From 5cef1e9a0e3fce8ad9c5f084e88993fde6a3f361 Mon Sep 17 00:00:00 2001 From: Vince Buffalo Date: Fri, 4 May 2012 11:36:36 -0700 Subject: [PATCH] fixed some minor errors in paper --- paper/graphics/roc-and-incorrect-trimmed.eps | 467 ++++++++++++++------------- paper/scythe-paper.tex | 28 +- testing/analysis.R | 4 +- 3 files changed, 251 insertions(+), 248 deletions(-) diff --git a/paper/graphics/roc-and-incorrect-trimmed.eps b/paper/graphics/roc-and-incorrect-trimmed.eps index 924a329..1a8465a 100644 --- a/paper/graphics/roc-and-incorrect-trimmed.eps +++ b/paper/graphics/roc-and-incorrect-trimmed.eps @@ -103,9 +103,9 @@ bp 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl -228.22 294.61 397.60 435.91 cl +228.22 294.61 397.60 421.66 cl 190.54 117.64 651.34 477.64 cl -401.20 294.61 570.58 435.91 cl +401.20 294.61 570.58 421.66 cl 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl @@ -119,17 +119,17 @@ bp 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl -228.22 448.14 570.58 463.24 cl +228.22 433.88 570.58 463.24 cl 190.54 117.64 651.34 477.64 cl 228.22 268.84 570.58 282.50 cl 190.54 117.64 651.34 477.64 cl -197.74 294.61 211.41 435.91 cl +197.74 294.61 211.41 421.66 cl 190.54 117.64 651.34 477.64 cl -570.58 294.61 636.94 435.91 cl +570.58 294.61 636.94 421.66 cl 190.54 117.64 651.34 477.64 cl -228.22 294.61 397.60 435.91 cl +228.22 294.61 397.60 421.66 cl /bg { 1 1 1 srgb } def -228.22 294.61 169.38 141.30 r p2 +228.22 294.61 169.38 127.05 r p2 0.9804 0.9804 0.9804 srgb 1.06 setlinewidth [] 0 setdash @@ -137,207 +137,207 @@ bp 1 setlinejoin 10.00 setmiterlimit np -228.22 313.88 m +228.22 311.94 m 169.38 0 l o np -228.22 339.57 m +228.22 335.04 m 169.38 0 l o np -228.22 365.26 m +228.22 358.14 m 169.38 0 l o np -228.22 390.95 m +228.22 381.23 m 169.38 0 l o np -228.22 416.65 m +228.22 404.33 m 169.38 0 l o np 251.32 294.61 m -0 141.30 l +0 127.05 l o np 282.12 294.61 m -0 141.30 l +0 127.05 l o np 312.91 294.61 m -0 141.30 l +0 127.05 l o np 343.71 294.61 m -0 141.30 l +0 127.05 l o np 374.51 294.61 m -0 141.30 l +0 127.05 l o 0.8980 0.8980 0.8980 srgb 0.43 setlinewidth [] 0 setdash np -228.22 301.04 m +228.22 300.39 m 169.38 0 l o np -228.22 326.73 m +228.22 323.49 m 169.38 0 l o np -228.22 352.42 m +228.22 346.59 m 169.38 0 l o np -228.22 378.11 m +228.22 369.68 m 169.38 0 l o np -228.22 403.80 m +228.22 392.78 m 169.38 0 l o np -228.22 429.49 m +228.22 415.88 m 169.38 0 l o np 235.92 294.61 m -0 141.30 l +0 127.05 l o np 266.72 294.61 m -0 141.30 l +0 127.05 l o np 297.52 294.61 m -0 141.30 l +0 127.05 l o np 328.31 294.61 m -0 141.30 l +0 127.05 l o np 359.11 294.61 m -0 141.30 l +0 127.05 l o np 389.90 294.61 m -0 141.30 l +0 127.05 l o /Font1 findfont 9 s 0.9725 0.4627 0.4275 srgb -235.92 304.44 (0) .5 0 t +235.92 303.12 (0) .5 0 t 0 0.7294 0.2196 srgb -239.18 370.18 (0) .5 0 t +239.18 362.23 (0) .5 0 t 0.3804 0.6118 1 srgb -235.92 297.80 (0) .5 0 t +235.92 297.16 (0) .5 0 t 0 0.7294 0.2196 srgb -239.18 372.93 (0.05) .5 0 t +239.18 364.70 (0.05) .5 0 t 0.3804 0.6118 1 srgb -239.82 383.70 (0.05) .5 0 t +239.82 374.39 (0.05) .5 0 t 0 0.7294 0.2196 srgb -239.18 375.16 (0.1) .5 0 t +239.18 366.70 (0.1) .5 0 t 0.3804 0.6118 1 srgb -247.07 386.38 (0.1) .5 0 t +247.07 376.79 (0.1) .5 0 t 0 0.7294 0.2196 srgb -239.64 377.01 (0.15) .5 0 t +239.64 368.37 (0.15) .5 0 t 0.3804 0.6118 1 srgb -250.44 388.74 (0.15) .5 0 t +250.44 378.91 (0.15) .5 0 t 0 0.7294 0.2196 srgb -245.26 379.95 (0.2) .5 0 t +245.26 371.02 (0.2) .5 0 t 0.3804 0.6118 1 srgb -255.10 391.52 (0.2) .5 0 t +255.10 381.41 (0.2) .5 0 t 0 0.7294 0.2196 srgb -258.46 384.42 (0.25) .5 0 t +258.46 375.03 (0.25) .5 0 t 0.3804 0.6118 1 srgb -268.08 394.25 (0.25) .5 0 t +268.08 383.87 (0.25) .5 0 t 0 0.7294 0.2196 srgb -265.65 387.12 (0.3) .5 0 t +265.65 377.46 (0.3) .5 0 t 0.3804 0.6118 1 srgb -272.63 396.98 (0.3) .5 0 t +272.63 386.32 (0.3) .5 0 t 0 0.7294 0.2196 srgb -306.44 397.34 (0.35) .5 0 t +306.44 386.65 (0.35) .5 0 t 0.3804 0.6118 1 srgb -279.06 400.92 (0.35) .5 0 t +279.06 389.87 (0.35) .5 0 t 0 0.7294 0.2196 srgb -354.49 409.73 (0.4) .5 0 t +354.49 397.79 (0.4) .5 0 t 0.3804 0.6118 1 srgb -283.79 403.65 (0.4) .5 0 t +283.79 392.32 (0.4) .5 0 t 0 0.7294 0.2196 srgb -387.56 424.46 (0.45) .5 0 t +387.56 411.03 (0.45) .5 0 t 0.3804 0.6118 1 srgb -289.74 407.23 (0.45) .5 0 t +289.74 395.54 (0.45) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.5) .5 0 t +389.90 412.65 (0.5) .5 0 t 0.3804 0.6118 1 srgb -290.17 407.24 (0.5) .5 0 t +290.17 395.55 (0.5) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.55) .5 0 t +389.90 412.65 (0.55) .5 0 t 0.3804 0.6118 1 srgb -290.27 407.24 (0.55) .5 0 t +290.27 395.56 (0.55) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.6) .5 0 t +389.90 412.65 (0.6) .5 0 t 0.3804 0.6118 1 srgb -290.42 407.25 (0.6) .5 0 t +290.42 395.56 (0.6) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.65) .5 0 t +389.90 412.65 (0.65) .5 0 t 0.3804 0.6118 1 srgb -290.51 407.26 (0.65) .5 0 t +290.51 395.57 (0.65) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.7) .5 0 t +389.90 412.65 (0.7) .5 0 t 0.3804 0.6118 1 srgb -290.72 407.27 (0.7) .5 0 t +290.72 395.57 (0.7) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.75) .5 0 t +389.90 412.65 (0.75) .5 0 t 0.3804 0.6118 1 srgb -291.40 407.28 (0.75) .5 0 t +291.40 395.58 (0.75) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.8) .5 0 t +389.90 412.65 (0.8) .5 0 t 0.3804 0.6118 1 srgb -292.55 407.30 (0.8) .5 0 t +292.55 395.60 (0.8) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.85) .5 0 t +389.90 412.65 (0.85) .5 0 t 0.3804 0.6118 1 srgb -292.76 407.31 (0.85) .5 0 t +292.76 395.61 (0.85) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.9) .5 0 t +389.90 412.65 (0.9) .5 0 t 0.3804 0.6118 1 srgb -293.58 407.34 (0.9) .5 0 t +293.58 395.64 (0.9) .5 0 