1 Problem 1: Patient Registry

1.1 Background

You are building a simple registry of three patients enrolled in a diabetes study: “Rahim”, “Karim”, and “Sultana”.

1.1.1 Task

Create a character vector with their names and print the second patient.

#  character vector
patients <- c("Rahim", "Karim", "Sultana")

# second patient
patients[2]
## [1] "Karim"

2 Problem 2: Blood Pressure Data

2.1 Background

Systolic blood pressure (SBP) values were recorded for four hypertensive patients: 145, 160, 138, 152.

2.1.1 Task

Store these in a numeric vector and extract the 3rd and 4th patients’ SBP.

sbp <- c(145, 160, 138, 152)
sbp[c(3, 4)]
## [1] 138 152

3 Problem 3: Gene Expression Counts

3.1 Background

Expression counts for the gene TP53 were measured in four samples: 500, 800, 450, 600.

3.1.1 Task

Create a vector and calculate the mean expression.

tp53_counts <- c(500, 800, 450, 600)
mean(tp53_counts)
## [1] 587.5

4 Problem 4: Small Cohort Data Frame

4.1 Task

Create a data frame from the dataset (Name, Age, BMI).

name <- c("Ali", "Sonia", "Kabir")
age <- c(35, 29, 41)
bmi <- c(24.5, 28.2, 31.0)
cohort_df <- data.frame(Name = name, Age = age, BMI = bmi)
cohort_df
##    Name Age  BMI
## 1   Ali  35 24.5
## 2 Sonia  29 28.2
## 3 Kabir  41 31.0

5 Problem 5: Add BMI Classification

5.1 Background

For clinical interpretation, classify BMI into: “Normal” if < 25; “Overweight” if 25–29.9; “Obese” if ≥ 30

5.1.1 Task

Add a new column “BMI_Class” to the data frame.

cohort_df$BMI_Class <- ifelse(cohort_df$BMI < 25, "Normal",
                  ifelse(cohort_df$BMI < 30, "Overweight",
                         "Obese"))
cohort_df
##    Name Age  BMI  BMI_Class
## 1   Ali  35 24.5     Normal
## 2 Sonia  29 28.2 Overweight
## 3 Kabir  41 31.0      Obese

6 Problem 6: Subset Patients by Age

6.1 Background

Researchers want only participants older than 30 years.

6.1.1 Task

Use conditional indexing to filter the data frame.

cohort_over30 <- cohort_df[cohort_df$Age > 30, ]
cohort_over30
##    Name Age  BMI BMI_Class
## 1   Ali  35 24.5    Normal
## 3 Kabir  41 31.0     Obese

7 Problem 7: Subset Patients by BMI

7.1 Background:

The team wants to see patients classified as “Obese”.

7.1.1 Task:

Filter the data frame to select only those rows.

cohort_obese <- cohort_df[cohort_df$BMI_Class == "Obese", ]
cohort_obese
##    Name Age BMI BMI_Class
## 3 Kabir  41  31     Obese

8 Problem 8: Create a Gene Expression Matrix

8.1 Background:

You measured expression of three genes (BRCA1, EGFR, MYC) across

three patients.

Gene P1 P2 P3

BRCA1 120 150 130

EGFR 300 350 400

MYC 800 900 950

8.2 Task:

Create this as a matrix with proper row and column names.

# Create a gene expression matrix
gene_expression <- matrix(
  c(120, 150, 130,
    300, 350, 400,
    800, 900, 950),
  nrow = 3,
  byrow = TRUE)

# Assign row names (genes)
rownames(gene_expression) <- c("BRCA1", "EGFR", "MYC")

# Assign column names (patients)
colnames(gene_expression) <- c("P1", "P2", "P3")

# Display the matrix
gene_expression
##        P1  P2  P3
## BRCA1 120 150 130
## EGFR  300 350 400
## MYC   800 900 950

9 Problem 9: Extract Specific Expression Value

9.1 Background:

You want MYC’s expression for Patient 2.

9.1.1 Task:

Extract this value from your matrix.

gene_expression["MYC", "P2"]
## [1] 900

10 Problem 10: Create a Multi-Object List

10.1 Background:

You want to store different analysis objects together: 1. A vector of patient ages: 35, 29, 41 2. The gene expression matrix from Problem 8 3. The nutrition data frame from Problem 4

10.1.1 Task:

Create a list with these three objects.

patient_age <- c(25, 29, 41)

multi_list <- list(patientAge= patient_age,
                   GeneExpression= gene_expression,
                   Nutritional= cohort_df)
multi_list
## $patientAge
## [1] 25 29 41
## 
## $GeneExpression
##        P1  P2  P3
## BRCA1 120 150 130
## EGFR  300 350 400
## MYC   800 900 950
## 
## $Nutritional
##    Name Age  BMI  BMI_Class
## 1   Ali  35 24.5     Normal
## 2 Sonia  29 28.2 Overweight
## 3 Kabir  41 31.0      Obese

#P roblem 11: Extract from a List

10.2 Background:

You want to analyze EGFR expression across all patients.

