforcing compliance by third parties with this License. An "entity transaction" is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations. If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts. You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License. For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it. 11. Patents. A "contributor" is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based. The work thus licensed is called the contributor's "contributor version". A contributor's "essential patent claims" are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version. For purposes of this definition, "control" includes the right to grant patent sublicenses in a manner consistent with the requirements of this License. Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version. In the following three paragraphs, a "patent license" is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement). To "grant" such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party. If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent license to downstream recipients. "Knowingly relying" means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid. If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it. A patent license is "discriminatory" if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License. You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007. Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law. 12. No Surrender of Others' Freedom. If conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not convey it at all. For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program. 13. Use with the GNU Affero General Public License. Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU Affero General Public License into a single combined work, and to convey the resulting work. The terms of this License will continue to apply to the part which is the covered work, but the special requirements of the GNU Affero General Public License, section 13, concerning interaction through a network will apply to the combination as such. 14. Revised Versions of this License. The Free Software Foundation may publish revised and/or new versions of the GNU General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies that a certain numbered version of the GNU General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the GNU General Public License, you may choose any version ever published by the Free Software Foundation. If the Program specifies that a proxy can decide which future versions of the GNU General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program. Later license versions may give you additional or different permissions. However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version. 15. Disclaimer of Warranty. THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 16. Limitation of Liability. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. 17. Interpretation of Sections 15 and 16. If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program. If not, see . Also add information on how to contact you by electronic and paper mail. If the program does terminal interaction, make it output a short notice like this when it starts in an interactive mode: Copyright (C) This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, your program's commands might be different; for a GUI interface, you would use an "about box". You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU GPL, see . The GNU General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. But first, please read . nanoget-1.16.1/MANIFEST.in0000644000175000017500000000010214135742676014327 0ustar nileshnileshinclude scripts/test.sh include scripts/test.py include README.md nanoget-1.16.1/nanoget/0000755000175000017500000000000014135742676014233 5ustar nileshnileshnanoget-1.16.1/nanoget/version.py0000644000175000017500000000002714135742676016271 0ustar nileshnilesh__version__ = "1.16.1" nanoget-1.16.1/nanoget/nanoget.py0000644000175000017500000001460014135742676016241 0ustar nileshnilesh""" This module provides functions to extract useful metrics from Oxford Nanopore sequencing reads and alignments. Data can be presented in the following formats, using the following functions: - A sorted bam file process_bam(bamfile, threads) - A standard fastq file process_fastq_plain(fastqfile, 'threads') - A fastq file with metadata from MinKNOW or Albacore process_fastq_rich(fastqfile) - A sequencing_summary file generated by