pyseqalignment 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (41) hide show
  1. pyseqalign/__init__.py +14 -0
  2. pyseqalign/core/__init__.py +12 -0
  3. pyseqalign/core/alignment.py +67 -0
  4. pyseqalign/core/needleman_wunsch.py +122 -0
  5. pyseqalign/core/smith_waterman.py +173 -0
  6. pyseqalign/learning/__init__.py +20 -0
  7. pyseqalign/learning/aleph.py +212 -0
  8. pyseqalign/learning/aleph_files/__init__.py +0 -0
  9. pyseqalign/learning/aleph_files/aleph_swi_ak.pl +10420 -0
  10. pyseqalign/learning/base.py +68 -0
  11. pyseqalign/learning/popper.py +215 -0
  12. pyseqalign/learning/task_builder.py +213 -0
  13. pyseqalign/prolog/__init__.py +5 -0
  14. pyseqalign/prolog/engine.py +102 -0
  15. pyseqalign/prolog/knowledge/__init__.py +0 -0
  16. pyseqalign/prolog/knowledge/amino_acids.pl +53 -0
  17. pyseqalign/prolog/knowledge/blosum50.pl +800 -0
  18. pyseqalign/prolog/knowledge/defaults.pl +15 -0
  19. pyseqalign/prolog/knowledge/distances.pl +119 -0
  20. pyseqalign/scoring/__init__.py +11 -0
  21. pyseqalign/scoring/distance.py +100 -0
  22. pyseqalign/scoring/matrices.py +362 -0
  23. pyseqalign/scoring/matrix_data/BLOSUM100 +31 -0
  24. pyseqalign/scoring/matrix_data/BLOSUM50 +31 -0
  25. pyseqalign/scoring/matrix_data/BLOSUM60 +31 -0
  26. pyseqalign/scoring/matrix_data/BLOSUM62 +31 -0
  27. pyseqalign/scoring/matrix_data/BLOSUM70 +31 -0
  28. pyseqalign/scoring/matrix_data/BLOSUM80 +31 -0
  29. pyseqalign/scoring/matrix_data/BLOSUM90 +31 -0
  30. pyseqalign/scoring/matrix_data/PAM150 +34 -0
  31. pyseqalign/scoring/matrix_data/PAM200 +34 -0
  32. pyseqalign/scoring/matrix_data/PAM250 +34 -0
  33. pyseqalign/scoring/matrix_data/PAM50 +34 -0
  34. pyseqalign/scoring/matrix_data/__init__.py +0 -0
  35. pyseqalign/utils/__init__.py +9 -0
  36. pyseqalign/utils/helpers.py +47 -0
  37. pyseqalignment-0.1.0.dist-info/METADATA +317 -0
  38. pyseqalignment-0.1.0.dist-info/RECORD +41 -0
  39. pyseqalignment-0.1.0.dist-info/WHEEL +5 -0
  40. pyseqalignment-0.1.0.dist-info/licenses/LICENSE +21 -0
  41. pyseqalignment-0.1.0.dist-info/top_level.txt +1 -0
pyseqalign/scoring/matrix_data/BLOSUM60 ADDED
@@ -0,0 +1,31 @@
1
+ # Matrix made by matblas from blosum60.iij
2
+ # * column uses minimum score
3
+ # BLOSUM Clustered Scoring Matrix in 1/2 Bit Units
4
+ # Blocks Database = /data/blocks_5.0/blocks.dat
5
+ # Cluster Percentage: >= 60
6
+ # Entropy = 0.6603, Expected = -0.4917
7
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
8
+ A 4 -1 -1 -2 0 -1 -1 0 -2 -1 -1 -1 -1 -2 -1 1 0 -3 -2 0 -2 -1 0 -4
9
+ R -1 5 0 -1 -3 1 0 -2 0 -3 -2 2 -1 -3 -2 -1 -1 -3 -2 -2 -1 0 -1 -4
10
+ N -1 0 6 1 -2 0 0 0 1 -3 -3 0 -2 -3 -2 1 0 -4 -2 -3 3 0 -1 -4
11
+ D -2 -1 1 6 -3 0 2 -1 -1 -3 -3 -1 -3 -3 -1 0 -1 -4 -3 -3 4 1 -1 -4
12
+ C 0 -3 -2 -3 9 -3 -3 -2 -3 -1 -1 -3 -1 -2 -3 -1 -1 -2 -2 -1 -3 -3 -2 -4
13
+ Q -1 1 0 0 -3 5 2 -2 1 -3 -2 1 0 -3 -1 0 -1 -2 -1 -2 0 3 -1 -4
