├── .gitignore ├── LICENSE ├── README.md ├── analysis_scripts ├── analysis.sh ├── chop_up_assembly.py ├── error_summary.py ├── fix_read_names.py ├── get_median_identity.py ├── read_length_identity.py ├── rotate_reference.py └── shred_assembly.py ├── basecalling_scripts ├── albacore_basecalling.sh ├── chiron_basecalling.sh ├── flappie_basecalling.sh ├── guppy_basecalling.sh └── scrappie_basecalling.sh ├── images ├── logo-bottom.png └── logo-top.png └── sloika_training_scripts ├── filter_reads.py ├── per-isolate_commands.sh ├── subdivide_read_dir.py ├── training_commands.sh └── trim_signal.py /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | .Rhistory 3 | plots/ 4 | gh-md-toc 5 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 2 |

logo

3 | 4 | 5 | # Performance of neural network basecalling tools for Oxford Nanopore sequencing 6 | 7 | __Ryan R. Wick1, Louise M. Judd1 and Kathryn E. Holt1,2__ 8 |
9 | 1. Department of Infectious Diseases, Central Clinical School, Monash University, Melbourne, Victoria 3004, Australia
2. London School of Hygiene & Tropical Medicine, London WC1E 7HT, UK 10 | 11 | 12 |

logo

13 | 14 | [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.1188469.svg)](https://doi.org/10.5281/zenodo.1188469) 15 | 16 | 17 | This repository contains the scripts used in the preparation of our manuscript on basecalling performance:
18 | [Wick RR, Judd LM, Holt KE. Performance of neural network basecalling tools for Oxford Nanopore sequencing. Genome Biology. 2019;20(1):129.](https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1727-y) 19 | 20 | In August 2019, I put a small addendum to this paper on GitHub which looks at a more recent version of Guppy as well as some different polishing strategies:
21 | [github.com/rrwick/August-2019-consensus-accuracy-update](https://github.com/rrwick/August-2019-consensus-accuracy-update) 22 | 23 | Previous versions of this repository contained the analysis results here in the README, but the current results are now in that manuscript and this repo just holds the scripts associated with the analysis. These scripts assume you're running on Ubuntu 16.04. They make work on other OSs, but no guarantees! 24 | 25 | If you're still interested in the older results, here is a link to the earlier version of this repo: [Comparison of Oxford Nanopore basecalling tools](https://github.com/rrwick/Basecalling-comparison/tree/95bf07476f61cda79e6971f20f48c6ac83e634b3). 26 | 27 | 28 | 29 | ## Basecalling 30 | 31 | Before you analyse a read set, you must generate the read set! The [`basecalling_scripts`](basecalling_scripts) directory contains Bash scripts with the loops/commands I used to run the various basecallers. You'll need to edit the paths at the top of these scripts before running them. 32 | 33 | 34 | 35 | ## Custom training of basecallers 36 | 37 | The [`sloika_training_scripts`](sloika_training_scripts) directory contains the commands we used to train the custom-_Kp_ and custom-_Kp_-big-net models using [our fork of Sloika](https://github.com/rrwick/sloika). 38 | 39 | We used many different isolates in our training set, so the `per-isolate_commands.sh` script contains the commands which must be run separately for each of them. 40 | 41 | After the prepartory work is done, the model can be trained with the commands in `training_commands.sh`. 42 | 43 | 44 | 45 | ## Read set analysis 46 | 47 | The [`analysis_scripts`](analysis_scripts) directory contains the scripts for processing and generating accuracy measurements from read sets. Before the analysis, the reads must be given consistent names, as different basecallers have different conventions for the fastq headers. The `fix_read_names.py` script will convert a read fastq into a format suitable for the next step. 48 | 49 | [`analysis.sh`](scripts/analysis.sh) is the 'master script' that will run all analyses on a given read set: read-level accuracy, assembly, assembly-level accuracy, nanopolish and nanopolish-level accuracy. It will use the other scripts in its execution. You also might want to edit some of the variables at the start of the script to change things like the output directories and the number of CPU threads. You can also comment out parts of this script if you only want to run some of the analyses. 50 | 51 | 52 | 53 | ## License 54 | 55 | [GNU General Public License, version 3](https://www.gnu.org/licenses/gpl-3.0.html) 56 | -------------------------------------------------------------------------------- /analysis_scripts/analysis.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | # https://github.com/rrwick/Basecalling-comparison 5 | 6 | # This program is free software: you can redistribute it and/or modify it under the terms of the 7 | # GNU General Public License as published by the Free Software Foundation, either version 3 of the 8 | # License, or (at your option) any later version. This program is distributed in the hope that it 9 | # will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 10 | # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You 11 | # should have received a copy of the GNU General Public License along with this program. If not, 12 | # see . 13 | 14 | # This script: 15 | # * takes one argument: a fastq/fasta file of reads for analysis: 16 | # * read names should be in UUID format 17 | # * reads should be sorted by name 18 | # * expects the following in the directory in which it's run: 19 | # * a reference.fasta file 20 | # * expects the following tools in the PATH: 21 | # * minimap2 (https://github.com/lh3/minimap2) 22 | # * rebaler (https://github.com/rrwick/Rebaler) 23 | # * racon (https://github.com/isovic/racon) 24 | # * nanopolish and nanopolish_makerange.py (https://github.com/jts/nanopolish) 25 | # * MUMmer tools: nucmer, delta-filter, show-snps (https://sourceforge.net/projects/mummer) 26 | 27 | 28 | # Some high-level settings for the script: 29 | threads=20 30 | assembly_dir=assemblies # where finished assemblies will go 31 | nanopolish_dir=nanopolish # where Nanopolished assemblies will go 32 | results_dir=results # where the result tables will go 33 | 34 | 35 | # This variable holds the directory of the other scripts (assumed to be in the same directory as 36 | # this script): 37 | scripts_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )" 38 | 39 | 40 | # Get the read set name from the filename: 41 | set=$(basename $1 | sed 's/.fastq.gz//' | sed 's/.fasta.gz//' | sed 's/.fastq//' | sed 's/.fasta//') 42 | if [[ $1 = *"fastq"* ]]; then read_type=fastq 43 | elif [[ $1 = *"fasta"* ]]; then read_type=fasta 44 | else echo "Error: cannot determine read type"; exit 1 45 | fi 46 | 47 | 48 | # Various file paths that will be used along the way: 49 | read_data="$results_dir"/"$set"_reads.tsv 50 | read_alignment="$results_dir"/"$set"_reads.paf 51 | trimmed_reads="$assembly_dir"/"$set"_trimmed."$read_type" 52 | filtlong_reads="$assembly_dir"/"$set"_filtlong."$read_type" 53 | assembly_reads="$assembly_dir"/"$set"_assembly_reads.fastq 54 | final_assembly="$assembly_dir"/"$set"_assembly.fasta 55 | assembly_pieces="$results_dir"/"$set"_assembly_pieces.fasta 56 | assembly_data="$results_dir"/"$set"_assembly.tsv 57 | assembly_alignment="$results_dir"/"$set"_assembly.paf 58 | nanopolish_assembly="$nanopolish_dir"/"$set"_nanopolish.fasta 59 | sequencing_summary=03_basecalling_output/"$set"/sequencing_summary.txt 60 | bam_file="$1".sorted.bam 61 | nanopolish_pieces="$results_dir"/"$set"_nanopolish_pieces.fasta 62 | nanopolish_data="$results_dir"/"$set"_nanopolish.tsv 63 | nanopolish_alignment="$results_dir"/"$set"_nanopolish.paf 64 | nanopolish_2_assembly="$nanopolish_dir"/"$set"_nanopolish_2.fasta 65 | bam_file_2="$1"_2.sorted.bam 66 | nanopolish_2_pieces="$results_dir"/"$set"_nanopolish_2_pieces.fasta 67 | nanopolish_2_data="$results_dir"/"$set"_nanopolish_2.tsv 68 | nanopolish_2_alignment="$results_dir"/"$set"_nanopolish_2.paf 69 | nanopolish_3_assembly="$nanopolish_dir"/"$set"_nanopolish_3.fasta 70 | bam_file_3="$1"_3.sorted.bam 71 | nanopolish_3_pieces="$results_dir"/"$set"_nanopolish_3_pieces.fasta 72 | nanopolish_3_data="$results_dir"/"$set"_nanopolish_3.tsv 73 | nanopolish_3_alignment="$results_dir"/"$set"_nanopolish_3.paf 74 | nanopolish_4_assembly="$nanopolish_dir"/"$set"_nanopolish_4.fasta 75 | bam_file_4="$1"_4.sorted.bam 76 | nanopolish_4_pieces="$results_dir"/"$set"_nanopolish_4_pieces.fasta 77 | nanopolish_4_data="$results_dir"/"$set"_nanopolish_4.tsv 78 | nanopolish_4_alignment="$results_dir"/"$set"_nanopolish_4.paf 79 | 80 | 81 | # Used for nucmer: 82 | prefix="$set"_details 83 | ref_contig=chromosome 84 | assembly_contig=chromosome 85 | 86 | 87 | 88 | 89 | printf "\n\n\n" 90 | echo "ASSESS READS: "$set 91 | echo "--------------------------------------------------------------------------------" 92 | mkdir -p "$results_dir" 93 | minimap2 -x map-ont -t $threads -c reference.fasta $1 > $read_alignment 94 | pypy3 "$scripts_dir"/read_length_identity.py $1 $read_alignment > $read_data 95 | rm $read_alignment 96 | 97 | 98 | 99 | 100 | printf "\n\n\n\n" 101 | echo "ASSEMBLY: "$set 102 | echo "--------------------------------------------------------------------------------" 103 | mkdir -p "$assembly_dir" 104 | # Run Porechop 105 | # --no_split: to save time, chimeras shouldn't matter for Rebaler anyway 106 | # --check_reads 1000: to save time, it's all one barcode, so 1000 reads should be plenty 107 | porechop -i $1 -o $trimmed_reads --no_split --threads $threads --check_reads 1000 108 | if [ "$read_type" = "fasta" ]; then 109 | seqtk seq $trimmed_reads > "$assembly_dir"/temp.fasta # make one-line-per-seq fasta 110 | mv "$assembly_dir"/temp.fasta $trimmed_reads 111 | fi 112 | # Run multiple replicates of Racon on shuffled reads and a rotated reference. 113 | # Each assembly is then coursely shredded into 'reads' for the final Racon round. 114 | for i in {0..9}; do 115 | sample_reads="$assembly_dir"/"$set"_sample_"$i"."