t 0 0.7294 0.2196 srgb -389.90 426.26 (0.95) .5 0 t +389.90 412.65 (0.95) .5 0 t 0.3804 0.6118 1 srgb -296.97 407.37 (0.95) .5 0 t +296.97 395.67 (0.95) .5 0 t 0.9725 0.4627 0.4275 srgb -235.92 307.22 (1) .5 0 t -235.92 309.85 (2) .5 0 t -235.92 312.47 (3) .5 0 t -235.92 315.32 (4) .5 0 t -235.92 318.00 (5) .5 0 t -235.92 320.74 (6) .5 0 t -235.92 323.76 (7) .5 0 t -235.93 326.89 (8) .5 0 t -236.03 329.99 (9) .5 0 t -236.90 333.22 (10) .5 0 t -242.30 337.24 (11) .5 0 t -265.10 345.08 (12) .5 0 t -322.29 366.70 (13) .5 0 t -376.85 408.26 (14) .5 0 t -389.50 425.67 (15) .5 0 t -389.90 426.26 (16) .5 0 t -389.90 426.26 (17) .5 0 t -389.90 426.26 (18) .5 0 t -389.90 426.26 (19) .5 0 t +235.92 305.63 (1) .5 0 t +235.92 307.99 (2) .5 0 t +235.92 310.34 (3) .5 0 t +235.92 312.91 (4) .5 0 t +235.92 315.32 (5) .5 0 t +235.92 317.78 (6) .5 0 t +235.92 320.49 (7) .5 0 t +235.93 323.31 (8) .5 0 t +236.03 326.09 (9) .5 0 t +236.90 329.00 (10) .5 0 t +242.30 332.62 (11) .5 0 t +265.10 339.66 (12) .5 0 t +322.29 359.10 (13) .5 0 t +376.85 396.47 (14) .5 0 t +389.50 412.12 (15) .5 0 t +389.90 412.65 (16) .5 0 t +389.90 412.65 (17) .5 0 t +389.90 412.65 (18) .5 0 t +389.90 412.65 (19) .5 0 t 0.4980 0.4980 0.4980 srgb 1.06 setlinewidth [] 0 setdash -228.22 294.61 169.38 141.30 r p1 +228.22 294.61 169.38 127.05 r p1 190.54 117.64 651.34 477.64 cl -401.20 294.61 570.58 435.91 cl +401.20 294.61 570.58 421.66 cl /bg { 1 1 1 srgb } def -401.20 294.61 169.38 141.30 r p2 +401.20 294.61 169.38 127.05 r p2 0.9804 0.9804 0.9804 srgb 1.06 setlinewidth [] 0 setdash @@ -345,203 +345,203 @@ o 1 setlinejoin 10.00 setmiterlimit np -401.20 313.88 m +401.20 311.94 m 169.38 0 l o np -401.20 339.57 m +401.20 335.04 m 169.38 0 l o np -401.20 365.26 m +401.20 358.14 m 169.38 0 l o np -401.20 390.95 m +401.20 381.23 m 169.38 0 l o np -401.20 416.65 m +401.20 404.33 m 169.38 0 l o np 424.30 294.61 m -0 141.30 l +0 127.05 l o np 455.10 294.61 m -0 141.30 l +0 127.05 l o np 485.89 294.61 m -0 141.30 l +0 127.05 l o np 516.69 294.61 m -0 141.30 l +0 127.05 l o np 547.49 294.61 m -0 141.30 l +0 127.05 l o 0.8980 0.8980 0.8980 srgb 0.43 setlinewidth [] 0 setdash np -401.20 301.04 m +401.20 300.39 m 169.38 0 l o np -401.20 326.73 m +401.20 323.49 m 169.38 0 l o np -401.20 352.42 m +401.20 346.59 m 169.38 0 l o np -401.20 378.11 m +401.20 369.68 m 169.38 0 l o np -401.20 403.80 m +401.20 392.78 m 169.38 0 l o np -401.20 429.49 m +401.20 415.88 m 169.38 0 l o np 408.90 294.61 m -0 141.30 l +0 127.05 l o np 439.70 294.61 m -0 141.30 l +0 127.05 l o np 470.50 294.61 m -0 141.30 l +0 127.05 l o np 501.29 294.61 m -0 141.30 l +0 127.05 l o np 532.09 294.61 m -0 141.30 l +0 127.05 l o np 562.88 294.61 m -0 141.30 l +0 127.05 l o /Font1 findfont 9 s 0.9725 0.4627 0.4275 srgb -408.90 304.42 (0) .5 0 t +408.90 303.11 (0) .5 0 t 0 0.7294 0.2196 srgb -411.91 370.00 (0) .5 0 t +411.91 362.07 (0) .5 0 t 0.3804 0.6118 