Albacore process_summary(sequencing_summary.txt, 'readtype') Fastq files can be compressed using gzip, bzip2 or bgzip. The data is returned as a pandas DataFrame with standardized headernames for convenient extraction. The functions perform logging while being called and extracting data. """ import sys import logging import pandas as pd from functools import partial import concurrent.futures as cfutures import nanoget.extraction_functions as ex def get_input(source, files, threads=4, readtype="1D", combine="simple", names=None, barcoded=False, huge=False, keep_supp=True): """Get input and process accordingly. Data can be: - a uncompressed, bgzip, bzip2 or gzip compressed fastq file - a uncompressed, bgzip, bzip2 or gzip compressed fasta file - a rich fastq containing additional key=value information in the description, as produced by MinKNOW and albacore with the same compression options as above - a sorted bam file - a sorted cram file - a (compressed) sequencing_summary.txt file generated by albacore/guppy If data is huge=True then no parallelization (using concurrent.futures) is used, as pickling these dataframes leads to crashes Handle is passed to the proper functions to get DataFrame with metrics Multiple files of the same type can be used to extract info from, which is done in parallel Arguments: - source: defines the input data type and the function that needs to be called - files: is a list of one or more files to operate on, from the type of - threads: is the amount of workers which can be used - readtype: (only relevant for summary input) and specifies which columns have to be extracted - combine: is either 'simple' or 'track', with the difference that with 'track' an additional field is created with the name of the dataset - names: if combine="track", the names to be used for the datasets. Needs to have same length as files, or None """ proc_functions = { 'fastq': ex.process_fastq_plain, 'fasta': ex.process_fasta, 'bam': ex.process_bam, 'summary': ex.process_summary, 'fastq_rich': ex.process_fastq_rich, 'fastq_minimal': ex.process_fastq_minimal, 'cram': ex.process_cram, 'ubam': ex.process_ubam, } if source not in proc_functions.keys(): logging.error("nanoget: Unsupported data source: {}".format(source)) sys.exit("Unsupported data source: {}".format(source)) filethreads = min(len(files), threads) threadsleft = threads - filethreads or 1 if huge: logging.info("nanoget: Running with a single huge input file.") if not len(files) == 1: logging.error("nanoget: Using multiple huge input files is currently not supported.") sys.exit("Using multiple huge input files is currently not supported.\n" "Please let me know on GitHub if that's of interest for your application.\n") datadf = proc_functions[source](files[0], threads=threadsleft, readtype=readtype, barcoded=barcoded, keep_supp=keep_supp, huge=True) else: with cfutures.ProcessPoolExecutor(max_workers=filethreads) as executor: extraction_function = partial(proc_functions[source], threads=threadsleft, readtype=readtype, barcoded=barcoded, keep_supp=keep_supp, huge=False) datadf = combine_dfs( dfs=[out for out in executor.map(extraction_function, files)], names=names or files, method=combine) if "readIDs" in datadf.columns and pd.isna(datadf["readIDs"]).any(): datadf.drop("readIDs", axis='columns', inplace=True) datadf = calculate_start_time(datadf) logging.info("Nanoget: Gathered all metrics of {} reads".format(len(datadf))) if len(datadf) == 0: logging.critical("Nanoget: no reads retrieved.") sys.exit("Fatal: No reads found in input.") else: return datadf def combine_dfs(dfs, names=None, method='simple'): """Combine dataframes. Combination is either done simple by just concatenating the DataFrames or performs tracking by adding the name of the dataset as a column.""" if method == "track": return pd.concat([df.assign(dataset=n) for df, n in zip(dfs, names)], ignore_index=True) elif method == "simple": return pd.concat(dfs, ignore_index=True) def calculate_start_time(df): """Calculate the start_time per read. Time data is either a "time" (in seconds, derived from summary files) or a "timestamp" (in UTC, derived from fastq_rich format) and has to be converted appropriately in a datetime format time_arr For both the time_zero is the minimal value of the time_arr, which is then used to subtract from all other times In the case of method=track (and dataset is a column in the df) then this subtraction is done per dataset """ if "time" in df.columns: df["time_arr"] = pd.Series(df["time"], dtype='datetime64[s]') elif "timestamp" in df.columns: df["time_arr"] = pd.Series(df["timestamp"], dtype="datetime64[ns]") else: return df if "dataset" in df.columns: for dset in df["dataset"].unique(): time_zero = df.loc[df["dataset"] == dset, "time_arr"].min() df.loc[df["dataset"] == dset, "start_time"] = \ df.loc[df["dataset"] == dset, "time_arr"] - time_zero else: df["start_time"] = df["time_arr"] - df["time_arr"].min() return df.drop(["time", "timestamp", "time_arr"], axis=1, errors="ignore") nanoget-1.16.1/nanoget/extraction_functions.py0000644000175000017500000004413714135742676021066 0ustar nileshnileshimport logging from functools import reduce import nanoget.utils as ut import pandas as pd import sys import pysam import re from Bio import SeqIO import concurrent.futures as cfutures from itertools import repeat def process_summary(summaryfile, **kwargs): """Extracting information from an albacore summary file. Only reads which have a >0 length are returned. The fields below may or may not exist, depending on the type of sequencing performed. Fields 1-14 are for 1D sequencing. Fields 1-23 for 2D sequencing. Fields 24-27, 2-5, 22-23 for 1D^2 (1D2) sequencing Fields 28-38 for barcoded workflows 1 filename 2 read_id 3 run_id 4 channel 5 start_time 6 duration 7 num_events 8 template_start 9 num_events_template 10 template_duration 11 num_called_template 12 sequence_length_template 13 mean_qscore_template 14 strand_score_template 15 complement_start 16 num_events_complement 17 complement_duration 18 num_called_complement 19 sequence_length_complement 20 mean_qscore_complement 21 strand_score_complement 22 sequence_length_2d 23 mean_qscore_2d 24 filename1 25 filename2 26 read_id1 27 read_id2 28 barcode_arrangement 29 barcode_score 30 barcode_full_arrangement 31 front_score 32 rear_score 33 front_begin_index 34 front_foundseq_length 35 rear_end_index 36 rear_foundseq_length 37 kit 38 variant """ logging.info("Nanoget: Collecting metrics from summary file {} for {} sequencing".format( summaryfile, kwargs["readtype"])) ut.check_existance(summaryfile) if kwargs["readtype"] == "1D": cols = ["channel", "start_time", "duration", "sequence_length_template", "mean_qscore_template"] elif kwargs["readtype"] in ["2D", "1D2"]: cols = ["channel", "start_time", "duration", "sequence_length_2d", "mean_qscore_2d"] if kwargs["barcoded"]: cols.append("barcode_arrangement") logging.info("Nanoget: Extracting metrics per barcode.") try: datadf = pd.read_csv( filepath_or_buffer=summaryfile, sep="\t", usecols=cols, ) except ValueError: logging.error("Nanoget: did not find expected columns in summary file {}:\n {}".format( summaryfile, ', '.join(cols))) sys.exit("ERROR: expected columns in summary file {} not found:\n {}".format( summaryfile, ', '.join(cols))) if kwargs["barcoded"]: datadf.columns = ["channelIDs", "time", "duration", "lengths", "quals", "barcode"] else: datadf.columns = ["channelIDs", "time", "duration", "lengths", "quals"] logging.info("Nanoget: Finished collecting statistics from summary file {}".format(summaryfile)) return ut.reduce_memory_usage(datadf.loc[datadf["lengths"] != 0].copy()) def check_bam(bam, samtype="bam"): """Check if bam file is valid. Bam file should: - exists - has an index (create if necessary) - is sorted by coordinate - has at least one mapped read """ ut.check_existance(bam) samfile = pysam.AlignmentFile(bam, "rb") if not samfile.has_index(): pysam.index(bam) samfile = pysam.AlignmentFile(bam, "rb") # Need to reload the samfile after creating index logging.info("Nanoget: No index for bam file could be found, created index.") if not samfile.header['HD']['SO'] == 'coordinate': logging.error("Nanoget: Bam file {} not sorted by coordinate!.".format(bam)) sys.exit("Please use a bam file sorted by coordinate.") if samtype == "bam": logging.info("Nanoget: Bam file {} contains {} mapped and {} unmapped reads.".format( bam, samfile.mapped, samfile.unmapped)) if samfile.mapped == 0: logging.error("Nanoget: Bam file {} does not contain aligned reads.".format(bam)) sys.exit("FATAL: not a single read was mapped in bam file {}".format(bam)) return samfile def process_ubam(bam, **kwargs): """Extracting metrics from unaligned bam format Extracting lengths """ logging.info("Nanoget: Starting to collect statistics from ubam file {}.".format(bam)) samfile = pysam.AlignmentFile(bam, "rb", check_sq=False) if not samfile.has_index(): pysam.index(bam) # Need to reload the samfile after creating index samfile = pysam.AlignmentFile(bam, "rb", check_sq=False) logging.info("Nanoget: No index for bam file could be found, created index.") datadf = pd.DataFrame( data=[(read.query_name, ut.ave_qual(read.query_qualities), read.query_length) for read in samfile.fetch(until_eof=True)], columns=["readIDs", "quals", "lengths"]) \ .dropna(axis='columns', how='all') \ .dropna(axis='index', how='any') logging.info("Nanoget: ubam {} contains {} reads.".format( bam, datadf["lengths"].size)) return ut.reduce_memory_usage(datadf) def process_bam(bam, **kwargs): """Combines metrics from bam after extraction. Processing function: calls pool of worker functions to extract from a bam file the following metrics: -lengths -aligned lengths -qualities -aligned qualities -mapping qualities -edit distances to the reference genome scaled by read length Returned in a pandas DataFrame """ logging.info("Nanoget: Starting to collect statistics from bam file {}.".format(bam)) samfile = check_bam(bam) chromosomes = samfile.references if len(chromosomes) > 100 or kwargs["huge"]: logging.info("Nanoget: lots of contigs (>100) or --huge, not running in separate processes") datadf = pd.DataFrame( data=extract_from_bam(bam, None, kwargs["keep_supp"]), columns=["readIDs", "quals", "aligned_quals", "lengths", "aligned_lengths", "mapQ", "percentIdentity"]) \ .dropna(axis='columns', how='all') \ .dropna(axis='index', how='any') else: unit = chromosomes with cfutures.ProcessPoolExecutor(max_workers=kwargs["threads"]) as executor: datadf = pd.DataFrame( data=[res for sublist in executor.map(extract_from_bam, repeat(bam), unit, repeat(kwargs["keep_supp"])) for res in sublist], columns=["readIDs", "quals", "aligned_quals", "lengths", "aligned_lengths", "mapQ", "percentIdentity"]) \ .dropna(axis='columns', how='all') \ .dropna(axis='index', how='any') logging.info(f"Nanoget: bam {bam} contains {datadf['lengths'].size} primary alignments.") return ut.reduce_memory_usage(datadf) def process_cram(cram, **kwargs): """Combines metrics from cram after extraction. Processing function: calls pool of worker functions to extract from a cram file the following metrics: -lengths -aligned lengths -qualities -aligned qualities -mapping qualities -edit distances to the reference genome scaled by read length Returned in a pandas DataFrame """ logging.info("Nanoget: Starting to collect statistics from cram file {}.".format(cram)) samfile = check_bam(cram, samtype="cram") chromosomes = samfile.references if len(chromosomes) > 100: unit = [None] logging.info("Nanoget: lots of contigs (>100), not running in separate processes") else: unit = chromosomes with cfutures.ProcessPoolExecutor(max_workers=kwargs["threads"]) as executor: datadf = pd.DataFrame( data=[res for sublist in executor.map(extract_from_bam, repeat(cram), unit, repeat(kwargs["keep_supp"])) for res in sublist], columns=["readIDs", "quals", "aligned_quals", "lengths", "aligned_lengths", "mapQ", "percentIdentity"]) \ .dropna(axis='columns', how='all') \ .dropna(axis='index', how='any') logging.info(f"Nanoget: cram {cram} contains {datadf['lengths'].size} primary alignments.") return ut.reduce_memory_usage(datadf) def extract_from_bam(bam, chromosome, keep_supplementary=True): """Extracts metrics from bam. Worker function per chromosome loop over a bam file and create list with tuples containing metrics: -qualities -aligned qualities -lengths -aligned lengths -mapping qualities -edit distances to the reference genome scaled by read length """ samfile = pysam.AlignmentFile(bam, "rb") if keep_supplementary: return [ (read.query_name, ut.ave_qual(read.query_qualities), ut.ave_qual(read.query_alignment_qualities), read.query_length, read.query_alignment_length, read.mapping_quality, get_pID(read)) for read in samfile.fetch(reference=chromosome, multiple_iterators=True) if not read.is_secondary and not read.is_unmapped] else: return [ (read.query_name, ut.ave_qual(read.query_qualities), ut.ave_qual(read.query_alignment_qualities), read.query_length, read.query_alignment_length, read.mapping_quality, get_pID(read)) for read in samfile.fetch(reference=chromosome, multiple_iterators=True) if not read.is_secondary and not read.is_unmapped and not read.is_supplementary] def get_pID(read): """Return the percent identity of a read. based on the NM tag if present, if not calculate from MD tag and CIGAR string read.query_alignment_length can be zero in the case of ultra long reads aligned with minimap2 -L """ match = reduce(lambda x, y: x + y[1] if y[0] in (0, 7, 8) else x, read.cigartuples, 0) ins = reduce(lambda x, y: x + y[1] if y[0] == 1 else x, read.cigartuples, 0) delt = reduce(lambda x, y: x + y[1] if y[0] == 2 else x, read.cigartuples, 0) alignment_length = match + ins + delt try: return (1 - read.get_tag("NM") / alignment_length) * 100 except KeyError: try: return 100 * (1 - (parse_MD(read.get_tag("MD")) + parse_CIGAR(read.cigartuples)) / alignment_length) except KeyError: return None except ZeroDivisionError: return None def parse_MD(MDlist): """Parse MD string to get number of mismatches and deletions.""" return sum([len(item) for item in re.split('[0-9^]', MDlist)]) def parse_CIGAR(cigartuples): """Count the insertions in the read using the CIGAR string.""" return sum([item[1] for item in cigartuples if item[0] == 1]) def handle_compressed_input(inputfq, file_type="fastq"): """Return handles from compressed files according to extension. Check for which fastq input is presented and open a handle accordingly Can read from compressed files (gz, bz2, bgz) or uncompressed Relies on file extensions to recognize compression """ ut.check_existance(inputfq) if inputfq.endswith(('.gz', 'bgz')): import gzip logging.info("Nanoget: Decompressing gzipped {} {}".format(file_type, inputfq)) return gzip.open(inputfq, 'rt') elif inputfq.endswith('.bz2'): import bz2 logging.info("Nanoget: Decompressing bz2 compressed {} {}".format(file_type, inputfq)) return bz2.open(inputfq, 'rt') elif inputfq.endswith(('.fastq', '.fq', 'fasta', '.fa', '.fas')): return open(inputfq, 'r') else: logging.error("INPUT ERROR: Unrecognized file extension {}".format(inputfq)) sys.exit('INPUT ERROR:\nUnrecognized file extension in {}\n' 'Supported are gz, bz2, bgz, fastq, fq, fasta, fa and fas'.format(inputfq)) def process_fasta(fasta, **kwargs): """Combine metrics extracted from a fasta file.""" logging.info("Nanoget: Starting to collect statistics from a fasta file.") inputfasta = handle_compressed_input(fasta, file_type="fasta") return ut.reduce_memory_usage(pd.DataFrame( data=[len(rec) for rec in SeqIO.parse(inputfasta, "fasta")], columns=["lengths"] ).dropna()) def process_fastq_plain(fastq, **kwargs): """Combine metrics extracted from a fastq file.""" logging.info("Nanoget: Starting to collect statistics from plain fastq file.") inputfastq = handle_compressed_input(fastq) return ut.reduce_memory_usage(pd.DataFrame( data=[res for res in extract_from_fastq(inputfastq) if res], columns=["quals", "lengths"] ).dropna()) def extract_from_fastq(fq): """Extract metrics from a fastq file. Return average quality and read length """ for rec in SeqIO.parse(fq, "fastq"): yield ut.ave_qual(rec.letter_annotations["phred_quality"]), len(rec) def stream_fastq_full(fastq, threads): """Generator for returning metrics extracted from fastq. Extract from a fastq file: -readname -average and median quality -read_lenght """ logging.info("Nanoget: Starting to collect full metrics from plain fastq file.") inputfastq = handle_compressed_input(fastq) with cfutures.ProcessPoolExecutor(max_workers=threads) as executor: for results in executor.map(extract_all_from_fastq, SeqIO.parse(inputfastq, "fastq")): yield results logging.info("Nanoget: Finished collecting statistics from plain fastq file.") def extract_all_from_fastq(rec): """Extract metrics from a fastq file. Return identifier, read length, average quality and median quality """ return (rec.id, len(rec), ut.ave_qual(rec.letter_annotations["phred_quality"]), None) def info_to_dict(info): """Get the key-value pairs from the albacore/minknow fastq description and return dict""" return {field.split('=')[0]: field.split('=')[1] for field in info.split(' ')[1:]} def process_fastq_rich(fastq, **kwargs): """Extract metrics from a richer fastq file. Extract information from fastq files generated by albacore or MinKNOW, containing richer information in the header (key-value pairs) read= [72] ch= [159] start_time= [2016-07-15T14:23:22Z] # UTC ISO 8601 ISO 3339 timestamp Z indicates UTC time, T is the delimiter between date expression and time expression dateutil.parser.parse("2016-07-15T14:23:22Z") imported as dparse -> datetime.datetime(2016, 7, 15, 14, 23, 22, tzinfo=tzutc()) """ logging.info("Nanoget: Starting to collect statistics from rich fastq file.") inputfastq = handle_compressed_input(fastq) res = [] for record in SeqIO.parse(inputfastq, "fastq"): try: read_info = info_to_dict(record.description) res.append( (ut.ave_qual(record.letter_annotations["phred_quality"]), len(record), read_info["ch"], read_info["start_time"], read_info["runid"])) except