$read_type" 116 | sample_assembly="$assembly_dir"/"$set"_assembly_"$i".fasta 117 | sample_reference="$assembly_dir"/"$set"_reference_"$i".fasta 118 | if [ "$read_type" = "fastq" ]; then 119 | cat $trimmed_reads | paste - - - - | shuf | awk -F'\t' '{OFS="\n"; print $1,$2,$3,$4}' > $sample_reads 120 | elif [ "$read_type" = "fasta" ]; then 121 | cat $trimmed_reads | paste - - | shuf | awk -F'\t' '{OFS="\n"; print $1,$2}' > $sample_reads 122 | fi 123 | "$scripts_dir"/rotate_reference.py reference.fasta $i > $sample_reference 124 | rebaler -t $threads $sample_reference $sample_reads > $sample_assembly 125 | "$scripts_dir"/shred_assembly.py $sample_assembly $i 50000 >> $assembly_reads 126 | rm $sample_reads $sample_assembly $sample_reference 127 | done 128 | rm $trimmed_reads 129 | rebaler -t $threads reference.fasta $assembly_reads > $final_assembly 130 | rm $assembly_reads 131 | 132 | 133 | 134 | 135 | printf "\n\n\n\n" 136 | echo "ASSESS ASSEMBLY: "$set 137 | echo "--------------------------------------------------------------------------------" 138 | python3 "$scripts_dir"/chop_up_assembly.py $final_assembly 10000 > $assembly_pieces 139 | minimap2 -x asm5 -t $threads -c reference.fasta $assembly_pieces > $assembly_alignment 140 | pypy3 "$scripts_dir"/read_length_identity.py $assembly_pieces $assembly_alignment > $assembly_data 141 | rm $assembly_pieces $assembly_alignment 142 | if [ ! -f "$results_dir"/assembly_error_details ]; then 143 | printf "assembly\tdcm\thomo_del\thomo_ins\tother_del\tother_ins\tsub\n" > "$results_dir"/assembly_error_details 144 | fi 145 | printf $set"\t" >> "$results_dir"/assembly_error_details 146 | nucmer --prefix="$prefix" reference.fasta $final_assembly 147 | delta-filter -r -q "$prefix".delta > "$prefix".filter 148 | show-snps -ClrTH -x5 "$prefix".filter | python3 "$scripts_dir"/error_summary.py "$ref_contig" "$assembly_contig" >> "$results_dir"/assembly_error_details 149 | printf $set"\tassembly\t" >> "$results_dir"/substitution_counts 150 | show-snps -ClrTH "$prefix".filter | awk '$2 != "." && $3 != "."' | wc -l >> "$results_dir"/substitution_counts 151 | rm "$prefix".delta "$prefix".filter 152 | 153 | 154 | 155 | 156 | printf "\n\n\n\n" 157 | echo "NANOPOLISH: "$set 158 | echo "--------------------------------------------------------------------------------" 159 | mkdir -p $nanopolish_dir 160 | if [ -f $sequencing_summary ]; then 161 | echo "Running nanopolish index with sequencing_summary.txt file" 162 | nanopolish index -d fast5s -s $sequencing_summary $1 163 | else 164 | echo "Running nanopolish index without sequencing_summary.txt file" 165 | nanopolish index -d fast5s $1 166 | fi 167 | minimap2 -x map-ont -a -t $threads $final_assembly $1 | samtools sort > $bam_file 168 | samtools index $bam_file 169 | nanopolish_makerange.py $final_assembly | parallel --results "$nanopolish_dir"/"$set"_nanopolish.results -P $threads nanopolish variants --consensus -o "$nanopolish_dir"/"$set"_polished.{1}.vcf -w {1} -r $1 -b $bam_file -g $final_assembly -t 2 --min-candidate-frequency 0.1 --methylation-aware=dcm,dam --fix-homopolymers 170 | nanopolish vcf2fasta -g $final_assembly "$nanopolish_dir"/"$set"_polished.*.vcf > $nanopolish_assembly 171 | rm "$nanopolish_dir"/"$set"_polished.*.vcf "$nanopolish_dir"/"$set"_nanopolish.results* 172 | rm "$1".index "$1".index.fai "$1".index.gzi "$1".index.readdb $bam_file "$bam_file".bai 173 | rm "$final_assembly".fai 174 | 175 | 176 | 177 | 178 | printf "\n\n\n\n" 179 | echo "ASSESS NANOPOLISHED ASSEMBLY: "$set 180 | echo "--------------------------------------------------------------------------------" 181 | python3 "$scripts_dir"/chop_up_assembly.py $nanopolish_assembly 10000 > $nanopolish_pieces 182 | minimap2 -x asm5 -t $threads -c reference.fasta $nanopolish_pieces > $nanopolish_alignment 183 | pypy3 "$scripts_dir"/read_length_identity.py $nanopolish_pieces $nanopolish_alignment > $nanopolish_data 184 | rm $nanopolish_pieces $nanopolish_alignment 185 | if [ ! -f "$results_dir"/nanopolish_error_details ]; then 186 | printf "assembly\tdcm\thomo_del\thomo_ins\tother_del\tother_ins\tsub\n" > "$results_dir"/nanopolish_error_details 187 | fi 188 | printf $set"\t" >> "$results_dir"/nanopolish_error_details 189 | nucmer --prefix="$prefix" reference.fasta $nanopolish_assembly 190 | delta-filter -r -q "$prefix".delta > "$prefix".filter 191 | show-snps -ClrTH -x5 "$prefix".filter | python3 "$scripts_dir"/error_summary.py "$ref_contig" "$assembly_contig" >> "$results_dir"/nanopolish_error_details 192 | printf $set"\tnanopolish\t" >> "$results_dir"/substitution_counts 193 | show-snps -ClrTH "$prefix".filter | awk '$2 != "." && $3 != "."' | wc -l >> "$results_dir"/substitution_counts 194 | rm "$prefix".delta "$prefix".filter 195 | 196 | 197 | 198 | 199 | # What follows are subsequent runs of Nanopolish. If you want to do them, comment out this exit 200 | # statement so the script can continue. 201 | exit 0 202 | 203 | 204 | 205 | 206 | printf "\n\n\n\n" 207 | echo "NANOPOLISH (SECOND TIME): "$set 208 | echo "--------------------------------------------------------------------------------" 209 | if [ -f $sequencing_summary ]; then 210 | echo "Running nanopolish index with sequencing_summary.txt file" 211 | nanopolish index -d fast5s -s $sequencing_summary $1 212 | else 213 | echo "Running nanopolish index without sequencing_summary.txt file" 214 | nanopolish index -d fast5s $1 215 | fi 216 | minimap2 -x map-ont -a -t $threads $nanopolish_assembly $1 | samtools sort > $bam_file_2 217 | samtools index $bam_file_2 218 | nanopolish_makerange.py $nanopolish_assembly | parallel --results "$nanopolish_dir"/"$set"_2_nanopolish.results -P $threads nanopolish variants --consensus -o "$nanopolish_dir"/"$set"_2_polished.{1}.vcf -w {1} -r $1 -b $bam_file_2 -g $nanopolish_assembly -t 2 --min-candidate-frequency 0.1 --methylation-aware=dcm,dam --fix-homopolymers 219 | nanopolish vcf2fasta -g $nanopolish_assembly "$nanopolish_dir"/"$set"_2_polished.*.vcf > $nanopolish_2_assembly 220 | rm "$nanopolish_dir"/"$set"_2_polished.*.vcf "$nanopolish_dir"/"$set"_2_nanopolish.results* 221 | rm "$1".index "$1".index.fai "$1".index.gzi "$1".index.readdb $bam_file_2 "$bam_file_2".bai 222 | rm "$nanopolish_assembly".fai 223 | 224 | 225 | 226 | printf "\n\n\n\n" 227 | echo "ASSESS NANOPOLISHED (SECOND TIME) ASSEMBLY: "$set 228 | echo "--------------------------------------------------------------------------------" 229 | python3 "$scripts_dir"/chop_up_assembly.py $nanopolish_2_assembly 10000 > $nanopolish_2_pieces 230 | minimap2 -x asm5 -t $threads -c reference.fasta $nanopolish_2_pieces > $nanopolish_2_alignment 231 | pypy3 "$scripts_dir"/read_length_identity.py $nanopolish_2_pieces $nanopolish_2_alignment > $nanopolish_2_data 232 | rm $nanopolish_2_pieces $nanopolish_2_alignment 233 | if [ ! -f "$results_dir"/nanopolish_2_error_details ]; then 234 | printf "assembly\tdcm\thomo_del\thomo_ins\tother_del\tother_ins\tsub\n" > "$results_dir"/nanopolish_2_error_details 235 | fi 236 | printf $set"\t" >> "$results_dir"/nanopolish_2_error_details 237 | nucmer --prefix="$prefix"_2 reference.fasta $nanopolish_2_assembly 238 | delta-filter -r -q "$prefix"_2.delta > "$prefix"_2.filter 239 | show-snps -ClrTH -x5 "$prefix"_2.filter | python3 "$scripts_dir"/error_summary.py "$ref_contig" "$assembly_contig" >> "$results_dir"/nanopolish_2_error_details 240 | rm "$prefix"_2.delta "$prefix"_2.filter 241 | 242 | 243 | 244 | 245 | printf "\n\n\n\n" 246 | echo "NANOPOLISH (THIRD TIME): "$set 247 | echo "--------------------------------------------------------------------------------" 248 | if [ -f $sequencing_summary ]; then 249 | echo "Running nanopolish index with sequencing_summary.txt file" 250 | nanopolish index -d fast5s -s $sequencing_summary $1 251 | else 252 | echo "Running nanopolish index without sequencing_summary.txt file" 253 | nanopolish index -d fast5s $1 254 | fi 255 | minimap2 -x map-ont -a -t $threads $nanopolish_2_assembly $1 | samtools sort > $bam_file_3 256 | samtools index $bam_file_3 257 | nanopolish_makerange.py $nanopolish_2_assembly | parallel --results "$nanopolish_dir"/"$set"_3_nanopolish.results -P $threads nanopolish variants --consensus -o "$nanopolish_dir"/"$set"_3_polished.{1}.vcf -w {1} -r $1 -b $bam_file_3 -g $nanopolish_2_assembly -t 2 --min-candidate-frequency 0.1 --methylation-aware=dcm,dam --fix-homopolymers 258 | nanopolish vcf2fasta -g $nanopolish_2_assembly "$nanopolish_dir"/"$set"_3_polished.*.vcf > $nanopolish_3_assembly 259 | rm "$nanopolish_dir"/"$set"_3_polished.*.vcf "$nanopolish_dir"/"$set"_3_nanopolish.results* 260 | rm "$1".index "$1".index.fai "$1".index.gzi "$1".index.readdb $bam_file_3 "$bam_file_3".bai 261 | rm "$nanopolish_2_assembly".fai 262 | 263 | 264 | 265 | printf "\n\n\n\n" 266 | echo "ASSESS NANOPOLISHED (THIRD TIME) ASSEMBLY: "$set 267 | echo "--------------------------------------------------------------------------------" 268 | python3 "$scripts_dir"/chop_up_assembly.py $nanopolish_3_assembly 10000 > $nanopolish_3_pieces 269 | minimap2 -x asm5 -t $threads -c reference.fasta $nanopolish_3_pieces > $nanopolish_3_alignment 270 | pypy3 "$scripts_dir"/read_length_identity.py $nanopolish_3_pieces $nanopolish_3_alignment > $nanopolish_3_data 271 | rm $nanopolish_3_pieces $nanopolish_3_alignment 272 | if [ ! -f "$results_dir"/nanopolish_3_error_details ]; then 273 | printf "assembly\tdcm\thomo_del\thomo_ins\tother_del\tother_ins\tsub\n" > "$results_dir"/nanopolish_3_error_details 274 | fi 275 | printf $set"\t" >> "$results_dir"/nanopolish_3_error_details 276 | nucmer --prefix="$prefix"_3 reference.fasta $nanopolish_3_assembly 277 | delta-filter -r -q "$prefix"_3.delta > "$prefix"_3.filter 278 | show-snps -ClrTH -x5 "$prefix"_3.filter | python3 "$scripts_dir"/error_summary.py "$ref_contig" "$assembly_contig" >> "$results_dir"/nanopolish_3_error_details 279 | rm "$prefix"_3.delta "$prefix"_3.filter 280 | 281 | 282 | 283 | 284 | printf "\n\n\n\n" 285 | echo "NANOPOLISH (FOURTH TIME): "$set 286 | echo "--------------------------------------------------------------------------------" 287 | if [ -f $sequencing_summary ]; then 288 | echo "Running nanopolish index with sequencing_summary.txt file" 289 | nanopolish index -d fast5s -s $sequencing_summary $1 290 | else 291 | echo "Running nanopolish index without sequencing_summary.txt file" 292 | nanopolish index -d fast5s $1 293 | fi 294 | minimap2 -x map-ont -a -t $threads $nanopolish_3_assembly $1 | samtools sort > $bam_file_4 295 | samtools index $bam_file_4 296 | nanopolish_makerange.py $nanopolish_3_assembly | parallel --results "$nanopolish_dir"/"$set"_4_nanopolish.results -P $threads nanopolish variants --consensus -o "$nanopolish_dir"/"$set"_4_polished.{1}.vcf -w {1} -r $1 -b $bam_file_4 -g $nanopolish_3_assembly -t 2 --min-candidate-frequency 0.1 --methylation-aware=dcm,dam --fix-homopolymers 297 | nanopolish vcf2fasta -g $nanopolish_3_assembly "$nanopolish_dir"/"$set"_4_polished.*.vcf > $nanopolish_4_assembly 298 | rm "$nanopolish_dir"/"$set"_4_polished.*.vcf "$nanopolish_dir"/"$set"_4_nanopolish.results* 299 | rm "$1".index "$1".index.fai "$1".index.gzi "$1".index.readdb $bam_file_4 "$bam_file_4".bai 300 | rm "$nanopolish_3_assembly".fai 301 | 302 | 303 | 304 | printf "\n\n\n\n" 305 | echo "ASSESS NANOPOLISHED (FOURTH TIME) ASSEMBLY: "$set 306 | echo "--------------------------------------------------------------------------------" 307 | python3 "$scripts_dir"/chop_up_assembly.py $nanopolish_4_assembly 10000 > $nanopolish_4_pieces 308 | minimap2 -x asm5 -t $threads -c reference.fasta $nanopolish_4_pieces > $nanopolish_4_alignment 309 | pypy3 "$scripts_dir"/read_length_identity.py $nanopolish_4_pieces $nanopolish_4_alignment > $nanopolish_4_data 310 | rm $nanopolish_4_pieces $nanopolish_4_alignment 311 | if [ ! -f "$results_dir"/nanopolish_4_error_details ]; then 312 | printf "assembly\tdcm\thomo_del\thomo_ins\tother_del\tother_ins\tsub\n" > "$results_dir"/nanopolish_4_error_details 313 | fi 314 | printf $set"\t" >> "$results_dir"/nanopolish_4_error_details 315 | nucmer --prefix="$prefix"_4 reference.fasta $nanopolish_4_assembly 316 | delta-filter -r -q "$prefix"_4.delta > "$prefix"_4.filter 317 | show-snps -ClrTH -x5 "$prefix"_4.filter | python3 "$scripts_dir"/error_summary.py "$ref_contig" "$assembly_contig" >> "$results_dir"/nanopolish_4_error_details 318 | rm "$prefix"_4.delta "$prefix"_4.filter 319 | -------------------------------------------------------------------------------- /analysis_scripts/chop_up_assembly.