up bin

src/bin/LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ 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.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    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 <http://www.gnu.org/licenses/>.
+
+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:
+
+    <program>  Copyright (C) <year>  <name of author>
+    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
+<http://www.gnu.org/licenses/>.
+
+  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
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.

src/bin/PROBE.py

@@ -0,0 +1,62 @@
+import yaml
+import pandas as pd
+import tqdm
+import semantic_similarity_infer as ssi
+import target_family_classifier as tfc
+import function_predictor as fp
+import binding_affinity_estimator as bae
+
+print("\n\nPROBE (Protein RepresentatiOn Benchmark) run is started...\n\n")
+
+with open('probe_config.yaml') as f:
+	args = yaml.load(f, Loader=yaml.FullLoader)
+
+if args["benchmark"] not in ["similarity","family","function","affinity","all"]:
+        parser.error('At least one benchmark type should be selected')
+
+print(args)
+
+def load_representation(multi_col_representation_vector_file_path):
+    multi_col_representation_vector = pd.read_csv(multi_col_representation_vector_file_path)
+    vals = multi_col_representation_vector.iloc[:,1:(len(multi_col_representation_vector.columns))]
+    original_values_as_df = pd.DataFrame({'Entry': pd.Series([], dtype='str'),'Vector': pd.Series([], dtype='object')})
+    for index, row in tqdm.tqdm(vals.iterrows(), total = len(vals)):
+        list_of_floats = [float(item) for item in list(row)]
+        original_values_as_df.loc[index] = [multi_col_representation_vector.iloc[index]['Entry']] + [list_of_floats]
+    return original_values_as_df
+
+if args["benchmark"] in  ["similarity","function","all"]:
+    print("\nRepresentation vectors are loading...\n")
+    representation_dataframe = load_representation(args["representation_file_human"])
+ 
+if args["benchmark"] in  ["similarity","all"]:
+    print("\nSemantic similarity Inference Benchmark is running...\n")
+    ssi.representation_dataframe = representation_dataframe
+    ssi.representation_name = args["representation_name"]
+    ssi.protein_names = ssi.representation_dataframe['Entry'].tolist()
+    ssi.similarity_tasks = args["similarity_tasks"]
+    ssi.detailed_output = args["detailed_output"]
+    ssi.calculate_all_correlations()
+if args["benchmark"] in  ["function","all"]:
+    print("\n\nOntology-based protein function prediction benchmark is running...\n")
+    fp.aspect_type = args["function_prediction_aspect"]
+    fp.dataset_type = args["function_prediction_dataset"]
+    fp.representation_dataframe = representation_dataframe
+    fp.representation_name = args["representation_name"]
+    fp.detailed_output = args["detailed_output"]
+    fp.pred_output()
+if args["benchmark"] in  ["family","all"]:
+    print("\n\nDrug target protein family classification benchmark is running...\n")
+    tfc.representation_path = args["representation_file_human"]
+    tfc.representation_name = args["representation_name"]
+    tfc.detailed_output = args["detailed_output"]
+    for dataset in args["family_prediction_dataset"]:
+	    tfc.score_protein_rep(dataset)
+if args["benchmark"] in  ["affinity","all"]:
+    print("\n\nProtein-protein binding affinity estimation benchmark is running...\n")
+    bae.skempi_vectors_path = args["representation_file_affinity"]
+    bae.representation_name = args["representation_name"]
+    bae.predict_affinities_and_report_results()
+print("\n\nPROBE (Protein RepresentatiOn Benchmark) run is finished...\n")
+
+

src/bin/binding_affinity_estimator.py

@@ -0,0 +1,189 @@
+import tqdm
+import multiprocessing
+import pandas as pd
+import numpy as np
+import scipy.stats
+
+from sklearn import linear_model
+from sklearn.model_selection import KFold
+from sklearn.metrics import mean_squared_error,mean_absolute_error
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.preprocessing import MinMaxScaler
+
+skempi_vectors_path = None
+representation_name = None
+
+def load_representation(multi_col_representation_vector_file_path):
+    print("\nLoading representation vectors...\n")
+    multi_col_representation_vector = pd.read_csv(multi_col_representation_vector_file_path)
+    vals = multi_col_representation_vector.iloc[:,1:(len(multi_col_representation_vector.columns))]
+    original_values_as_df = pd.DataFrame({'PDB_ID': pd.Series([], dtype='str'),'Vector': pd.Series([], dtype='object')})
+    for index, row in tqdm.tqdm(vals.iterrows(), total = len(vals)):
+        list_of_floats = [float(item) for item in list(row)]
+        original_values_as_df.loc[index] = [multi_col_representation_vector.iloc[index]['PDB_ID']] + [list_of_floats]
+    return original_values_as_df
+
+def calc_train_error(X_train, y_train, model):
+    '''returns in-sample error for already fit model.'''
+    predictions = model.predict(X_train)
+    mse = mean_squared_error(y_train, predictions)
+    mae = mean_absolute_error(y_train, predictions)
+    corr = scipy.stats.pearsonr(y_train, predictions)
+    return mse,mae,corr
+    
+def calc_validation_error(X_test, y_test, model):
+    '''returns out-of-sample error for already fit model.'''