KeyError: logging.error("Nanoget: keyerror when processing record {}".format(record.description)) sys.exit("Unexpected fastq identifier:\n{}\n\n \ missing one or more of expected fields 'ch', 'start_time' or 'runid'".format( record.description)) df = pd.DataFrame( data=res, columns=["quals", "lengths", "channelIDs", "timestamp", "runIDs"]).dropna() df["channelIDs"] = df["channelIDs"].astype("int64") return ut.reduce_memory_usage(df) def readfq(fp): """Generator function adapted from https://github.com/lh3/readfq.""" last = None # this is a buffer keeping the last unprocessed line while True: # mimic closure; is it a bad idea? if not last: # the first record or a record following a fastq for l in fp: # search for the start of the next record if l[0] in '>@': # fasta/q header line last = l[:-1] # save this line break if not last: break name, seqs, last = last[1:].partition(" ")[0], [], None for l in fp: # read the sequence if l[0] in '@+>': last = l[:-1] break seqs.append(l[:-1]) if not last or last[0] != '+': # this is a fasta record yield name, ''.join(seqs), None # yield a fasta record if not last: break else: # this is a fastq record seq, leng, seqs = ''.join(seqs), 0, [] for l in fp: # read the quality seqs.append(l[:-1]) leng += len(l) - 1 if leng >= len(seq): # have read enough quality last = None yield name, seq, ''.join(seqs) # yield a fastq record break if last: # reach EOF before reading enough quality yield name, seq, None # yield a fasta record instead break def fq_minimal(fq): """Minimal fastq metrics extractor. Quickly parse a fasta/fastq file - but makes expectations on the file format There will be dragons if unexpected format is used Expects a fastq_rich format, but extracts only timestamp and length """ try: while True: time = next(fq)[1:].split(" ")[4][11:-1] length = len(next(fq)) next(fq) next(fq) yield time, length except StopIteration: yield None def process_fastq_minimal(fastq, **kwargs): """Swiftly extract minimal features (length and timestamp) from a rich fastq file""" infastq = handle_compressed_input(fastq) try: df = pd.DataFrame( data=[rec for rec in fq_minimal(infastq) if rec], columns=["timestamp", "lengths"] ) except IndexError: logging.error("Fatal: Incorrect file structure for fastq_minimal") sys.exit("Error: file does not match expected structure for fastq_minimal") return ut.reduce_memory_usage(df) nanoget-1.16.1/nanoget/__init__.py0000644000175000017500000000007014135742676016341 0ustar nileshnileshfrom .nanoget import * from .version import __version__ nanoget-1.16.1/nanoget/utils.py0000644000175000017500000000374714135742676015760 0ustar nileshnileshimport sys import logging import pandas as pd from os import path as opath from math import log def reduce_memory_usage(df): """reduce memory usage of the dataframe - convert runIDs to categorical - downcast ints and floats """ usage_pre = df.memory_usage(deep=True).sum() if "runIDs" in df: df.loc[:, "runIDs"] = df.loc[:, "runIDs"].astype("category") df_int = df.select_dtypes(include=['int']) df_float = df.select_dtypes(include=['float']) df.loc[:, df_int.columns] = df_int.apply(pd.to_numeric, downcast='integer') df.loc[:, df_float.columns] = df_float.apply(pd.to_numeric, downcast='float') usage_post = df.memory_usage(deep=True).sum() logging.info("Reduced DataFrame memory usage from {}Mb to {}Mb".format( usage_pre / 1024**2, usage_post / 1024**2)) if usage_post > 4e9 and "readIDs" in df: logging.info("DataFrame of features is too big, dropping read identifiers.") return df.drop(["readIDs"], axis=1, errors="ignore") else: return df def check_existance(f): """Check if the file supplied as input exists.""" if not opath.isfile(f): logging.error("Nanoget: File provided doesn't exist or the path is incorrect: {}".format(f)) sys.exit("File provided doesn't exist or the path is incorrect: {}".format(f)) def errs_tab(n): """Generate list of error rates for qualities less than equal than n.""" return [10**(q / -10) for q in range(n+1)] def ave_qual(quals, qround=False, tab=errs_tab(128)): """Calculate average basecall quality of a read. Receive the integer quality scores of a read and return the average quality for that read First convert Phred scores to probabilities, calculate average error probability convert average back to Phred scale """ if quals: mq = -10 * log(sum([tab[q] for q in quals]) / len(quals), 10) if qround: return round(mq) else: return mq else: return None