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script takes an assembly as input and produces an output of 'reads': the assembly chopped into pieces. 15 | It is for assessing the distribution of identity over the assembly. 16 | """ 17 | 18 | import sys 19 | 20 | 21 | def main(): 22 | assembly_filename = sys.argv[1] 23 | piece_size = int(sys.argv[2]) 24 | contigs = load_fasta(assembly_filename) 25 | read_num = 0 26 | for contig in contigs: 27 | seq = contig[1] 28 | for i in range(0, len(seq), piece_size): 29 | piece_seq = seq[i:i+piece_size] 30 | if len(piece_seq) == piece_size: 31 | read_num += 1 32 | print('>' + str(read_num)) 33 | print(piece_seq) 34 | 35 | 36 | def load_fasta(fasta_filename): 37 | fasta_seqs = [] 38 | with open(fasta_filename, 'rt') as fasta_file: 39 | name = '' 40 | sequence = '' 41 | for line in fasta_file: 42 | line = line.strip() 43 | if not line: 44 | continue 45 | if line[0] == '>': # Header line = start of new contig 46 | if name: 47 | fasta_seqs.append((name.split()[0], sequence, name)) 48 | sequence = '' 49 | name = line[1:] 50 | else: 51 | sequence += line 52 | if name: 53 | fasta_seqs.append((name.split()[0], sequence, name)) 54 | return fasta_seqs 55 | 56 | 57 | if __name__ == '__main__': 58 | main() 59 | -------------------------------------------------------------------------------- /analysis_scripts/error_summary.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script takes MUMmer SNPs as input (via stdin) and outputs a summary of the assembly's errors. 15 | Use it like this: 16 | 17 | prefix=ref_vs_assembly 18 | ref_fasta=ref.fasta 19 | assembly_fasta=assembly.fasta 20 | ref_contig=chromosome 21 | assembly_contig=tig00000001 22 | 23 | nucmer --prefix="$prefix" "$ref_fasta" "$assembly_fasta" 24 | delta-filter -r -q "$prefix".delta > "$prefix".filter 25 | rm "$prefix".delta 26 | show-snps -ClrTH -x5 "$prefix".filter | python3 error_summary.py "$ref_contig" "$assembly_contig" 27 | """ 28 | 29 | import collections 30 | import math 31 | import sys 32 | 33 | 34 | homo_lengths_to_count = [3, 4, 5, 6, 7, 8] 35 | 36 | 37 | def main(): 38 | r_contig = sys.argv[1] 39 | a_contig = sys.argv[2] 40 | 41 | r_length, alignment_length = None, None 42 | snp_count = 0 43 | homo_ins_count, non_homo_ins_count = 0, 0 44 | homo_del_count, non_homo_del_count = 0, 0 45 | homo_ins_counts = collections.defaultdict(int) 46 | homo_del_counts = collections.defaultdict(int) 47 | sub_count = 0 48 | dcm_count, no_motif_count = 0, 0 49 | 50 | error_type_counts = collections.defaultdict(int) 51 | 52 | for line in sys.stdin: 53 | parts = line.strip().split('\t') 54 | if parts[12] != r_contig or parts[13] != a_contig: 55 | continue 56 | 57 | if r_length is None: 58 | r_length = int(parts[7]) 59 | alignment_length = r_length 60 | snp_count += 1 61 | r_base = parts[1] 62 | a_base = parts[2] 63 | ref_seq = parts[8] 64 | 65 | error_type = get_error_type(r_base, a_base, ref_seq) 66 | error_type_counts[error_type] += 1 67 | 68 | for error_type in ['dcm', 'homo del', 'homo ins', 'other del', 'other ins', 'sub']: 69 | rate = error_type_counts[error_type] / r_length 70 | end_char = '\n' if error_type == 'sub' else '\t' 71 | print('{:.7f}'.format(rate), end=end_char) 72 | 73 | 74 | def get_deletion_homopolymer_length(seq): 75 | seq_len = len(seq) 76 | middle_i = seq_len // 2 77 | base = seq[middle_i] 78 | start = middle_i 79 | while start > 0: 80 | if seq[start-1] == base: 81 | start -= 1 82 | else: 83 | break 84 | end = middle_i+1 85 | while end < seq_len: 86 | if seq[end] == base: 87 | end += 1 88 | else: 89 | break 90 | homopolymer = seq[start:end].replace('.', '') 91 | return len(homopolymer) 92 | 93 | 94 | def get_insertion_homopolymer_length(seq): 95 | seq_len = len(seq) 96 | middle_i = seq_len // 2 97 | base_1 = seq[middle_i-1] 98 | base_2 = seq[middle_i+1] 99 | if base_1 != base_2: 100 | return 1 101 | start = middle_i 102 | while start > 0: 103 | if seq[start-1] == base_1: 104 | start -= 1 105 | else: 106 | break 107 | end = middle_i+1 108 | while end < seq_len: 109 | if seq[end] == base_1: 110 | end += 1 111 | else: 112 | break 113 | homopolymer = seq[start:end].replace('.', '') 114 | return len(homopolymer) 115 | 116 | 117 | def error_in_dcm_motif(seq): 118 | seq = seq[1:-1] 119 | seq = seq.replace('.', '') 120 | return ('CCAGG' in seq) or ('CCTGG' in seq) 121 | 122 | 123 | def get_error_type(r_base, a_base, ref_seq): 124 | if error_in_dcm_motif(ref_seq): 125 | return 'dcm' 126 | if a_base == '.' and get_deletion_homopolymer_length(ref_seq) >= 3: 127 | return 'homo del' 128 | if r_base == '.' and get_insertion_homopolymer_length(ref_seq) >= 3: 129 | return 'homo ins' 130 | if a_base == '.': # deletion 131 | return 'other del' 132 | if r_base == '.': # insertion 133 | return 'other ins' 134 | return 'sub' 135 | 136 | 137 | if __name__ == '__main__': 138 | main() 139 | -------------------------------------------------------------------------------- /analysis_scripts/fix_read_names.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script adjusts read headers to be consistent between basecallers and compatible with 15 | Nanopolish. After running, each read header should be in this format: 16 | 5a8d447e-84e2-4f6f-922c-5ad7269f688c_Basecall_1D_template 5210_N125509_20170425_FN2002039725_MN19691_sequencing_run_klebs_033_restart_87298_ch152_read14914_strand 17 | 18 | It also sorts the reads alphabetically by their new headers and removes 0-length reads. 19 | 20 | Usage: 21 | fix_read_names.py input_reads.fastq.gz read_id_to_fast5 | gzip > output_reads.fastq.gz 22 | 23 | It can take either fasta or fastq input and will output in the same format. 24 | 25 | The read_id_to_fast5 file is a tab-delimited file with read IDs in the first column and fast5 26 | filenames in the second. For example: 27 | 00052d2b-be8b-4649-b6d5-9bdbd88a1ea5 5210_N128870_20170602_FN_MN20200_sequencing_run_sample_id_99953_ch225_read22973_strand.fast5 28 | 0005323f-791d-4bd1-bd5f-3f110cb72b08 5210_N128870_20170602_FN_MN20200_sequencing_run_sample_id_99953_ch341_read18592_strand.fast5 29 | 00077d28-f985-4800-898e-d4baede5d2aa 5210_N128870_20170602_FN_MN20200_sequencing_run_sample_id_99953_ch117_read27051_strand.fast5 30 | """ 31 | 32 | import sys 33 | import os 34 | import gzip 35 | import re 36 | 37 | 38 | def main(): 39 | input_reads_filename = sys.argv[1] 40 | read_id_to_fast5_filename = sys.argv[2] 41 | 42 | print('\nReading ' + read_id_to_fast5_filename, file=sys.stderr, flush=True) 43 | read_id_to_fast5, fast5_to_read_id = {}, {} 44 | with open(read_id_to_fast5_filename, 'rt') as read_id_to_fast5_file: 45 | for line in read_id_to_fast5_file: 46 | parts = line.strip().split('\t') 47 | if len(parts) == 2: 48 | read_id, fast5 = parts 49 | if fast5.endswith('.fast5'): 50 | fast5 = fast5[:-6] 51 | if read_id in read_id_to_fast5: 52 | sys.exit('Error: duplicate read ID in ' + read_id_to_fast5_filename + ': ' + read_id) 53 | if fast5 in fast5_to_read_id: 54 | sys.exit('Error: duplicate fast5 in ' + read_id_to_fast5_filename + ': ' + fast5) 55 | read_id_to_fast5[read_id] = fast5 56 | fast5_to_read_id[fast5] = read_id 57 | 58 | print('Loading reads from ' + input_reads_filename, file=sys.stderr, flush=True) 59 | reads, read_type = load_fasta_or_fastq(input_reads_filename) 60 | 61 | print('Fixing read names', file=sys.stderr, flush=True) 62 | output_reads = [] 63 | for header, seq, qual in reads: 64 | read_id, fast5_name = None, None 65 | try: 66 | read_id = re.search(r'[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}', header).group(0) 67 | except AttributeError: 68 | read_id = None 69 | try: 70 | fast5_name = re.search(r'\w+_ch\d+_read\d+_\w+', header).group(0) 71 | except AttributeError: 72 | fast5_name = None 73 | if read_id is None and fast5_name is None: 74 | sys.exit('Error: could not parse read header\n' + header) 75 | 76 | if read_id is not None: 77 | new_header = read_id + ' ' + read_id_to_fast5[read_id] 78 | else: 79 | new_header = fast5_to_read_id[fast5_name] + ' ' + fast5_name 80 | 81 | output_reads.append((new_header, seq, qual)) 82 | 83 | print('Sorting reads', file=sys.stderr, flush=True) 84 | output_reads = sorted(output_reads) 85 | 86 | print('Outputting reads', file=sys.stderr, flush=True) 87 | for header, seq, qual in output_reads: 88 | if len(seq) == 0: 89 | continue 90 | if read_type == 'FASTA': 91 | print('>' + header) 92 | print(seq) 93 | else: # read_type == 'FASTQ' 94 | print('@' + header) 95 | print(seq) 96 | print('+') 97 | print(qual) 98 | print('Done!\n', file=sys.stderr, flush=True) 99 | 100 | 101 | def get_compression_type(filename): 102 | magic_dict = {'gz': (b'\x1f', b'\x8b', b'\x08'), 103 | 'bz2': (b'\x42', b'\x5a', b'\x68'), 104 | 'zip': (b'\x50', b'\x4b', b'\x03', b'\x04')} 105 | max_len = max(len(x) for x in magic_dict) 106 | 107 | unknown_file = open(filename, 'rb') 108 | file_start = unknown_file.read(max_len) 109 | unknown_file.close() 110 | compression_type = 'plain' 111 | for filetype, magic_bytes in magic_dict.items(): 112 | if file_start.startswith(magic_bytes): 113 | compression_type = filetype 114 | if compression_type == 'bz2': 115 | sys.exit('Error: cannot use bzip2 format - use gzip instead') 116 | if compression_type == 'zip': 117 | sys.exit('Error: cannot use zip format - use gzip instead') 118 | return compression_type 119 | 120 | 121 | def get_sequence_file_type(filename): 122 | if not os.path.isfile(filename): 123 | sys.exit('Error: could not find ' + filename) 124 | if get_compression_type(filename) == 'gz': 125 | open_func = gzip.open 126 | else: # plain text 127 | open_func = open 128 | 129 | with open_func(filename, 'rt') as seq_file: 130 | try: 131 | first_char = seq_file.read(1) 132 | except UnicodeDecodeError: 133 | first_char = '' 134 | 135 | if first_char == '>': 136 | return 'FASTA' 137 | elif first_char == '@': 138 | return 'FASTQ' 139 | else: 140 | raise ValueError('File is neither FASTA or FASTQ') 141 | 142 | 143 | def load_fasta_or_fastq(filename): 144 | try: 145 | file_type = get_sequence_file_type(filename) 146 | if file_type == 'FASTA': 147 | return load_fasta(filename), 'FASTA' 148 | else: # FASTQ 149 | return load_fastq(filename), 'FASTQ' 150 | except IndexError: 151 | sys.exit('\nError: ' + filename + ' could not be parsed - is it formatted correctly?') 