+    predictions = model.predict(X_test)
+    mse = mean_squared_error(y_test, predictions)
+    mae = mean_absolute_error(y_test, predictions)
+    corr = scipy.stats.pearsonr(y_test, predictions)
+    return mse,mae,corr
+    
+def calc_metrics(X_train, y_train, X_test, y_test, model):
+    '''fits model and returns the metrics for in-sample error and out-of-sample error'''
+    model.fit(X_train, y_train)
+    train_mse_error,train_mae_error,train_corr = calc_train_error(X_train, y_train, model)
+    val_mse_error,val_mae_error,val_corr = calc_validation_error(X_test, y_test, model)
+    return train_mse_error, val_mse_error, train_mae_error, val_mae_error,train_corr,val_corr
+
+def report_results(
+    train_mse_error_list,
+    validation_mse_error_list,
+    train_mae_error_list,
+    validation_mae_error_list,
+    train_corr_list,
+    validation_corr_list,
+    train_corr_pval_list,
+    validation_corr_pval_list,
+):
+    result_df = pd.DataFrame(
+        {
+            "train_mse_error": round(np.mean(train_mse_error_list) * 100, 4),
+            "train_mse_std": round(np.std(train_mse_error_list) * 100, 4),
+            "val_mse_error": round(np.mean(validation_mse_error_list) * 100, 4),
+            "val_mse_std": round(np.std(validation_mse_error_list) * 100, 4),
+            "train_mae_error": round(np.mean(train_mae_error_list) * 100, 4),
+            "train_mae_std": round(np.std(train_mae_error_list) * 100, 4),
+            "val_mae_error": round(np.mean(validation_mae_error_list) * 100, 4),
+            "val_mae_std": round(np.std(validation_mae_error_list) * 100, 4),
+            "train_corr": round(np.mean(train_corr_list), 4),
+            "train_corr_pval": round(np.mean(train_corr_pval_list), 4),
+            "validation_corr": round(np.mean(validation_corr_list), 4),
+            "validation_corr_pval": round(np.mean(validation_corr_pval_list), 4),
+        },
+        index=[0],
+    )
+
+    result_detail_df = pd.DataFrame(
+        {
+            "train_mse_errors": list(np.multiply(train_mse_error_list, 100)),
+            "val_mse_errors": list(np.multiply(validation_mse_error_list, 100)),
+            "train_mae_errors": list(np.multiply(train_mae_error_list, 100)),
+            "val_mae_errors": list(np.multiply(validation_mae_error_list, 100)),
+            "train_corrs": list(np.multiply(train_corr_list, 100)),
+            "train_corr_pvals": list(np.multiply(train_corr_pval_list, 100)),
+            "validation_corr": list(np.multiply(validation_corr_list, 100)),
+            "validation_corr_pval": list(np.multiply(validation_corr_pval_list, 100)),
+        },
+        index=range(len(train_mse_error_list)),
+    )
+    return result_df, result_detail_df
+
+
+def predictAffinityWithModel(regressor_model,multiplied_vectors_df):
+    K = 10
+    kf = KFold(n_splits=K, shuffle=True, random_state=42)
+
+    train_mse_error_list = []
+    validation_mse_error_list = []
+    train_mae_error_list = []
+    validation_mae_error_list = []
+    train_corr_list = []
+    validation_corr_list = []
+    train_corr_pval_list = []
+    validation_corr_pval_list = []
+
+    data = np.array(np.asarray(multiplied_vectors_df["Vector"].tolist()), dtype=float)
+    ppi_affinity_filtered_df = ppi_affinity_df\
+    [ppi_affinity_df['Protein1'].isin(multiplied_vectors_df['Protein1']) &\
+     ppi_affinity_df['Protein2'].isin(multiplied_vectors_df['Protein2']) ]
+    target = np.array(ppi_affinity_filtered_df["Affinity"])
+    scaler = MinMaxScaler()
+    scaler.fit(target.reshape(-1, 1))
+    target = scaler.transform(target.reshape(-1, 1))[:, 0]
+    for train_index, val_index in tqdm.tqdm(kf.split(data, target), total=K):
+
+        # split data
+        X_train, X_val = data[train_index], data[val_index]
+        y_train, y_val = target[train_index], target[val_index]
+
+        # instantiate model
+        reg = regressor_model #linear_model.BayesianRidge()
+
+        # calculate error_list
+        (
+            train_mse_error,
+            val_mse_error,
+            train_mae_error,
+            val_mae_error,
+            train_corr,
+            val_corr,
+        ) = calc_metrics(X_train, y_train, X_val, y_val, reg)
+
+        # append to appropriate list
+        train_mse_error_list.append(train_mse_error)
+        validation_mse_error_list.append(val_mse_error)
+
+        train_mae_error_list.append(train_mae_error)
+        validation_mae_error_list.append(val_mae_error)
+
+        train_corr_list.append(train_corr[0])
+        validation_corr_list.append(val_corr[0])
+
+        train_corr_pval_list.append(train_corr[1])
+        validation_corr_pval_list.append(val_corr[1])
+
+    return report_results(
+        train_mse_error_list,
+        validation_mse_error_list,
+        train_mae_error_list,
+        validation_mae_error_list,
+        train_corr_list,
+        validation_corr_list,
+        train_corr_pval_list,
+        validation_corr_pval_list,
+    )
+
+ppi_affinity_file = "../data/auxilary_input/skempi_pipr/SKEMPI_all_dg_avg.txt"
+ppi_affinity_df = pd.read_csv(ppi_affinity_file,sep="\t",header=None)
+ppi_affinity_df.columns = ['Protein1', 'Protein2', 'Affinity']
+
+#Calculate vector element-wise multiplication as described in https://academic.oup.com/bioinformatics/article/35/14/i305/5529260
+
+def calculate_vector_multiplications(skempi_vectors_df):
+    multiplied_vectors = pd.DataFrame({'Protein1': pd.Series([], dtype='str'),\
