bioroebe 0.10.80

data/lib/bioroebe/yaml/agarose/agarose_concentrations.yml

@@ -0,0 +1,21 @@
+# =========================================================================== #
+# === agarose_concentrations.yml
+#
+# This small "table" shows the agarose concentration, in [% (w/v)], and how
+# long the DNA fragments that can be separated, may be, in kb.
+#
+# In other words, the higher the agarose concentration, the smaller the DNA
+# fragments will be.
+# =========================================================================== #
+
+# =========================================================================== #
+# agarose concentration in [% w/v] : DNA-length in kb
+# =========================================================================== #
+
+0.3:  5   - 50 
+0.6:  1   - 20 
+0.7:  0.8 - 10 
+0.9:  0.5 -  7 
+1.2:  0.4 -  6 
+1.5:  0.2 -  3 
+2.0:  0.1 -  2

data/lib/bioroebe/yaml/aminoacids/amino_acids.yml

@@ -0,0 +1,92 @@
+# =========================================================================== #
+# Keep the keys and values all downcased.
+# =========================================================================== #
+# x = YAML.load_file(Bioroebe::FILE_AMINO_ACIDS)
+# =========================================================================== #
+
+A:
+ ala:    alanine       # https://en.wikipedia.org/wiki/Alanine
+ dgroup: methyl
+
+C:
+ cys:    cystein       # https://en.wikipedia.org/wiki/Cysteine
+ dgroup: sulphydryl
+
+D: # Aspartic acid (Aspartat)
+ asp:    aspartic acid # https://en.wikipedia.org/wiki/Aspartic_acid
+ dgroup: carboxyl
+
+E: # Glutamat
+ glu:    Glutaminsäure # https://en.wikipedia.org/wiki/Glutamic_acid
+ dgroup: carboxyl
+
+F:
+ phe:    phenylalanine # https://en.wikipedia.org/wiki/Phenylalanine
+ dgroup: phenyl
+
+G:
+ gly:    glycine
+ dgroup: hydrogen
+
+H:
+ his:    histidine
+ dgroup: imidazole
+
+I:
+ ile:    isoleucin
+ dgroup: methyl
+
+K:
+ lys:    lysine
+ dgroup: amino
+
+L:
+ leu:    leucine
+ dgroup: methyl
+
+M:
+ met:    methionine
+ dgroup: methyl
+
+N:
+ asn:    asparagine
+ dgroup: amide
+
+O:
+ pyl:    pyrrolysine
+
+P:
+ pro:    proline
+ dgroup: pyrrolidine
+
+Q:
+ gln:    glutamine
+ dgroup: amide
+
+R:
+ arg:    arginine
+ dgroup: guanidinium
+ 
+S:
+ ser:    serine
+ dgroup: hydroxyl
+
+T:
+ thr:    threonine
+ dgroup: hydroxyl
+
+U:
+ sec:    selenocysteine
+ dgroup: unknown # maybe -SH
+
+V:
+ val:    valine
+ dgroup: methyl
+
+W:
+ trp:    tryptophane
+ dgroup: indole
+
+Y:
+ tyr:    tyrosine
+ dgroup: hydroxyl

data/lib/bioroebe/yaml/aminoacids/amino_acids_abbreviations.yml

@@ -0,0 +1,31 @@
+# =========================================================================== #
+# x = YAML.load_file(Bioroebe.file_amino_acids_abbreviations.yml)
+#
+# In code this will be:
+#
+#   AMINO_ACIDS_ABBREVIATIONS
+#
+# =========================================================================== #
+# This will translate towards the english name for the aminoacids.
+# =========================================================================== #
+
+ala: alanine          # A
+cys: cysteine         # C
+phe: phenylalanine    # F
+gly: glycine          # G
+his: histidine        # H
+ile: isoleucine       # I
+lys: lysine           # K
+leu: leucine          # L
+met: methionine       # M
+asn: asparagine       # N
+pyl: pyrrolysinee     # O
+pro: proline          # P
+gln: glutamine        # Q
+arg: arginine         # R
+ser: serine           # S
+thr: threonine        # T
+sec: selenocysteine   # U
+val: valine           # V
+trp: tryptophane      # W
+tyr: tyrosine         # Y