152 | 153 | 154 | def load_fasta(fasta_filename): 155 | if get_compression_type(fasta_filename) == 'gz': 156 | open_func = gzip.open 157 | else: # plain text 158 | open_func = open 159 | fasta_seqs = [] 160 | with open_func(fasta_filename, 'rt') as fasta_file: 161 | name = '' 162 | sequence = '' 163 | for line in fasta_file: 164 | line = line.strip() 165 | if not line: 166 | continue 167 | if line[0] == '>': # Header line = start of new contig 168 | if name: 169 | fasta_seqs.append((name, sequence, '')) 170 | sequence = '' 171 | name = line[1:] 172 | else: 173 | sequence += line 174 | if name: 175 | fasta_seqs.append((name, sequence, '')) 176 | return fasta_seqs 177 | 178 | 179 | def load_fastq(fastq_filename): 180 | if get_compression_type(fastq_filename) == 'gz': 181 | open_func = gzip.open 182 | else: # plain text 183 | open_func = open 184 | reads = [] 185 | 186 | extra_empty_line = False 187 | with open_func(fastq_filename, 'rt') as fastq: 188 | for line in fastq: 189 | _ = next(fastq) 190 | _ = next(fastq) 191 | _ = next(fastq) 192 | fifth_line = next(fastq).strip() 193 | if len(fifth_line) == 0: 194 | extra_empty_line = True 195 | break 196 | 197 | with open_func(fastq_filename, 'rt') as fastq: 198 | for line in fastq: 199 | name = line.strip()[1:] 200 | sequence = next(fastq).strip() 201 | _ = next(fastq) 202 | qualities = next(fastq).strip() 203 | if extra_empty_line: 204 | _ = next(fastq) 205 | reads.append((name, sequence, qualities)) 206 | return reads 207 | 208 | 209 | if __name__ == '__main__': 210 | main() 211 | -------------------------------------------------------------------------------- /analysis_scripts/get_median_identity.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script reads a tsv file (for either read or assembly data) and returns the median identity. 15 | It can optionally take a total number of sequences, which will make it add zeros to get to that 16 | number (useful for basecallers that didn't basecall all of the reads). 17 | """ 18 | 19 | import statistics 20 | import sys 21 | 22 | identities = [] 23 | with open(sys.argv[1], 'rt') as data_file: 24 | for line in data_file: 25 | parts = line.strip().split() 26 | if parts[0] == 'Name': 27 | continue 28 | identities.append(float(parts[2])) 29 | 30 | try: 31 | total_count = int(sys.argv[2]) 32 | while len(identities) < total_count: 33 | identities.append(0.0) 34 | except IndexError: 35 | pass 36 | 37 | print(statistics.median(identities)) 38 | -------------------------------------------------------------------------------- /analysis_scripts/read_length_identity.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script produces a table with information for each read. 15 | 16 | Inputs: 17 | * Read file 18 | * minimap2 PAF 19 | 20 | Output: 21 | * tsv file with these columns: length, identity, relative length 22 | 23 | If less than half of a read aligns, it is deemed unaligned and given an identity of 0. If more than 24 | half aligns, only the aligned parts are used to determined the read identity. 25 | 26 | Relative length is included to see if the reads are systematically too short or too long. 27 | """ 28 | 29 | 30 | import collections 31 | import gzip 32 | import os 33 | import statistics 34 | import sys 35 | 36 | 37 | def main(): 38 | read_filename = sys.argv[1] 39 | paf_filename = sys.argv[2] 40 | 41 | read_lengths = get_read_lengths(read_filename) 42 | read_names = sorted(read_lengths.keys()) 43 | read_alignments = load_alignments(paf_filename, read_lengths) 44 | 45 | print('\t'.join(['Name', 'Length', 'Identity', 'Relative length'])) 46 | for read_num, read_name in enumerate(read_names): 47 | read_length = read_lengths[read_name] 48 | alignments = read_alignments[read_name] 49 | identity_by_base = [0.0] * read_length 50 | total_read_length, total_ref_length = 0, 0 51 | 52 | for read_start, read_end, ref_start, ref_end, identity in alignments: 53 | for i in range(read_start, read_end): 54 | if identity > identity_by_base[i]: 55 | identity_by_base[i] = identity 56 | total_read_length += read_end - read_start 57 | total_ref_length += ref_end - ref_start 58 | 59 | # If less than half the read aligned, then we call it an unaligned read. 60 | if identity_by_base.count(0.0) > read_length / 2.0: 61 | whole_read_identity = 0.0 62 | 63 | # Otherwise, the read's identity is the average of the aligned parts. 64 | else: 65 | whole_read_identity = statistics.mean([x for x in identity_by_base if x > 0.0]) 66 | 67 | if whole_read_identity > 0.0: 68 | relative_length = '%.5f' % (100.0 * total_read_length / total_ref_length) 69 | else: 70 | relative_length = '' 71 | 72 | print('{}\t{}\t{:.5f}\t{}'.format(read_name, read_length, whole_read_identity, relative_length)) 73 | print_progress(read_num, len(read_names)) 74 | print('\n', file=sys.stderr) 75 | 76 | 77 | def print_progress(done_count, total_count): 78 | print('\r{:,} / {:,} reads complete'.format(done_count+1, total_count), 79 | end='', flush=True, file=sys.stderr) 80 | 81 | 82 | def load_alignments(paf_filename, read_lengths): 83 | print('Loading alignments...', end='', flush=True, file=sys.stderr) 84 | read_alignments = collections.defaultdict(list) 85 | with open(paf_filename, 'rt') as paf: 86 | for line in paf: 87 | paf_parts = line.strip().split('\t') 88 | if len(paf_parts) < 11: 89 | continue 90 | read_name = paf_parts[0] 91 | read_length = int(paf_parts[1]) 92 | assert read_length == read_lengths[read_name] 93 | read_start = int(paf_parts[2]) 94 | read_end = int(paf_parts[3]) 95 | ref_start = int(paf_parts[7]) 96 | ref_end = int(paf_parts[8]) 97 | identity = 100.0 * int(paf_parts[9]) / int(paf_parts[10]) 98 | read_alignments[read_name].append((read_start, read_end, ref_start, ref_end, identity)) 99 | print(' done', file=sys.stderr) 100 | return read_alignments 101 | 102 | 103 | def get_compression_type(filename): 104 | """ 105 | Attempts to guess the compression (if any) on a file using the first few bytes. 106 | http://stackoverflow.com/questions/13044562 107 | """ 108 | magic_dict = {'gz': (b'\x1f', b'\x8b', b'\x08'), 109 | 'bz2': (b'\x42', b'\x5a', b'\x68'), 110 | 'zip': (b'\x50', b'\x4b', b'\x03', b'\x04')} 111 | max_len = max(len(x) for x in magic_dict) 112 | 113 | unknown_file = open(filename, 'rb') 114 | file_start = unknown_file.read(max_len) 115 | unknown_file.close() 116 | compression_type = 'plain' 117 | for filetype, magic_bytes in magic_dict.items(): 118 | if file_start.startswith(magic_bytes): 119 | compression_type = filetype 120 | if compression_type == 'bz2': 121 | sys.exit('Error: cannot use bzip2 format - use gzip instead') 122 | if compression_type == 'zip': 123 | sys.exit('Error: cannot use zip format - use gzip instead') 124 | return compression_type 125 | 126 | 127 | def get_sequence_file_type(filename): 128 | if not os.path.isfile(filename): 129 | sys.exit('Error: could not find ' + filename) 130 | if get_compression_type(filename) == 'gz': 131 | open_func = gzip.open 132 | else: # plain text 133 | open_func = open 134 | with open_func(filename, 'rt') as seq_file: 135 | try: 136 | first_char = seq_file.read(1) 137 | except UnicodeDecodeError: 138 | first_char = '' 139 | if first_char == '>': 140 | return 'FASTA' 141 | elif first_char == '@': 142 | return 'FASTQ' 143 | else: 144 | raise ValueError('File is neither FASTA or FASTQ') 145 | 146 | 147 | def get_read_lengths(filename): 148 | print('Loading read lengths...', end='', flush=True, file=sys.stderr) 149 | try: 150 | file_type = get_sequence_file_type(filename) 151 | if file_type == 'FASTA': 152 | return get_fasta_lengths(filename) 153 | else: # FASTQ 154 | return get_fastq_lengths(filename) 155 | except IndexError: 156 | sys.exit('\nError: ' + filename + ' could not be parsed - is it formatted correctly?') 157 | 158 | 159 | def get_fasta_lengths(fasta_filename): 160 | if get_compression_type(fasta_filename) == 'gz': 161 | open_func = gzip.open 162 | else: # plain text 163 | open_func = open 164 | read_lengths = {} 165 | with open_func(fasta_filename, 'rt') as fasta_file: 166 | name = '' 167 | sequence = [] 168 | for line in fasta_file: 169 | line = line.strip() 170 | if not line: 171 | continue 172 | if line[0] == '>': # Header line = start of new contig 173 | if name: 174 | read_lengths[name.split()[0]] = len(''.join(sequence)) 175 | sequence = [] 176 | name = line[1:] 177 | else: 178 | sequence.append(line) 179 | if name: 180 | read_lengths[name.split()[0]] = len(''.join(sequence)) 181 | print(' done', file=sys.stderr) 182 | return read_lengths 183 | 184 | 185 | def get_fastq_lengths(fastq_filename): 186 | if get_compression_type(fastq_filename) == 'gz': 187 | open_func = gzip.open 188 | else: # plain text 189 | open_func = open 190 | read_lengths = {} 191 | with open_func(fastq_filename, 'rt') as fastq: 192 | for line in fastq: 193 | name = line.strip()[1:].split()[0] 194 | sequence = next(fastq).strip() 195 | next(fastq) 196 | next(fastq) 197 | read_lengths[name] = len(sequence) 198 | print(' done', file=sys.stderr) 199 | return read_lengths 200 | 201 | 202 | if __name__ == '__main__': 203 | main() 204 | -------------------------------------------------------------------------------- /analysis_scripts/rotate_reference.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script takes a one-contig circular assembly as input and produces a rotated version of the 15 | assembly (with a new starting point). 16 | """ 17 | 18 | 19 | import random 20 | import sys 21 | 22 | 23 | def main(): 24 | ref = load_fasta(sys.argv[1]) 25 | random.seed(int(sys.argv[2])) 26 | assert len(ref) == 1 27 | ref_seq = ref[0][1] 28 | assert len(ref_seq) > 1000000 29 | if random.random() < 0.5: 30 | ref_seq = reverse_complement(ref_seq) 31 | new_start_pos = random.randint(0, len(ref_seq) - 1) 32 | ref_seq = ref_seq[new_start_pos:] + ref_seq[:new_start_pos] 33 | print('>reference circular=true') 34 | print(ref_seq) 35 | 36 | 37 | def load_fasta(fasta_filename): 38 | fasta_seqs = [] 39 | with open(fasta_filename, 'rt') as fasta_file: 40 | name = '' 41 | sequence = [] 42 | for line in fasta_file: 43 | line = line.strip() 44 | if not line: 45 | continue 46 | if line[0] == '>': # Header line = start of new contig 47 | if name: 48 | fasta_seqs.append((name.split()[0], ''.join(sequence), name)) 49 | sequence = [] 50 | name = line[1:] 51 | else: 52 | sequence.append(line) 53 | if name: 54 | fasta_seqs.append((name.split()[0], ''.join(sequence), name)) 55 | return fasta_seqs 56 | 57 | 58 | REV_COMP_DICT = {'A': 'T', 'T': 'A', 'G': 'C', 'C': 'G', 59 | 'a': 't', 't': 'a', 'g': 'c', 'c': 'g', 60 | 'R': 'Y', 'Y': 'R', 'S': 'S', 'W': 'W', 61 | 'K': 'M', 'M': 'K', 'B': 'V', 'V': 'B', 62 | 'D': 'H', 'H': 'D', 'N': 'N', 63 | 'r': 'y', 'y': 'r', 's': 's', 'w': 'w', 64 | 'k': 'm', 'm': 'k', 'b': 'v', 'v': 'b', 65 | 'd': 'h', 'h': 'd', 'n': 'n', 66 | '.': '.', '-': '-', '?': '?'} 67 | 68 | 69 | def complement_base(base): 70 | try: 71 | return REV_COMP_DICT[base] 72 | except KeyError: 73 | return 'N' 74 | 75 | 76 | def reverse_complement(seq): 77 | return ''.join([complement_base(x) for x in seq][::-1]) 78 | 79 | 80 | if __name__ == '__main__': 81 | main() 82 | -------------------------------------------------------------------------------- /analysis_scripts/shred_assembly.