ydeng/bch441-work-abc-units
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

2020 updates - deactivate for maintenance

Browse Source
This commit is contained in:
hyginn 2020-09-18 21:56:30 +10:00
parent 89bdd14d1c
commit 37ef655d47
42 changed files with 447 additions and 243 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
.init.R
View File

@ -1,42 +0,0 @@
# .init.R
# Functions to initialize this collection of learning units
# Boris Steipe
# ====================================================================
# Create a local copy of myScript.R if required, and not been done yet.
if (! file.exists("myScript.R") && file.exists(".tmp.R")) {
file.copy(".tmp.R", "myScript.R")
}
# If it doesn't exist yet, set up a profile:
if (! file.exists(".myProfile.R")) {
# setup profile data
cat("\nPlease enter the requested values correctly, no spaces, and\n")
cat("press <enter>.\n")
e <- readline("Please enter your UofT eMail address: ")
n <- readline("Please enter your Student Number: ")
conn <- file(".myProfile.R")
writeLines(c(sprintf("myEMail <- \"%s\"", e),
sprintf("myStudentNumber <- %d", as.numeric(n))),
conn)
close(conn)
rm(e, n, conn)
}
# Patch YFO -> MYSPE if necessary:
tmp <- readLines(".myProfile.R")
if (length(grep("^YFO", tmp)) > 0) {
idx <- grep("^YFO", tmp)
tmp[idx] <- gsub("^YFO", "MYSPE", tmp[idx])
writeLines(tmp, ".myProfile.R")
}
rm(tmp)
source(".myProfile.R")
source(".utilities.R")
file.edit("ABC-units.R")
# [End]

20
.utilities.R
View File

@ -181,19 +181,29 @@ fetchMSAmotif <- function(ali, mot) {
# ====== PDB ID selection ====================================================== # ====== PDB ID selection ======================================================
selectPDBrep <- function(n) { selectPDBrep <- function(n, seed = as.numeric(Sys.time())) {
# Select n PDB IDs from a list of high-resolution, non-homologous, single # Select n PDB IDs from a list of high-resolution, non-homologous, single
# domain, single chain structure files that represent a CATH topology # domain, single chain structure files that represent a CATH topology
# group. # group.
# Parameters n num number of IDs to return. # Parameters:
# n num number of IDs to return
# seed num a seed for the RNG
#
# Value: char PDB IDs # Value: char PDB IDs
# Note: the list is loaded from an RData file in the data directory #
# Note: the list is loaded from an RData file in the "./data" directory.
# If you use this function for a course submissio, it MUST be invoked as:
#
# selectPDBrep(n, seed = myStudentNumber)
#
# ... and myStudentNumber MUST be correctly initialized
load("./data/pdbRep.RData") # loads pdbRep load("./data/pdbRep.RData") # loads pdbRep
if (n > length(pdbRep)) { if (n > length(pdbRep)) {
stop(sprintf("You can select no more than %d IDs.", length(pdbRep))) stop(sprintf("There are only %d PDB IDs in the table to choose from.",
length(pdbRep)))
} }
set.seed(as.numeric(Sys.time())) set.seed(seed)
return(sample(pdbRep, n)) return(sample(pdbRep, n))
} }

42
ABC-units.R
View File

@ -2,11 +2,16 @@
# #
# Purpose: A Bioinformatics Course: R code for learning units # Purpose: A Bioinformatics Course: R code for learning units
# #
# Version: 0.1 # Version: 4.0
# #
# Date: 2017 08 18 # Date: 2020 09 16
# Author: Boris Steipe (boris.steipe@utoronto.ca) # Author: Boris Steipe (boris.steipe@utoronto.ca)
# #
# Versions:
# V 4.0 2020 version
# V 3.0 2019 version
# V 2.0 2018 version
# V 1.0 2017 version
# V 0.1 First code # V 0.1 First code
# #
# TODO: # TODO:
@ -14,23 +19,19 @@
# #
# == HOW TO WORK WITH LEARNING UNIT FILES ====================================== # == HOW TO WORK WITH LEARNING UNIT FILES ======================================
# #
# Expect that the learning unit files will be continuously updated. # The R-scripts and datasets in this project will be continuously updated,
# # and updates will be posted on GitHub. To bring your version into the latest
# state use the Git-pane (top left) and "pull" (blue downward arrow) from the
# repository. However, this will overwrite locally edited version of files.
# If you wish to edit any of the code, for example to add your own comments and # To edit code and experiment with it, for example to add your own comments and
# examples, save any edited version under a different name. Otherwise you will # examples, save your edited version into the "myScripts" folder. Otherwise you
# have problems with git when you update the project to a new version. # may have problems with git when you update the project to a new version. It's
# good practice to change the filename, for example by prepending your initials.
# This helps distinguish the files you are working with e.g. in a list of
# recent files. For example if your name is Honjo Tasuku, your edited
# BIN-Sequence.R might be named HT-BIN-Sequence.R
# DO NOT SIMPLY source() THESE FILES!
# If there are portions you don't understand, use R's help system, Google for an
# answer, or ask your instructor. Don't continue if you don't understand what's
# going on. That's not how it works ...
#
# While this file itself should not be edited by you this is YOUR project
# directory, and files that you create (notes etc.) will not be harmed when you
# pull updated version of the master, or other new files, from github.
#
# If you pull from github and get the following type of error ... # If you pull from github and get the following type of error ...
# --------------- # ---------------
# error: Your local changes to the following files would be # error: Your local changes to the following files would be
@ -41,8 +42,11 @@
# ... then, you need to bring the offending file into its original state. # ... then, you need to bring the offending file into its original state.
# Open the Commit window, select the file, and click on the Revert button. # Open the Commit window, select the file, and click on the Revert button.
# #
# Of course, you can save a local copy under a different name before you revert, # When working with these script DO NOT SIMPLY source() THESE FILES!
# in case you want to keep your changes.
# If there are portions you don't understand, use R's help system, Google for an
# answer, or ask your instructor. Don't continue if you don't understand what's
# going on. That's not how it works ...
# #
# #
# ============================================================================== # ==============================================================================

12
BIN-ALI-BLAST.R
View File

@ -1,4 +1,10 @@
# BIN-ALI-BLAST.R # tocID <- "BIN-ALI-BLAST.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-ALI-BLAST unit. # R code accompanying the BIN-ALI-BLAST unit.
@ -29,13 +35,13 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> --------------------------------------------------- #TOC> ---------------------------------------------------
#TOC> 1 Defining the APSES domain 42 #TOC> 1 Defining the APSES domain 42
#TOC> 2 Executing the BLAST search 64 #TOC> 2 Executing the BLAST search 64
#TOC> 3 Analysing results 86 #TOC> 3 Analysing results 86
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

12
BIN-ALI-Dotplot.R
View File

@ -1,4 +1,10 @@
# BIN-ALI-Dotplot.R # tocID <- "BIN-ALI-Dotplot.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-ALI-Dotplot unit. # R code accompanying the BIN-ALI-Dotplot unit.
@ -27,12 +33,12 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> -------------------------------------- #TOC> --------------------------------------
#TOC> 1 ___Section___ 39 #TOC> 1 ___Section___ 39
#TOC> 2 Tasks 187 #TOC> 2 Tasks 187
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