14
+ E -1 0 0 2 -3 2 5 -2 0 -3 -3 1 -2 -3 -1 0 -1 -3 -2 -2 1 4 -1 -4
15
+ G 0 -2 0 -1 -2 -2 -2 6 -2 -3 -4 -1 -2 -3 -2 0 -2 -2 -3 -3 -1 -2 -1 -4
16
+ H -2 0 1 -1 -3 1 0 -2 7 -3 -3 -1 -1 -1 -2 -1 -2 -2 2 -3 0 0 -1 -4
17
+ I -1 -3 -3 -3 -1 -3 -3 -3 -3 4 2 -3 1 0 -3 -2 -1 -2 -1 3 -3 -3 -1 -4
18
+ L -1 -2 -3 -3 -1 -2 -3 -4 -3 2 4 -2 2 0 -3 -2 -1 -2 -1 1 -3 -2 -1 -4
19
+ K -1 2 0 -1 -3 1 1 -1 -1 -3 -2 4 -1 -3 -1 0 -1 -3 -2 -2 0 1 -1 -4
20
+ M -1 -1 -2 -3 -1 0 -2 -2 -1 1 2 -1 5 0 -2 -1 -1 -1 -1 1 -3 -1 -1 -4
21
+ F -2 -3 -3 -3 -2 -3 -3 -3 -1 0 0 -3 0 6 -4 -2 -2 1 3 -1 -3 -3 -1 -4
22
+ P -1 -2 -2 -1 -3 -1 -1 -2 -2 -3 -3 -1 -2 -4 7 -1 -1 -4 -3 -2 -2 -1 -2 -4
23
+ S 1 -1 1 0 -1 0 0 0 -1 -2 -2 0 -1 -2 -1 4 1 -3 -2 -2 0 0 0 -4
24
+ T 0 -1 0 -1 -1 -1 -1 -2 -2 -1 -1 -1 -1 -2 -1 1 4 -2 -2 0 0 -1 0 -4
25
+ W -3 -3 -4 -4 -2 -2 -3 -2 -2 -2 -2 -3 -1 1 -4 -3 -2 10 2 -3 -4 -2 -2 -4
26
+ Y -2 -2 -2 -3 -2 -1 -2 -3 2 -1 -1 -2 -1 3 -3 -2 -2 2 6 -1 -2 -2 -1 -4
27
+ V 0 -2 -3 -3 -1 -2 -2 -3 -3 3 1 -2 1 -1 -2 -2 0 -3 -1 4 -3 -2 -1 -4
28
+ B -2 -1 3 4 -3 0 1 -1 0 -3 -3 0 -3 -3 -2 0 0 -4 -2 -3 4 1 -1 -4
29
+ Z -1 0 0 1 -3 3 4 -2 0 -3 -2 1 -1 -3 -1 0 -1 -2 -2 -2 1 3 -1 -4
30
+ X 0 -1 -1 -1 -2 -1 -1 -1 -1 -1 -1 -1 -1 -1 -2 0 0 -2 -1 -1 -1 -1 -1 -4
31
+ * -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 1
pyseqalign/scoring/matrix_data/BLOSUM62 ADDED
@@ -0,0 +1,31 @@
1
+ # Matrix made by matblas from blosum62.iij
2
+ # * column uses minimum score
3
+ # BLOSUM Clustered Scoring Matrix in 1/2 Bit Units
4
+ # Blocks Database = /data/blocks_5.0/blocks.dat
5
+ # Cluster Percentage: >= 62
6
+ # Entropy = 0.6979, Expected = -0.5209
7
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
8
+ A 4 -1 -2 -2 0 -1 -1 0 -2 -1 -1 -1 -1 -2 -1 1 0 -3 -2 0 -2 -1 0 -4
9
+ R -1 5 0 -2 -3 1 0 -2 0 -3 -2 2 -1 -3 -2 -1 -1 -3 -2 -3 -1 0 -1 -4
10
+ N -2 0 6 1 -3 0 0 0 1 -3 -3 0 -2 -3 -2 1 0 -4 -2 -3 3 0 -1 -4
11
+ D -2 -2 1 6 -3 0 2 -1 -1 -3 -4 -1 -3 -3 -1 0 -1 -4 -3 -3 4 1 -1 -4
12
+ C 0 -3 -3 -3 9 -3 -4 -3 -3 -1 -1 -3 -1 -2 -3 -1 -1 -2 -2 -1 -3 -3 -2 -4
13
+ Q -1 1 0 0 -3 5 2 -2 0 -3 -2 1 0 -3 -1 0 -1 -2 -1 -2 0 3 -1 -4
14
+ E -1 0 0 2 -4 2 5 -2 0 -3 -3 1 -2 -3 -1 0 -1 -3 -2 -2 1 4 -1 -4
15
+ G 0 -2 0 -1 -3 -2 -2 6 -2 -4 -4 -2 -3 -3 -2 0 -2 -2 -3 -3 -1 -2 -1 -4
16
+ H -2 0 1 -1 -3 0 0 -2 8 -3 -3 -1 -2 -1 -2 -1 -2 -2 2 -3 0 0 -1 -4
17
+ I -1 -3 -3 -3 -1 -3 -3 -4 -3 4 2 -3 1 0 -3 -2 -1 -3 -1 3 -3 -3 -1 -4
18
+ L -1 -2 -3 -4 -1 -2 -3 -4 -3 2 4 -2 2 0 -3 -2 -1 -2 -1 1 -4 -3 -1 -4
19
+ K -1 2 0 -1 -3 1 1 -2 -1 -3 -2 5 -1 -3 -1 0 -1 -3 -2 -2 0 1 -1 -4
20
+ M -1 -1 -2 -3 -1 0 -2 -3 -2 1 2 -1 5 0 -2 -1 -1 -1 -1 1 -3 -1 -1 -4
21
+ F -2 -3 -3 -3 -2 -3 -3 -3 -1 0 0 -3 0 6 -4 -2 -2 1 3 -1 -3 -3 -1 -4
22
+ P -1 -2 -2 -1 -3 -1 -1 -2 -2 -3 -3 -1 -2 -4 7 -1 -1 -4 -3 -2 -2 -1 -2 -4
23
+ S 1 -1 1 0 -1 0 0 0 -1 -2 -2 0 -1 -2 -1 4 1 -3 -2 -2 0 0 0 -4
24