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script takes an assembly as input and produces an output of 'reads': the assembly chopped into 15 | overlapping pieces. It is used in assembly polishing to turn individual Racon-polished assemblies 16 | into 'reads' which can then be used as input for a final Racon polish. 17 | """ 18 | 19 | import random 20 | import sys 21 | import uuid 22 | 23 | 24 | def main(): 25 | assembly = load_fasta(sys.argv[1]) 26 | random.seed(int(sys.argv[2])) 27 | read_length = int(sys.argv[3]) 28 | assert len(assembly) == 1 29 | assembly_seq = assembly[0][1] 30 | assert len(assembly_seq) > 1000000 31 | 32 | # Add a bit of overlap so reads can span the junction. 33 | assembly_seq = assembly_seq + assembly_seq[:read_length] 34 | 35 | read_start = 0 36 | read_end = read_length 37 | while read_end <= len(assembly_seq): 38 | read_seq = assembly_seq[read_start:read_end] 39 | if random.random() < 0.5: 40 | read_seq = reverse_complement(read_seq) 41 | read_qual = ''.join([chr(random.randint(65, 75)) for _ in range(read_length)]) 42 | print('@' + str(uuid.uuid4())) 43 | print(read_seq) 44 | print('+') 45 | print(read_qual) 46 | read_start += read_length // 3 47 | read_end += read_length // 3 48 | 49 | 50 | def load_fasta(fasta_filename): 51 | fasta_seqs = [] 52 | with open(fasta_filename, 'rt') as fasta_file: 53 | name = '' 54 | sequence = [] 55 | for line in fasta_file: 56 | line = line.strip() 57 | if not line: 58 | continue 59 | if line[0] == '>': # Header line = start of new contig 60 | if name: 61 | fasta_seqs.append((name.split()[0], ''.join(sequence), name)) 62 | sequence = [] 63 | name = line[1:] 64 | else: 65 | sequence.append(line) 66 | if name: 67 | fasta_seqs.append((name.split()[0], ''.join(sequence), name)) 68 | return fasta_seqs 69 | 70 | 71 | REV_COMP_DICT = {'A': 'T', 'T': 'A', 'G': 'C', 'C': 'G', 72 | 'a': 't', 't': 'a', 'g': 'c', 'c': 'g', 73 | 'R': 'Y', 'Y': 'R', 'S': 'S', 'W': 'W', 74 | 'K': 'M', 'M': 'K', 'B': 'V', 'V': 'B', 75 | 'D': 'H', 'H': 'D', 'N': 'N', 76 | 'r': 'y', 'y': 'r', 's': 's', 'w': 'w', 77 | 'k': 'm', 'm': 'k', 'b': 'v', 'v': 'b', 78 | 'd': 'h', 'h': 'd', 'n': 'n', 79 | '.': '.', '-': '-', '?': '?'} 80 | 81 | 82 | def complement_base(base): 83 | try: 84 | return REV_COMP_DICT[base] 85 | except KeyError: 86 | return 'N' 87 | 88 | 89 | def reverse_complement(seq): 90 | return ''.join([complement_base(x) for x in seq][::-1]) 91 | 92 | 93 | if __name__ == '__main__': 94 | main() 95 | -------------------------------------------------------------------------------- /basecalling_scripts/albacore_basecalling.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | # https://github.com/rrwick/Basecalling-comparison 5 | 6 | # This program is free software: you can redistribute it and/or modify it under the terms of the 7 | # GNU General Public License as published by the Free Software Foundation, either version 3 of the 8 | # License, or (at your option) any later version. This program is distributed in the hope that it 9 | # will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 10 | # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You 11 | # should have received a copy of the GNU General Public License along with this program. If not, 12 | # see . 13 | 14 | # This script will execute each version of Albacore on the reads. 15 | 16 | 17 | # Edit the following paths before running, as appropriate for your environment: 18 | fast5_dir=/path/to/fast5s # all fast5s must be directly in this directory (i.e. not nested in subdirectories) 19 | output_prefix=/path/to/basecalling_output # Albacore output directories and consolidated fastqs will go in this directory 20 | albacore_installers=/path/to/albacore_installers # must contain the whl/deb files for the Albacore versions - this script installs each version before running it 21 | fast5_to_fastq=/path/to/fastq_to_fastq.py # path to fastq_to_fastq.py script (from https://github.com/rrwick/Fast5-to-Fastq) - required for older versions of Albacore 22 | 23 | 24 | cd $output_prefix 25 | 26 | # The most recent versions of Albacore: 27 | for v in 2.1.0 2.1.1 2.1.1 2.1.2 2.1.3 2.1.5 2.1.6 2.1.7 2.1.9 2.1.10 2.2.1 2.2.2 2.2.4 2.2.6 2.2.7 2.3.0 2.3.1 2.3.2 2.3.3 2.3.4; do 28 | pip3 install "$albacore_installers"/ont_albacore-"$v"-cp35-cp35m-manylinux1_x86_64.whl 29 | out_dir="$output_prefix"/albacore_v"$v" 30 | /usr/bin/time -v -o albacore_v"$v".time read_fast5_basecaller.py -f FLO-MIN106 -k SQK-LSK108 -i $fast5_dir -t 12 -s $out_dir -o fastq --disable_filtering --disable_pings 31 | cat "$out_dir"/workspace/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > albacore_v"$v".fastq 32 | done 33 | 34 | # These versions don't have --disable_pings: 35 | for v in 2.0.0 2.0.1 2.0.2; do 36 | pip3 install "$albacore_installers"/ont_albacore-"$v"-cp35-cp35m-manylinux1_x86_64.whl 37 | out_dir="$output_prefix"/albacore_v"$v" 38 | /usr/bin/time -v -o albacore_v"$v".time read_fast5_basecaller.py -f FLO-MIN106 -k SQK-LSK108 -i $fast5_dir -t 12 -s $out_dir -o fastq --disable_filtering 39 | cat "$out_dir"/workspace/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > albacore_v"$v".fastq 40 | done 41 | 42 | # These versions don't have --disable_filtering: 43 | for v in 1.2.0 1.2.1 1.2.2 1.2.3 1.2.4 1.2.5 1.2.6 1.3.1; do 44 | pip3 install "$albacore_installers"/ont_albacore-"$v"-cp35-cp35m-manylinux1_x86_64.whl 45 | out_dir="$output_prefix"/albacore_v"$v" 46 | /usr/bin/time -v -o albacore_v"$v".time read_fast5_basecaller.py -f FLO-MIN106 -k SQK-LSK108 -i $fast5_dir -t 12 -s $out_dir -o fastq 47 | cat "$out_dir"/workspace/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > albacore_v"$v".fastq 48 | done 49 | 50 | # These versions mess up the fastq files (extra line break) which requires fixing: 51 | for v in 1.1.0 1.1.1 1.1.2; do 52 | pip3 install "$albacore_installers"/ont_albacore-"$v"-cp35-cp35m-manylinux1_x86_64.whl 53 | out_dir="$output_prefix"/albacore_v"$v" 54 | /usr/bin/time -v -o albacore_v"$v".time read_fast5_basecaller.py -f FLO-MIN106 -k SQK-LSK108 -i $fast5_dir -t 12 -s $out_dir -o fastq 55 | cat "$out_dir"/workspace/*.fastq | paste - - - - - | sort -k1,1 -t " " | tr "\t" "\n" > albacore_v"$v".fastq 56 | done 57 | 58 | # These versions can't output to fastq: 59 | for v in 1.0.1 1.0.2 1.0.3 1.0.4; do 60 | pip3 install "$albacore_installers"/ont_albacore-"$v"-cp35-cp35m-manylinux1_x86_64.whl 61 | out_dir="$output_prefix"/albacore_v"$v" 62 | /usr/bin/time -v -o albacore_v"$v".time read_fast5_basecaller.py -f FLO-MIN106 -k SQK-LSK108 -i $fast5_dir -t 12 -s $out_dir 63 | ~/Fast5-to-Fastq/fast5_to_fastq.py "$out_dir"/workspace | paste - - - - | sed 's/_Basecall_1D_template/ Basecall_1D_template/' | sort -k1,1 -t " " | tr "\t" "\n" > albacore_v"$v".fastq 64 | done 65 | 66 | # These versions don't have flowcell and kit options (need to specify config): 67 | for v in 0.8.2 0.8.4 0.9.1; do 68 | pip3 install "$albacore_installers"/ont_albacore-"$v"-cp35-cp35m-manylinux1_x86_64.whl 69 | out_dir="$output_prefix"/albacore_v"$v" 70 | /usr/bin/time -v -o albacore_v"$v".time read_fast5_basecaller.py -c FLO-MIN106_LSK108_linear.cfg -i $fast5_dir -t 12 -s $out_dir 71 | "$fast5_to_fastq" "$out_dir"/workspace | paste - - - - | sed 's/_Basecall_1D_template/ Basecall_1D_template/' | sort -k1,1 -t " " | tr "\t" "\n" > albacore_v"$v".fastq 72 | done 73 | 74 | # 0.7.5 is the only version without a Python wheel: 75 | v=0.7.5 76 | apt install "$albacore_installers"/python3-ont-albacore_"$v"-1-xenial_amd64.deb 77 | out_dir="$output_prefix"/albacore_v"$v" 78 | /usr/bin/time -v -o albacore_v"$v".time read_fast5_basecaller.py -c FLO-MIN106_LSK108_linear.cfg -i $fast5_dir -t 12 -s $out_dir 79 | "$fast5_to_fastq" "$out_dir"/workspace | paste - - - - | sed 's/_Basecall_1D_template/ Basecall_1D_template/' | sort -k1,1 -t " " | tr "\t" "\n" > albacore_v"$v".fastq 80 | -------------------------------------------------------------------------------- /basecalling_scripts/chiron_basecalling.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | # https://github.com/rrwick/Basecalling-comparison 5 | 6 | # This program is free software: you can redistribute it and/or modify it under the terms of the 7 | # GNU General Public License as published by the Free Software Foundation, either version 3 of the 8 | # License, or (at your option) any later version. This program is distributed in the hope that it 9 | # will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 10 | # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You 11 | # should have received a copy of the GNU General Public License along with this program. If not, 12 | # see . 13 | 14 | # This script will execute each version of Chiron on the reads. Chiron takes a long time to run, 15 | # so I ran it on smaller batches of files so I could start/stop the basecalling as needed. 16 | 17 | 18 | # Edit the following paths before running, as appropriate for your environment: 19 | fast5_dir=/path/to/fast5s_100_read_dirs # should contain numbered subdirectories (000 to 151), each containing fast5 files 20 | output_prefix=/path/to/basecalling_output # Chiron output fastqs will go in this directory 21 | chiron_dirs=/path/to/Chiron # should contain a subdirectory for each version of Chiron, e.g. Chiron-v0.4.2 22 | 23 | # TensorFlow/CUDA requirements might change between Chiron versions: 24 | cuda_bin_path=/path/to/cuda-8.0/bin 25 | cuda_lib_path=/path/to/cuda-8.0/lib64 26 | 27 | 28 | cd $output_prefix 29 | 30 | # Versions 0.4, 0.4.1 and 0.4.2 all seem to produce the same reads, so I'm only running v0.4.2. 31 | v=0.4.2 32 | for d in {000..151}; do 33 | out_dir="$output_prefix"/chiron_v"$v"_"$d" 34 | out_file=chiron_v"$v"_"$d".fastq 35 | time_file=chiron_v"$v"_"$d".time 36 | if [ ! -f $out_file ]; then 37 | rm -rf $out_dir 38 | rm -f $time_file 39 | /usr/bin/time -v -o $time_file python "$chiron_dirs"/Chiron-"$v"/chiron/entry.py call -i "$fast5_dir"/"$d" -o $out_dir || break 40 | cat "$out_dir"/result/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > $out_file 41 | fi 42 | done 43 | cat chiron_v"$v"_*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > chiron_v"$v".fastq 44 | cat chiron_v"$v"_*.time > chiron_v"$v".time 45 | 46 | # Older versions need TensorFlow 1.0.1, which needs CUDA 8.0. 47 | export PATH="$cuda_bin_path":"$PATH" 48 | export LD_LIBRARY_PATH="$cuda_lib_path":"$LD_LIBRARY_PATH" 49 | 50 | for v in 0.3 0.2; do 51 | for d in "{000..151}"; do 52 | out_dir="$output_prefix"/chiron_v"$v"_"$d" 53 | out_file=chiron_v"$v"_"$d".fastq 54 | time_file=chiron_v"$v"_"$d".time 55 | if [ ! -f $out_file ]; then 56 | rm -rf $out_dir 57 | rm -f $time_file 58 | /usr/bin/time -v -o $time_file python "$chiron_dirs"/Chiron-"$v"/chiron/entry.py call -i "$fast5_dir"/"$d" -o $out_dir || break 59 | cat "$out_dir"/result/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > $out_file 60 | fi 61 | done 62 | cat chiron_v"$v"_*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > chiron_v"$v".fastq 63 | cat chiron_v"$v"_*.time > chiron_v"$v".time 64 | done 65 | -------------------------------------------------------------------------------- /basecalling_scripts/flappie_basecalling.