14
BIN-ALI-MSA.R
View File

@ -1,4 +1,10 @@
# BIN-ALI-MSA.R # tocID <- "BIN-ALI-MSA.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-ALI-MSA unit. # R code accompanying the BIN-ALI-MSA unit.
@ -29,7 +35,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ------------------------------------------------------------------ #TOC> ------------------------------------------------------------------
#TOC> 1 Preparations 54 #TOC> 1 Preparations 54
@ -47,7 +53,7 @@
#TOC> 6 Sequence Logos 546 #TOC> 6 Sequence Logos 546
#TOC> 6.1 Subsetting an alignment by motif 555 #TOC> 6.1 Subsetting an alignment by motif 555
#TOC> 6.2 Plot a Sequence Logo 604 #TOC> 6.2 Plot a Sequence Logo 604
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -239,7 +245,7 @@ for (i in seq_along(highScoringRanges$lengths)) {
# - adjust the sequence names # - adjust the sequence names
# - convert to msaAAMultipleAlignment object # - convert to msaAAMultipleAlignment object
# === 4.1.1 importing an .aln file # === 4.1.1 importing an .aln file
# The seqinr package has a function to read CLUSTAL W formatted .aln files ... # The seqinr package has a function to read CLUSTAL W formatted .aln files ...
if (! requireNamespace("seqinr", quietly=TRUE)) { if (! requireNamespace("seqinr", quietly=TRUE)) {

8
BIN-ALI-Optimal_sequence_alignment.R
View File

@ -1,4 +1,10 @@
# BIN-ALI-Optimal_sequence_alignment.R # tocID <- "BIN-ALI-Optimal_sequence_alignment.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-ALI-Optimal_sequence_alignment unit. # R code accompanying the BIN-ALI-Optimal_sequence_alignment unit.

12
BIN-ALI-Similarity.R
View File

@ -1,4 +1,10 @@
# BIN-ALI-Similarity.R # tocID <- "BIN-ALI-Similarity.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-ALI-Similarity unit. # R code accompanying the BIN-ALI-Similarity unit.
@ -28,13 +34,13 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ---------------------------------------------- #TOC> ----------------------------------------------
#TOC> 1 Amino Acid Properties 41 #TOC> 1 Amino Acid Properties 41
#TOC> 2 Mutation Data matrix 158 #TOC> 2 Mutation Data matrix 158
#TOC> 3 Background score 199 #TOC> 3 Background score 199
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

12
BIN-Data_integration.R
View File

@ -1,4 +1,10 @@
# BIN-Data_integration.R # tocID <- "BIN-Data_integration.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-Data_integration unit. # R code accompanying the BIN-Data_integration unit.
@ -30,12 +36,12 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ------------------------------------------------- #TOC> -------------------------------------------------
#TOC> 1 Identifier mapping 42 #TOC> 1 Identifier mapping 42
#TOC> 2 Cross-referencing tables 165 #TOC> 2 Cross-referencing tables 165
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

14
BIN-FUNC-Domain_annotation.R
View File

@ -1,4 +1,10 @@
# BIN-FUNC-Domain_annotation.R # tocID <- "BIN-FUNC-Domain_annotation.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-FUNC-Domain_annotation unit. # R code accompanying the BIN-FUNC-Domain_annotation unit.
@ -25,7 +31,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ----------------------------------------------------------------------------------- #TOC> -----------------------------------------------------------------------------------
#TOC> 1 Update your database script 41 #TOC> 1 Update your database script 41
@ -34,7 +40,7 @@
#TOC> 1.1.2 If you HAVE done the BIN-ALI-Optimal_sequence_alignment 93 #TOC> 1.1.2 If you HAVE done the BIN-ALI-Optimal_sequence_alignment 93
#TOC> 1.2 Execute and Validate 119 #TOC> 1.2 Execute and Validate 119
#TOC> 2 Plot Annotations 144 #TOC> 2 Plot Annotations 144
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -90,7 +96,7 @@
# Then SKIP the next section. # Then SKIP the next section.
# #
# #
# === 1.1.2 If you HAVE done the BIN-ALI-Optimal_sequence_alignment # === 1.1.2 If you HAVE done the BIN-ALI-Optimal_sequence_alignment
# #
# #
# You DO already have a file called "<MYSPE>-Annotations.json" in the # You DO already have a file called "<MYSPE>-Annotations.json" in the

34
BIN-FUNC-Semantic_similarity.R
View File

@ -1,4 +1,10 @@
# BIN-FUNC_Semantic_similarity.R # tocID <- "BIN-FUNC_Semantic_similarity.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-FUNC_Semantic_similarity unit. # R code accompanying the BIN-FUNC_Semantic_similarity unit.
@ -28,14 +34,14 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> -------------------------------------------------------------------- #TOC> --------------------------------------------------------------------
#TOC> 1 Preparations: Packages, AnnotationDB, Setup 42 #TOC> 1 Preparations: Packages, AnnotationDB, Setup 42
#TOC> 2 Fetch GO Annotations 98 #TOC> 2 Fetch GO Annotations 98
#TOC> 3 Semantic Similarities 107 #TOC> 3 Semantic Similarities 107
#TOC> 4 GO Term Enrichment in Gene Sets 125 #TOC> 4 GO Term Enrichment in Gene Sets 125
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -158,27 +164,9 @@ myEnr <- GOenrichment(mySet, allGenes)
sort(myEnr$p.values) # Any significantly enriched terms? All of these are ... sort(myEnr$p.values) # Any significantly enriched terms? All of these are ...
#Yes: most significantly enriched is GO:0071931. What is this? #Most significantly enriched is GO:0071931. What is this?
getGOTerm("GO:0071931") # ... makes sense. annotate::getGOTerm("GO:0071931") # ... makes sense.
(fullSet <- myEnr$genes$`GO:0071931`) # What genes are annotated to this term?
intersect(mySet, fullSet) # These are in both sets
setdiff(mySet, fullSet) # These mySet members are not annotated to that term
setdiff(fullSet, mySet) # These are annotated to that term but not in mySet.
# ... that's the most interesting set. From a set of
# genes we have identified a function that they
# share, and that shared function has allowed us
# to identify
# What are these genes?
# Select annotations from the annotation database:
AnnotationDbi::select(org.Sc.sgd.db,
keys = setdiff(fullSet, mySet),
columns = c("COMMON", "DESCRIPTION"))
# Note that these annotations are partially redundant to several different
# aliases of the same three genes.