1 srgb -408.90 297.80 (0) .5 0 t +408.90 297.16 (0) .5 0 t 0 0.7294 0.2196 srgb -411.91 372.75 (0.05) .5 0 t +411.91 364.54 (0.05) .5 0 t 0.3804 0.6118 1 srgb -412.62 383.77 (0.05) .5 0 t +412.62 374.45 (0.05) .5 0 t 0 0.7294 0.2196 srgb -411.92 375.15 (0.1) .5 0 t +411.92 366.69 (0.1) .5 0 t 0.3804 0.6118 1 srgb -419.51 386.32 (0.1) .5 0 t +419.51 376.74 (0.1) .5 0 t 0 0.7294 0.2196 srgb -412.46 377.04 (0.15) .5 0 t +412.46 368.39 (0.15) .5 0 t 0.3804 0.6118 1 srgb -423.13 388.68 (0.15) .5 0 t +423.13 378.87 (0.15) .5 0 t 0 0.7294 0.2196 srgb -418.30 379.88 (0.2) .5 0 t +418.30 370.95 (0.2) .5 0 t 0.3804 0.6118 1 srgb -427.76 391.55 (0.2) .5 0 t +427.76 381.44 (0.2) .5 0 t 0 0.7294 0.2196 srgb -432.28 384.30 (0.25) .5 0 t +432.28 374.92 (0.25) .5 0 t 0.3804 0.6118 1 srgb -440.50 394.37 (0.25) .5 0 t +440.50 383.98 (0.25) .5 0 t 0 0.7294 0.2196 srgb -439.36 387.08 (0.3) .5 0 t +439.36 377.42 (0.3) .5 0 t 0.3804 0.6118 1 srgb -445.67 397.11 (0.3) .5 0 t +445.67 386.44 (0.3) .5 0 t 0 0.7294 0.2196 srgb -480.53 397.54 (0.35) .5 0 t +480.53 386.83 (0.35) .5 0 t 0.3804 0.6118 1 srgb -452.03 400.92 (0.35) .5 0 t +452.03 389.87 (0.35) .5 0 t 0 0.7294 0.2196 srgb -528.61 410.29 (0.4) .5 0 t +528.61 398.29 (0.4) .5 0 t 0.3804 0.6118 1 srgb -456.56 403.62 (0.4) .5 0 t +456.56 392.30 (0.4) .5 0 t 0 0.7294 0.2196 srgb -560.64 424.46 (0.45) .5 0 t +560.64 411.03 (0.45) .5 0 t 0.3804 0.6118 1 srgb -462.32 407.25 (0.45) .5 0 t +462.32 395.56 (0.45) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.5) .5 0 t +562.88 412.65 (0.5) .5 0 t 0.3804 0.6118 1 srgb -462.73 407.26 (0.5) .5 0 t +462.73 395.57 (0.5) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.55) .5 0 t +562.88 412.65 (0.55) .5 0 t 0.3804 0.6118 1 srgb -462.79 407.26 (0.55) .5 0 t +462.79 395.57 (0.55) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.6) .5 0 t +562.88 412.65 (0.6) .5 0 t 0.3804 0.6118 1 srgb -462.93 407.27 (0.6) .5 0 t +462.93 395.58 (0.6) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.65) .5 0 t +562.88 412.65 (0.65) .5 0 t 0.3804 0.6118 1 srgb -463.03 407.27 (0.65) .5 0 t +463.03 395.58 (0.65) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.7) .5 0 t +562.88 412.65 (0.7) .5 0 t 0.3804 0.6118 1 srgb -463.25 407.30 (0.7) .5 0 t +463.25 395.60 (0.7) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.75) .5 0 t +562.88 412.65 (0.75) .5 0 t 0.3804 0.6118 1 srgb -463.92 407.32 (0.75) .5 0 t +463.92 395.62 (0.75) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.8) .5 0 t +562.88 412.65 (0.8) .5 0 t 0.3804 0.6118 1 srgb -465.14 407.33 (0.8) .5 0 t +465.14 395.64 (0.8) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.85) .5 0 t +562.88 412.65 (0.85) .5 0 t 0.3804 0.6118 1 srgb -465.41 407.35 (0.85) .5 0 t +465.41 395.65 (0.85) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.9) .5 0 t +562.88 412.65 (0.9) .5 0 t 0.3804 0.6118 1 srgb -466.26 407.38 (0.9) .5 0 t +466.26 