+ T 0 -1 0 -1 -1 -1 -1 -2 -2 -1 -1 -1 -1 -2 -1 1 5 -2 -2 0 -1 -1 0 -4
25
+ W -3 -3 -4 -4 -2 -2 -3 -2 -2 -3 -2 -3 -1 1 -4 -3 -2 11 2 -3 -4 -3 -2 -4
26
+ Y -2 -2 -2 -3 -2 -1 -2 -3 2 -1 -1 -2 -1 3 -3 -2 -2 2 7 -1 -3 -2 -1 -4
27
+ V 0 -3 -3 -3 -1 -2 -2 -3 -3 3 1 -2 1 -1 -2 -2 0 -3 -1 4 -3 -2 -1 -4
28
+ B -2 -1 3 4 -3 0 1 -1 0 -3 -4 0 -3 -3 -2 0 -1 -4 -3 -3 4 1 -1 -4
29
+ Z -1 0 0 1 -3 3 4 -2 0 -3 -3 1 -1 -3 -1 0 -1 -3 -2 -2 1 4 -1 -4
30
+ X 0 -1 -1 -1 -2 -1 -1 -1 -1 -1 -1 -1 -1 -1 -2 0 0 -2 -1 -1 -1 -1 -1 -4
31
+ * -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 1
pyseqalign/scoring/matrix_data/BLOSUM70 ADDED
@@ -0,0 +1,31 @@
1
+ # Matrix made by matblas from blosum70.iij
2
+ # * column uses minimum score
3
+ # BLOSUM Clustered Scoring Matrix in 1/2 Bit Units
4
+ # Blocks Database = /data/blocks_5.0/blocks.dat
5
+ # Cluster Percentage: >= 70
6
+ # Entropy = 0.8391, Expected = -0.6313
7
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
8
+ A 4 -2 -2 -2 -1 -1 -1 0 -2 -2 -2 -1 -1 -2 -1 1 0 -3 -2 0 -2 -1 -1 -5
9
+ R -2 6 -1 -2 -4 1 0 -3 0 -3 -3 2 -2 -3 -2 -1 -1 -3 -2 -3 -1 0 -1 -5
10
+ N -2 -1 6 1 -3 0 0 -1 0 -4 -4 0 -2 -3 -2 0 0 -4 -2 -3 3 0 -1 -5
11
+ D -2 -2 1 6 -4 -1 1 -2 -1 -4 -4 -1 -3 -4 -2 0 -1 -5 -4 -4 4 1 -2 -5
12
+ C -1 -4 -3 -4 9 -3 -4 -3 -4 -1 -2 -4 -2 -2 -3 -1 -1 -3 -3 -1 -4 -4 -2 -5
13
+ Q -1 1 0 -1 -3 6 2 -2 1 -3 -2 1 0 -3 -2 0 -1 -2 -2 -2 0 3 -1 -5
14
+ E -1 0 0 1 -4 2 5 -2 0 -4 -3 1 -2 -4 -1 0 -1 -4 -3 -3 1 4 -1 -5
15
+ G 0 -3 -1 -2 -3 -2 -2 6 -2 -4 -4 -2 -3 -4 -3 -1 -2 -3 -4 -4 -1 -2 -2 -5
16
+ H -2 0 0 -1 -4 1 0 -2 8 -4 -3 -1 -2 -1 -2 -1 -2 -2 2 -3 -1 0 -1 -5
17
+ I -2 -3 -4 -4 -1 -3 -4 -4 -4 4 2 -3 1 0 -3 -3 -1 -3 -1 3 -4 -3 -1 -5
18
+ L -2 -3 -4 -4 -2 -2 -3 -4 -3 2 4 -3 2 0 -3 -3 -2 -2 -1 1 -4 -3 -1 -5
19
+ K -1 2 0 -1 -4 1 1 -2 -1 -3 -3 5 -2 -3 -1 0 -1 -3 -2 -3 -1 1 -1 -5
20
+ M -1 -2 -2 -3 -2 0 -2 -3 -2 1 2 -2 6 0 -3 -2 -1 -2 -1 1 -3 -2 -1 -5
21
+ F -2 -3 -3 -4 -2 -3 -4 -4 -1 0 0 -3 0 6 -4 -3 -2 1 3 -1 -4 -4 -2 -5
22
+ P -1 -2 -2 -2 -3 -2 -1 -3 -2 -3 -3 -1 -3 -4 8 -1 -1 -4 -3 -3 -2 -1 -2 -5
23
+ S 1 -1 0 0 -1 0 0 -1 -1 -3 -3 0 -2 -3 -1 4 1 -3 -2 -2 0 0 -1 -5
24
+ T 0 -1 0 -1 -1 -1 -1 -2 -2 -1 -2 -1 -1 -2 -1 1 5 -3 -2 0 -1 -1 -1 -5
25
+ W -3 -3 -4 -5 -3 -2 -4 -3 -2 -3 -2 -3 -2 1 -4 -3 -3 11 2 -3 -4 -3 -3 -5
26
+ Y -2 -2 -2 -4 -3 -2 -3 -4 2 -1 -1 -2 -1 3 -3 -2 -2 2 7 -2 -3 -2 -2 -5
27
+ V 0 -3 -3 -4 -1 -2 -3 -4 -3 3 1 -3 1 -1 -3 -2 0 -3 -2 4 -3 -3 -1 -5
28
+ B -2 -1 3 4 -4 0 1 -1 -1 -4 -4 -1 -3 -4 -2 0 -1 -4 -3 -3 4 0 -1 -5
29
+ Z -1 0 0 1 -4 3 4 -2 0 -3 -3 1 -2 -4 -1 0 -1 -3 -2 -3 0 4 -1 -5
30
+ X -1 -1 -1 -2 -2 -1 -1 -2 -1 -1 -1 -1 -1 -2 -2 -1 -1 -3 -2 -1 -1 -1 -1 -5
31
+ * -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 1
pyseqalign/scoring/matrix_data/BLOSUM80 ADDED
@@ -0,0 +1,31 @@
1
+ # Matrix made by matblas from blosum80_3.iij
2
+ # * column uses minimum score
3
+ # BLOSUM Clustered Scoring Matrix in 1/3 Bit Units
4