+                                       'Protein2': pd.Series([], dtype='str'),\
+                                       'Vector': pd.Series([], dtype='object')}) 
+    print("Element-wise vector multiplications are being calculated")
+    rep_prot_list = list(skempi_vectors_df['PDB_ID'])
+    for index,row in tqdm.tqdm(ppi_affinity_df.iterrows()):
+        if row['Protein1'] in rep_prot_list and row['Protein2'] in rep_prot_list:
+            vec1 = list(skempi_vectors_df[skempi_vectors_df['PDB_ID']\
+                                                 == row['Protein1']]['Vector'])[0]
+            vec2 = list(skempi_vectors_df[skempi_vectors_df['PDB_ID']\
+                                                 == row['Protein2']]['Vector'])[0]
+            multiplied_vec = np.multiply(vec1,vec2)
+
+            multiplied_vectors = multiplied_vectors.\
+                append({'Protein1':row['Protein1'], 'Protein2':row['Protein2'],\
+                        'Vector':multiplied_vec},ignore_index = True)
+    return multiplied_vectors
+
+def predict_affinities_and_report_results():
+    skempi_vectors_df = load_representation(skempi_vectors_path)
+    multiplied_vectors_df = calculate_vector_multiplications(skempi_vectors_df)
+    model = linear_model.BayesianRidge()
+    result_df, result_detail_df = predictAffinityWithModel(model,multiplied_vectors_df)
+    result_df.to_csv(r"../results/Affinity_prediction_skempiv1_{0}.csv".format(representation_name),index=False)
+    result_detail_df.to_csv(r"../results/Affinity_prediction_skempiv1_{0}_detail.csv".format(representation_name),index=False)
+

src/bin/function_predictor.py

@@ -0,0 +1,216 @@
+# -*- coding: utf-8 -*-
+import pandas as pd
+import numpy as np
+from datetime import datetime
+import pickle
+import os
+import multiprocessing
+from tqdm import tqdm
+
+from sklearn.svm import SVC
+from sklearn.linear_model import SGDClassifier
+from sklearn.model_selection import cross_val_predict, KFold
+from skmultilearn.problem_transform import BinaryRelevance
+from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score, hamming_loss
+
+
+aspect_type = ""
+dataset_type = ""
+representation_dataframe = ""
+representation_name = ""
+detailed_output = False
+
+def warn(*args, **kwargs):
+    pass
+import warnings
+warnings.warn = warn
+
+def check_for_at_least_two_class_sample_exits(y):
+    for column in y:
+        column_sum = np.sum(y[column].array)
+        if column_sum < 2:
+           print('At least 2 positive samples are required for each class {0} class has {1} positive samples'.format(column,column_sum))
+           return False
+    return True
+
+def create_valid_kfold_object_for_multilabel_splits(X,y,kf):
+    check_for_at_least_two_class_sample_exits(y)
+    sample_class_occurance = dict(zip(y.columns,np.zeros(len(y.columns))))
+    for column in y:
+        for fold_train_index,fold_test_index in kf.split(X,y):
+            fold_col_sum = np.sum(y.iloc[fold_test_index,:][column].array)
+            if fold_col_sum > 0:
+                sample_class_occurance[column] += 1 
+
+    for key in sample_class_occurance:
+        value = sample_class_occurance[key]
+        if value < 2:
+            random_state = np.random.randint(1000)
+            print("Random state is changed since at least two positive samples are required in different train/test folds.\
+                    \nHowever, only one fold exits with positive samples for class {0}".format(key))
+            print("Selected random state is {0}".format(random_state))
+            kf = KFold(n_splits=5, shuffle=True, random_state=random_state)
+            create_valid_kfold_object_for_multilabel_splits(X,y,kf)
+        else:
+            return kf
+
+def MultiLabelSVC_cross_val_predict(representation_name, dataset, X, y, classifier):
+    #dataset split, estimator, cv
+    clf = classifier
+    Xn = np.array(np.asarray(X.values.tolist()), dtype=float)
+    kf_init = KFold(n_splits=5, shuffle=True, random_state=42)
+    kf = create_valid_kfold_object_for_multilabel_splits(X,y,kf_init)
+    y_pred = cross_val_predict(clf, Xn, y, cv=kf)
+
+    if detailed_output:
+        with open(r"../results/Ontology_based_function_prediction_{1}_{0}_model.pkl".format(representation_name,dataset.split(".")[0]),"wb") as file:
+            pickle.dump(clf,file)
+        
+    acc_cv = []
+    f1_mi_cv = []
+    f1_ma_cv = []
+    f1_we_cv = []
+    pr_mi_cv = []
+    pr_ma_cv = []
+    pr_we_cv = []
+    rc_mi_cv = []
+    rc_ma_cv = []
+    rc_we_cv = []
+    hamm_cv = []
+    for fold_train_index,fold_test_index in kf.split(X,y):
+        acc = accuracy_score(y.iloc[fold_test_index,:],y_pred[fold_test_index])
+        acc_cv.append(np.round(acc,decimals=5))
+        f1_mi = f1_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="micro")
+        f1_mi_cv.append(np.round(f1_mi,decimals=5))
+        f1_ma = f1_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="macro")
+        f1_ma_cv.append(np.round(f1_ma,decimals=5))
+        f1_we = f1_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="weighted")
+        f1_we_cv.append(np.round(f1_we,decimals=5))
+        pr_mi = precision_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="micro")
+        pr_mi_cv.append(np.round(pr_mi,decimals=5))
+        pr_ma = precision_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="macro")
+        pr_ma_cv.append(np.round(pr_ma,decimals=5))
+        pr_we = precision_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="weighted")