data/lib/bioroebe/yaml/aminoacids/amino_acids_average_mass_table.yml

@@ -0,0 +1,33 @@
+# ====================================================================== #
+# === Average mass table
+#
+# Note that this is the weight when the water has been removed.
+#
+# We gathered this table from:
+#
+#   http://education.expasy.org/student_projects/isotopident/htdocs/aa-list.html
+#
+# ====================================================================== #
+# x = YAML.load_file(ENV['SCI'].to_s+'/YAML/amino_acids_average_mass_table.yml')
+# ====================================================================== #
+
+A:   71.0788
+C:  103.1388
+D:  115.0886
+E:  129.1155
+F:  147.1766
+G:   57.0519
+H:  137.1411
+I:  113.1594
+K:  128.1741
+L:  113.1594
+M:  131.1926
+N:  114.1038 
+P:   97.1167
+Q:  128.1307
+R:  156.1875
+S:   87.0782
+T:  101.1051
+V:   99.1326
+W:  186.2132
+Y:  163.1760

data/lib/bioroebe/yaml/aminoacids/amino_acids_classification.yml

@@ -0,0 +1,18 @@
+# x = YAML.load_file('amino_acids_classification.yml')
+tiny:
+ - G
+ - A
+ - S
+ - T
+ - C
+
+small:
+ - G
+ - A
+ - V
+ - P
+ - S
+ - T
+ - N
+ - C
+ - D

data/lib/bioroebe/yaml/aminoacids/amino_acids_english.yml

@@ -0,0 +1,26 @@
+# =========================================================================== #
+# x = YAML.load_file(ENV['BIOROEBE']+'/yaml/amino_acids_english.yml')
+# =========================================================================== #
+
+A: Alanine
+C: Cysteine
+D: Aspartate
+E: Glutamate
+F: Phenylalanine
+G: Glycine
+H: Histidine
+I: Isoleucine
+K: Lysine
+L: Leucine
+M: Methionine
+N: Asparagine
+O: Pyrrolysine
+P: Proline
+Q: Glutamine
+R: Arginine
+S: Serine
+T: Threonine
+U: Selenocysteine
+V: Valine
+W: Tryptophan
+Y: Tyrosine

data/lib/bioroebe/yaml/aminoacids/amino_acids_frequency.yml

@@ -0,0 +1,44 @@
+# =========================================================================== #
+# The table here is based on the second page in this .pdf file:
+# 
+#   http://onlinelibrary.wiley.com/doi/10.1110/ps.9.6.1203/pdf
+#
+# Title of that paper from ~December 2008:
+#
+#   "Amino acid repeat patterns in protein sequences: Their diversity
+#    and structural-functional implications"
+#
+# The specific table had this header:
+#
+#   "Number of proteins in the SWISS-PROT database containing tandem
+#    single amino acid repeats".
+#
+# Do note that the file 9606_Homo_sapiens.yml should include this
+# information as well. Still, I think keeping this file here
+# around is useful, in order to retain a simple quick visual
+# cue.
+# =========================================================================== #
+
+# =========================================================================== #
+# Aminoacid : frequency in %
+# =========================================================================== #
+Leu:  9.44
+Ala:  7.58
+Ser:  7.13
+Gly:  6.84
+Val:  6.58
+Glu:  6.37
+Lys:  5.95
+Ile:  5.81
+Thr:  5.68
+Asp:  5.28
+Arg:  5.16
+Pro:  4.92
+Asn:  4.44
+Phe:  4.10
+Gln:  3.97
+Tyr:  3.19
+His:  2.25
+Met:  2.38
+Cys:  1.66
+Trp:  1.24

data/lib/bioroebe/yaml/aminoacids/amino_acids_long_name_to_one_letter.yml

@@ -0,0 +1,61 @@
+# =========================================================================== #
+# x = YAML.load_file(Bioroebe.file_amino_acids_long_name_to_one_letter)
+#
+# In code this will be:
+#
+#   AMINO_ACIDS_LONG_NAME_TO_ONE_LETTER
+#
+# Note that the file here stores both the english and the german names.
+# =========================================================================== #
+# 'amino_acids_long_name_to_one_letter.yml'
+# =========================================================================== #
+
+# =========================================================================== #
+# First, the english names:
+# =========================================================================== #
+alanine:        A
+cysteine:       C
+aspartic acid:  D
+glutamic acid:  E
+phenylalanine:  F
+glycine:        G
+histidine:      H
+isoleucine:     I
+lysine:         K
+leucine:        L
+methionine:     M
+asparagine:     N
+proline:        P
+glutamine:      Q
+arginine:       R
+serine:         S
+threonine:      T
+valine:         V
+tryptophan:     W
+tyrosine:       Y
+
+# =========================================================================== #
+# Next the german names:
+# =========================================================================== #
+alanin:         A
+cystein:        C
+asparaginsäure: D
+glutaminsäure:  E
+phenylalanin:   F
+glycin:         G
+histidin:       H
+isoleucin:      I
+lysin:          K
+leucin:         L
+methionin:      M
+asparagin:      N
+pyrrolysine:    O
+prolin:         P
+glutamin:       Q
+arginin:        R
+serin:          S
+threonin:       T
+selenocystein:  U
+valin:          V
+tryptophan:     W
+tyrosin:        Y