+ # Blocks Database = /data/blocks_5.0/blocks.dat
5
+ # Cluster Percentage: >= 80
6
+ # Entropy = 0.9868, Expected = -0.7442
7
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
8
+ A 7 -3 -3 -3 -1 -2 -2 0 -3 -3 -3 -1 -2 -4 -1 2 0 -5 -4 -1 -3 -2 -1 -8
9
+ R -3 9 -1 -3 -6 1 -1 -4 0 -5 -4 3 -3 -5 -3 -2 -2 -5 -4 -4 -2 0 -2 -8
10
+ N -3 -1 9 2 -5 0 -1 -1 1 -6 -6 0 -4 -6 -4 1 0 -7 -4 -5 5 -1 -2 -8
11
+ D -3 -3 2 10 -7 -1 2 -3 -2 -7 -7 -2 -6 -6 -3 -1 -2 -8 -6 -6 6 1 -3 -8
12
+ C -1 -6 -5 -7 13 -5 -7 -6 -7 -2 -3 -6 -3 -4 -6 -2 -2 -5 -5 -2 -6 -7 -4 -8
13
+ Q -2 1 0 -1 -5 9 3 -4 1 -5 -4 2 -1 -5 -3 -1 -1 -4 -3 -4 -1 5 -2 -8
14
+ E -2 -1 -1 2 -7 3 8 -4 0 -6 -6 1 -4 -6 -2 -1 -2 -6 -5 -4 1 6 -2 -8
15
+ G 0 -4 -1 -3 -6 -4 -4 9 -4 -7 -7 -3 -5 -6 -5 -1 -3 -6 -6 -6 -2 -4 -3 -8
16
+ H -3 0 1 -2 -7 1 0 -4 12 -6 -5 -1 -4 -2 -4 -2 -3 -4 3 -5 -1 0 -2 -8
17
+ I -3 -5 -6 -7 -2 -5 -6 -7 -6 7 2 -5 2 -1 -5 -4 -2 -5 -3 4 -6 -6 -2 -8
18
+ L -3 -4 -6 -7 -3 -4 -6 -7 -5 2 6 -4 3 0 -5 -4 -3 -4 -2 1 -7 -5 -2 -8
19
+ K -1 3 0 -2 -6 2 1 -3 -1 -5 -4 8 -3 -5 -2 -1 -1 -6 -4 -4 -1 1 -2 -8
20
+ M -2 -3 -4 -6 -3 -1 -4 -5 -4 2 3 -3 9 0 -4 -3 -1 -3 -3 1 -5 -3 -2 -8
21
+ F -4 -5 -6 -6 -4 -5 -6 -6 -2 -1 0 -5 0 10 -6 -4 -4 0 4 -2 -6 -6 -3 -8
22
+ P -1 -3 -4 -3 -6 -3 -2 -5 -4 -5 -5 -2 -4 -6 12 -2 -3 -7 -6 -4 -4 -2 -3 -8
23
+ S 2 -2 1 -1 -2 -1 -1 -1 -2 -4 -4 -1 -3 -4 -2 7 2 -6 -3 -3 0 -1 -1 -8
24
+ T 0 -2 0 -2 -2 -1 -2 -3 -3 -2 -3 -1 -1 -4 -3 2 8 -5 -3 0 -1 -2 -1 -8
25
+ W -5 -5 -7 -8 -5 -4 -6 -6 -4 -5 -4 -6 -3 0 -7 -6 -5 16 3 -5 -8 -5 -5 -8
26
+ Y -4 -4 -4 -6 -5 -3 -5 -6 3 -3 -2 -4 -3 4 -6 -3 -3 3 11 -3 -5 -4 -3 -8
27
+ V -1 -4 -5 -6 -2 -4 -4 -6 -5 4 1 -4 1 -2 -4 -3 0 -5 -3 7 -6 -4 -2 -8
28
+ B -3 -2 5 6 -6 -1 1 -2 -1 -6 -7 -1 -5 -6 -4 0 -1 -8 -5 -6 6 0 -3 -8
29
+ Z -2 0 -1 1 -7 5 6 -4 0 -6 -5 1 -3 -6 -2 -1 -2 -5 -4 -4 0 6 -1 -8
30
+ X -1 -2 -2 -3 -4 -2 -2 -3 -2 -2 -2 -2 -2 -3 -3 -1 -1 -5 -3 -2 -3 -1 -2 -8
31
+ * -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 1
pyseqalign/scoring/matrix_data/BLOSUM90 ADDED
@@ -0,0 +1,31 @@
1
+ # Matrix made by matblas from blosum90.iij
2
+ # * column uses minimum score
3
+ # BLOSUM Clustered Scoring Matrix in 1/2 Bit Units
4
+ # Blocks Database = /data/blocks_5.0/blocks.dat
5
+ # Cluster Percentage: >= 90
6
+ # Entropy = 1.1806, Expected = -0.8887
7
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
8
+ A 5 -2 -2 -3 -1 -1 -1 0 -2 -2 -2 -1 -2 -3 -1 1 0 -4 -3 -1 -2 -1 -1 -6
9
+ R -2 6 -1 -3 -5 1 -1 -3 0 -4 -3 2 -2 -4 -3 -1 -2 -4 -3 -3 -2 0 -2 -6
10
+ N -2 -1 7 1 -4 0 -1 -1 0 -4 -4 0 -3 -4 -3 0 0 -5 -3 -4 4 -1 -2 -6
11
+ D -3 -3 1 7 -5 -1 1 -2 -2 -5 -5 -1 -4 -5 -3 -1 -2 -6 -4 -5 4 0 -2 -6
12
+ C -1 -5 -4 -5 9 -4 -6 -4 -5 -2 -2 -4 -2 -3 -4 -2 -2 -4 -4 -2 -4 -5 -3 -6
13
+ Q -1 1 0 -1 -4 7 2 -3 1 -4 -3 1 0 -4 -2 -1 -1 -3 -3 -3 -1 4 -1 -6
14
+ E -1 -1 -1 1 -6 2 6 -3 -1 -4 -4 0 -3 -5 -2 -1 -1 -5 -4 -3 0 4 -2 -6
15