+        pr_we_cv.append(np.round(pr_we,decimals=5))
+        rc_mi = recall_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="micro")
+        rc_mi_cv.append(np.round(rc_mi,decimals=5))
+        rc_ma = recall_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="macro")
+        rc_ma_cv.append(np.round(rc_ma,decimals=5))
+        rc_we = recall_score(y.iloc[fold_test_index,:],y_pred[fold_test_index],average="weighted")
+        rc_we_cv.append(np.round(rc_we,decimals=5))
+        hamm = hamming_loss(y.iloc[fold_test_index,:],y_pred[fold_test_index])
+        hamm_cv.append(np.round(hamm,decimals=5))
+
+    means = list(np.mean([acc_cv,f1_mi_cv,f1_ma_cv,f1_we_cv,pr_mi_cv,pr_ma_cv,pr_we_cv,rc_mi_cv,rc_ma_cv,rc_we_cv,hamm_cv], axis=1))
+    means = [np.round(i,decimals=5) for i in means]
+
+    stds = list(np.std([acc_cv,f1_mi_cv,f1_ma_cv,f1_we_cv,pr_mi_cv,pr_ma_cv,pr_we_cv,rc_mi_cv,rc_ma_cv,rc_we_cv,hamm_cv], axis=1))
+    stds = [np.round(i,decimals=5) for i in stds]
+
+    return ([representation_name+"_"+dataset,acc_cv,f1_mi_cv,f1_ma_cv,f1_we_cv,pr_mi_cv,pr_ma_cv,pr_we_cv,rc_mi_cv,rc_ma_cv,rc_we_cv,hamm_cv],\
+            [representation_name+"_"+dataset]+means,\
+            [representation_name+"_"+dataset]+stds,\
+            y_pred)
+   
+def ProtDescModel():   
+    #desc_file = pd.read_csv(r"protein_representations\final\{0}_dim{1}.tsv".format(representation_name,desc_dim),sep="\t")    
+    datasets = os.listdir(r"../data/auxilary_input/GO_datasets") 
+    if  dataset_type == "All_Data_Sets" and aspect_type == "All_Aspects":
+        filtered_datasets = datasets
+    elif dataset_type == "All_Data_Sets":
+        filtered_datasets = [dataset for dataset in datasets if aspect_type in dataset]
+    elif aspect_type == "All_Aspects":
+        filtered_datasets = [dataset for dataset in datasets if dataset_type in dataset]
+    else:
+        filtered_datasets = [dataset for dataset in datasets if aspect_type in dataset and dataset_type in dataset]
+    cv_results = []
+    cv_mean_results = []
+    cv_std_results = []
+
+    for dt in tqdm(filtered_datasets,total=len(filtered_datasets)):
+        print(r"Protein function prediction is started for the dataset: {0}".format(dt.split(".")[0]))
+        dt_file = pd.read_csv(r"../data/auxilary_input/GO_datasets/{0}".format(dt),sep="\t")
+        dt_merge = dt_file.merge(representation_dataframe,left_on="Protein_Id",right_on="Entry")
+
+        dt_X = dt_merge['Vector']
+        dt_y = dt_merge.iloc[:,1:-2]
+        if check_for_at_least_two_class_sample_exits(dt_y) == False:
+            print(r"No funtion will be predicted for the dataset: {0}".format(dt.split(".")[0]))
+            continue
+        #print("raw dt vs. dt_merge: {} - {}".format(len(dt_file),len(dt_merge)))
+        #print("Calculating predictions for " +  dt.split(".")[0])
+        #model = MultiLabelSVC_cross_val_predict(representation_name, dt.split(".")[0], dt_X, dt_y, classifier=BinaryRelevance(SVC(kernel="linear", random_state=42)))
+        cpu_number  = multiprocessing.cpu_count()
+        model = MultiLabelSVC_cross_val_predict(representation_name, dt.split(".")[0], dt_X, dt_y, classifier=BinaryRelevance(SGDClassifier(n_jobs=cpu_number, random_state=42)))
+        cv_results.append(model[0])                
+        cv_mean_results.append(model[1])
+        cv_std_results.append(model[2])
+
+        predictions = dt_merge.iloc[:,:6]
+        predictions["predicted_values"] = list(model[3].toarray())
+        if detailed_output:
+            predictions.to_csv(r"../results/Ontology_based_function_prediction_{1}_{0}_predictions.tsv".format(representation_name,dt.split(".")[0]),sep="\t",index=None)
+
+    return (cv_results, cv_mean_results,cv_std_results)             
+
+#def pred_output(representation_name, desc_dim):
+def pred_output():
+    model = ProtDescModel()
+    cv_result = model[0]
+    df_cv_result = pd.DataFrame({"Model": pd.Series([], dtype='str') ,"Accuracy": pd.Series([], dtype='float'),"F1_Micro": pd.Series([], dtype='float'),\
+            "F1_Macro": pd.Series([], dtype='float'),"F1_Weighted": pd.Series([], dtype='float'),"Precision_Micro": pd.Series([], dtype='float'),\
+            "Precision_Macro": pd.Series([], dtype='float'),"Precision_Weighted": pd.Series([], dtype='float'),"Recall_Micro": pd.Series([], dtype='float'),\
+            "Recall_Macro": pd.Series([], dtype='float'),"Recall_Weighted": pd.Series([], dtype='float'),"Hamming_Distance": pd.Series([], dtype='float')})
+    for i in cv_result:
+        df_cv_result.loc[len(df_cv_result)] = i
+    if detailed_output:
+        df_cv_result.to_csv(r"../results/Ontology_based_function_prediction_5cv_{0}.tsv".format(representation_name),sep="\t",index=None)
+
+    cv_mean_result = model[1]
+    df_cv_mean_result =  pd.DataFrame({"Model": pd.Series([], dtype='str') ,"Accuracy": pd.Series([], dtype='float'),"F1_Micro": pd.Series([], dtype='float'),\
+            "F1_Macro": pd.Series([], dtype='float'),"F1_Weighted": pd.Series([], dtype='float'),"Precision_Micro": pd.Series([], dtype='float'),\
+            "Precision_Macro": pd.Series([], dtype='float'),"Precision_Weighted": pd.Series([], dtype='float'),"Recall_Micro": pd.Series([], dtype='float'),\
+            "Recall_Macro": pd.Series([], dtype='float'),"Recall_Weighted": pd.Series([], dtype='float'),"Hamming_Distance": pd.Series([], dtype='float')})
+
+    