8
BIN-MYSPE.R
View File

@ -1,4 +1,10 @@
# BIN-MYSPE.R # tocID <- "BIN-MYSPE.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-MYSPE unit # R code accompanying the BIN-MYSPE unit

12
BIN-PHYLO-Data_preparation.R
View File

@ -1,4 +1,10 @@
# BIN-PHYLO-Data_preparation.R # tocID <- "BIN-PHYLO-Data_preparation.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-PHYLO-Data_preparation unit. # R code accompanying the BIN-PHYLO-Data_preparation unit.
@ -29,7 +35,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> --------------------------------------------------------- #TOC> ---------------------------------------------------------
#TOC> 1 Preparations 44 #TOC> 1 Preparations 44
@ -37,7 +43,7 @@
#TOC> 3 Multiple Sequence Alignment 117 #TOC> 3 Multiple Sequence Alignment 117
#TOC> 4 Reviewing and Editing Alignments 136 #TOC> 4 Reviewing and Editing Alignments 136
#TOC> 4.1 Masking workflow 152 #TOC> 4.1 Masking workflow 152
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

12
BIN-PHYLO-Tree_analysis.R
View File

@ -1,4 +1,10 @@
# BIN-PHYLO-Tree_analysis.R # tocID <- "BIN-PHYLO-Tree_analysis.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-PHYLO-Tree_analysis unit. # R code accompanying the BIN-PHYLO-Tree_analysis unit.
@ -31,7 +37,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> -------------------------------------------------- #TOC> --------------------------------------------------
#TOC> 1 Preparation and Tree Plot 46 #TOC> 1 Preparation and Tree Plot 46
@ -39,7 +45,7 @@
#TOC> 2.1 Rooting Trees 145 #TOC> 2.1 Rooting Trees 145
#TOC> 2.2 Rotating Clades 190 #TOC> 2.2 Rotating Clades 190
#TOC> 2.3 Computing tree distances 241 #TOC> 2.3 Computing tree distances 241
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

20
BIN-PHYLO-Tree_building.R
View File

@ -1,4 +1,10 @@
# BIN-PHYLO-Tree_building.R # tocID <- "BIN-PHYLO-Tree_building.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-PHYLO-Tree_building unit. # R code accompanying the BIN-PHYLO-Tree_building unit.
@ -29,7 +35,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ----------------------------------------------------------- #TOC> -----------------------------------------------------------
#TOC> 1 Calculating Trees 46 #TOC> 1 Calculating Trees 46
@ -39,7 +45,7 @@
#TOC> 1.1.3 ... on Linux 96 #TOC> 1.1.3 ... on Linux 96
#TOC> 1.1.4 Confirming PROMLPATH 101 #TOC> 1.1.4 Confirming PROMLPATH 101
#TOC> 1.2 Building a maximum likelihood tree 110 #TOC> 1.2 Building a maximum likelihood tree 110
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -68,7 +74,7 @@ if (! requireNamespace("Rphylip", quietly = TRUE)) {
# on your computer Phylip has been installed and define the path # on your computer Phylip has been installed and define the path
# to the proml program that calculates a maximum-likelihood tree. # to the proml program that calculates a maximum-likelihood tree.
# === 1.1.1 ... on the Mac # === 1.1.1 ... on the Mac
# On the Mac, the standard installation places a phylip folder # On the Mac, the standard installation places a phylip folder
# in the /Applications directory. That folder contains all the # in the /Applications directory. That folder contains all the
# individual phylip programs as <name>.app files. These are not # individual phylip programs as <name>.app files. These are not
@ -79,7 +85,7 @@ if (! requireNamespace("Rphylip", quietly = TRUE)) {
# directly to that subdirectory to find the program it needs: # directly to that subdirectory to find the program it needs:
# PROMLPATH <- "/Applications/phylip-3.695/exe/proml.app/Contents/MacOS" # PROMLPATH <- "/Applications/phylip-3.695/exe/proml.app/Contents/MacOS"
# === 1.1.2 ... on Windows # === 1.1.2 ... on Windows
# On Windows you need to know where the programs have been installed, and you # On Windows you need to know where the programs have been installed, and you
# need to specify a path that is correct for the Windows OS. Find the folder # need to specify a path that is correct for the Windows OS. Find the folder
# that is named "exe", and right-click to inspect its properties. The path # that is named "exe", and right-click to inspect its properties. The path
@ -93,12 +99,12 @@ if (! requireNamespace("Rphylip", quietly = TRUE)) {
# I have heard that your path must not contain spaces, and it is prudent to # I have heard that your path must not contain spaces, and it is prudent to
# avoid other special characters as well. # avoid other special characters as well.
# === 1.1.3 ... on Linux # === 1.1.3 ... on Linux
# If you are running Linux I trust you know what to do. It's probably # If you are running Linux I trust you know what to do. It's probably
# something like # something like
# PROMLPATH <- "/usr/local/phylip-3.695/bin" # PROMLPATH <- "/usr/local/phylip-3.695/bin"
# === 1.1.4 Confirming PROMLPATH # === 1.1.4 Confirming PROMLPATH
# Confirm that the settings are right. # Confirm that the settings are right.
PROMLPATH # returns the path PROMLPATH # returns the path
list.dirs(PROMLPATH) # returns the directories in that path list.dirs(PROMLPATH) # returns the directories in that path

12
BIN-PPI-Analysis.R
View File

@ -1,4 +1,10 @@
# BIN-PPI-Analysis.R # tocID <- "BIN-PPI-Analysis.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-PPI-Analysis unit. # R code accompanying the BIN-PPI-Analysis unit.
@ -29,7 +35,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> --------------------------------------------------------------- #TOC> ---------------------------------------------------------------
#TOC> 1 Setup and data 46 #TOC> 1 Setup and data 46
@ -39,7 +45,7 @@
#TOC> 2.3 Betweenness Centrality 180 #TOC> 2.3 Betweenness Centrality 180
#TOC> 3 biomaRt 226 #TOC> 3 biomaRt 226
#TOC> 4 Task for submission 296 #TOC> 4 Task for submission 296
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

12
BIN-SEQA-Composition.R
View File

@ -1,4 +1,10 @@
# BIN-SEQA-Composition.R # tocID <- "BIN-SEQA-Composition.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-SEQA-Comparison unit # R code accompanying the BIN-SEQA-Comparison unit
@ -29,7 +35,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ---------------------------------------------------------- #TOC> ----------------------------------------------------------
#TOC> 1 Preparation 47 #TOC> 1 Preparation 47
@ -40,7 +46,7 @@
#TOC> 3.3 Plotting log ratios 185 #TOC> 3.3 Plotting log ratios 185
#TOC> 3.4 Sort by frequency 200 #TOC> 3.4 Sort by frequency 200
#TOC> 3.5 Color by amino acid type 215 #TOC> 3.5 Color by amino acid type 215
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