10.2.1 Task:

Extract the second row of the matrix from the list.

multi_list$GeneExpression[2, ]
##  P1  P2  P3 
## 300 350 400

11 Problem 12: Conditional Statement for Glucose Check

11.1 Background:

Fasting blood glucose (FBG) was measured for a patient and stored as x. • If FBG < 100 → “Normal” • If FBG 100–125 → “Prediabetes” • If FBG ≥ 126 → “Diabetes”

11.1.1 Task:

Write an if-else statement to classify the patient based on x.

# Assign fasting blood glucose value
x <- 115

# Classify blood glucose level
if (x < 100) {print("Normal") } else if (x >= 100 & x <= 125) {print("Prediabetes")} else {print("Diabetes")}
## [1] "Prediabetes"

12 Problem 13: Identify High-Risk Patients

12.1 Background:

A cardiovascular study defines “high risk” as patients who are both older

than 40 years AND have BMI ≥ 30.

Name Age BMI

Tania 42 31.5

Mahir 37 28.0

Jui 45 29.5

Imran 50 32.0

12.2 Task:

    1. Create this as a data frame.

Use conditional indexing to extract patients classified as “high risk.”

# Create patient data frame
cv_patients <- data.frame(
  Name = c("Tania", "Mahir", "Jui", "Imran"),
  Age = c(42, 37, 45, 50),
  BMI = c(31.5, 28.0, 29.5, 32.0))

# Display the data frame
cv_patients
##    Name Age  BMI
## 1 Tania  42 31.5
## 2 Mahir  37 28.0
## 3   Jui  45 29.5
## 4 Imran  50 32.0
# Select patients older than 40 years AND BMI >= 30
high_risk <- cv_patients[
  cv_patients$Age > 40 & cv_patients$BMI >= 30, ]

# Display high-risk patients
high_risk
##    Name Age  BMI
## 1 Tania  42 31.5
## 4 Imran  50 32.0

13 Problem 14: Integrate DiYerent Biomedical Data in a List

13.1 Background:

In an oncology project, you need to store:

• A patient demographic data frame (Name, Age, Sex).

• A matrix of tumor marker expression values (CA125, CEA, PSA across 3 patients).

• A vector of survival times (months).

13.1.1 Task:

  1. Create a list containing all three objects.

  2. Extract:

o The CEA expression for the 2nd patient.

o The survival time for the 3rd patient.

# Patient demographic information
patient_demo <- data.frame(
  Name = c("Tania", "Mahir", "Jui"),
  Age = c(42, 37, 45),
  Sex = c("Female", "Male", "Female"))

# Display demographic data
patient_demo
##    Name Age    Sex
## 1 Tania  42 Female
## 2 Mahir  37   Male
## 3   Jui  45 Female
# Tumor marker expression values
tumor_expression <- matrix(
  c(120, 150, 130,
    300, 350, 400,
    800, 900, 950),
  nrow = 3, byrow = TRUE)

# Assign row and column names
rownames(tumor_expression) <- c("CA125", "CEA", "PSA")
colnames(tumor_expression) <- c("P1", "P2", "P3")

# Display matrix
tumor_expression
##        P1  P2  P3
## CA125 120 150 130
## CEA   300 350 400
## PSA   800 900 950
# Survival time in months
survival_time <- c(24, 36, 18)

# Combine all three objects into a list
oncology_data <- list(
  Demographics = patient_demo,
  Tumor_Expression = tumor_expression,
  Survival_Time = survival_time)

# Display the list
oncology_data
## $Demographics
##    Name Age    Sex
## 1 Tania  42 Female
## 2 Mahir  37   Male
## 3   Jui  45 Female
## 
## $Tumor_Expression
##        P1  P2  P3
## CA125 120 150 130
## CEA   300 350 400
## PSA   800 900 950
## 
## $Survival_Time
## [1] 24 36 18
# Extract the CEA expression for the second patient
oncology_data$Tumor_Expression["CEA", "P2"]
## [1] 350
# Extract the survival time for the third patient
oncology_data$Survival_Time[3]
## [1] 18

14 Problem 15: Automated Classification of Anemia Status

14.1 Background:

Hemoglobin (Hb) values were measured for 6 patients: 11.2, 13.5, 9.8, 14.1, 12.0, 8.7. WHO guidelines: • Hb < 12 → “Anemia” • Hb ≥ 12 → “Normal”

14.2 Task:

Store the Hb values in a vector. Use ifelse() to create a classification vector (“Anemia” or “Normal”). Add this classification as a new column in a data frame of patients.

# Store hemoglobin values
Hb <- c(11.2, 13.5, 9.8, 14.1, 12.0, 8.7)

# Display Hb values
Hb
## [1] 11.2 13.5  9.8 14.1 12.0  8.7
# Use ifelse() to classify anemia status

Anemia_Status <- ifelse(Hb < 12, "Anemia", "Normal")

# Display classification
Anemia_Status
## [1] "Anemia" "Normal" "Anemia" "Normal" "Normal" "Anemia"
# Create patient data frame

patient_data_An <- data.frame(
  Patient_ID = c("P1", "P2", "P3", "P4", "P5", "P6"),
  Hb = Hb,
  Anemic_patient = Anemia_Status)

# Display patient data
patient_data_An
##   Patient_ID   Hb Anemic_patient
## 1         P1 11.2         Anemia
## 2         P2 13.5         Normal
## 3         P3  9.8         Anemia
## 4         P4 14.1         Normal
## 5         P5 12.0         Normal
## 6         P6  8.7         Anemia