395.68 (0.9) .5 0 t 0 0.7294 0.2196 srgb -562.88 426.26 (0.95) .5 0 t +562.88 412.65 (0.95) .5 0 t 0.3804 0.6118 1 srgb -469.71 407.42 (0.95) .5 0 t +469.71 395.71 (0.95) .5 0 t 0.9725 0.4627 0.4275 srgb -408.90 307.24 (1) .5 0 t -408.90 309.63 (2) .5 0 t -408.90 312.37 (3) .5 0 t -408.90 315.00 (4) .5 0 t -408.90 317.84 (5) .5 0 t -408.90 320.64 (6) .5 0 t -408.90 323.58 (7) .5 0 t -408.91 326.47 (8) .5 0 t -409.01 329.52 (9) .5 0 t -409.96 332.70 (10) .5 0 t -415.38 336.78 (11) .5 0 t -437.94 344.60 (12) .5 0 t -494.38 366.22 (13) .5 0 t -549.31 408.24 (14) .5 0 t -562.37 425.61 (15) .5 0 t -562.88 426.26 (16) .5 0 t -562.88 426.26 (17) .5 0 t -562.88 426.26 (18) .5 0 t -562.88 426.26 (19) .5 0 t +408.90 305.64 (1) .5 0 t +408.90 307.79 (2) .5 0 t +408.90 310.25 (3) .5 0 t +408.90 312.62 (4) .5 0 t +408.90 315.17 (5) .5 0 t +408.90 317.69 (6) .5 0 t +408.90 320.33 (7) .5 0 t +408.91 322.93 (8) .5 0 t +409.01 325.67 (9) .5 0 t +409.96 328.53 (10) .5 0 t +415.38 332.20 (11) .5 0 t +437.94 339.23 (12) .5 0 t +494.38 358.67 (13) .5 0 t +549.31 396.45 (14) .5 0 t +562.37 412.06 (15) .5 0 t +562.88 412.65 (16) .5 0 t +562.88 412.65 (17) .5 0 t +562.88 412.65 (18) .5 0 t +562.88 412.65 (19) .5 0 t 0.4980 0.4980 0.4980 srgb 1.06 setlinewidth [] 0 setdash -401.20 294.61 169.38 141.30 r p1 +401.20 294.61 169.38 127.05 r p1 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl /bg { 0.8000 0.8000 0.8000 srgb } def @@ -551,10 +551,10 @@ o 1 setlinecap 1 setlinejoin 10.00 setmiterlimit -228.22 435.91 169.38 12.23 r p3 +228.22 421.66 169.38 12.23 r p3 /Font1 findfont 7 s 0 0 0 srgb -312.91 439.51 (0.4) .5 0 t +312.91 425.26 (0.4) .5 0 t 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl /bg { 0.8000 0.8000 0.8000 srgb } def @@ -564,20 +564,20 @@ o 1 setlinecap 1 setlinejoin 10.00 setmiterlimit -401.20 435.91 169.38 12.23 r p3 +401.20 421.66 169.38 12.23 r p3 /Font1 findfont 7 s 0 0 0 srgb -485.89 439.51 (0.7) .5 0 t +485.89 425.26 (0.7) .5 0 t 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl /Font1 findfont 7 s 0 0 0 srgb -221.14 298.52 (0.0) 1 0 t -221.14 324.21 (0.2) 1 0 t -221.14 349.90 (0.4) 1 0 t -221.14 375.60 (0.6) 1 0 t -221.14 401.29 (0.8) 1 0 t -221.14 426.98 (1.0) 1 0 t +221.14 297.87 (0.0) 1 0 t +221.14 320.97 (0.2) 1 0 t +221.14 344.07 (0.4) 1 0 t +221.14 367.17 (0.6) 1 0 t +221.14 390.27 (0.8) 1 0 t +221.14 413.37 (1.0) 1 0 t 190.54 117.64 651.34 477.64 cl 0 0 0 srgb 0.43 setlinewidth @@ -586,27 +586,27 @@ o 1 setlinejoin 10.00 setmiterlimit np -223.97 301.04 m +223.97 300.39 m 4.25 0 l o np -223.97 326.73 m +223.97 323.49 m 4.25 0 l o np -223.97 352.42 m +223.97 346.59 m 4.25 0 l o np -223.97 378.11 m +223.97 369.68 m 4.25 0 l o np -223.97 403.80 m +223.97 392.78 m 4.25 0 l o np -223.97 429.49 m +223.97 415.88 m 4.25 0 l o 190.54 117.64 651.34 477.64 cl @@ -700,13 +700,16 @@ o 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl -228.22 