24
BIN-Sequence.R
View File

@ -1,4 +1,10 @@
# BIN-Sequence.R # tocID <- "BIN-Sequence.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-Sequence unit. # R code accompanying the BIN-Sequence unit.
@ -30,7 +36,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ---------------------------------------------------- #TOC> ----------------------------------------------------
#TOC> 1 Prepare 63 #TOC> 1 Prepare 63
@ -50,7 +56,7 @@
#TOC> 7.2 Sampling 306 #TOC> 7.2 Sampling 306
#TOC> 7.2.1 Equiprobable characters 308 #TOC> 7.2.1 Equiprobable characters 308
#TOC> 7.2.2 Defined probability vector 350 #TOC> 7.2.2 Defined probability vector 350
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -171,16 +177,16 @@ cat(sprintf("\n%s fish", c("one", "two", "red", "blue")))
# = 6 Changing strings ==================================================== # = 6 Changing strings ====================================================
# === 6.1.1 Changing case # === 6.1.1 Changing case
tolower(s) tolower(s)
toupper(tolower(s)) toupper(tolower(s))
# === 6.1.2 Reverse # === 6.1.2 Reverse
reverse(s) reverse(s)
# === 6.1.3 Change characters # === 6.1.3 Change characters
# chartr(old, new, x) maps all characters in x that appear in "old" to the # chartr(old, new, x) maps all characters in x that appear in "old" to the
# correpsonding character in "new." # correpsonding character in "new."
@ -208,7 +214,7 @@ chartr(myCypher, lett, x)
# (Nb. substitution cyphers are easy to crack!) # (Nb. substitution cyphers are easy to crack!)
# === 6.1.4 Substitute characters # === 6.1.4 Substitute characters
(s <- gsub("IV", "i-v", s)) # gsub can change length, first argument is (s <- gsub("IV", "i-v", s)) # gsub can change length, first argument is
# a "regular expression"! # a "regular expression"!
@ -305,7 +311,7 @@ sum(d <= 2.5) # 276. 276 of our 10000 samples are just as bunched near the
# == 7.2 Sampling ========================================================== # == 7.2 Sampling ==========================================================
# === 7.2.1 Equiprobable characters # === 7.2.1 Equiprobable characters
# Assume you need a large random-nucleotide string for some statistical model. # Assume you need a large random-nucleotide string for some statistical model.
# How to create such a string? sample() can easily create it: # How to create such a string? sample() can easily create it:
@ -347,7 +353,7 @@ length(unlist(x))
# of the smaller number of Cs and Gs - before biology even comes into play. How # of the smaller number of Cs and Gs - before biology even comes into play. How
# do we account for that? # do we account for that?
# === 7.2.2 Defined probability vector # === 7.2.2 Defined probability vector
# This is where we need to know how to create samples with specific probability # This is where we need to know how to create samples with specific probability
# distributions. A crude hack would be to create a sampling source vector with # distributions. A crude hack would be to create a sampling source vector with

22
BIN-Storing_data.R
View File

@ -1,4 +1,10 @@
# BIN-Storing_data.R # tocID <- "BIN-Storing_data.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the BIN-Storing_data unit # R code accompanying the BIN-Storing_data unit
@ -27,7 +33,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ----------------------------------------------------------------------- #TOC> -----------------------------------------------------------------------
#TOC> 1 A Relational Datamodel in R: review 57 #TOC> 1 A Relational Datamodel in R: review 57
@ -50,7 +56,7 @@
#TOC> 3.3 Create an R script to create your own database 535 #TOC> 3.3 Create an R script to create your own database 535
#TOC> 3.3.1 Check and validate 555 #TOC> 3.3.1 Check and validate 555
#TOC> 3.4 Task: submit for credit (part 2/2) 596 #TOC> 3.4 Task: submit for credit (part 2/2) 596
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -205,7 +211,7 @@ str(philDB)
# go back, re-read, play with it, and ask for help. This is essential. # go back, re-read, play with it, and ask for help. This is essential.
# === 1.1.1 completing the database # === 1.1.1 completing the database
# Next I'll add one more person, and create the other two tables: # Next I'll add one more person, and create the other two tables:
@ -369,7 +375,7 @@ dbSanitizeSequence(x)
# == 2.3 Create a protein table for our data model ========================= # == 2.3 Create a protein table for our data model =========================
# === 2.3.1 Initialize the database # === 2.3.1 Initialize the database
# The function dbInit contains all the code to return a list of empty # The function dbInit contains all the code to return a list of empty
@ -381,7 +387,7 @@ myDB <- dbInit()
str(myDB) str(myDB)
# === 2.3.2 Add data # === 2.3.2 Add data
# fromJSON() returns a dataframe that we can readily process to add data # fromJSON() returns a dataframe that we can readily process to add data
@ -428,7 +434,7 @@ source("./scripts/ABC-createRefDB.R")
str(myDB) str(myDB)
# === 2.4.1 Examples of navigating the database # === 2.4.1 Examples of navigating the database
# You can look at the contents of the tables in the usual way we access # You can look at the contents of the tables in the usual way we access
@ -552,7 +558,7 @@ myDB$taxonomy$species[sel]
# in any of the JSON files. Later you will add more information ... # in any of the JSON files. Later you will add more information ...
# === 3.3.1 Check and validate # === 3.3.1 Check and validate
# Is your protein named according to the pattern "MBP1_MYSPE"? It should be. # Is your protein named according to the pattern "MBP1_MYSPE"? It should be.

12
FND-Genetic_code.R
View File

@ -1,4 +1,10 @@
# FND-Genetic_code.R # tocID <- "FND-Genetic_code.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the FND-Genetic_code unit. # R code accompanying the FND-Genetic_code unit.
@ -28,7 +34,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ---------------------------------------------------------------- #TOC> ----------------------------------------------------------------
#TOC> 1 Storing the genetic code 45 #TOC> 1 Storing the genetic code 45
@ -38,7 +44,7 @@
#TOC> 3 An alternative representation: 3D array 212 #TOC> 3 An alternative representation: 3D array 212
#TOC> 3.1 Print a Genetic code table 246 #TOC> 3.1 Print a Genetic code table 246
#TOC> 4 Tasks 272 #TOC> 4 Tasks 272
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

14
FND-MAT-Graphs_and_networks.R
View File

@ -1,4 +1,10 @@
# FND-MAT-Graphs_and_networks.R # tocID <- "FND-MAT-Graphs_and_networks.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the FND-MAT-Graphs_and_networks unit. # R code accompanying the FND-MAT-Graphs_and_networks unit.
@ -29,7 +35,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ------------------------------------------------------------ #TOC> ------------------------------------------------------------
#TOC> 1 Review 50 #TOC> 1 Review 50
@ -43,7 +49,7 @@
#TOC> 4 RANDOM GRAPHS AND GRAPH METRICS 539 #TOC> 4 RANDOM GRAPHS AND GRAPH METRICS 539
#TOC> 4.1 Diameter 576 #TOC> 4.1 Diameter 576
#TOC> 5 GRAPH CLUSTERING 645 #TOC> 5 GRAPH CLUSTERING 645
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -280,7 +286,7 @@ plot(GBA,
vertex.color=heat.colors(max(igraph::degree(GBA)+1))[igraph::degree(GBA)+1], vertex.color=heat.colors(max(igraph::degree(GBA)+1))[igraph::degree(GBA)+1],
vertex.size = 200 + (30 * igraph::degree(GBA)), vertex.size = 200 + (30 * igraph::degree(GBA)),
vertex.label = NA) vertex.label = NA)
par(oPar) # restore grphics state par(oPar) # restore graphics state
# This is a very obviously different graph! Some biological networks have # This is a very obviously different graph! Some biological networks have
# features that look like that - but in my experience the hub nodes are usually # features that look like that - but in my experience the hub nodes are usually

