Data Science

What does it mean that biology is now a “data science”?

Modern biology relies heavily on collecting, analyzing, and interpreting large datasets using computational tools

How are computers involved in modern biological and medical research?

Computers are used in every step, including experimental design, data collection, data analysis, visualization, and interpretation

What is a computer, according to the lecture definition?

A machine that stores information, manipulates information according to rules, and produces new information as output

What are the three basic steps everything a computer does reduces to?

Input, processing, and output

What are binary digits (bits)?

The smallest units of information in a computer, represented as 0 or 1

Why do computers use binary instead of continuous values?

Binary is robust to noise and easy to represent physically as on/off or high/low voltage states

What is the role of the central processing unit (CPU)?

The CPU executes instructions, including arithmetic, logical comparisons, and data movement

What does it mean that modern CPUs have multiple cores?

They can perform multiple operations in parallel, increasing computational speed

What is random access memory (RAM)?

Temporary, fast-access memory that stores active data, variables, and intermediate results

Why is RAM considered volatile?

Its contents are lost when the computer is powered off

What is long-term storage used for?

Storing data and programs permanently, even when the computer is powered off

How does storage differ from RAM?

Storage is much larger and non-volatile but significantly slower to access than RAM

What is the operating system (OS)?

Software that manages hardware resources, schedules programs, allocates memory, and handles files and errors

What is code in the context of computing?

A precise, human-readable set of instructions that tells a computer exactly what to do

What is R and how does it compare to other languages?

R is a programming language designed for statistics, data analysis, and visualization; compared to other tools, it excels at reproducible analysis and scientific graphics, while other languages like Python are more general-purpose and Excel is not reproducible

What is swirl in R?

An interactive R package used to learn R by typing responses directly into the console

Where is swirl used in RStudio?

Only in the Console pane, not the Script pane

What do file extensions define?

The type of data contained in a file and which programs can open it

What are the four fundamental data types in R?

Numeric, character, logical, and missing values (NA)

What is an object (variable) in R?

A container that stores data and has a name, value, and data type

How are objects created in R?

Using the assignment operator <-

What does the class() function do?

It returns the data type of an object

What is a vector in R?

An object that stores a sequence of values of the same data type

How are vectors created in R?

Using the c() function

What is indexing in R?

Accessing elements of a vector using square brackets

What types of values can be used for indexing?

Numeric indices or logical values

What is a function in R?

A small program that takes inputs called arguments and returns output

How can ranges of values be created in R?

Using the colon operator or the seq() function

What are error messages in R?

Messages produced when R cannot run a command due to syntax or logical problems

How do warnings differ from errors in R?

Warnings do not stop the program but indicate something unusual may have occurred

What does the error “object not found” mean?

R cannot find an object with that name in memory

What causes errors from using the wrong data type?

Providing a function with a type of data it cannot operate on

Why does forgetting quotes around strings cause an error?

R interprets unquoted text as an object name instead of character data

What causes missing or extra parentheses errors?

An unmatched opening or closing parenthesis in a command

What are the two key functions for using packages in R?

install.packages() to install a package and library() to load it into memory

What are SNP tables used for in biology?

To organize genotype data with rows as samples and columns as genomic loci

What does geographic occurrence data represent in a matrix?

Locations arranged in rows and columns corresponding to geographic points or samples

What is gene expression data commonly stored as in R?

A matrix with rows as samples and columns as genes

Define a matrix in R.

A 2D array where all elements must be of the same data type

What does SNP stand for and mean?

Single Nucleotide Polymorphism; a position in the genome with variation among individuals

What is polymorphism in genetics?

The existence of multiple alleles or genetic variants within a population

What distinguishes gene expression matrices from other data?

They quantify gene activity levels across samples, arranged in matrix form

What is a data frame in R?

A 2D data structure that can hold different data types in each column

How do you create a data frame in R?

Using the data.frame() function with vectors as columns

hat is the purpose of the $ operator in R?

To access a specific named column in a data frame

How do you index elements in matrices or data frames?

Using square brackets [row, column]

What are logical operators used for in R?

To evaluate expressions and return TRUE or FALSE values

What is a logical expression?

A statement in R that evaluates to TRUE or FALSE

Name some common comparison operators in R.

== (equal), != (not equal), <, >, <=, >=

What does the logical AND operator (&) do?

Returns TRUE only if both sides of the expression are TRUE

What does the logical OR operator (|) do?

Returns TRUE if either or both sides of the expression are TRUE

Why should you avoid recycling vectors in logical operations?

Because recycling shorter vectors can cause unintended comparisons and warnings

How can logical expressions be useful when working with biological data?

For filtering datasets based on conditions, such as genotypes or expression thresholds