+ G 0 -3 -1 -2 -4 -3 -3 6 -3 -5 -5 -2 -4 -5 -3 -1 -3 -4 -5 -5 -2 -3 -2 -6
16
+ H -2 0 0 -2 -5 1 -1 -3 8 -4 -4 -1 -3 -2 -3 -2 -2 -3 1 -4 -1 0 -2 -6
17
+ I -2 -4 -4 -5 -2 -4 -4 -5 -4 5 1 -4 1 -1 -4 -3 -1 -4 -2 3 -5 -4 -2 -6
18
+ L -2 -3 -4 -5 -2 -3 -4 -5 -4 1 5 -3 2 0 -4 -3 -2 -3 -2 0 -5 -4 -2 -6
19
+ K -1 2 0 -1 -4 1 0 -2 -1 -4 -3 6 -2 -4 -2 -1 -1 -5 -3 -3 -1 1 -1 -6
20
+ M -2 -2 -3 -4 -2 0 -3 -4 -3 1 2 -2 7 -1 -3 -2 -1 -2 -2 0 -4 -2 -1 -6
21
+ F -3 -4 -4 -5 -3 -4 -5 -5 -2 -1 0 -4 -1 7 -4 -3 -3 0 3 -2 -4 -4 -2 -6
22
+ P -1 -3 -3 -3 -4 -2 -2 -3 -3 -4 -4 -2 -3 -4 8 -2 -2 -5 -4 -3 -3 -2 -2 -6
23
+ S 1 -1 0 -1 -2 -1 -1 -1 -2 -3 -3 -1 -2 -3 -2 5 1 -4 -3 -2 0 -1 -1 -6
24
+ T 0 -2 0 -2 -2 -1 -1 -3 -2 -1 -2 -1 -1 -3 -2 1 6 -4 -2 -1 -1 -1 -1 -6
25
+ W -4 -4 -5 -6 -4 -3 -5 -4 -3 -4 -3 -5 -2 0 -5 -4 -4 11 2 -3 -6 -4 -3 -6
26
+ Y -3 -3 -3 -4 -4 -3 -4 -5 1 -2 -2 -3 -2 3 -4 -3 -2 2 8 -3 -4 -3 -2 -6
27
+ V -1 -3 -4 -5 -2 -3 -3 -5 -4 3 0 -3 0 -2 -3 -2 -1 -3 -3 5 -4 -3 -2 -6
28
+ B -2 -2 4 4 -4 -1 0 -2 -1 -5 -5 -1 -4 -4 -3 0 -1 -6 -4 -4 4 0 -2 -6
29
+ Z -1 0 -1 0 -5 4 4 -3 0 -4 -4 1 -2 -4 -2 -1 -1 -4 -3 -3 0 4 -1 -6
30
+ X -1 -2 -2 -2 -3 -1 -2 -2 -2 -2 -2 -1 -1 -2 -2 -1 -1 -3 -2 -2 -2 -1 -2 -6
31
+ * -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 -6 1
pyseqalign/scoring/matrix_data/PAM150 ADDED
@@ -0,0 +1,34 @@
1
+ #
2
+ # This matrix was produced by "pam" Version 1.0.6 [28-Jul-93]
3
+ #
4
+ # PAM 150 substitution matrix, scale = ln(2)/2 = 0.346574
5
+ #
6
+ # Expected score = -1.25, Entropy = 0.754 bits
7
+ #
8
+ # Lowest score = -7, Highest score = 12
9
+ #
10
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
11
+ A 3 -2 0 0 -2 -1 0 1 -2 -1 -2 -2 -1 -4 1 1 1 -6 -3 0 0 0 -1 -7
12
+ R -2 6 -1 -2 -4 1 -2 -3 1 -2 -3 3 -1 -4 -1 -1 -2 1 -4 -3 -2 0 -1 -7
13
+ N 0 -1 3 2 -4 0 1 0 2 -2 -3 1 -2 -4 -1 1 0 -4 -2 -2 3 1 -1 -7
14
+ D 0 -2 2 4 -6 1 3 0 0 -3 -5 -1 -3 -6 -2 0 -1 -7 -4 -3 3 2 -1 -7
15
+ C -2 -4 -4 -6 9 -6 -6 -4 -3 -2 -6 -6 -5 -5 -3 0 -3 -7 0 -2 -5 -6 -3 -7
16
+ Q -1 1 0 1 -6 5 2 -2 3 -3 -2 0 -1 -5 0 -1 -1 -5 -4 -2 1 4 -1 -7
17
+ E 0 -2 1 3 -6 2 4 -1 0 -2 -4 -1 -2 -6 -1 -1 -1 -7 -4 -2 2 4 -1 -7
18
+ G 1 -3 0 0 -4 -2 -1 4 -3 -3 -4 -2 -3 -5 -1 1 -1 -7 -5 -2 0 -1 -1 -7
19
+ H -2 1 2 0 -3 3 0 -3 6 -3 -2 -1 -3 -2 -1 -1 -2 -3 0 -3 1 1 -1 -7
20
+ I -1 -2 -2 -3 -2 -3 -2 -3 -3 5 1 -2 2 0 -3 -2 0 -5 -2 3 -2 -2 -1 -7
21
+ L -2 -3 -3 -5 -6 -2 -4 -4 -2 1 5 -3 3 1 -3 -3 -2 -2 -2 1 -4 -3 -2 -7
22
+ K -2 3 1 -1 -6 0 -1 -2 -1 -2 -3 4 0 -6 -2 -1 0 -4 -4 -3 0 0 -1 -7
23
+ M -1 -1 -2 -3 -5 -1 -2 -3 -3 2 3 0 7 -1 -3 -2 -1 -5 -3 1 -3 -2 -1 -7
24
+ F -4 -4 -4 -6 -5 -5 -6 -5 -2 0 1 -6 -1 7 -5 -3 -3 -1 5 -2 -5 -5 -3 -7
25
+ P 1 -1 -1 -2 -3 0 -1 -1 -1 -3 -3 -2 -3 -5 6 1 0 -6 -5 -2 -2 -1 -1 -7
26
+ S 1 -1 1 0 0 -1 -1 1 -1 -2 -3 -1 -2 -3 1 2 1 -2 -3 -1 0 -1 0 -7
27
+ T 1 -2 0 -1 -3 -1 -1 -1 -2 0 -2 0 -1 -3 0 1 4 -5 -3 0 0 -1 -1 -7
28
+ W -6 1 -4 -7 -7 -5 -7 -7 -3 -5 -2 -4 -5 -1 -6 -2 -5 12 -1 -6 -5 -6 -4 -7