41
FND-STA-Information_theory.R
View File

@ -1,14 +1,21 @@
# FND-STA-Information_theory.R # tocID <- "FND-STA-Information_theory.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the FND-STA-Information_theory unit. # R code accompanying the FND-STA-Information_theory unit.
# #
# Version: 0.2 # Version: 0.2.1
# #
# Date: 2017 MM DD # Date: 2017 - 2019
# Author: Boris Steipe (boris.steipe@utoronto.ca) # Author: Boris Steipe (boris.steipe@utoronto.ca)
# #
# Versions: # Versions:
# 0.2.1 Maintenance
# 0.2 Under development # 0.2 Under development
# 0.1 First code copied from 2016 material. # 0.1 First code copied from 2016 material.
# #
@ -58,11 +65,33 @@ AAref["Y"] <- 0.0294
sum(AAref) sum(AAref)
# Function to calculate Shannon entropy # Function to calculate Shannon entropy
H <- function(v) { H <- function(pmf) {
# Shannon entropy (bits) # Calculate Shannon entropy
return(-sum(v * (log(v) / log(2)))) # Parameters:
# pmf (numeric) probability mass function: a vector of states and
# associated probabilities. Each element of
# pmf must be in (0, 1] and sum(pmf) must be 1.
# Value:
# Shannon entropy in bits.
# Examples:
# H(c(A=0.25, C=0.25, G=0.25, T=0.25)) # 2 bits entropy in a random
# # nucleotide sequence
# H(1) # If all elements are the same, entropy is zero
#
if (any(pmf <= 0 | pmf > 1) || isFALSE(all.equal(1.0, sum(pmf)))) {
stop("Input is not a discrete probability distribution.")
}
H <- -sum(pmf * (log(pmf) / log(2)))
return(H)
} }
# Why use all.equal()? Exact comparisons with floating point numbers are
# brittle. Consider for example:
1/6 + 1/6 + 1/6 + 1/6 + 1/6 + 1/6 == 1
print(1/6 + 1/6 + 1/6 + 1/6 + 1/6 + 1/6, digits = 22) # 0.9999999999999998889777
# all.equal() tests for _near_ equality with tolerance of ~ 1.5e-8
# Entropy of the database frequencies (in bits): # Entropy of the database frequencies (in bits):
(Href <- H(AAref)) (Href <- H(AAref))

16
FND-STA-Probability_distribution.R
View File

@ -1,4 +1,10 @@
# FND-STA-Probability_distribution.R # tocID <- "FND-STA-Probability_distribution.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the FND-STA-Probability_distribution unit. # R code accompanying the FND-STA-Probability_distribution unit.
@ -28,7 +34,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ----------------------------------------------------------------------------- #TOC> -----------------------------------------------------------------------------
#TOC> 1 Introduction 52 #TOC> 1 Introduction 52
@ -45,7 +51,7 @@
#TOC> 4.2.1 An example from tossing dice 463 #TOC> 4.2.1 An example from tossing dice 463
#TOC> 4.2.2 An example from lognormal distributions 586 #TOC> 4.2.2 An example from lognormal distributions 586
#TOC> 4.3 Kolmogorov-Smirnov test for continuous distributions 629 #TOC> 4.3 Kolmogorov-Smirnov test for continuous distributions 629
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -460,7 +466,7 @@ chisq.test(countsL1, countsG1.9, simulate.p.value = TRUE, B = 10000)
# be applied to discrete distributions. But we need to talk a bit about # be applied to discrete distributions. But we need to talk a bit about
# converting counts to p.m.f.'s. # converting counts to p.m.f.'s.
# === 4.2.1 An example from tossing dice # === 4.2.1 An example from tossing dice
# The p.m.f of an honest die is (1:1/6, 2:1/6, 3:1/6, 4:1/6, 5:1/6, 6:1/6). But # The p.m.f of an honest die is (1:1/6, 2:1/6, 3:1/6, 4:1/6, 5:1/6, 6:1/6). But
# there is an issue when we convert sampled counts to frequencies, and estimate # there is an issue when we convert sampled counts to frequencies, and estimate
@ -583,7 +589,7 @@ abline(v = KLdiv(rep(1/6, 6), pmfPC(counts, 1:6)), col="firebrick")
# somewhat but not drastically atypical. # somewhat but not drastically atypical.
# === 4.2.2 An example from lognormal distributions # === 4.2.2 An example from lognormal distributions
# We had compared a set of lognormal and gamma distributions above, now we # We had compared a set of lognormal and gamma distributions above, now we
# can use KL-divergence to quantify their similarity: # can use KL-divergence to quantify their similarity:

14
FND-STA-Significance.R
View File

@ -1,4 +1,10 @@
# FND-STA-Significance.R # tocID <- "FND-STA-Significance.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the FND-STA-Significance unit. # R code accompanying the FND-STA-Significance unit.
@ -25,7 +31,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ------------------------------------------------------------------ #TOC> ------------------------------------------------------------------
#TOC> 1 Significance and p-value 43 #TOC> 1 Significance and p-value 43
@ -36,7 +42,7 @@
#TOC> 3 Significance by integration 198 #TOC> 3 Significance by integration 198
#TOC> 4 Significance by simulation or permutation 204 #TOC> 4 Significance by simulation or permutation 204
#TOC> 5 Final tasks 312 #TOC> 5 Final tasks 312
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -100,7 +106,7 @@ print(x, digits = 22)
# curve, as a fraction of the whole. # curve, as a fraction of the whole.
# === 1.2.1 p-value illustrated # === 1.2.1 p-value illustrated
# Let's illustrate. First we draw a million random values from our # Let's illustrate. First we draw a million random values from our
# standard, normal distribution: # standard, normal distribution:

2
README.md
View File

@ -1,2 +1,4 @@
# ABC-units # ABC-units
A Bioinformatics Course: R modules for learning units A Bioinformatics Course: R modules for learning units
Follow the instructions in the learning unit to install your local copy of this R-project.

8
RPR-Biostrings.R
View File

@ -1,4 +1,10 @@
# RPR-Biostrings.R # tocID <- "RPR-Biostrings.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-Biostrings unit. # R code accompanying the RPR-Biostrings unit.

8
RPR-FASTA.R
View File

@ -1,4 +1,10 @@
# RPR-FASTA.R # tocID <- "RPR-FASTA.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-FASTA unit. # R code accompanying the RPR-FASTA unit.