+    #pd.DataFrame(columns=["Model","Accuracy","F1_Micro","F1_Macro","F1_Weighted","Precision_Micro","Precision_Macro","Precision_Weighted",\
+    #                                     "Recall_Micro","Recall_Macro","Recall_Weighted","Hamming_Distance"])
+
+    for j in cv_mean_result:
+        df_cv_mean_result.loc[len(df_cv_mean_result)] = j
+    df_cv_mean_result.to_csv(r"../results/Ontology_based_function_prediction_5cv_mean_{0}.tsv".format(representation_name),sep="\t",index=None)
+
+#save std deviation of scores to file
+    cv_std_result = model[2]
+    df_cv_std_result =  pd.DataFrame({"Model": pd.Series([], dtype='str') ,"Accuracy": pd.Series([], dtype='float'),"F1_Micro": pd.Series([], dtype='float'),\
+            "F1_Macro": pd.Series([], dtype='float'),"F1_Weighted": pd.Series([], dtype='float'),"Precision_Micro": pd.Series([], dtype='float'),\
+            "Precision_Macro": pd.Series([], dtype='float'),"Precision_Weighted": pd.Series([], dtype='float'),"Recall_Micro": pd.Series([], dtype='float'),\
+            "Recall_Macro": pd.Series([], dtype='float'),"Recall_Weighted": pd.Series([], dtype='float'),"Hamming_Distance": pd.Series([], dtype='float')})
+
+    
+    #pd.DataFrame(columns=["Model","Accuracy","F1_Micro","F1_Macro","F1_Weighted","Precision_Micro","Precision_Macro","Precision_Weighted",\
+    #                                     "Recall_Micro","Recall_Macro","Recall_Weighted","Hamming_Distance"])
+
+    for k in cv_std_result:
+        df_cv_std_result.loc[len(df_cv_std_result)] = k
+    df_cv_std_result.to_csv(r"../results/Ontology_based_function_prediction_5cv_std_{0}.tsv".format(representation_name),sep="\t",index=None)
+
+print(datetime.now())      
+
+
+# tcga = pred_output("tcga","50") 
+# protvec = pred_output("protvec","100")  
+# unirep = pred_output("unirep","5700")  
+# gene2vec = pred_output("gene2vec","200")   
+# learned_embed = pred_output("learned_embed","64") 
+# mut2vec = pred_output("mut2vec","300")    
+# seqvec = pred_output("seqvec","1024") 
+
+#bepler = pred_output("bepler","100") 
+# resnet_rescaled = pred_output("resnet-rescaled","256") 
+# transformer_avg = pred_output("transformer","768") 
+# transformer_pool = pred_output("transformer-pool","768") 
+
+# apaac = pred_output("apaac","80") 
+#ksep = pred_output("ksep","400") 
+

src/bin/probe_config.yaml

@@ -0,0 +1,37 @@
+#Representation name (used for naming output files):
+representation_name: AAC
+#representation_name: LEARNED-VEC
+#representation_name: T5
+
+#Benchmarks (should be one of the "similarity","family","function","affinity","all"):
+# "similarity" for running protein semantic similarity inference benchmark
+# "function" for running ontology-based function prediction benchmark
+# "family" for running drug target protein family classification benchmark
+# "affinity" for running protein-protein binding affinity estimation benchmark
+# "all" for running all benchmarks
+benchmark: all
+
+#Path of the file containing representation vectors of UniProtKB/Swiss-Prot human proteins:
+representation_file_human: ../data/representation_vectors/AAC_UNIPROT_HUMAN.csv
+#representation_file_human: ../data/representation_vectors/LEARNED-VEC_UNIPROT_HUMAN.csv
+#representation_file_human: ../data/representation_vectors/T5_UNIPROT_HUMAN.csv
+
+#Path of the file containing representation vectors of samples in the SKEMPI dataset: 
+representation_file_affinity: ../data/representation_vectors/skempi_aac_representation_multi_col.csv
+#representation_file_affinity: ../data/representation_vectors/skempi_learned-vec_representation_multi_col.csv
+#representation_file_affinity: ../data/representation_vectors/skempi_t5_representation_multi_col.csv
+
+#Semantic similarity inference benchmark dataset (should be a list that includes any combination of "Sparse", "200", and "500"):
+similarity_tasks: ["Sparse","200","500"]
+
+#Ontology-based function prediction benchmark dataset in terms of GO aspect (should be one of the following: "MF", "BP", "CC", or "All_Aspects"):
+function_prediction_aspect: All_Aspects
+
+#Ontology-based function prediction benchmark dataset in terms of size-based-splits (should be one of the following: "High", "Middle", "Low", or "All_Data_Sets")
+function_prediction_dataset: All_Data_Sets
+
+#Drug target protein family classification benchmark dataset in terms of similarity-based splits (should be a list that includes any combination of "nc", "uc50", "uc30", and "mm15")
+family_prediction_dataset: ["nc","uc50","uc30","mm15"]
+
+#Detailed results (can be True or False)
+detailed_output: False

src/bin/semantic_similarity_infer.py

@@ -0,0 +1,160 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+import pandas as pd
+import numpy as np
+import gzip
+import itertools
+import multiprocessing
+import csv
+import pickle
+import random
+from sklearn.metrics.pairwise import cosine_similarity as cosine
+from sklearn.metrics import mean_squared_error as mse
+from tqdm import tqdm, tqdm_notebook
+from multiprocessing import Manager, Pool
+from scipy.spatial.distance import cdist
+from numpy.linalg import norm
+from scipy.stats import spearmanr, pearsonr
+from functools import partial
+
+manager = Manager()
+similarity_list = manager.list()
+proteinListNew = manager.list()
+ 
+representation_dataframe = ""
+protein_names =  ""
+# define similarity_list and proteinList as global variables
+representation_name = ""
+similarity_tasks = ""
+detailed_output = False
+
+def parallelSimilarity(paramList):