29
+ Y -3 -4 -2 -4 0 -4 -4 -5 0 -2 -2 -4 -3 5 -5 -3 -3 -1 8 -3 -3 -4 -3 -7
30
+ V 0 -3 -2 -3 -2 -2 -2 -2 -3 3 1 -3 1 -2 -2 -1 0 -6 -3 4 -2 -2 -1 -7
31
+ B 0 -2 3 3 -5 1 2 0 1 -2 -4 0 -3 -5 -2 0 0 -5 -3 -2 3 2 -1 -7
32
+ Z 0 0 1 2 -6 4 4 -1 1 -2 -3 0 -2 -5 -1 -1 -1 -6 -4 -2 2 4 -1 -7
33
+ X -1 -1 -1 -1 -3 -1 -1 -1 -1 -1 -2 -1 -1 -3 -1 0 -1 -4 -3 -1 -1 -1 -1 -7
34
+ * -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 -7 1
pyseqalign/scoring/matrix_data/PAM200 ADDED
@@ -0,0 +1,34 @@
1
+ #
2
+ # This matrix was produced by "pam" Version 1.0.6 [28-Jul-93]
3
+ #
4
+ # PAM 200 substitution matrix, scale = ln(2)/3 = 0.231049
5
+ #
6
+ # Expected score = -1.23, Entropy = 0.507 bits
7
+ #
8
+ # Lowest score = -9, Highest score = 18
9
+ #
10
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
11
+ A 3 -2 0 0 -3 -1 0 1 -2 -1 -2 -2 -2 -4 1 1 1 -7 -4 0 0 0 0 -9
12
+ R -2 7 0 -2 -4 1 -2 -4 2 -2 -4 4 -1 -5 0 -1 -1 2 -5 -3 -1 0 -1 -9
13
+ N 0 0 3 3 -5 1 2 0 2 -2 -4 1 -2 -4 -1 1 0 -5 -2 -2 3 1 0 -9
14
+ D 0 -2 3 5 -6 2 4 0 0 -3 -5 0 -4 -7 -2 0 0 -8 -5 -3 4 3 -1 -9
15
+ C -3 -4 -5 -6 12 -7 -7 -4 -4 -3 -7 -7 -6 -6 -4 0 -3 -9 0 -2 -5 -7 -4 -9
16
+ Q -1 1 1 2 -7 5 3 -2 3 -3 -2 1 -1 -6 0 -1 -1 -6 -5 -3 1 4 -1 -9
17
+ E 0 -2 2 4 -7 3 5 0 0 -3 -4 0 -3 -7 -1 0 -1 -9 -5 -2 3 4 -1 -9
18
+ G 1 -4 0 0 -4 -2 0 6 -3 -3 -5 -2 -4 -6 -1 1 0 -8 -6 -2 0 -1 -1 -9
19
+ H -2 2 2 0 -4 3 0 -3 8 -3 -3 -1 -3 -2 -1 -1 -2 -3 0 -3 1 2 -1 -9
20
+ I -1 -2 -2 -3 -3 -3 -3 -3 -3 6 2 -2 2 1 -3 -2 0 -6 -2 4 -3 -3 -1 -9
21
+ L -2 -4 -4 -5 -7 -2 -4 -5 -3 2 7 -4 4 2 -3 -4 -2 -2 -2 2 -4 -3 -2 -9
22
+ K -2 4 1 0 -7 1 0 -2 -1 -2 -4 6 1 -7 -2 0 0 -4 -5 -3 0 0 -1 -9
23
+ M -2 -1 -2 -4 -6 -1 -3 -4 -3 2 4 1 8 0 -3 -2 -1 -5 -3 2 -3 -2 -1 -9
24
+ F -4 -5 -4 -7 -6 -6 -7 -6 -2 1 2 -7 0 10 -6 -4 -4 0 7 -2 -6 -6 -3 -9
25
+ P 1 0 -1 -2 -4 0 -1 -1 -1 -3 -3 -2 -3 -6 7 1 0 -7 -6 -2 -1 -1 -1 -9
26
+ S 1 -1 1 0 0 -1 0 1 -1 -2 -4 0 -2 -4 1 2 2 -3 -3 -1 1 -1 0 -9
27
+ T 1 -1 0 0 -3 -1 -1 0 -2 0 -2 0 -1 -4 0 2 4 -6 -3 0 0 -1 0 -9
28
+ W -7 2 -5 -8 -9 -6 -9 -8 -3 -6 -2 -4 -5 0 -7 -3 -6 18 -1 -8 -6 -7 -5 -9
29
+ Y -4 -5 -2 -5 0 -5 -5 -6 0 -2 -2 -5 -3 7 -6 -3 -3 -1 11 -3 -4 -5 -3 -9
30
+ V 0 -3 -2 -3 -2 -3 -2 -2 -3 4 2 -3 2 -2 -2 -1 0 -8 -3 5 -3 -2 -1 -9
31
+ B 0 -1 3 4 -5 1 3 0 1 -3 -4 0 -3 -6 -1 1 0 -6 -4 -3 3 2 -1 -9
32
+ Z 0 0 1 3 -7 4 4 -1 2 -3 -3 0 -2 -6 -1 -1 -1 -7 -5 -2 2 4 -1 -9
33
+ X 0 -1 0 -1 -4 -1 -1 -1 -1 -1 -2 -1 -1 -3 -1 0 0 -5 -3 -1 -1 -1 -1 -9
34
+ * -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 -9 1
pyseqalign/scoring/matrix_data/PAM250 ADDED
@@ -0,0 +1,34 @@
1
+ #
2
+ # This matrix was produced by "pam" Version 1.0.6 [28-Jul-93]
3
+ #
4
+ # PAM 250 substitution matrix, scale = ln(2)/3 = 0.231049
5
+ #
6
+ # Expected score = -0.844, Entropy = 0.354 bits
7
+ #
8
+ # Lowest score = -8, Highest score = 17
9
+ #
10
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
11
