From a86681109f3b9be838ae3fb2dd9d6db544be4bce Mon Sep 17 00:00:00 2001 From: jprocter Date: Thu, 6 Sep 2012 15:19:40 +0100 Subject: [PATCH] JAL-1027 JAL-1167 documentation and patched DNA/RNA matrix --- help/html/calculations/scorematrices.html | 95 ++++++++++++++++++++++++++++ src/jalview/schemes/ResidueProperties.java | 14 ++-- 2 files changed, 102 insertions(+), 7 deletions(-) create mode 100644 help/html/calculations/scorematrices.html diff --git a/help/html/calculations/scorematrices.html b/help/html/calculations/scorematrices.html new file mode 100644 index 0000000..9a40e69 --- /dev/null +++ b/help/html/calculations/scorematrices.html @@ -0,0 +1,95 @@ + + +Substitution matrices in Jalview + + +Substitution Matrices available in Jalview +

Jalview includes a small number of built in substitution matrices, used for different types of analysis.

+ + +

BLOSUM62
+ + + + + + + + + + + + + + + + + + + + + + + + + + +
 A  B  C  D  E  F  G  H  I  K  L  M  N  P  Q  R  S  T  U  V  W  X  Y  Z 
A4-20-2-1-20-2-1-1-1-1-2-1-1-11000-30-2-1
B-24-341-3-10-30-4-33-20-10-1-1-3-4-1-31
C0-39-3-4-2-3-3-1-3-1-1-3-3-33-1-1-2-1-2-2-2-3
D-24-362-3-1-1-3-1-4-31-10-20-1-1-3-4-1-31
E-11-425-3-20-31-3-20-1200-1-1-2-3-1-24
F-2-3-2-3-36-3-10-300-3-4-3-3-2-2-1-11-13-3
G0-1-3-1-2-36-2-4-2-4-30-2-2-20-2-1-3-2-1-3-2
H-20-3-10-1-28-3-1-3-21-200-1-2-1-3-2-120
I-1-3-1-3-30-4-34-321-3-3-3-3-2-1-13-3-1-1-3
K-10-3-11-3-2-1-35-2-10-1120-1-1-2-3-1-21
L-1-4-1-4-30-4-32-242-3-3-2-2-2-1-11-2-1-1-3
M-1-3-1-3-20-3-21-125-2-20-1-1-1-11-1-1-1-1
N-23-310-301-30-3-26-20010-1-3-4-1-20
P-1-2-3-1-1-4-2-2-3-1-3-2-27-1-2-1-1-2-2-4-2-3-1
Q-10-302-3-20-31-200-1510-1-1-2-2-1-13
R-1-1-3-20-3-20-32-2-10-215-1-1-1-3-3-1-20
S10-100-20-1-20-2-11-10-1410-2-30-20
T0-1-1-1-1-2-2-2-1-1-1-10-1-1-11500-20-2-1
U0-1-2-1-1-1-1-1-1-1-1-1-1-2-1-100-1-1-2-1-1-1
V0-3-1-3-2-1-3-33-211-3-2-2-3-20-14-3-1-1-2
W-3-4-2-4-31-2-2-3-3-2-1-4-4-2-3-3-2-2-311-22-3
X0-1-2-1-1-1-1-1-1-1-1-1-1-2-1-100-1-1-2-1-1-1
Y-2-3-2-3-23-32-1-2-1-1-2-3-1-2-2-2-1-12-17-2
Z-11-314-3-20-31-3-10-1300-1-1-2-3-1-24
+