+    protein_embedding_dataframe = representation_dataframe
+    i = paramList[0]
+    j = paramList[1] 
+    aspect = paramList[2]
+    if j>i:
+        protein1 = proteinListNew[i]
+        protein2 = proteinListNew[j]
+        if protein1 in protein_names and protein2 in protein_names:
+            prot1vec = np.asarray(protein_embedding_dataframe.query("Entry == @protein1")['Vector'].item())
+            prot2vec = np.asarray(protein_embedding_dataframe.query("Entry == @protein2")['Vector'].item())
+            #cosine will return in shape of input vectors first dimension
+            cos = cosine(prot1vec.reshape(1,-1),prot2vec.reshape(1,-1)).item()
+            manhattanDist = cdist(prot1vec.reshape(1,-1), prot2vec.reshape(1,-1), 'cityblock')
+            manhattanDistNorm = manhattanDist/(norm(prot1vec,1) + norm(prot2vec,1))
+            manhattanSim = 1-manhattanDistNorm.item()
+            if (norm(prot1vec,1)==0 and norm(prot2vec,1) == 0):
+                manhattanSim = 1.0
+                #print((protein1,protein2))
+                #print(manhattanDist)
+                #print(norm(prot1vec,1))
+                #print(norm(prot2vec,1))
+            euclideanDist = cdist(prot1vec.reshape(1,-1), prot2vec.reshape(1,-1), 'euclidean')
+            euclideanDistNorm = euclideanDist/(norm(prot1vec,2) + norm(prot2vec,2))
+            euclidianSim =  1-euclideanDistNorm.item()
+            if (norm(prot1vec,1)==0 and norm(prot2vec,1) == 0):
+                euclidianSim = 1.0
+            real = paramList[3]
+            # To ensure real and calculated values appended to same postion they saved similtanously and then decoupled
+            similarity_list.append((real,cos,manhattanSim ,euclidianSim))
+    return similarity_list
+
+def calculateCorrelationforOntology(aspect,matrix_type):
+    print("\n\nSemantic similarity correlation calculation for aspect: " + aspect + " using matrix/dataset: " + matrix_type + " ...\n")
+    #Clear lists before each aspect
+    similarity_list[:] = []
+    proteinListNew[:] = []
+    
+    similarityMatrixNameDict = {}
+    similarityMatrixNameDict["All"] = "../data/preprocess/human_"+aspect+"_proteinSimilarityMatrix.csv" 
+    similarityMatrixNameDict["500"] = "../data/preprocess/human_"+aspect+"_proteinSimilarityMatrix_for_highest_annotated_500_proteins.csv"
+    similarityMatrixNameDict["Sparse"] = "../data/preprocess/human_"+aspect+"_proteinSimilarityMatrix_for_highest_annotated_500_proteins.csv" 
+    similarityMatrixNameDict["200"] = "../data/preprocess/human_"+aspect+"_proteinSimilarityMatrix_for_highest_annotated_200_proteins.csv"
+
+    similarityMatrixFileName = similarityMatrixNameDict[matrix_type]
+
+    human_proteinSimilarityMatrix = pd.read_csv(similarityMatrixFileName)
+    human_proteinSimilarityMatrix.set_index(human_proteinSimilarityMatrix.columns, inplace = True)
+    proteinList = human_proteinSimilarityMatrix.columns
+
+    #proteinListNew is referanced using Manager
+    for prot in proteinList:
+        proteinListNew.append(prot)
+    if matrix_type == "Sparse":
+        #sparsified_similarities = np.load("SparsifiedSimilarites_for_highest_500.npy")
+        sparsified_similarity_coordinates = np.load("../data/auxilary_input/SparsifiedSimilarityCoordinates_"+aspect+"_for_highest_500.npy")
+        protParamList = sparsified_similarity_coordinates
+    else:     
+        i = range(len(proteinList))
+        j = range(len(proteinList))
+        protParamList = list(itertools.product(i,j))
+    protParamListNew = []
+    # Prepare parameters for parallel processing these parameters will be 
+    # used concurrently by different processes
+    for tup in tqdm(protParamList):
+        i = tup[0]
+        j = tup[1]
+
+        if matrix_type == "Sparse":
+            protein1 = proteinListNew[i]
+            protein2 = proteinListNew[j]
+            real = human_proteinSimilarityMatrix.loc[protein1,protein2]
+            tupNew = (tup[0],tup[1],aspect,real)
+            protParamListNew.append(tupNew)
+        else:
+            if j > i:
+                protein1 = proteinListNew[i]
+                protein2 = proteinListNew[j]
+                real = human_proteinSimilarityMatrix.loc[protein1,protein2]
+                tupNew = (tup[0],tup[1],aspect,real)
+                protParamListNew.append(tupNew)
+
+    total_task_num=len(protParamListNew)
+    pool = Pool()
+    similarity_listRet = []
+    #parallelSimilarityPartial = partial(parallelSimilarity,protein_embedding_type)
+    for similarity_listRet in tqdm(pool.imap_unordered(parallelSimilarity,protParamListNew), total=total_task_num , position=0, leave=True ):
+        pass
+        #time.sleep(0.1)
+    pool.close()
+    pool.join()
+
+    real_distance_list = [value[0] for value in similarity_listRet]
+    cosine_distance_list = [value[1] for value in similarity_listRet]
+    manhattan_distance_list = [value[2] for value in similarity_listRet]
+    euclidian_distance_list = [value[3] for value in similarity_listRet]
+
+    distance_lists = [real_distance_list,cosine_distance_list,manhattan_distance_list,euclidian_distance_list]
+    if detailed_output:
+        report_detailed_distance_scores(representation_name,matrix_type,aspect,distance_lists)
+    
+    cosineCorr = spearmanr(real_distance_list, cosine_distance_list)
+    manhattanCorr = spearmanr(real_distance_list, manhattan_distance_list)
+    euclidianCorr = spearmanr(real_distance_list, euclidian_distance_list)   