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | # https://github.com/rrwick/Basecalling-comparison 5 | 6 | # This program is free software: you can redistribute it and/or modify it under the terms of the 7 | # GNU General Public License as published by the Free Software Foundation, either version 3 of the 8 | # License, or (at your option) any later version. This program is distributed in the hope that it 9 | # will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 10 | # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You 11 | # should have received a copy of the GNU General Public License along with this program. If not, 12 | # see . 13 | 14 | # This script will execute each version of Flappie on the reads. 15 | 16 | 17 | # Edit the following paths before running, as appropriate for your environment: 18 | fast5_dir=/path/to/fast5s # all fast5s must be directly in this directory (i.e. not nested in subdirectories) 19 | output_prefix=/path/to/basecalling_output # Flappie output fastqs will go in this directory 20 | binaries=/path/to/binaries # should contain Flappie binaries named with the version number, e.g. flappie-v1.1 21 | 22 | 23 | cd $output_prefix 24 | export OPENBLAS_NUM_THREADS=1 25 | 26 | for v in 1.0 1.1; do 27 | out_dir="$output_prefix"/flappie_v"$v" 28 | flappie="$binaries"/flappie-"$v" 29 | 30 | # I can't use time for Flappie because I run it in separate processes with the parallel 31 | # command, so I just run date before and after to get the total time. 32 | date 33 | find $fast5_dir -name \*.fast5 | parallel -P 12 -X $flappie --model r941_native > flappie_v"$v".fastq 34 | date 35 | done 36 | -------------------------------------------------------------------------------- /basecalling_scripts/guppy_basecalling.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | # https://github.com/rrwick/Basecalling-comparison 5 | 6 | # This program is free software: you can redistribute it and/or modify it under the terms of the 7 | # GNU General Public License as published by the Free Software Foundation, either version 3 of the 8 | # License, or (at your option) any later version. This program is distributed in the hope that it 9 | # will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 10 | # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You 11 | # should have received a copy of the GNU General Public License along with this program. If not, 12 | # see . 13 | 14 | # This script will execute each version of Guppy on the reads. In order to also use the 15 | # custom-trained models, the model files(holtlab_kp_r9.4_r9.4.1_nov_2018.jsn and 16 | # holtlab_kp_big_r9.4_r9.4.1_nov_2018.jsn) must be put into Guppy's data directory. 17 | 18 | 19 | # Edit the following paths before running, as appropriate for your environment: 20 | fast5_dir=/path/to/fast5s # all fast5s must be directly in this directory (i.e. not nested in subdirectories) 21 | output_prefix=/path/to/basecalling_output # Guppy output directories and consolidated fastqs will go in this directory 22 | guppy_installers=/path/to/guppy_installers # must contain the deb files for the Guppy versions - this script installs each version before running it 23 | 24 | 25 | cd $output_prefix 26 | 27 | # For the most recent versions of Guppy, I'm using both the default and flip-flop models: 28 | for v in 2.1.3 2.2.3; do 29 | apt install "$guppy_installers"/ont-guppy_"$v"-1~xenial_amd64.deb 30 | out_dir="$output_prefix"/guppy_v"$v" 31 | /usr/bin/time -v -o guppy_v"$v".time guppy_basecaller --config dna_r9.4.1_450bps.cfg --device auto -i $fast5_dir -t 12 -s $out_dir 32 | cat "$out_dir"/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > guppy_v"$v".fastq 33 | out_dir="$output_prefix"/guppy_v"$v"_flipflop 34 | /usr/bin/time -v -o guppy_v"$v"_flipflop.time guppy_basecaller --config dna_r9.4.1_450bps_flipflop.cfg --device auto -i $fast5_dir -t 12 -s $out_dir 35 | cat "$out_dir"/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > guppy_v"$v"_flipflop.fastq 36 | done 37 | 38 | # For only the most recent version of Guppy, I also tried our custom-trained models: 39 | v=2.2.3 40 | out_dir="$output_prefix"/guppy_v"$v"_custom_kp_model 41 | /usr/bin/time -v -o guppy_v"$v"_custom_kp_model.time guppy_basecaller --model_file holtlab_kp_r9.4_r9.4.1_nov_2018.jsn --config dna_r9.4.1_450bps.cfg --device auto -i $fast5_dir -t 12 -s $out_dir 42 | cat "$out_dir"/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > guppy_v"$v"_custom_kp_model.fastq 43 | out_dir="$output_prefix"/guppy_v"$v"_custom_kp_big_net_model 44 | /usr/bin/time -v -o guppy_v"$v"_custom_kp_big_net_model.time guppy_basecaller --model_file holtlab_kp_big_r9.4_r9.4.1_nov_2018.jsn --config dna_r9.4.1_450bps.cfg -i $fast5_dir -t 12 -s $out_dir 45 | cat "$out_dir"/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > guppy_v"$v"_custom_kp_big_net_model.fastq 46 | 47 | 48 | for v in 1.5.1 1.6.0 1.8.1 1.8.3 1.8.5; do 49 | apt install "$guppy_installers"/ont-guppy_"$v"-1~xenial_amd64.deb 50 | out_dir="$output_prefix"/guppy_v"$v" 51 | /usr/bin/time -v -o guppy_v"$v".time guppy_basecaller --config dna_r9.4_450bps.cfg --device auto -i $fast5_dir -t 12 -s $out_dir 52 | cat "$out_dir"/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > guppy_v"$v".fastq 53 | done 54 | 55 | # I couldn't make v1.4.3 run on the GPU so I used the CPU instead: 56 | v=1.4.3 57 | apt install "$guppy_installers"/ont-guppy_"$v"-1~xenial_amd64.deb 58 | out_dir="$output_prefix"/guppy_v"$v" 59 | /usr/bin/time -v -o guppy_v"$v".time guppy_basecaller --config dna_r9.4_450bps.cfg -i $fast5_dir -t 12 -s $out_dir 60 | cat "$out_dir"/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > guppy_v"$v".fastq 61 | 62 | v=0.5.4 63 | apt install "$guppy_installers"/ont-guppy_"$v"-1~xenial_amd64.deb 64 | out_dir="$output_prefix"/guppy_v"$v" 65 | /usr/bin/time -v -o guppy_v"$v".time guppy_basecaller --config dna_r9.4_450bps.cfg --device cuda:00000000:65:00.0 -i $fast5_dir -t 12 -s $out_dir 66 | cat "$out_dir"/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > guppy_v"$v".fastq 67 | 68 | # I couldn't make v0.3.0 run on the GPU so I used the CPU instead: 69 | v=0.3.0 70 | apt install "$guppy_installers"/ont-guppy_"$v"-1~xenial_amd64.deb 71 | out_dir="$output_prefix"/guppy_v"$v" 72 | /usr/bin/time -v -o guppy_v"$v".time guppy --config dna_r9.4_450bps.cfg --device cpu -i $fast5_dir -s $out_dir 73 | cat "$out_dir"/*.fastq | paste - - - - | sort -k1,1 -t " " | tr "\t" "\n" > guppy_v"$v".fastq 74 | -------------------------------------------------------------------------------- /basecalling_scripts/scrappie_basecalling.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | # https://github.com/rrwick/Basecalling-comparison 5 | 6 | # This program is free software: you can redistribute it and/or modify it under the terms of the 7 | # GNU General Public License as published by the Free Software Foundation, either version 3 of the 8 | # License, or (at your option) any later version. This program is distributed in the hope that it 9 | # will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 10 | # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You 11 | # should have received a copy of the GNU General Public License along with this program. If not, 12 | # see . 13 | 14 | # This script will execute each version of Scrappie on the reads. 15 | 16 | 17 | # Edit the following paths before running, as appropriate for your environment: 18 | fast5_dir=/path/to/fast5s # all fast5s must be directly in this directory (i.e. not nested in subdirectories) 19 | output_prefix=/path/to/basecalling_output # Scrappie output fastas will go in this directory 20 | binaries=/path/to/binaries # should contain Scrappie binaries named with the version number, e.g. scrappie-v1.4.1 21 | 22 | 23 | cd $output_prefix 24 | export OMP_NUM_THREADS=$(nproc) 25 | export OPENBLAS_NUM_THREADS=1 26 | 27 | # For recent versions of Scrappie, I ran both raw and event basecalling: 28 | for v in 1.4.1 1.4.0 1.3.2 1.3.1 1.3.0 1.2.0 1.1.1 1.1.0; do 29 | out_dir="$output_prefix"/scrappie_v"$v" 30 | scrappie="$binaries"/scrappie-v"$v" 31 | /usr/bin/time -v -o scrappie_raw_v"$v".time $scrappie raw $fast5_dir > scrappie_raw_v"$v".fasta 32 | /usr/bin/time -v -o scrappie_events_v"$v".time $scrappie events $fast5_dir > scrappie_events_v"$v".fasta 33 | done 34 | 35 | # These versions can't call events on their own - they rely on events already 36 | # being present, e.g. from Albacore. I therefore skipped scrappie events 37 | # (because it's not a stand-alone basecaller) and just ran scrappie raw. 38 | for v in 1.0.0 0.3.2 0.3.1 0.3.0; do 39 | out_dir="$output_prefix"/scrappie_v"$v" 40 | scrappie="$binaries"/scrappie-v"$v" 41 | /usr/bin/time -v -o scrappie_raw_v"$v".time $scrappie raw $fast5_dir > scrappie_raw_v"$v".fasta 42 | done 43 | 44 | 45 | # Versions earlier than 0.3.0 can only do event-based basecalling, so I'm skipping all of them. 46 | -------------------------------------------------------------------------------- /images/logo-bottom.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rrwick/Basecalling-comparison/40c4802b3e78d262f0d6f07851e4e648bff39670/images/logo-bottom.png -------------------------------------------------------------------------------- /images/logo-top.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rrwick/Basecalling-comparison/40c4802b3e78d262f0d6f07851e4e648bff39670/images/logo-top.png -------------------------------------------------------------------------------- /sloika_training_scripts/filter_reads.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script filters fast5 reads based on their alignment to reference contigs. 15 | The reads which pass filtering should be suitable for Sloika training. 