12
RPR-GEO2R.R
View File

@ -1,4 +1,10 @@
# RPR_GEO2R.R # tocID <- "RPR_GEO2R.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR_GEO2R unit. # R code accompanying the RPR_GEO2R unit.
@ -34,7 +40,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> -------------------------------------------------------------------------- #TOC> --------------------------------------------------------------------------
#TOC> 1 Preparations 56 #TOC> 1 Preparations 56
@ -49,7 +55,7 @@
#TOC> 5.1 Final task: Gene descriptions 504 #TOC> 5.1 Final task: Gene descriptions 504
#TOC> 6 Improving on Discovery by Differential Expression 510 #TOC> 6 Improving on Discovery by Differential Expression 510
#TOC> 7 Annotation data 594 #TOC> 7 Annotation data 594
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

20
RPR-Genetic_code_optimality.R
View File

@ -1,4 +1,10 @@
# RPR-Genetic_code_optimality.R # tocID <- "RPR-Genetic_code_optimality.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-Genetic_code_optimality unit. # R code accompanying the RPR-Genetic_code_optimality unit.
@ -30,7 +36,7 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> -------------------------------------------------------------- #TOC> --------------------------------------------------------------
#TOC> 1 Designing a computational experiment 57 #TOC> 1 Designing a computational experiment 57
@ -43,7 +49,7 @@
#TOC> 2.2.4 measure effect 213 #TOC> 2.2.4 measure effect 213
#TOC> 3 Run the experiment 260 #TOC> 3 Run the experiment 260
#TOC> 4 Task solutions 356 #TOC> 4 Task solutions 356
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================
@ -142,7 +148,7 @@ swappedGC <- function(GC) {
# - we count the number of mutations and evaluate their severity. # - we count the number of mutations and evaluate their severity.
# === 2.2.1 reverse-translate # === 2.2.1 reverse-translate
# To reverse-translate an amino acid vector, we randomly pick one of its # To reverse-translate an amino acid vector, we randomly pick one of its
# codons from a genetic code, and assemble all codons to a sequence. # codons from a genetic code, and assemble all codons to a sequence.
@ -167,7 +173,7 @@ traRev <- function(s, GC) {
} }
# === 2.2.2 Randomly mutate # === 2.2.2 Randomly mutate
# To mutate, we split a codon into it's three nucleotides, then randomly replace # To mutate, we split a codon into it's three nucleotides, then randomly replace
# one of the three with another nucleotide. # one of the three with another nucleotide.
@ -192,7 +198,7 @@ randMut <- function(vC) {
# === 2.2.3 Forward- translate # === 2.2.3 Forward- translate
traFor <- function(vC, GC) { traFor <- function(vC, GC) {
# Parameters: # Parameters:
@ -210,7 +216,7 @@ traFor <- function(vC, GC) {
} }
# === 2.2.4 measure effect # === 2.2.4 measure effect
# How do we evaluate the effect of the mutation? We'll take a simple ad hoc # How do we evaluate the effect of the mutation? We'll take a simple ad hoc
# approach: we divide amino acids into hydrophobic, hydrophilic, and neutral # approach: we divide amino acids into hydrophobic, hydrophilic, and neutral

8
RPR-Introduction.R
View File

@ -1,4 +1,10 @@
# RPR-Introduction.R # tocID <- "RPR-Introduction.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-Introduction unit # R code accompanying the RPR-Introduction unit

12
RPR-PROSITE_POST.R
View File

@ -1,4 +1,10 @@
# RPR-PROSITE_POST.R # tocID <- "RPR-PROSITE_POST.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-Scripting_data_downloads unit. # R code accompanying the RPR-Scripting_data_downloads unit.
@ -29,13 +35,13 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> --------------------------------------------------------------------- #TOC> ---------------------------------------------------------------------
#TOC> 1 Constructing a POST command from a Web query 42 #TOC> 1 Constructing a POST command from a Web query 42
#TOC> 1.1 Task - fetchPrositeFeatures() function 142 #TOC> 1.1 Task - fetchPrositeFeatures() function 142
#TOC> 2 Task solutions 150 #TOC> 2 Task solutions 150
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

8
RPR-RegEx.R
View File

@ -1,4 +1,10 @@
# RPR-RegEx.R # tocID <- "RPR-RegEx.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-RegEx unit # R code accompanying the RPR-RegEx unit

8
RPR-SX-PDB.R
View File

@ -1,4 +1,10 @@
# RPR-SX-PDB.R # tocID <- "RPR-SX-PDB.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-SX-PDB unit. # R code accompanying the RPR-SX-PDB unit.

12
RPR-UniProt_GET.R
View File

@ -1,4 +1,10 @@
# RPR-UniProt_GET.R # tocID <- "RPR-UniProt_GET.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-Scripting_data_downloads unit. # R code accompanying the RPR-Scripting_data_downloads unit.
@ -28,13 +34,13 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ---------------------------------------------------------- #TOC> ----------------------------------------------------------
#TOC> 1 UniProt files via GET 41 #TOC> 1 UniProt files via GET 41
#TOC> 1.1 Task - fetchUniProtSeq() function 103 #TOC> 1.1 Task - fetchUniProtSeq() function 103
#TOC> 2 Task solutions 110 #TOC> 2 Task solutions 110
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

16
RPR-Unit_testing.R
View File

@ -1,4 +1,10 @@
# RPR-Unit_testing.R # tocID <- "RPR-Unit_testing.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-Unit_testing unit. # R code accompanying the RPR-Unit_testing unit.
@ -29,10 +35,10 @@
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ------------------------------------------------- #TOC> -------------------------------------------------
#TOC> 1 Unit Tests with testthat 40 #TOC> 1 Unit Tests with testthat 46
#TOC> 2 Organizing your tests 159 #TOC> 2 Organizing your tests 165
#TOC> 2.1 Testing scripts 183 #TOC> 2.1 Testing scripts 189
#TOC> 3 Task solutions 198 #TOC> 3 Task solutions 204
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

12
RPR-eUtils_XML.R
View File

@ -1,4 +1,10 @@
# RPR-eUtils_and_XML.R # tocID <- "RPR-eUtils_and_XML.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
# #
# Purpose: A Bioinformatics Course: # Purpose: A Bioinformatics Course:
# R code accompanying the RPR-Scripting_data_downloads unit. # R code accompanying the RPR-Scripting_data_downloads unit.
@ -28,13 +34,13 @@
#TOC> ========================================================================== #TOC> ==========================================================================
#TOC> #TOC>
#TOC> Section Title Line #TOC> Section Title Line
#TOC> ----------------------------------------------------------- #TOC> -----------------------------------------------------------
#TOC> 1 Working with NCBI eUtils 41 #TOC> 1 Working with NCBI eUtils 41
#TOC> 1.1 Task - fetchNCBItaxData() function 144 #TOC> 1.1 Task - fetchNCBItaxData() function 144
#TOC> 2 Task solutions 151 #TOC> 2 Task solutions 151
#TOC> #TOC>
#TOC> ========================================================================== #TOC> ==========================================================================

2
scripts/ABC-createRefDB.R
View File

@ -8,7 +8,7 @@
# http://steipe.biochemistry.utoronto.ca/abc/index.php/Reference_species_for_fungi # http://steipe.biochemistry.utoronto.ca/abc/index.php/Reference_species_for_fungi
# #
# For the data model, see # For the data model, see
# https://docs.google.com/drawings/d/1uupNvz18_FYFwyyVPebTM0CUxcJCPDQuxuIJGpjWQWg # https://docs.google.com/presentation/d/13vWaVcFpWEOGeSNhwmqugj2qTQuH1eZROgxWdHGEMr0
# For the schema, see dbInit() in ./scripts/ABC-dbUtilities.R # For the schema, see dbInit() in ./scripts/ABC-dbUtilities.R
# #
# ============================================================================== # ==============================================================================