+
+    #print("Cosine Correlation for "+aspect+" is " + str(cosineCorr))
+    #print("Manhattan Correlation for "+aspect+" is " + str(manhattanCorr))
+    #print("Euclidian Correlation for "+aspect+" is " + str(euclidianCorr))
+
+    return (cosineCorr,manhattanCorr,euclidianCorr)
+
+def report_detailed_distance_scores(representation_name,similarity_matrix_type,aspect,distance_lists):
+    saveFileName = "../results/Semantic_sim_inference_detailed_distance_scores"+aspect+"_"+similarity_matrix_type+"_"+representation_name+".pkl"
+    with open(saveFileName, "wb") as f:
+            pickle.dump(distance_lists, f)
+
+def calculate_all_correlations():
+    for similarity_matrix_type in similarity_tasks:
+        saveFileName = "../results/Semantic_sim_inference_"+similarity_matrix_type+"_"+representation_name+".csv"
+        buffer = "Semantic Aspect,CosineSim_Correlation,CosineSim_Correlation p-value, ManhattanSim_Correlation,ManhattanSim_Correlation p-value, EuclidianSim_Correlation,EuclidianSim_Correlation p-value \n"
+        f = open(saveFileName,'w')
+        f.write(buffer)
+        for aspect in ["MF","BP","CC"]:
+            corr =  calculateCorrelationforOntology(aspect,similarity_matrix_type) 
+            buffer = "" + aspect + ","+ str(round(corr[0][0],5))+ ","+ str(round(corr[0][1],5))+ ","+ str(round(corr[1][0],5))\
+            + ","+ str(round(corr[1][1],5))+ ","+ str(round(corr[2][0],5))+ ","+str(round(corr[2][1],5))+"\n" 
+            f = open(saveFileName,'a')
+            f.write(buffer)
+            f.close()

src/bin/target_family_classifier.py

@@ -0,0 +1,226 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Jun  8 09:32:26 2020
+
+@author: Muammer
+"""
+
+import numpy as np
+from sklearn.model_selection import cross_validate
+from sklearn.model_selection import cross_val_predict
+from sklearn.metrics import matthews_corrcoef
+from sklearn.metrics import classification_report
+from sklearn.multiclass import OneVsRestClassifier
+from sklearn import linear_model
+from sklearn.metrics import f1_score
+from sklearn.metrics import confusion_matrix
+from sklearn.model_selection import train_test_split
+import pandas as pd 
+from numpy import save
+from sklearn.metrics import precision_recall_fscore_support
+from tqdm import tqdm
+from sklearn.metrics import accuracy_score
+import math
+
+
+representation_name = ""
+representation_path = ""
+dataset = "nc"
+detailed_output = False
+
+def convert_dataframe_to_multi_col(representation_dataframe):
+    entry = pd.DataFrame(representation_dataframe['Entry'])
+    vector = pd.DataFrame(list(representation_dataframe['Vector']))
+    multi_col_representation_vector = pd.merge(left=entry,right=vector,left_index=True, right_index=True)
+    return multi_col_representation_vector
+
+def class_based_scores(c_report, c_matrix):
+    c_report = pd.DataFrame(c_report).transpose()
+    #print(c_report)
+    c_report = c_report.drop(['precision', 'recall'], axis=1)
+    c_report = c_report.drop(labels=['accuracy', 'macro avg', 'weighted avg'], axis=0)
+    cm = c_matrix.astype('float') / c_matrix.sum(axis=1)[:, np.newaxis]
+    #print(c_report)
+    accuracy = cm.diagonal()
+    
+    #print(accuracy)
+    #if len(accuracy) == 6:
+     #   accuracy = np.delete(accuracy, 5)
+
+    accuracy = pd.Series(accuracy, index=c_report.index)
+    c_report['accuracy'] = accuracy
+    
+    total = c_report['support'].sum()
+    #print(total)
+    num_classes = np.shape(c_matrix)[0]
+    mcc = np.zeros(shape=(num_classes,), dtype='float32')
+    weights = np.sum(c_matrix, axis=0)/np.sum(c_matrix)
+    total_tp = 0
+    total_fp = 0
+    total_fn = 0
+    total_tn = 0
+
+    for j in range(num_classes):
+        tp = np.sum(c_matrix[j, j])
+        fp = np.sum(c_matrix[j, np.concatenate((np.arange(0, j), np.arange(j+1, num_classes)))])
+        fn = np.sum(c_matrix[np.concatenate((np.arange(0, j), np.arange(j+1, num_classes))), j])
+        tn = int(total - tp - fp - fn)
+        total_tp = total_tp + tp
+        total_fp = total_fp + fp
+        total_fn = total_fn + fn
+        total_tn = total_tn + tn
+        #print(tp,fp,fn,tn)
+        mcc[j] = ((tp*tn)-(fp*fn))/math.sqrt((tp+fp)*(tp+fn)*(tn+fp)*(tn+fn))
+    #print(mcc)
+    #if len(mcc) == 6:
+     #   mcc = np.delete(mcc, 5)
+
+    mcc = pd.Series(mcc, index=c_report.index)
+    c_report['mcc'] = mcc
+    #c_report.to_excel('../results/resultss_class_based_'+dataset+'.xlsx')
+    #print(c_report)
+    return c_report, total_tp, total_fp, total_fn, total_tn
+
+
+
+def score_protein_rep(dataset):
+#def score_protein_rep(pkl_data_path):
+
+    vecsize = 0
+    #protein_list = pd.read_csv('../data/auxilary_input/entry_class.csv')
+    protein_list = pd.read_csv('../data/preprocess/entry_class_nn.csv')
+    dataframe = pd.read_csv(representation_path)
+    #dataframe = convert_dataframe_to_multi_col(dataframe)    
+    #dataframe = pd.read_pickle(pkl_data_path)
+    vecsize = dataframe.shape[1]-1    
+    x = np.empty([0, vecsize])
+    xemp = np.zeros((1, vecsize), dtype=float)
+    y = []
+    ne = []
+
+    print("\n\nPreprocessing data for drug-target protein family prediction...\n ")
+    for index, row in tqdm(protein_list.iterrows(), total=len(protein_list)):
+        pdrow = dataframe.loc[dataframe['Entry'] == row['Entry']]
+        if len(pdrow) != 0:
+            a = pdrow.loc[ : , pdrow.columns != 'Entry']
+            a = np.array(a)
+            a.shape = (1,vecsize)