16 | """ 17 | 18 | import argparse 19 | import glob 20 | import os 21 | import re 22 | import shutil 23 | import sys 24 | 25 | 26 | def get_arguments(): 27 | parser = argparse.ArgumentParser(description='Trim fast5 files at the signal level') 28 | 29 | parser.add_argument('--min_basecalled_length', type=int, required=False, default=5000, 30 | help='Reads will fail if basecalled to shorter than this amount') 31 | parser.add_argument('--max_unaligned_bases', type=int, required=False, default=100, 32 | help='Reads will fail if they have more than this many bases unaligned') 33 | parser.add_argument('--max_window_indels', type=float, required=False, default=0.8, 34 | help='Reads will fail if they have any CIGAR window with more than this ' 35 | 'fraction of indels') 36 | parser.add_argument('--window_size', type=int, required=False, default=25, 37 | help='Window size for CIGAR indel check') 38 | 39 | parser.add_argument('in_fast5_dir', type=str, 40 | help='Directory containing trimmed fast5 files') 41 | parser.add_argument('seq_summary', type=str, 42 | help='Albacore/Guppy\'s sequencing_summary.txt file for the basecalling ' 43 | 'of the trimmed fast5 files') 44 | parser.add_argument('reference', type=str, 45 | help='Reference FASTA (used to generate alignment)') 46 | parser.add_argument('paf_alignment', type=str, 47 | help='Minimap2 alignment of basecalled reads to reference contigs') 48 | parser.add_argument('out_fast5_dir', type=str, 49 | help='Output directory of passing fast5 files') 50 | parser.add_argument('out_ref', type=str, 51 | help='Output file per-read reference sequences') 52 | 53 | args = parser.parse_args() 54 | return args 55 | 56 | 57 | def main(): 58 | args = get_arguments() 59 | filename_to_read_id = read_seq_summary(args.seq_summary) 60 | read_id_to_alignment_info = read_paf(args.paf_alignment) 61 | make_output_dir(args.out_fast5_dir) 62 | references = load_fasta(args.reference) 63 | 64 | with open(args.out_ref, 'w') as out_ref: 65 | for fast5_file in glob.iglob(args.in_fast5_dir + '/**/*.fast5', recursive=True): 66 | print() 67 | print(fast5_file) 68 | filename = fast5_file.rpartition('/')[2] 69 | read_id = filename_to_read_id[filename] 70 | print(' ID: {}'.format(read_id)) 71 | 72 | try: 73 | read_length, read_start, read_end, cigar, _, strand, contig_name, contig_start, contig_end = read_id_to_alignment_info[read_id] 74 | except KeyError: 75 | print(' FAIL due to no alignment') 76 | continue 77 | 78 | print(' Length: {:,} bp'.format(read_length)) 79 | if read_length < args.min_basecalled_length: 80 | print(' FAIL due to short length') 81 | continue 82 | 83 | unaligned_bases = read_start + (read_length - read_end) 84 | print(' Unaligned: {:,} bp'.format(unaligned_bases)) 85 | if unaligned_bases > args.max_unaligned_bases: 86 | print(' FAIL due to too much unaligned') 87 | continue 88 | 89 | expanded_cigar = get_expanded_cigar(cigar) 90 | worst_window_indel_fraction = 0.0 91 | for i in range(len(expanded_cigar) - args.window_size): 92 | cigar_window = expanded_cigar[i:i+args.window_size] 93 | window_indel_fraction = (cigar_window.count('I') + cigar_window.count('D')) / args.window_size 94 | worst_window_indel_fraction = max(worst_window_indel_fraction, window_indel_fraction) 95 | print(' Worst window indels: {:.4f}'.format(worst_window_indel_fraction)) 96 | if worst_window_indel_fraction > args.max_window_indels: 97 | print(' FAIL due to bad window indels') 98 | continue 99 | 100 | print(' PASS') 101 | new_file = '{}/{}'.format(args.out_fast5_dir, filename) 102 | print(' making a copy here: {}'.format(new_file)) 103 | if os.path.exists(new_file): 104 | print() 105 | sys.exit('Error: {} already exists'.format(new_file)) 106 | shutil.copyfile(fast5_file, new_file) 107 | 108 | print(' getting reference sequence from {} ({}-{}, {} strand)'.format(contig_name, contig_start, contig_end, strand)) 109 | ref_header = '>' + os.path.basename(os.path.splitext(fast5_file)[0]) 110 | ref_seq = references[contig_name][contig_start:contig_end] 111 | if strand == '-': 112 | ref_seq = reverse_complement(ref_seq) 113 | 114 | out_ref.write(ref_header) 115 | out_ref.write('\n') 116 | out_ref.write(ref_seq) 117 | out_ref.write('\n') 118 | 119 | 120 | def read_seq_summary(seq_summary_filename): 121 | filename_to_read_id = {} 122 | with open(seq_summary_filename, 'r') as seq_summary: 123 | for line in seq_summary: 124 | parts = line.split('\t') 125 | if parts[0] == 'filename': # header line 126 | continue 127 | filename, read_id = parts[0], parts[1] 128 | filename_to_read_id[filename] = read_id 129 | return filename_to_read_id 130 | 131 | 132 | def read_paf(paf_filename): 133 | read_id_to_alignment_info = {} 134 | with open(paf_filename, 'r') as paf_file: 135 | for line in paf_file: 136 | parts = line.split('\t') 137 | read_id = parts[0] 138 | read_length = int(parts[1]) 139 | read_start = int(parts[2]) 140 | read_end = int(parts[3]) 141 | strand = parts[4] 142 | contig_name = parts[5] 143 | contig_start = int(parts[7]) 144 | contig_end = int(parts[8]) 145 | cigar, alignment_score = None, None 146 | for part in parts: 147 | if part.startswith('cg:Z:'): 148 | cigar = part[5:] 149 | if part.startswith('AS:i:'): 150 | alignment_score = int(part[5:]) 151 | assert cigar is not None and alignment_score is not None 152 | alignment_info = read_length, read_start, read_end, cigar, alignment_score, strand, contig_name, contig_start, contig_end 153 | 154 | # If there are multiple alignments for a read, we keep the one with the best score. 155 | if read_id in read_id_to_alignment_info: 156 | _, _, _, _, existing_score, _, _, _, _ = read_id_to_alignment_info[read_id] 157 | if alignment_score > existing_score: 158 | read_id_to_alignment_info[read_id] = alignment_info 159 | else: 160 | read_id_to_alignment_info[read_id] = alignment_info 161 | return read_id_to_alignment_info 162 | 163 | 164 | def get_expanded_cigar(cigar): 165 | expanded_cigar = [] 166 | cigar_parts = re.findall(r'\d+\w', cigar) 167 | for cigar_part in cigar_parts: 168 | num = int(cigar_part[:-1]) 169 | letter = cigar_part[-1] 170 | if letter == 'M' or letter == 'I' or letter == 'D': 171 | expanded_cigar.append(letter * num) 172 | return ''.join(expanded_cigar) 173 | 174 | 175 | def make_output_dir(out_dir): 176 | if os.path.exists(out_dir): 177 | sys.exit('Error: output directory already exists') 178 | os.makedirs(out_dir) 179 | 180 | 181 | def load_fasta(fasta_filename): 182 | fasta_seqs = {} 183 | with open(fasta_filename, 'rt') as fasta_file: 184 | name = '' 185 | sequence = [] 186 | for line in fasta_file: 187 | line = line.strip() 188 | if not line: 189 | continue 190 | if line[0] == '>': # Header line = start of new contig 191 | if name: 192 | fasta_seqs[name.split()[0]] = ''.join(sequence) 193 | sequence = [] 194 | name = line[1:] 195 | else: 196 | sequence.append(line) 197 | if name: 198 | fasta_seqs[name.split()[0]] = ''.join(sequence) 199 | return fasta_seqs 200 | 201 | 202 | REV_COMP_DICT = {'A': 'T', 'T': 'A', 'G': 'C', 'C': 'G', 203 | 'a': 't', 't': 'a', 'g': 'c', 'c': 'g', 204 | 'R': 'Y', 'Y': 'R', 'S': 'S', 'W': 'W', 205 | 'K': 'M', 'M': 'K', 'B': 'V', 'V': 'B', 206 | 'D': 'H', 'H': 'D', 'N': 'N', 207 | 'r': 'y', 'y': 'r', 's': 's', 'w': 'w', 208 | 'k': 'm', 'm': 'k', 'b': 'v', 'v': 'b', 209 | 'd': 'h', 'h': 'd', 'n': 'n', 210 | '.': '.', '-': '-', '?': '?'} 211 | 212 | 213 | def complement_base(base): 214 | try: 215 | return REV_COMP_DICT[base] 216 | except KeyError: 217 | return 'N' 218 | 219 | 220 | def reverse_complement(seq): 221 | return ''.join([complement_base(x) for x in seq][::-1]) 222 | 223 | 224 | if __name__ == '__main__': 225 | main() 226 | -------------------------------------------------------------------------------- /sloika_training_scripts/per-isolate_commands.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | # https://github.com/rrwick/Basecalling-comparison 5 | 6 | # This program is free software: you can redistribute it and/or modify it under the terms of the 7 | # GNU General Public License as published by the Free Software Foundation, either version 3 of the 8 | # License, or (at your option) any later version. This program is distributed in the hope that it 9 | # will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 10 | # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You 11 | # should have received a copy of the GNU General Public License along with this program. If not, 12 | # see . 13 | 14 | # These commands assume you are running in a directory with a subdirectory titled 15 | # 01_original_fast5s, which contains the isolate's fast5s. It will make a few more directories as 16 | # it runs. 17 | 18 | 19 | # Edit the following paths before running, as appropriate for your environment: 20 | script_dir=/path/to/python_script_dir # directory with other Python scripts (trim_signal.py, filter_reads.py and subdivide_read_dir.py) 21 | r1=/path/to/reads_1.fastq.gz # Illumina reads (pair 1) 22 | r2=/path/to/reads_2.fastq.gz # Illumina reads (pair 2) 23 | sloika_dir=/path/to/sloika_dir # directory of Sloika clone (https://github.com/rrwick/sloika) 24 | 25 | 26 | # Make reference FASTA: 27 | skesa --fastq "$r1","$r2" --cores 16 --memory 128 > ref_contigs.fasta 28 | 29 | # Signal-level trimming of fast5s: 30 | python3 "$script_dir"/trim_signal.py --trim_amount 2000 --min_size 50000 01_original_fast5s 02_trimmed_fast5s 31 | 32 | # Basecalling and alignment - prep for QC: 33 | read_fast5_basecaller.py -f FLO-MIN106 -k SQK-LSK108 -i 02_trimmed_fast5s -t 12 -s 03_basecalling -o fastq --disable_filtering --disable_pings 34 | cat 03_basecalling/workspace/*.fastq > temp.fastq 35 | minimap2 -c -x map-ont -t 20 ref_contigs.fasta temp.fastq > alignments.paf 36 | rm temp.fastq 37 | 38 | # Alignment-based QC and per-read references: 39 | python3 "$script_dir"/filter_reads.py --min_basecalled_length 5000 --max_unaligned_bases 30 --max_window_indels 0.8 --window_size 25 02_trimmed_fast5s 03_basecalling/sequencing_summary.txt ref_contigs.fasta alignments.paf 04_filtered_fast5s read_references.fasta 40 | 41 | # Run the first round of Sloika chunky in parallel on smallish groups of reads. This means that 42 | # troublesome reads which hang and/or use lots of RAM only mess up their batch, not the whole 43 | # group. 44 | python3 "$script_dir"/subdivide_read_dir.py 04_filtered_fast5s 50 45 | cd 04_filtered_fast5s 46 | for d in *; do 47 | if (( d < 240 )); then # limit to 240 batches (12k reads) 48 | sbatch --job-name=Sloika_chunkify_"$d" --account=js66 --ntasks=4 --nodes=1-1 --time=1:00:00 --mem=40000 --wrap "module load python/3.5.2-gcc5; source ~/programs/sloika/build/env/bin/activate; export THEANO_FLAGS=device=cpu,floatX=float32,mode=FAST_RUN,blas.ldflags='-lblas',scan.allow_gc=False; /usr/bin/time -v ~/programs/sloika/bin/chunkify.py raw_remap --overwrite --jobs 4 --chunk_len 4000 --downsample_factor 5 --output_strand_list ../unfiltered_strands.txt "$d" remapped_unfiltered_"$d".hdf5 ~/programs/sloika/models/pretrained.pkl ../read_references.fasta" 49 | sleep 0.1 50 | fi 51 | done 52 | rm remapped_unfiltered_*.hdf5 53 | cd .. 