82
scripts/ABC-dbUtilities.R
View File

@ -1,12 +1,35 @@
# ABC-dbUtilities.R # tocID <- "scripts/ABC-dbUtilities.R"
#
# database utilities for ABC learning units # database utilities for ABC learning units
# #
# ============================================================================== # ==============================================================================
#
# ====== PACKAGES ============================================================== #TOC> ==========================================================================
#TOC>
#TOC> Section Title Line
#TOC> -------------------------------------------------
#TOC> 1 PACKAGES 32
#TOC> 2 FUNCTIONS 50
#TOC> 2.01 dbSanitizeSequence() 53
#TOC> 2.02 dbConfirmUnique() 88
#TOC> 2.03 dbInit() 106
#TOC> 2.04 dbAutoincrement() 147
#TOC> 2.05 dbAddProtein() 160
#TOC> 2.06 dbAddFeature() 180
#TOC> 2.07 dbAddTaxonomy() 199
#TOC> 2.08 dbAddAnnotation() 215
#TOC> 2.09 dbFetchUniProtSeq() 243
#TOC> 2.10 dbFetchPrositeFeatures() 267
#TOC> 2.11 node2text() 311
#TOC> 2.12 dbFetchNCBItaxData() 323
#TOC> 2.13 UniProtIDmap() 362
#TOC> 3 TESTS 399
#TOC>
#TOC> ==========================================================================
# = 1 PACKAGES ============================================================
if (! requireNamespace("jsonlite", quietly = TRUE)) { if (! requireNamespace("jsonlite", quietly = TRUE)) {
@ -24,9 +47,10 @@ if (! requireNamespace("xml2", quietly = TRUE)) {
} }
# ====== FUNCTIONS ============================================================= # = 2 FUNCTIONS ===========================================================
# == 2.01 dbSanitizeSequence() =============================================
dbSanitizeSequence <- function(s, unambiguous = TRUE) { dbSanitizeSequence <- function(s, unambiguous = TRUE) {
# Remove FASTA header lines, if any, # Remove FASTA header lines, if any,
# flatten any structure that s has, # flatten any structure that s has,
@ -61,6 +85,7 @@ dbSanitizeSequence <- function(s, unambiguous = TRUE) {
} }
# == 2.02 dbConfirmUnique() ================================================
dbConfirmUnique <- function(x) { dbConfirmUnique <- function(x) {
# x is a vector of logicals. # x is a vector of logicals.
# returns x if x has exactly one TRUE element. # returns x if x has exactly one TRUE element.
@ -78,24 +103,27 @@ dbConfirmUnique <- function(x) {
} }
# == 2.03 dbInit() =========================================================
dbInit <- function() { dbInit <- function() {
# Return an empty instance of the protein database # Return an empty instance of the protein database
# Open the link and study the schema:
# https://docs.google.com/presentation/d/13vWaVcFpWEOGeSNhwmqugj2qTQuH1eZROgxWdHGEMr0
db <- list() db <- list()
db$version <- "1.0"
db$protein <- data.frame( db$protein <- data.frame(
ID = numeric(), ID = numeric(),
name = character(), name = character(),
RefSeqID = character(), RefSeqID = character(),
UniProtID = character(), UniProtID = character(),
taxonomyID = numeric(), taxonomyID = numeric(),
sequence = character(), sequence = character())
stringsAsFactors = FALSE)
db$taxonomy <- data.frame( db$taxonomy <- data.frame(
ID = numeric(), ID = numeric(),
species = character(), species = character())
stringsAsFactors = FALSE)
db$annotation <- data.frame( db$annotation <- data.frame(
@ -103,21 +131,20 @@ dbInit <- function() {
proteinID = numeric(), proteinID = numeric(),
featureID = numeric(), featureID = numeric(),
start = numeric(), start = numeric(),
end = numeric(), end = numeric())
stringsAsFactors = FALSE)
db$feature <- data.frame( db$feature <- data.frame(
ID = numeric(), ID = numeric(),
name = character(), name = character(),
description = character(), description = character(),
sourceDB = character(), sourceDB = character(),
accession = character(), accession = character())
stringsAsFactors = FALSE)
return(db) return(db)
} }
# == 2.04 dbAutoincrement() ================================================
dbAutoincrement <- function(tb) { dbAutoincrement <- function(tb) {
# Return a unique integer that can be used as a primary key # Return a unique integer that can be used as a primary key
# Value: # Value:
@ -130,6 +157,7 @@ dbAutoincrement <- function(tb) {
} }
# == 2.05 dbAddProtein() ===================================================
dbAddProtein <- function(db, jsonDF) { dbAddProtein <- function(db, jsonDF) {
# Add one or more protein entries to the database db. # Add one or more protein entries to the database db.
# Parameters: # Parameters:
@ -142,14 +170,14 @@ dbAddProtein <- function(db, jsonDF) {
RefSeqID = jsonDF$RefSeqID[i], RefSeqID = jsonDF$RefSeqID[i],
UniProtID = jsonDF$UniProtID[i], UniProtID = jsonDF$UniProtID[i],
taxonomyID = jsonDF$taxonomyID[i], taxonomyID = jsonDF$taxonomyID[i],
sequence = dbSanitizeSequence(jsonDF$sequence[i]), sequence = dbSanitizeSequence(jsonDF$sequence[i]))
stringsAsFactors = FALSE)
db$protein <- rbind(db$protein, x) db$protein <- rbind(db$protein, x)
} }
return(db) return(db)
} }
# == 2.06 dbAddFeature() ===================================================
dbAddFeature <- function(db, jsonDF) { dbAddFeature <- function(db, jsonDF) {
# Add one or more feature entries to the database db. # Add one or more feature entries to the database db.
# Parameters: # Parameters:
@ -161,14 +189,14 @@ dbAddFeature <- function(db, jsonDF) {
name = jsonDF$name[i], name = jsonDF$name[i],
description = jsonDF$description[i], description = jsonDF$description[i],
sourceDB = jsonDF$sourceDB[i], sourceDB = jsonDF$sourceDB[i],
accession = jsonDF$accession[i], accession = jsonDF$accession[i])
stringsAsFactors = FALSE)
db$feature <- rbind(db$feature, x) db$feature <- rbind(db$feature, x)
} }
return(db) return(db)
} }
# == 2.07 dbAddTaxonomy() ==================================================
dbAddTaxonomy <- function(db, jsonDF) { dbAddTaxonomy <- function(db, jsonDF) {
# Add one or more taxonomy entries to the database db. # Add one or more taxonomy entries to the database db.
# Parameters: # Parameters:
@ -178,13 +206,13 @@ dbAddTaxonomy <- function(db, jsonDF) {
for (i in seq_len(nrow(jsonDF))) { for (i in seq_len(nrow(jsonDF))) {
x <- data.frame( x <- data.frame(
ID = jsonDF$ID[i], ID = jsonDF$ID[i],
species = jsonDF$species[i], species = jsonDF$species[i])
stringsAsFactors = FALSE)
db$taxonomy <- rbind(db$taxonomy, x) db$taxonomy <- rbind(db$taxonomy, x)
} }
return(db) return(db)
} }
# == 2.08 dbAddAnnotation() ================================================
dbAddAnnotation <- function(db, jsonDF) { dbAddAnnotation <- function(db, jsonDF) {
# Add one or more annotation entries to the database db. # Add one or more annotation entries to the database db.
# Parameters: # Parameters:
@ -205,14 +233,14 @@ dbAddAnnotation <- function(db, jsonDF) {
proteinID = pID, proteinID = pID,
featureID = fID, featureID = fID,
start = as.integer(jsonDF$start[i]), start = as.integer(jsonDF$start[i]),
end = as.integer(jsonDF$end[i]), end = as.integer(jsonDF$end[i]))
stringsAsFactors = FALSE)
db$annotation <- rbind(db$annotation, x) db$annotation <- rbind(db$annotation, x)
} }
return(db) return(db)
} }
# == 2.09 dbFetchUniProtSeq() ==============================================
dbFetchUniProtSeq <- function(ID) { dbFetchUniProtSeq <- function(ID) {
# Fetch a protein sequence from UniProt. # Fetch a protein sequence from UniProt.
# Parameters: # Parameters:
@ -236,6 +264,7 @@ dbFetchUniProtSeq <- function(ID) {
} }
# == 2.10 dbFetchPrositeFeatures() =========================================
dbFetchPrositeFeatures <- function(ID) { dbFetchPrositeFeatures <- function(ID) {
# Fetch feature annotations from ScanProsite. # Fetch feature annotations from ScanProsite.
# Parameters: # Parameters:
@ -272,14 +301,14 @@ dbFetchPrositeFeatures <- function(ID) {
start = as.numeric(tokens[4]), start = as.numeric(tokens[4]),
end = as.numeric(tokens[5]), end = as.numeric(tokens[5]),
psID = tokens[6], psID = tokens[6],
psName = tokens[7], psName = tokens[7]))
stringsAsFactors = FALSE))
} }
} }
return(myFeatures) return(myFeatures)
} }
# == 2.11 node2text() ======================================================
node2text <- function(doc, tag) { node2text <- function(doc, tag) {
# an extractor function for the contents of elements # an extractor function for the contents of elements
# between given tags in an XML response. # between given tags in an XML response.
@ -291,6 +320,7 @@ node2text <- function(doc, tag) {
} }
# == 2.12 dbFetchNCBItaxData() =============================================
dbFetchNCBItaxData <- function(ID) { dbFetchNCBItaxData <- function(ID) {
# Fetch feature taxID and Organism from the NCBI. # Fetch feature taxID and Organism from the NCBI.
# Parameters: # Parameters:
@ -329,6 +359,7 @@ dbFetchNCBItaxData <- function(ID) {
# == 2.13 UniProtIDmap() ===================================================
UniProtIDmap <- function (s, mapFrom = "P_REFSEQ_AC", mapTo = "ACC") { UniProtIDmap <- function (s, mapFrom = "P_REFSEQ_AC", mapTo = "ACC") {
# Use UniProt ID mapping service to map one or more IDs # Use UniProt ID mapping service to map one or more IDs
# Parameters: # Parameters:
@ -351,8 +382,7 @@ UniProtIDmap <- function (s, mapFrom = "P_REFSEQ_AC", mapTo = "ACC") {
if (httr::status_code(response) == 200) { # 200: oK if (httr::status_code(response) == 200) { # 200: oK
myMap <- read.delim(file = textConnection(httr::content(response)), myMap <- read.delim(file = textConnection(httr::content(response)),
sep = "\t", sep = "\t")
stringsAsFactors = FALSE)
myMap <- myMap[ , c(1,3)] myMap <- myMap[ , c(1,3)]
colnames(myMap) <- c("From", "To") colnames(myMap) <- c("From", "To")
} else { } else {
@ -366,7 +396,7 @@ UniProtIDmap <- function (s, mapFrom = "P_REFSEQ_AC", mapTo = "ACC") {
} }
# ====== TESTS ================================================================= # = 3 TESTS ===============================================================
if (FALSE) { if (FALSE) {
if (! requireNamespace("testthat", quietly = TRUE)) { if (! requireNamespace("testthat", quietly = TRUE)) {