data/lib/bioroebe/yaml/aminoacids/amino_acids_molecular_formula.yml

@@ -0,0 +1,32 @@
+# =========================================================================== #
+# Taken from here:
+#   https://www.webqc.org/aminoacids.php
+# =========================================================================== #
+# This is the normal, uncharged variant.
+#
+# In Bioroebe, this file is made available via the constant
+# FILE_AMINOACIDS_MOLECULAR_FORMULA.
+# =========================================================================== #
+
+Alanine:        C3H7NO2
+Arginine:       C6H14N4O2
+Asparagine:     C4H8N2O3
+Aspartic acid:  C4H7NO4
+Aspartate:      C4H7NO4 # <- alias to the above ^^^.
+Cysteine:       C3H7NO2S
+Glutamine:      C5H10N2O3
+Glutamic acid:  C5H9NO4
+Glutamate:      C5H9NO4 # <- alias to the above ^^^.
+Glycine:        C2H5NO2
+Histidine:      C6H9N3O2
+Isoleucine:     C6H13NO2
+Leucine:        C6H13NO2
+Lysine:         C6H14N2O2
+Methionine:     C5H11NO2S
+Phenylalanine:  C9H11NO2
+Proline:        C5H9NO2
+Serine:         C3H7NO3
+Threonine:      C4H9NO3
+Tryptophan:     C11H12N2O2
+Tyrosine:       C9H11NO3
+Valine:         C5H11NO2

data/lib/bioroebe/yaml/aminoacids/amino_acids_monoisotopic_mass_table.yml

@@ -0,0 +1,38 @@
+# =========================================================================== #
+# === Monoisotopic mass table
+#
+# This table can be used for calculating the masses of amino acid residues
+# using the most common isotopes of each atom occurring in the amino acid.
+#
+# We gathered the original table from:
+#
+#   https://education.expasy.org/student_projects/isotopident/htdocs/aa-list.html
+#
+# In July 2021 I realized that the table did not include the water molecule,
+# so downstream calculations were wrong as well. Since July 2021 I am using
+# the entries at wikipedia instead. I also added the formula in this
+# file as-is, so that others can verify the information.
+# =========================================================================== #
+# x = YAML.load_file(Bioroebe.file_amino_acids_monoisotopic_mass_table+'amino_acids_mass_table.yml')
+# =========================================================================== #
+
+A:   89.09300 # Alanine.       Formula: C3H7NO2
+C:  121.15800 # Cysteine.      Formula: C3H7NO2S
+D:  133.10200 # Aspartate.     Formula: C4H7NO4
+E:  147.12900 # Glutamate.     Formula: C5H9NO4
+F:  165.19200 # Phenylalanine. Formula: C9H11NO2
+G:   75.06700 # Glycine.       Formula: C2H5NO2
+H:  155.15700 # Histidine.     Formula: C6H9N3O2
+I:  131.17500 # Isoleucine.    Formula: C6H13NO2
+K:  146.18900 # Lysine.        Formula: C6H14N2O2
+L:  131.17500 # Leucine.       Formula: C6H13NO2
+M:  149.21000 # Methionine.    Formula: C5H11NO2S
+N:  132.11900 # Asparagine.    Formula: C4H8N2O3
+P:  115.13200 # Proline.       Formula: C5H9NO2
+Q:  146.14600 # Glutamine.     Formula: C5H10N2O3
+R:  174.20400 # Arginine.      Formula: C6H14N4O2
+S:  105.09300 # Serine.        Formula: C3H7NO3
+T:  119.12000 # Threonine.     Formula: C4H9NO3
+V:  117.14800 # Valine.        Formula: C5H11NO2
+W:  204.22900 # Tryptophan.    Formula: C11H12N2O2
+Y:  181.19100 # Tyrosine.      Formula: C9H11NO3