54 | 55 | # Optionally, visualise the distributions of scores and proportions of stays: 56 | tail -n+2 unfiltered_strands.txt | awk '{print $3;}' | histogram.py --min 0 --max 1.6 --buckets 40 57 | tail -n+2 unfiltered_strands.txt | awk '{print $4 / ($7 - $6 + $4);}' | histogram.py --min 0 --max 1 --buckets 40 58 | 59 | # QC pass using the chunkify strand info: 60 | low_score=$(tail -n+2 unfiltered_strands.txt | awk '{print $3;}' | sort -n | awk '{all[NR] = $0} END{print all[int(NR*0.15 - 0.5)]}') 61 | high_score=$(tail -n+2 unfiltered_strands.txt | awk '{print $3;}' | sort -n | awk '{all[NR] = $0} END{print all[int(NR*0.95 - 0.5)]}') 62 | min_cov=$(tail -n+2 unfiltered_strands.txt | awk '{print ($7 - $6) / $5;}' | sort -n | awk '{all[NR] = $0} END{print all[int(NR*0.1 - 0.5)]}') 63 | min_cov=$(( min_cov > 0.975 ? min_cov : 0.975 )) 64 | max_stay=$(tail -n+2 unfiltered_strands.txt | awk '{print $4 / ($7 - $6 + $4);}' | sort -n | awk '{all[NR] = $0} END{print all[int(NR*0.75 - 0.5)]}') 65 | (head -n 1 unfiltered_strands.txt ; cat unfiltered_strands.txt | awk -v a="$low_score" -v b="$high_score" -v c="$min_cov" -v d="$max_stay" '$3 > a && $3 < b && ($7 - $6) > c * $5 && $4 / ($7 - $6 + $4) < d && $6 > 0') > filtered_strand_list.txt 66 | 67 | # Split reads into a training set (most of them) and a validation set (a small fraction): 68 | mkdir 05_training_fast5s 69 | for f in $(tail -n+2 filtered_strand_list.txt | cut -f1); do 70 | cp 04_filtered_fast5s/*/"$f" 05_training_fast5s 71 | done 72 | mkdir 06_validation_fast5s 73 | for f in $(ls 05_training_fast5s | shuf | head -n 20); do 74 | mv 05_training_fast5s/"$f" 06_validation_fast5s 75 | done 76 | python3 "$script_dir"/subdivide_read_dir.py 05_training_fast5s 1000 77 | 78 | # The second round of Sloika chunkify: 79 | isolate_name=$(basename "$PWD") 80 | cd 05_training_fast5s 81 | for d in *; do 82 | sbatch --job-name=Chunkify_"$isolate_name"_"$d" --account=js66 --ntasks=12 --nodes=1-1 --time=24:00:00 --mem=120000 --wrap "module load python/3.5.2-gcc5; source ~/programs/sloika/build/env/bin/activate; export THEANO_FLAGS=device=cpu,floatX=float32,mode=FAST_RUN,blas.ldflags='-lblas',scan.allow_gc=False; /usr/bin/time -v ~/programs/sloika/bin/chunkify.py raw_remap --jobs 12 --chunk_len 4000 --downsample_factor 5 --output_strand_list strands_"$d".txt "$d" remapped_"$d".hdf5 ~/programs/sloika/models/pretrained.pkl ../read_references.fasta" 83 | sleep 0.1 84 | done 85 | -------------------------------------------------------------------------------- /sloika_training_scripts/subdivide_read_dir.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This script moves fast5 files into subdirectories with a particular number of files per directory. 15 | """ 16 | 17 | import glob 18 | import math 19 | import os 20 | import shutil 21 | import sys 22 | 23 | input_dir = sys.argv[1] 24 | target_reads_per_dir = int(sys.argv[2]) 25 | 26 | fast5_files = glob.glob(input_dir + '/*.fast5') 27 | file_count = len(fast5_files) 28 | print('Found {} fast5 files in {}'.format(file_count, input_dir)) 29 | 30 | dir_count = int(round(file_count / target_reads_per_dir)) 31 | if dir_count == 0: 32 | dir_count = 1 33 | files_per_dir = int(math.ceil(file_count / dir_count)) 34 | 35 | dir_num = 0 36 | while file_count > 0: 37 | dir_name = input_dir + '/{:04d}'.format(dir_num) 38 | os.makedirs(dir_name) 39 | 40 | if file_count >= files_per_dir: 41 | move_files = files_per_dir 42 | else: 43 | move_files = file_count 44 | print('Moving {} files to {}'.format(move_files, dir_name)) 45 | for f in fast5_files[:move_files]: 46 | shutil.move(f, dir_name) 47 | 48 | fast5_files = fast5_files[move_files:] 49 | file_count -= move_files 50 | dir_num += 1 51 | -------------------------------------------------------------------------------- /sloika_training_scripts/training_commands.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | # https://github.com/rrwick/Basecalling-comparison 5 | 6 | # This program is free software: you can redistribute it and/or modify it under the terms of the 7 | # GNU General Public License as published by the Free Software Foundation, either version 3 of the 8 | # License, or (at your option) any later version. This program is distributed in the hope that it 9 | # will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 10 | # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You 11 | # should have received a copy of the GNU General Public License along with this program. If not, 12 | # see . 13 | 14 | 15 | # Edit the following paths before running, as appropriate for your environment: 16 | out_dir=training_output 17 | training_input_dir=/path/to/training_data # this directory must contain the hdf5 files made by Sloika chunkify 18 | sloika_dir=/path/to/sloika_dir # directory of Sloika clone (https://github.com/rrwick/sloika) 19 | model=/path/to/sloika/models/raw_0.98_rgrgr.py # model file - change this to change the neural network architecture 20 | 21 | 22 | # Do the actual training: 23 | "$sloika_dir"/bin/train_network.py raw --min_prob 1e-5 --reload_after_batches 500 --save_every 500 --niteration 100000 "$model" "$out_dir" "$training_input_dir"/*.hdf5 24 | 25 | # Convert the trained models into both CPU and GPU appropriate forms: 26 | for f in "$out_dir"/model_*.pkl; do 27 | "$sloika_dir"/misc/model_convert.py --target cpu $f "$f".cpu 28 | "$sloika_dir"/misc/model_convert.py --target gpu $f "$f".gpu 29 | done 30 | -------------------------------------------------------------------------------- /sloika_training_scripts/trim_signal.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """ 3 | Copyright 2019 Ryan Wick (rrwick@gmail.com) 4 | https://github.com/rrwick/Basecalling-comparison 5 | 6 | This program is free software: you can redistribute it and/or modify it under the terms of the GNU 7 | General Public License as published by the Free Software Foundation, either version 3 of the 8 | License, or (at your option) any later version. This program is distributed in the hope that it 9 | will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 10 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should 11 | have received a copy of the GNU General Public License along with this program. If not, see 12 | . 13 | 14 | This is a tool for trimming fast5s at the signal level. 15 | 16 | It does two steps for each read: 17 | 1) Trim off what looks like open-pore signal from the start and end of reads. 18 | 2) Trim off a fixed amount of signal from the start and end of reads. 19 | 20 | The final result should be reads with no adapter sequence, making them more suitable for Sloika. 21 | """ 22 | 23 | import argparse 24 | import glob 25 | import h5py 26 | import numpy as np 27 | import os 28 | import shutil 29 | import sys 30 | 31 | 32 | def get_arguments(): 33 | parser = argparse.ArgumentParser(description='Trim fast5 files at the signal level') 34 | 35 | parser.add_argument('--trim_amount', type=int, required=False, default=2000, 36 | help='Signal values to be trimmed from the start/end of the signal') 37 | parser.add_argument('--min_size', type=int, required=False, default=50000, 38 | help='Don\'t keep reads with a trimmed signal smaller than this') 39 | 40 | parser.add_argument('in_dir', type=str, 41 | help='Directory containing fast5 files to trim') 42 | parser.add_argument('out_dir', type=str, 43 | help='Output directory of trimmed fast5 files (will be made)') 44 | 45 | args = parser.parse_args() 46 | return args 47 | 48 | 49 | def main(): 50 | args = get_arguments() 51 | make_output_dir(args.out_dir) 52 | 53 | for original_file in glob.iglob(args.in_dir + '/**/*.fast5', recursive=True): 54 | print(original_file) 55 | 56 | # Make a copy of the file which we will modify. 57 | new_file = '{}/{}'.format(args.out_dir, original_file.rpartition('/')[2]) 58 | print(' making a copy here: {}'.format(new_file)) 59 | if os.path.exists(new_file): 60 | print() 61 | sys.exit('Error: {} already exists'.format(new_file)) 62 | shutil.copyfile(original_file, new_file) 63 | 64 | # Find the signal. 65 | hdf5_file = h5py.File(new_file, 'r+') 66 | signal_location = get_signal_location(hdf5_file) 67 | read_location = signal_location.replace('/Signal', '') 68 | signal = hdf5_file[signal_location].value 69 | orignal_length = len(signal) 70 | print(' original signal length = {:,}'.format(orignal_length)) 71 | 72 | # Trim off open-pore signal 73 | try: 74 | start_trim = find_signal_start_pos(signal) 75 | print(' open-pore signal at start: {}'.format(start_trim)) 76 | end_trim = find_signal_start_pos(signal[::-1]) 77 | print(' open-pore signal at end: {}'.format(end_trim)) 78 | except CannotTrim: 79 | print(' cannot trim - skipping') 80 | hdf5_file.close() 81 | os.remove(new_file) 82 | continue 83 | 84 | if start_trim + end_trim >= orignal_length: 85 | print(' too short - skipping') 86 | hdf5_file.close() 87 | os.remove(new_file) 88 | continue 89 | signal = signal[start_trim:-end_trim] 90 | no_open_pore_length = len(signal) 91 | print(' open-pore trimmed signal length = {:,}'.format(no_open_pore_length)) 92 | 93 | if no_open_pore_length - (2 * args.trim_amount) < args.min_size: 94 | print(' too short - skipping') 95 | hdf5_file.close() 96 | os.remove(new_file) 97 | else: 98 | # Trim the signal and rewrite it. 99 | signal = signal[args.trim_amount:-args.trim_amount] 100 | del hdf5_file[signal_location] 101 | dset = hdf5_file.create_dataset(signal_location, compression='gzip', 102 | compression_opts=9, data=signal) 103 | new_length = len(signal) 104 | hdf5_file[read_location].attrs['duration'] = new_length 105 | print(' final trimmed signal length = {:,}'.format(new_length)) 106 | hdf5_file.close() 107 | print() 108 | 109 | 110 | def make_output_dir(out_dir): 111 | if os.path.exists(out_dir): 112 | sys.exit('Error: output directory already exists') 113 | os.makedirs(out_dir) 114 | 115 | 116 | def get_signal_location(hdf5_file): 117 | names = [] 118 | hdf5_file.visit(names.append) 119 | signal_locations = sorted([x for x in names if x.endswith('/Signal')]) 120 | assert len(signal_locations) == 1 121 | return signal_locations[0] 122 | 123 | 124 | def find_signal_start_pos(signal): 125 | """ 126 | Given a signal, this function attempts to identify the approximate position where the open 127 | pore signal ends and the real signal begins. 128 | """ 129 | initial_trim_size = 10 130 | trim_increment = 25 131 | stdev_threshold = 20 132 | look_forward_windows = 5 133 | window_count_threshold = 4 134 | 135 | # Always trim off the first few values as these are often dodgy. 136 | pos = initial_trim_size 137 | 138 | # Look at the stdev of the signal in the upcoming windows. Trimming is finished when: 139 | # 1. the next window has a high stdev 140 | # 2. enough of the other upcoming windows have a high stdev 141 | while True: 142 | next_window_stdev = get_window_stdev(signal, pos, 0, trim_increment) 143 | if next_window_stdev > stdev_threshold: 144 | upcoming_window_stdevs = [get_window_stdev(signal, pos, i, trim_increment) 145 | for i in range(look_forward_windows)] 146 | num_high_stdevs = sum(1 if x > stdev_threshold else 0 147 | for x in upcoming_window_stdevs) 148 | if num_high_stdevs >= window_count_threshold: 149 | return pos 150 | pos += trim_increment 151 | 152 | 153 | class CannotTrim(IndexError): 154 | pass 155 | 156 | 157 | def get_window_stdev(signal, current_pos, window_num, increment): 158 | window_start = current_pos + (window_num * increment) 159 | window_end = window_start + increment 160 | if window_end > len(signal): 161 | raise CannotTrim 162 | return np.std(signal[window_start:window_end]) 163 | 164 | 165 | if __name__ == '__main__': 166 | main() 167 | --------------------------------------------------------------------------------