+            x = np.append(x, a, axis=0)
+            y.append(row['Class'])
+        else:
+            ne.append(index)
+            x = np.append(x, xemp, axis=0,)
+            y.append(0.0)
+            #print(index)
+
+    x = x.astype(np.float64)
+    y = np.array(y)
+    y = y.astype(np.float64)
+    #print(len(y))
+    scoring = ['precision_weighted', 'recall_weighted', 'f1_weighted', 'accuracy']
+    target_names = ['Enzyme', 'Membrane receptor', 'Transcription factor', 'Ion channel', 'Other']
+    labels = [1.0, 11.0, 12.0, 1005.0, 2000.0]
+    
+    f1 = []
+    accuracy = []
+    mcc = []
+    f1_perclass = []
+    ac_perclass = []
+    mcc_perclass = []
+    sup_perclass = []
+    report_list = []
+    train_index = pd.read_csv('../data/preprocess/indexes/'+dataset+'_trainindex.csv')
+    test_index = pd.read_csv('../data/preprocess/indexes/testindex_family.csv')
+    train_index = train_index.dropna(axis=1) 
+    test_index = test_index.dropna(axis=1)
+    #print(train_index)
+    #for index in ne:
+       
+
+    conf = pd.DataFrame()
+
+    print('Producing protein family predictions...\n')
+    for i in tqdm(range(10)): 
+        clf = linear_model.SGDClassifier(class_weight="balanced", loss="log", penalty="elasticnet", max_iter=1000, tol=1e-3,random_state=i,n_jobs=-1)
+        clf2 = OneVsRestClassifier(clf,n_jobs=-1)
+        #print(test_index)
+        train_indexx = train_index.iloc[i].astype(int)
+        test_indexx = test_index.iloc[i].astype(int)
+        #print(train_indexx)
+        #train_indexx.drop(labels=ne)
+        #print(type(train_indexx))
+        for index in ne:
+            
+            train_indexx = train_indexx[train_indexx!=index]
+            test_indexx = test_indexx[test_indexx!=index]
+            
+
+
+        train_X, test_X = x[train_indexx], x[test_indexx]
+        train_y, test_y = y[train_indexx], y[test_indexx]
+
+        clf2.fit(train_X, train_y)    
+            
+        #print(train_X)
+        y_pred = clf2.predict(test_X)
+           
+        #y_pred = cross_val_predict(clf2, x, y, cv=10, n_jobs=-1)
+        #mcc.append(matthews_corrcoef(test_y, y_pred, sample_weight = test_y))
+        f1_ = f1_score(test_y, y_pred, average='weighted')
+        f1.append(f1_)
+        ac = accuracy_score(test_y, y_pred)
+        accuracy.append(ac)
+        c_report = classification_report(test_y, y_pred, target_names=target_names, output_dict=True)
+        c_matrix = confusion_matrix(test_y, y_pred, labels=labels)
+
+        conf = conf.append(pd.DataFrame(c_matrix, columns=['Enzymes', 'Membrane receptor', 'Transcription factor', 'Ion channel', 'Other']), ignore_index=True) 
+        class_report, tp, fp, fn, tn = class_based_scores(c_report, c_matrix)
+        
+        #print(total_tp)
+        mcc.append(((tp*tn)-(fp*fn))/math.sqrt((tp+fp)*(tp+fn)*(tn+fp)*(tn+fn)))
+
+        
+        f1_perclass.append(class_report['f1-score'])
+        ac_perclass.append(class_report['accuracy'])
+        mcc_perclass.append(class_report['mcc'])
+        sup_perclass.append(class_report['support'])
+        report_list.append(class_report)
+    
+    if detailed_output:
+        conf.to_csv('../results/Drug_target_protein_family_classification_confusion_'+dataset+'_'+representation_name+'.csv', index=None)
+
+    f1_perclass = pd.concat(f1_perclass, axis=1)
+    ac_perclass = pd.concat(ac_perclass, axis=1)
+    mcc_perclass = pd.concat(mcc_perclass, axis=1)
+    sup_perclass = pd.concat(sup_perclass, axis=1)
+    
+    report_list = pd.concat(report_list, axis=1)
+    report_list.to_csv('../results/Drug_target_protein_family_classification_class_based_results_'+dataset+'_'+representation_name+'.csv')
+    
+    report = pd.DataFrame()    
+    f1mean = np.mean(f1, axis=0)
+    #print(f1mean)
+    f1mean = f1mean.round(decimals=5)
+    f1std = np.std(f1).round(decimals=5)
+    acmean = np.mean(accuracy, axis=0).round(decimals=5)
+    acstd = np.std(accuracy).round(decimals=5)
+    mccmean = np.mean(mcc, axis=0).round(decimals=5)
+    mccstd = np.std(mcc).round(decimals=5)
+    labels = ['Average Score', 'Standard Deviation']
+    report['Protein Family'] = labels
+    report['F1_score'] = [f1mean, f1std]
+    report['Accuracy'] = [acmean, acstd]
+    report['MCC'] = [mccmean, mccstd]
+
+    report.to_csv('../results/Drug_target_protein_family_classification_mean_results_'+dataset+'_'+representation_name+'.csv',index=False)
+    #report.to_csv('scores_general.csv')
+    #print(report)   
+    if detailed_output:
+        save('../results/Drug_target_protein_family_classification_f1_'+dataset+'_'+representation_name+'.npy', f1)
+        save('../results/Drug_target_protein_family_classification_accuracy_'+dataset+'_'+representation_name+'.npy', accuracy)
+        save('../results/Drug_target_protein_family_classification_mcc_'+dataset+'_'+representation_name+'.npy', mcc) 
+        save('../results/Drug_target_protein_family_classification_class_based_f1_'+dataset+'_'+representation_name+'.npy', f1_perclass)
+        save('../results/Drug_target_protein_family_classification_class_based_accuracy_'+dataset+'_'+representation_name+'.npy', ac_perclass)
+        save('../results/Drug_target_protein_family_classification_class_based_mcc_'+dataset+'_'+representation_name+'.npy', mcc_perclass) 
+        save('../results/Drug_target_protein_family_classification_class_based_support_'+dataset+'_'+representation_name+'.npy', sup_perclass) 
+