+ A 2 -2 0 0 -2 0 0 1 -1 -1 -2 -1 -1 -3 1 1 1 -6 -3 0 0 0 0 -8
12
+ R -2 6 0 -1 -4 1 -1 -3 2 -2 -3 3 0 -4 0 0 -1 2 -4 -2 -1 0 -1 -8
13
+ N 0 0 2 2 -4 1 1 0 2 -2 -3 1 -2 -3 0 1 0 -4 -2 -2 2 1 0 -8
14
+ D 0 -1 2 4 -5 2 3 1 1 -2 -4 0 -3 -6 -1 0 0 -7 -4 -2 3 3 -1 -8
15
+ C -2 -4 -4 -5 12 -5 -5 -3 -3 -2 -6 -5 -5 -4 -3 0 -2 -8 0 -2 -4 -5 -3 -8
16
+ Q 0 1 1 2 -5 4 2 -1 3 -2 -2 1 -1 -5 0 -1 -1 -5 -4 -2 1 3 -1 -8
17
+ E 0 -1 1 3 -5 2 4 0 1 -2 -3 0 -2 -5 -1 0 0 -7 -4 -2 3 3 -1 -8
18
+ G 1 -3 0 1 -3 -1 0 5 -2 -3 -4 -2 -3 -5 0 1 0 -7 -5 -1 0 0 -1 -8
19
+ H -1 2 2 1 -3 3 1 -2 6 -2 -2 0 -2 -2 0 -1 -1 -3 0 -2 1 2 -1 -8
20
+ I -1 -2 -2 -2 -2 -2 -2 -3 -2 5 2 -2 2 1 -2 -1 0 -5 -1 4 -2 -2 -1 -8
21
+ L -2 -3 -3 -4 -6 -2 -3 -4 -2 2 6 -3 4 2 -3 -3 -2 -2 -1 2 -3 -3 -1 -8
22
+ K -1 3 1 0 -5 1 0 -2 0 -2 -3 5 0 -5 -1 0 0 -3 -4 -2 1 0 -1 -8
23
+ M -1 0 -2 -3 -5 -1 -2 -3 -2 2 4 0 6 0 -2 -2 -1 -4 -2 2 -2 -2 -1 -8
24
+ F -3 -4 -3 -6 -4 -5 -5 -5 -2 1 2 -5 0 9 -5 -3 -3 0 7 -1 -4 -5 -2 -8
25
+ P 1 0 0 -1 -3 0 -1 0 0 -2 -3 -1 -2 -5 6 1 0 -6 -5 -1 -1 0 -1 -8
26
+ S 1 0 1 0 0 -1 0 1 -1 -1 -3 0 -2 -3 1 2 1 -2 -3 -1 0 0 0 -8
27
+ T 1 -1 0 0 -2 -1 0 0 -1 0 -2 0 -1 -3 0 1 3 -5 -3 0 0 -1 0 -8
28
+ W -6 2 -4 -7 -8 -5 -7 -7 -3 -5 -2 -3 -4 0 -6 -2 -5 17 0 -6 -5 -6 -4 -8
29
+ Y -3 -4 -2 -4 0 -4 -4 -5 0 -1 -1 -4 -2 7 -5 -3 -3 0 10 -2 -3 -4 -2 -8
30
+ V 0 -2 -2 -2 -2 -2 -2 -1 -2 4 2 -2 2 -1 -1 -1 0 -6 -2 4 -2 -2 -1 -8
31
+ B 0 -1 2 3 -4 1 3 0 1 -2 -3 1 -2 -4 -1 0 0 -5 -3 -2 3 2 -1 -8
32
+ Z 0 0 1 3 -5 3 3 0 2 -2 -3 0 -2 -5 0 0 -1 -6 -4 -2 2 3 -1 -8
33
+ X 0 -1 0 -1 -3 -1 -1 -1 -1 -1 -1 -1 -1 -2 -1 0 0 -4 -2 -1 -1 -1 -1 -8
34
+ * -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 1
pyseqalign/scoring/matrix_data/PAM50 ADDED
@@ -0,0 +1,34 @@
1
+ #
2
+ # This matrix was produced by "pam" Version 1.0.6 [28-Jul-93]
3
+ #
4
+ # PAM 50 substitution matrix, scale = ln(2)/2 = 0.346574
5
+ #
6
+ # Expected score = -3.70, Entropy = 2.00 bits
7
+ #
8
+ # Lowest score = -13, Highest score = 13
9
+ #
10
+ A R N D C Q E G H I L K M F P S T W Y V B Z X *
11
+ A 5 -5 -2 -2 -5 -3 -1 -1 -5 -3 -5 -5 -4 -7 0 0 0 -11 -6 -1 -2 -2 -2 -13
12
+ R -5 8 -4 -7 -6 0 -7 -7 0 -4 -7 1 -3 -8 -3 -2 -5 -1 -8 -6 -5 -2 -4 -13
13
+ N -2 -4 7 2 -8 -2 -1 -2 1 -4 -6 0 -6 -7 -4 1 -1 -7 -3 -6 5 -1 -2 -13
14
+ D -2 -7 2 7 -11 -1 3 -2 -2 -6 -10 -3 -8 -12 -6 -2 -3 -12 -9 -6 6 2 -4 -13
15
+ C -5 -6 -8 -11 9 -11 -11 -7 -6 -5 -12 -11 -11 -10 -6 -2 -6 -13 -3 -5 -9 -11 -7 -13
16
+ Q -3 0 -2 -1 -11 8 2 -5 2 -6 -4 -2 -3 -10 -2 -4 -4 -10 -9 -5 -2 6 -3 -13
17
+ E -1 -7 -1 3 -11 2 7 -3 -3 -4 -7 -3 -5 -11 -4 -3 -4 -13 -7 -5 2 6 -3 -13
18
+ G -1 -7 -2 -2 -7 -5 -3 6 -7 -8 -9 -6 -7 -8 -4 -1 -4 -12 -11 -4 -2 -4 -4 -13
19
+ H -5 0 1 -2 -6 2 -3 -7 9 -7 -5 -4 -8 -5 -3 -4 -5 -6 -2 -5 0 0 -4 -13
20
+ I -3 -4 -4 -6 -5 -6 -4 -8 -7 8 0 -5 0 -1 -7 -5 -1 -11 -5 3 -5 -5 -3 -13
21
+ L -5 -7 -6 -10 -12 -4 -7 -9 -5 0 6 -6 2 -1 -6 -7 -5 -5 -5 -1 -7 -5 -5 -13
22