448.14 570.58 463.24 cl +228.22 433.88 570.58 463.24 cl /Font1 findfont 11 s 0 0 0 srgb -370.99 451.74 (R) 0 ta +266.14 451.74 (\(a\) R) 0 ta -0.220 (OC Cur) tb 0.330 (v) tb --0.275 (e) tb gr +-0.275 (e f) tb +-0.330 (or Btr) tb +0.165 (im, Cutadapt, and Scythe Across) tb gr +399.40 437.48 (40% and 70% Read Contamination Rates) .5 0 t 190.54 117.64 651.34 477.64 cl 228.22 268.84 570.58 282.50 cl /Font1 findfont 9 s @@ -716,82 +719,82 @@ o -0.225 (e r) tb -0.090 (ate) tb gr 190.54 117.64 651.34 477.64 cl -197.74 294.61 211.41 435.91 cl +197.74 294.61 211.41 421.66 cl /Font1 findfont 9 s 0 0 0 srgb -207.81 332.00 (tr) 90 ta +207.81 324.87 (tr) 90 ta 0.135 (ue positiv) tb -0.225 (e r) tb -0.090 (ate) tb gr 190.54 117.64 651.34 477.64 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl /Font2 findfont 7 s 0 0 0 srgb -580.62 390.83 (trimmer) 0 0 t -570.58 294.61 636.94 435.91 cl +580.62 383.70 (trimmer) 0 0 t +570.58 294.61 636.94 421.66 cl 0.8000 0.8000 0.8000 srgb 1.06 setlinewidth [] 0 setdash 1 setlinecap 1 setlinejoin 10.00 setmiterlimit -580.62 369.23 17.28 17.28 r p1 -570.58 294.61 636.94 435.91 cl +580.62 362.10 17.28 17.28 r p1 +570.58 294.61 636.94 421.66 cl /Font1 findfont 9 s 0.9725 0.4627 0.4275 srgb -589.26 374.64 (a) .5 0 t -570.58 294.61 636.94 435.91 cl +589.26 367.51 (a) .5 0 t +570.58 294.61 636.94 421.66 cl 0.8000 0.8000 0.8000 srgb 1.06 setlinewidth [] 0 setdash 1 setlinecap 1 setlinejoin 10.00 setmiterlimit -580.62 351.95 17.28 17.28 r p1 -570.58 294.61 636.94 435.91 cl +580.62 344.82 17.28 17.28 r p1 +570.58 294.61 636.94 421.66 cl /Font1 findfont 9 s 0 0.7294 0.2196 srgb -589.26 357.36 (a) .5 0 t -570.58 294.61 636.94 435.91 cl +589.26 350.23 (a) .5 0 t +570.58 294.61 636.94 421.66 cl 0.8000 0.8000 0.8000 srgb 1.06 setlinewidth [] 0 setdash 1 setlinecap 1 setlinejoin 10.00 setmiterlimit -580.62 334.67 17.28 17.28 r p1 -570.58 294.61 636.94 435.91 cl +580.62 327.54 17.28 17.28 r p1 +570.58 294.61 636.94 421.66 cl /Font1 findfont 9 s 0.3804 0.6118 1 srgb -589.26 340.08 (a) .5 0 t -570.58 294.61 636.94 435.91 cl +589.26 332.95 (a) .5 0 t +570.58 294.61 636.94 421.66 cl /Font1 findfont 7 s 0 0 0 srgb -600.06 375.36 (btr) 0 ta +600.06 368.23 (btr) 0 ta 0.105 (im) tb gr -570.58 294.61 636.94 435.91 cl +570.58 294.61 636.94 421.66 cl /Font1 findfont 7 s 0 0 0 srgb -600.06 358.08 (cutadapt) 0 0 t -570.58 294.61 636.94 435.91 cl +600.06 350.95 (cutadapt) 0 0 t +570.58 294.61 636.94 421.66 cl /Font1 findfont 7 s 0 0 0 srgb -600.06 340.80 (scythe) 0 0 t -570.58 294.61 636.94 435.91 cl -570.58 294.61 636.94 435.91 cl +600.06 333.67 (scythe) 0 0 t +570.58 294.61 636.94 421.66 cl +570.58 294.61 636.94 421.66 cl 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl 190.54 117.64 651.34 477.64 cl @@ -1443,7 +1446,7 @@ o 251.98 232.14 590.86 247.24 cl /Font1 findfont 11 s 0 0 0 srgb -288.18 235.74 (Incorrectly T) 0 ta +279.93 235.74 (\(b\) Incorrectly