data/lib/bioroebe/yaml/aminoacids/amino_acids_reste.yml

@@ -0,0 +1,35 @@
+# =========================================================================== #
+# x = YAML.load_file('amino_acids_reste.yml')
+# =========================================================================== #
+# This file will show the residues of each of the 20 canonical aminoacids.
+#
+# We will include both german and english names here.
+# =========================================================================== #
+
+# =========================================================================== #
+# === English names
+#
+# Next follow the english names. They are all distinct from the german
+# names, hence we can use them in the same file without having to
+# worry about them being overwritten.
+# =========================================================================== #
+Alanine:        -CH3
+Arginine:       -CH2CH2CH2NH-C(NH)NH2
+Asparagine:     -CH2CONH2
+Aspartic acid:  -CH2COOH
+Cysteine:       -CH2SH
+Glutamine:      -CH2CH2CONH2
+Glutamic acid:  -CH2CH2COOH
+Glycine:        -H
+Histidine:      -CH2(C3H3N2)
+Isoleucine:     -CH(CH3)CH2CH3
+Leucine:        -CH2CH(CH3)2
+Lysine:         -CH2CH2CH2CH2NH2
+Methionine:     -CH2CH2SCH3
+Phenylalanine:  -CH2(C6H5)
+Proline:        -CH2CH2CH2-
+Serine:         -CH2OH
+Threonine:      -CH(OH)CH3
+Tryptophane:    -CH2(C8H6N)
+Tyrosine:       -CH2(C6H4)OH
+Valine:         -CH(CH3)2

data/lib/bioroebe/yaml/aminoacids/amino_acids_three_to_one.yml

@@ -0,0 +1,34 @@
+# =========================================================================== #
+# x = YAML.load_file(Bioroebe.file_aminoacids_three_to_one)
+# =========================================================================== #
+# Map the 3 letter combination to the 1 letter representation.
+#
+# In the bioroebe project, this will become:
+#
+#   AMINO_ACIDS_THREE_TO_ONE
+#
+# But we will downcase the keys, since this appears to be easier to deal
+# with it.
+# =========================================================================== #
+
+Ala: A
+Cys: C
+Asp: D
+Glu: E
+Phe: F
+Gly: G
+His: H
+Ile: I
+Lys: K
+Leu: L
+Met: M
+Asn: N
+Pro: P
+Gln: Q
+Arg: R
+Ser: S
+Thr: T
+Sec: U
+Val: V
+Trp: W
+Tyr: Y

data/lib/bioroebe/yaml/aminoacids/hydropathy_table.yml

@@ -0,0 +1,44 @@
+# =========================================================================== #
+# === hydropathy_table.yml
+#
+# The following values were taken from:
+#
+#   http://www.thinkpeptides.com/aminoacidproperties.html
+#
+# They state that they took the numbers from this original paper:
+#
+#   (Kyte and Doolittle, 1982: A simple method for displaying the hydropathic
+#    character of a protein. J. Mol. Biol. 157:105-132.) [PubMedID: 7108955]
+#
+# The hydropathy index is a number representing the hydrophobic or
+# hydrophilic properties of the side-chain of an amino acid.
+# =========================================================================== #
+# We'll only store the short amino acid code here - it is easier to translate
+# from that single-letter into the corresponding english or german long
+# aminoacid.
+#
+# Keep them sorted from top down - most hydrophobic one comes first,
+# most hydrophilic one comes last. So on top will be Isoleucine (I),
+# on bottom will be Arginin (R).
+# =========================================================================== #
+
+I:  4.5
+V:  4.2
+L:  3.8
+F:  2.8
+C:  2.5
+A:  1.8
+M:  1.9
+G: -0.4
+T: -0.7
+S: -0.8
+W: -0.9
+Y: -1.3
+P: -1.6
+H: -3.2
+E: -3.5
+N: -3.5
+D: -3.5
+Q: -3.5
+K: -3.9
+R: -4.5

data/lib/bioroebe/yaml/aminoacids/molecular_weight.yml

@@ -0,0 +1,29 @@
+# =========================================================================== #
+# === molecular_weight.yml
+#
+# To test, try:
+#
+#   x = YAML.load_file('molecular_weight.yml')
+#
+# =========================================================================== #
+
+A:  89.09 #  89.09 g/mol for Alanine.
+C: 121.16 # 121.16 g/mol for Cysteine.
+D: 133.11 # 133.11 g/mol for Aspartic acid.
+E: 147.13 # 147.13 g/mol for Glutamic acid.
+F: 165.19 # 165.19 g/mol for Phenylalanine.
+G:  75.07 #  75.07 g/mol for Glycine.
+H: 155.15 # 155.15 g/mol for Histidine.
+I: 131.17 # 131.17 g/mol for Isoleucine.
+K: 146.19 # 146.19 g/mol for Lysine.
+L: 131.17 # 131.17 g/mol for Leucine.
+M: 149.21 # 149.21 g/mol for Methionine.
+N: 132.12 # 132.12 g/mol for Asparagine.
+P: 115.13 # 115.13 g/mol for Proline.
+Q: 146.14 # 146.14 g/mol for Glutamine.
+R: 174.20 # 174.20 g/mol for Arginine.
+S: 105.09 # 105.09 g/mol for Serine.
+T: 119.12 # 119.12 g/mol for Threonine.
+V: 117.10 # 117.10 g/mol for Valine.
+W: 204.23 # 204.23 g/mol for Tryptophan.
+Y: 181.19 # 181.19 g/mol for Tyrosine.