+ K -5 1 0 -3 -11 -2 -3 -6 -4 -5 -6 6 -1 -11 -5 -3 -2 -9 -8 -7 -1 -2 -4 -13
23
+ M -4 -3 -6 -8 -11 -3 -5 -7 -8 0 2 -1 10 -3 -6 -4 -3 -10 -8 0 -7 -4 -4 -13
24
+ F -7 -8 -7 -12 -10 -10 -11 -8 -5 -1 -1 -11 -3 9 -8 -5 -7 -3 3 -6 -9 -11 -6 -13
25
+ P 0 -3 -4 -6 -6 -2 -4 -4 -3 -7 -6 -5 -6 -8 8 -1 -3 -11 -11 -4 -5 -3 -4 -13
26
+ S 0 -2 1 -2 -2 -4 -3 -1 -4 -5 -7 -3 -4 -5 -1 6 1 -4 -5 -4 -1 -3 -2 -13
27
+ T 0 -5 -1 -3 -6 -4 -4 -4 -5 -1 -5 -2 -3 -7 -3 1 6 -10 -5 -2 -2 -4 -2 -13
28
+ W -11 -1 -7 -12 -13 -10 -13 -12 -6 -11 -5 -9 -10 -3 -11 -4 -10 13 -4 -12 -8 -11 -9 -13
29
+ Y -6 -8 -3 -9 -3 -9 -7 -11 -2 -5 -5 -8 -8 3 -11 -5 -5 -4 9 -6 -5 -8 -6 -13
30
+ V -1 -6 -6 -6 -5 -5 -5 -4 -5 3 -1 -7 0 -6 -4 -4 -2 -12 -6 7 -6 -5 -3 -13
31
+ B -2 -5 5 6 -9 -2 2 -2 0 -5 -7 -1 -7 -9 -5 -1 -2 -8 -5 -6 5 1 -3 -13
32
+ Z -2 -2 -1 2 -11 6 6 -4 0 -5 -5 -2 -4 -11 -3 -3 -4 -11 -8 -5 1 6 -3 -13
33
+ X -2 -4 -2 -4 -7 -3 -3 -4 -4 -3 -5 -4 -4 -6 -4 -2 -2 -9 -6 -3 -3 -3 -4 -13
34
+ * -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 -13 1
pyseqalign/scoring/matrix_data/__init__.py ADDED
File without changes
pyseqalign/utils/__init__.py ADDED
@@ -0,0 +1,9 @@
1
+ """Utility functions and helpers."""
2
+
3
+ from pyseqalign.utils.helpers import amino_acid_to_id, encode_sequence, id_to_amino_acid
4
+
5
+ __all__ = [
6
+ "amino_acid_to_id",
7
+ "id_to_amino_acid",
8
+ "encode_sequence",
9
+ ]
pyseqalign/utils/helpers.py ADDED
@@ -0,0 +1,47 @@
1
+ """Helper utilities for sequence encoding and decoding.
2
+
3
+ Ported from the legacy aminoAcids.pl mappings and C helper functions.
4
+ """
5
+
6
+ from __future__ import annotations
7
+
8
+ from pyseqalign.scoring.matrices import AMINO_ACIDS
9
+
10
+ # Build lookup tables from the canonical amino acid list.
11
+ _AA_TO_ID: dict[str, int] = {aa: idx for idx, aa in enumerate(AMINO_ACIDS)}
12
+ _ID_TO_AA: dict[int, str] = {idx: aa for idx, aa in enumerate(AMINO_ACIDS)}
13
+
14
+
15
+ def amino_acid_to_id(aa: str) -> int:
16
+ """Convert a single-letter amino acid code to its integer ID.
17
+
18
+ Returns 0 (gap) for unknown characters.
19
+ """
20
+ return _AA_TO_ID.get(aa.lower(), 0)
21
+
22
+
23
+ def id_to_amino_acid(element_id: int) -> str:
24
+ """Convert an integer element ID back to its amino acid character."""
25
+ return _ID_TO_AA.get(element_id, "-")
26
+
27
+
28
+ def encode_sequence(sequence: str) -> list[int]:
29
+ """Encode an amino acid string into a list of integer IDs.
30
+
31
+ Example::
32
+
33
+ >>> encode_sequence("HEAGAWGHEE")
34
+ [9, 7, 1, 8, 1, 18, 8, 9, 7, 7]
35
+ """
36
+ return [amino_acid_to_id(ch) for ch in sequence]
37
+
38
+
39
+ def decode_sequence(ids: list[int]) -> str:
40
+ """Decode a list of integer IDs back into an amino acid string.
41
+
42
+ Example::
43
+
44
+ >>> decode_sequence([9, 7, 1, 8, 1, 18, 8, 9, 7, 7])
45
+ 'heagawghee'
46
+ """
47
+ return "".join(id_to_amino_acid(i) for i in ids)