PAM250
+ + + + + + + + + + + + + + + + + + + + + + + + + + +
 A  B  C  D  E  F  G  H  I  K  L  M  N  P  Q  R  S  T  U  V  W  X  Y  Z 
A20-200-31-1-1-1-2-1010-21100-60-30
B03-433-401-21-3-22-11-100-1-2-5-1-32
C-2-412-5-5-4-3-3-2-5-6-5-4-3-5-40-2-3-2-8-30-5
D03-543-611-20-4-32-12-100-1-2-7-1-43
E03-534-501-20-3-21-12-100-1-2-7-1-43
F-3-4-4-6-59-5-21-520-3-5-5-4-3-3-2-10-27-5
G10-310-55-2-3-2-4-300-1-310-1-1-7-1-50
H-11-311-2-26-20-2-22032-1-1-1-2-3-102
I-1-2-2-2-21-3-25-222-2-2-2-2-10-14-5-1-1-2
K-11-500-5-20-25-301-11300-1-2-3-1-40
L-2-3-6-4-32-4-22-364-3-3-2-3-3-2-12-2-1-1-3
M-1-2-5-3-20-3-22046-2-2-10-2-1-12-4-1-2-2
N02-421-302-21-3-22010100-2-40-21
P1-1-3-1-1-500-2-1-3-2060010-1-1-6-1-50
Q01-522-5-13-21-2-11041-1-1-1-2-5-1-43
R-2-1-4-1-1-4-32-23-3000160-1-1-22-1-40
S10000-31-1-10-3-211-10210-1-20-30
T10-200-30-100-2-100-1-11300-50-3-1
U0-1-3-1-1-2-1-1-1-1-1-10-1-1-100-1-1-4-1-2-1
V0-2-2-2-2-1-1-24-222-2-1-2-2-10-14-6-1-2-2
W-6-5-8-7-70-7-3-5-3-2-4-4-6-52-2-5-4-617-40-6
X0-1-3-1-1-2-1-1-1-1-1-10-1-1-100-1-1-4-1-2-1
Y-3-30-4-47-50-1-4-1-2-2-5-4-4-3-3-2-20-210-4
Z02-533-502-20-3-210300-1-1-2-6-1-43
+ +

Simple Nucleotide Substitution
+This is an ad-hoc matrix which, in addition to penalising mutations between the common nucleotides (ACGT), includes T/U equivalence in order to allow both DNA and/or RNA. +In addition, it encodes weak equivalence between R and Y with AG and CTU, respectively, and N is allowed to match any other base weakly. This matrix also includes I (Inosine) and X (Xanthine), but encodes them to weakly match any of (ACGTU), and unfavourably match each other. + + + + + + + + + + + + +
 A  C  G  I  N  R  T  U  X  Y 
A10-8-8111-8-81-8
C-810-811-8-8-811
G-8-810111-8-81-8
I11110101100
N11111011111
R1-810110-8-80-8
T-8-8-811-8101011
U-8-8-811-8101011
X11101011100
Y-81-801-811010
+This nucleotide matrix was introduced in + Jalview 2.8. If you'd like to improve it - please take a look at Issue JAL-1027 + - introduce a nucleotide substitution matrix that supports RNA/DNA + and ambiguity codes + + + \ No newline at end of file diff --git a/src/jalview/schemes/ResidueProperties.java b/src/jalview/schemes/ResidueProperties.java index 98b7101..99fc074 100755 --- a/src/jalview/schemes/ResidueProperties.java +++ b/src/jalview/schemes/ResidueProperties.java @@ -589,15 +589,15 @@ public class ResidueProperties // static final int[][] DNA = { - { 10, -8, -8, -8, -8, 1, 1, -8, 1, 1, 1 }, // C - { -8, 10, -8, -8, 10, 1, 1, -8, 1, 1, 1 }, // T - { -8, -8, 10, -8, -8, 1, 1, 1, -8, 1, 1 }, // A - { -8, -8, -8, 10, -8, 1, 1, 1, -8, 1, 1 }, // G - { -8, 10, -8, -8, 10, 1, 1, -8, 1, 1, 1 }, // U + { 10, -8, -8, -8, -8, 1, 1, 1, -8, 1, 1 }, // A + { -8, 10, -8, -8, -8, 1, 1, -8, 1, 1, 1 }, // C + { -8, -8, 10, -8, -8, 1, 1, 1, -8, 1, 1 }, // G + { -8, -8, -8, 10, 10, 1, 1, -8, 1, 1, 1 }, // T + { -8, -8, -8, 10, 10, 1, 1, -8, 1, 1, 1 }, // U { 1, 1, 1, 1, 1, 10, 0, 0, 0, 1, 1 }, // I { 1, 1, 1, 1, 1, 0, 10, 0, 0, 1, 1 }, // X - { -8, -8, 1, 1, -8, 0, 0, 10, 0, 1, 1 }, // R - { 1, 1, -8, -8, 1, 0, 0, 0, 10, 1, 1 }, // Y + { 1, -8, 1, -8, -8, 0, 0, 10, -8, 1, 1 }, // R + { -8, 1, -8, 1, 1, 0, 0, -8, 10, 1, 1 }, // Y { 1, 1, 1, 1, 1, 1, 1, 1, 1, 10, 1 }, // N { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, // - }; -- 1.7.10.2