2
scripts/ABC-makeScCCnet.R
View File

@ -1,4 +1,4 @@
# ABC-makeScCCnet.R # tocID <- "scripts/ABC-makeScCCnet.R"
# #
# Create a subnetwork of high-confidence yeast genes with a "mitotic cell cycle" # Create a subnetwork of high-confidence yeast genes with a "mitotic cell cycle"
# GOSlim annotation. # GOSlim annotation.

2
scripts/ABC-writeALN.R
View File

@ -1,4 +1,4 @@
# ABC-writeALN.R # tocID <- "scripts/ABC-writeALN.R"
# #
# ToDo: calculate consensus line # ToDo: calculate consensus line
# append sequence numbers # append sequence numbers

4
scripts/ABC-writeMFA.R
View File

@ -40,7 +40,7 @@ writeMFA <- function(ali,
if (is.na(blockWidth)) { if (is.na(blockWidth)) {
stop("PANIC: parameter \"blockWidth\" must be numeric.") stop("PANIC: parameter \"blockWidth\" must be numeric.")
} }
if (blockWidth < 1){ if (! blockWidth > 0){
stop("PANIC: parameter \"blockWidth\" must be greater than zero.") stop("PANIC: parameter \"blockWidth\" must be greater than zero.")
} }
@ -105,7 +105,7 @@ writeMFA <- function(ali,
txt <- c(txt, "") # append an empty line for readability txt <- c(txt, "") # append an empty line for readability
} }
writeLines(txt, con= myCon) writeLines(txt, con = myCon)
} }

31
scripts/BLAST.R
View File

@ -357,20 +357,23 @@ parseBLASTalignment <- function(hit) {
# ==== TESTS =================================================================== # ==== TESTS ===================================================================
# define query: if (FALSE) {
# q <- paste("IYSARYSGVDVYEFIHSTGSIMKRKKDDWVNATHI", # Mbp1 APSES domain # define query:
# "LKAANFAKAKRTRILEKEVLKETHEKVQGGFGKYQ", q <- paste("IYSARYSGVDVYEFIHSTGSIMKRKKDDWVNATHI", # Mbp1 APSES domain
# "GTWVPLNIAKQLAEKFSVYDQLKPLFDFTQTDGSASP", "LKAANFAKAKRTRILEKEVLKETHEKVQGGFGKYQ",
# sep="") "GTWVPLNIAKQLAEKFSVYDQLKPLFDFTQTDGSASP",
# or ... sep="")
# q <- "NP_010227" # refseq ID # or ...
# q <- "NP_010227" # refseq ID
# test <- BLAST(q,
# nHits = 100, test <- BLAST(q,
# E = 0.001, nHits = 100,
# rid = "", E = 0.001,
# limits = "txid4751[ORGN]") rid = "",
# length(test$hits) limits = "txid4751[ORGN]")
str(test)
length(test$hits)
}
# [END] # [END]