data/lib/bioroebe/yaml/aminoacids/simple_aminoacids.yml

@@ -0,0 +1,66 @@
+# =========================================================================== #
+# === simple_aminoacids.yml
+#
+#   x = YAML.load_file(Bioroebe.file_simple_aminoacids+'aminoacids.yml'); pp x; ''
+#
+# =========================================================================== #
+A:
+- Alanine
+- Ala
+C:
+- Cysteine
+- Cys
+D:
+- Aspartic acid
+- Asp
+E:
+- Glutamic acid
+- Glu
+F:
+- Phenylalanine
+- Phe
+G:
+- Glycine
+- Gly
+H:
+- Histidine
+- His
+I:
+- Isoleucine
+- Ile
+K:
+- Lysine
+- Lys
+L:
+- Leucine
+- Leu
+M:
+- Methionine
+- Met
+N:
+- Asparagine
+- Asn
+P:
+- Proline
+- Pro
+Q:
+- Glutamine
+- Gln
+R:
+- Arginine
+- Arg
+S:
+- Serine
+- Ser
+T:
+- Threonine 
+- Thr
+V:
+- Valine
+- Val
+W:
+- Tryptophan
+- Trp
+Y:
+- Tyrosine
+- Tyr

data/lib/bioroebe/yaml/aminoacids/weight_of_common_proteins.yml

@@ -0,0 +1,33 @@
+# =========================================================================== #
+# === weight_of_common_proteins.yml
+#
+# This file will keep the weight of some common proteins and peptide
+# fragments.
+#
+# The weight will be given in kDa, so a value of 55 here really means
+# "55 kDa" effectively. No exceptions to that rule are allowed, for
+# simplicity reasons and sake of consistency.
+#
+# Keep these entries sorted, please, from the lightest to the heaviest
+# protein registered in this file.
+# =========================================================================== #
+
+                                 n kDa
+----------------------------------------------------------------------------------------
+ATP:                             0.507  # Yup, ATP has a molecular weight of about 507 Dalton. Formula is: C₁₀H₁6N5O₁3P3
+tRNAs:                           25     # This applies to mature tRNAs with an average of 76 nucleotides.
+GFP:                             26.9   # The good, old "Green Fluorescent Protein". 
+scFv:                            27     # The "scFv fragment".
+recA-Protein:                    38     # The recA Protein in Prokaryotes.
+Protein A:                       42     # Protein A from "Staphylococcus aureus".
+RUBISCO monomer:                 55     # Yes, the RUBISCO monomer has a weight of 55 kDa.
+Fab fragment:                    55     # Part of a typical antibody, e. g. IgG antibody.
+Luciferase:                      62     # Originally from the firefly.
+IgG:                            150     # IgG antibodies have a weight of approximately 150 kDa.
+IgA:                            160     # IgA antibodies have a weight of approximately 160 kDa.
+IgD:                            175     # IgD antibodies have a weight of approximately 175 kDa.
+IgE:                            190     # IgE antibodies have a weight of approximately 190 kDa.
+IgA-dimers:                     400     # IgA dimers have a MW of 400.000 Da.
+Apolipoprotein:                +500     # The Apolipoprotein is fairly large.
+ATP synthase:                 500-600   # Has a weight between ~500-600 kDa; probably species-dependent.
+IgM-pentamers:                  950     # IgM pentamers have a MW of 950.000 Da. Other sources claim 900.000 Da.

data/lib/bioroebe/yaml/antisense/antisense.yml

@@ -0,0 +1,9 @@
+# =========================================================================== #
+# This file contains some sequences for antisense-nucleotides.
+#
+# Assume the sequence to be read from 5' to 3', left to right,
+# if 5' and 3' is omitted.
+# =========================================================================== #
+
+mipomersen: 5'-GCCTCAGTCTGCTTCGCACC-3'
+nusinersen: 5'-UCACUUUCAUAAUGCUGG-3'