T) 0 ta -1.320 (r) tb 0.165 (immed Reads b) tb -0.220 (y T) tb diff --git a/paper/scythe-paper.tex b/paper/scythe-paper.tex index 5f707a3..a2e1e31 100644 --- a/paper/scythe-paper.tex +++ b/paper/scythe-paper.tex @@ -6,8 +6,8 @@ \firstpage{1} \title[Scythe]{Scythe: A tool for removing 3'-end adapter contaminants using Bayesian classification} -\author[Buffalo \textit{et~al}]{Vince Buffalo\,$^{1,}\footnote{to whom correspondence should be addressed}$, Joseph Fass\,$^{1}$ and Dawei Lin\,$^1$} -\address{$^{1}$Bioinformatics Core, UC Davis Genome Center} +\author[Buffalo \textit{et~al}]{Vince Buffalo\,\footnote{to whom correspondence should be addressed}, Joseph Fass\, and Dawei Lin} +\address{Bioinformatics Core, UC Davis Genome Center} \history{Received on XXXXX; revised on XXXXX; accepted on XXXXX} @@ -27,9 +27,9 @@ \section{Results:} Scythe is a program designed specifically to remove 3'-end contaminants. It searches for 3'-end contaminants and uses a Bayesian model that considers individual base qualities to decide whether a -given match is a contaminant or background sequence. Even for a -variety of prior contamination rates, Scythe outperforms other adapter -removal software tools. +given match is a contaminant or background sequence. With a variety of +contamination rates, Scythe outperforms other adapter removal software +tools. \section{Availability:} Scythe is freely available under the MIT license at @@ -79,9 +79,9 @@ \section{String Matching in Scythe} against the read sequence, starting from the entire contaminant in the 3'-end to incrementally fewer bases. A minimum match length can be specified via a parameter (by default, 5). Each of these alignments is -scored using a 1 for mismatch, -1 for mismatch approach. The top +scored using a $1$ for match, $-1$ for mismatch approach. The top scoring alignment is then passed to the probabilistic classification -procedure, which decides whether the match is background sequence of a +procedure, which decides whether the match is background sequence or a contaminant. The time complexity of Scythe's matching algorithm for a single adapter of length $l_a$ is $O(l_a^2 R)$ for a FASTQ file with $R$ entries. @@ -113,7 +113,7 @@ \section{Bayesian Classification of Top-Scoring Matches} $$ P(S | C') = \prod_{i=1}^{l_t} \left(\frac{1}{4}\right)^{m_i} \cdot \left(\frac{3}{4}\right)^{1 - m_i} $$ These likelihoods can then be combined using Bayes' Thereom to give -the probability of contamination given then top-scoring match: +the probability of contamination given the top-scoring match: $$ P(C|S) = \frac{P(C) P(S|C)}{P(S)} $$ @@ -148,7 +148,7 @@ \section{Results} To test Scythe, Btrim, and Cutadapt at 3'-end adapter contaminant removal, random reads were generated and contaminated at fixed -contamination rates of 40\% and 70\%. FASTQ qualities from a Illumina +contamination rates of 40\% and 70\%. FASTQ qualities from an Illumina HiSeq run were added to these read sequences. Real base qualities were used because properly modeling and simulating 3'-end quality degradation is an arduous task. For the two fixed contamination rates, @@ -161,11 +161,11 @@ \section{Results} and false positive rates change. Btrim uses a fixed number of mismatches, so integer values from 0 to 10 were used. Cutadapt uses an error rate for a matched sequence, which was varied from 0 to 0.95 in -0.05 increments. Likewise, Scythe also uses the same values for its -prior parameter. Each piece of software was run with all other options -off to ensure a fair comparison of 3'-end contaminant removal. +0.05 increments. Likewise, Scythe uses the same values for its prior +parameter. Each piece of software was run with all other options off +to ensure a fair comparison of 3'-end contaminant removal. -While Cutadapt and Scythe only trims reads, Btrim occasionally removes +While Cutadapt and Scythe only trim reads, Btrim occasionally removes a read entirely from the sample. For comparison purposes, we count this as trimming the entire length of a read. We compared the length of the original simulated read to the trimmed read for all programs, @@ -178,7 +178,7 @@ \section{Results} In these tests, we find that Scythe outperforms Btrim and Cutadapt in terms of true positive rates for a variety of false positive rates -across a variety of parameters (see Fig. \ref{fig:02}). Furthermore, +across a variety of parameters (Fig. \ref{fig:02}). Furthermore, Scythe also has fewer incorrectly trimmed reads across a variety of parameters compared to Btrim and Cutadapt. Differences in contamination rates (40\% and 70\%) do not adversely affect Scythe's diff --git a/testing/analysis.R b/testing/analysis.R index 4e15938..aebe5f5 100644 --- a/testing/analysis.R +++ b/testing/analysis.R @@ -166,7 +166,7 @@ p <- ggplot(ds) + geom_text(aes(x=fpr, y=tpr, color=trimmer, label=parameter), s p <- p + scale_y_continuous("true positive rate") p <- p + scale_x_continuous("false positive rate") p <- p + theme_bw(base_size=bs) + facet_wrap(~ contam.rate) -p <- p + opts(title="ROC Curve") +p <- p + opts(title="(a) ROC Curve for Btrim, Cutadapt, and Scythe Across\n40% and 70% Read Contamination Rates") #ggsave(file="trimmer-roc-curve.png", plot=p, height=600, width=800) ## look at incorrect trimmed @@ -174,7 +174,7 @@ ds$width <- ifelse(ds$trimmer == 'btrim', 0.8, 0.04) q <- ggplot(ds, aes(x=parameter, y=incorrectly.trimmed/total, width=width)) + geom_bar(stat="identity") q <- q + scale_y_continuous("proportion\nincorrectly\ntrimmed") q <- q + facet_wrap(~ trimmer, scales="free_x") + theme_bw(base_size=bs) -q <- q + opts(title="Incorrectly Trimmed Reads by Trimmer and Parameter") +q <- q + opts(title="(b) Incorrectly Trimmed Reads by Trimmer and Parameter") vplayout <- function(x, y) viewport(layout.pos.row = x, layout.pos.col = y)