Cell Biology: The Foundation of Life Sciences

# Install (if needed) and load ggplot2
if (!requireNamespace("ggplot2", quietly = TRUE)) {
  install.packages("ggplot2", repos = "https://cloud.r-project.org")
}
library(ggplot2)

# Install (if needed) and load required packages
if (!requireNamespace("ggrepel", quietly = TRUE)) {
  install.packages("ggrepel", repos = "https://cloud.r-project.org")
}
library(ggrepel)

# Optional: if you later get an error for scale_color_viridis_d, either:
#   - update ggplot2, or
#   - install viridis and use viridis::scale_color_viridis(discrete = TRUE)
if (!requireNamespace("viridis", quietly = TRUE)) {
  install.packages("viridis", repos = "https://cloud.r-project.org")
}
# library(viridis)  # not required if ggplot2 is recent

# R: Cell Biology Applications Analysis
# Market trends and research impact assessment

# Biotechnology market data (simplified)
biotech_markets <- data.frame(
    application = c("Cell Therapy", "Drug Discovery", "Diagnostics", "Vaccines", 
                   "Tissue Engineering", "Gene Therapy", "Biomanufacturing"),
    market_size_billion_usd = c(15.2, 65.2, 45.1, 35.8, 8.9, 12.4, 28.7),
    growth_rate_percent = c(12.5, 8.7, 6.9, 9.2, 15.2, 18.4, 11.3),
    cell_based = c(TRUE, TRUE, FALSE, TRUE, TRUE, TRUE, TRUE),
    maturity = c("Emerging", "Mature", "Mature", "Mature", "Emerging", "Emerging", "Growing")
)

# Research publication trends (hypothetical data)
research_trends <- data.frame(
    year = 2015:2024,
    stem_cells = c(2500, 2800, 3200, 3800, 4200, 4800, 5200, 5800, 6200, 6800),
    cancer_biology = c(8000, 8500, 9200, 9800, 10500, 11200, 11800, 12500, 13100, 13800),
    gene_editing = c(800, 1200, 1800, 2800, 4200, 6000, 7200, 8500, 9800, 11000),
    synthetic_biology = c(600, 800, 1100, 1500, 2000, 2600, 3200, 3900, 4800, 5500)
)

# Create market analysis plot
market_plot <- ggplot(biotech_markets, aes(x = market_size_billion_usd, 
                                           y = growth_rate_percent, 
                                           color = maturity,
                                           size = market_size_billion_usd)) +
    geom_point(alpha = 0.8) +
    geom_text_repel(aes(label = application), size = 3) +
    scale_color_viridis_d() +
    labs(title = "Cell Biology Applications Market Analysis",
         subtitle = "Market Size vs Growth Rate (2024)",
         x = "Market Size (Billion USD)",
         y = "Annual Growth Rate (%)",
         color = "Market Maturity",
         size = "Market Size") +
    theme_minimal() +
    guides(size = "none") +
    geom_hline(yintercept = 10, linetype = "dashed", alpha = 0.5) +
    annotate("text", x = 60, y = 10.5, label = "High growth threshold", size = 3)

print(market_plot)

# Research trends visualization
# Reshape data for plotting
research_long <- data.frame(
    year = rep(research_trends$year, 4),
    publications = c(research_trends$stem_cells, research_trends$cancer_biology,
                    research_trends$gene_editing, research_trends$synthetic_biology),
    field = rep(c("Stem Cells", "Cancer Biology", "Gene Editing", "Synthetic Biology"), 
               each = length(research_trends$year))
)

research_plot <- ggplot(research_long, aes(x = year, y = publications, color = field)) +
    geom_line(size = 1.2) +
    geom_point(size = 2) +
    scale_color_viridis_d() +
    scale_x_continuous(breaks = seq(2015, 2024, 2)) +
    labs(title = "Research Publication Trends in Cell Biology",
         subtitle = "Annual Publications by Field (2015-2024)",
         x = "Year",
         y = "Number of Publications",
         color = "Research Field") +
    theme_minimal() +
    theme(legend.position = "bottom")

print(research_plot)

# Cell-based therapy timeline
therapy_milestones <- data.frame(
    year = c(1990, 1995, 2003, 2012, 2017, 2020, 2024),
    milestone = c("First gene therapy", "Stem cell discovery", "Human genome", 
                  "iPSC therapies", "CAR-T approval", "COVID vaccines", "CRISPR therapies"),
    impact = c(6, 8, 9, 8, 9, 10, 9),
    category = c("Gene", "Stem Cell", "Genomics", "Stem Cell", "Immune", "Vaccine", "Gene")
)

timeline_plot <- ggplot(therapy_milestones, aes(x = year, y = impact, color = category)) +
    geom_point(size = 4, alpha = 0.8) +
    geom_line(aes(group = 1), alpha = 0.4, size = 1) +
    geom_text_repel(aes(label = milestone), size = 3) +
    scale_x_continuous(breaks = seq(1990, 2025, 5)) +
    scale_y_continuous(breaks = 1:10) +
    scale_color_viridis_d() +
    labs(title = "Cell-Based Therapy Milestones",
         subtitle = "Major Breakthroughs in Clinical Applications (1990-2024)",
         x = "Year",
         y = "Clinical Impact (1-10)",
         color = "Therapy Type") +
    theme_minimal()

print(timeline_plot)

# Analysis summary
cat("\n=== Cell Biology Applications Analysis ===\n")

# Market analysis
total_market <- sum(biotech_markets$market_size_billion_usd)
cell_based_market <- sum(biotech_markets[biotech_markets$cell_based, "market_size_billion_usd"])
cell_based_percentage <- (cell_based_market / total_market) * 100

cat("Biotechnology market insights:\n")
cat("  Total market size:", total_market, "billion USD\n")
cat("  Cell-based applications:", round(cell_based_percentage, 1), "%\n")

fastest_growing <- biotech_markets[which.max(biotech_markets$growth_rate_percent), ]
largest_market <- biotech_markets[which.max(biotech_markets$market_size_billion_usd), ]
cat("  Fastest growing:", fastest_growing$application, 
    "(", fastest_growing$growth_rate_percent, "%/year)\n")
cat("  Largest market:", largest_market$application, 
    "(", largest_market$market_size_billion_usd, "billion USD)\n")

# Research trends analysis
cat("\nResearch publication growth (2015-2024):\n")
fields <- c("stem_cells", "cancer_biology", "gene_editing", "synthetic_biology")
field_names <- c("Stem Cells", "Cancer Biology", "Gene Editing", "Synthetic Biology")

for(i in 1:length(fields)) {
    initial <- research_trends[[fields[i]]][1]
    final <- research_trends[[fields[i]]][length(research_trends[[fields[i]]])]
    growth_factor <- final / initial
    cat(sprintf("  %s: %.1f× increase (%d to %d publications)\n", 
                field_names[i], growth_factor, initial, final))
}

# Therapy development timeline
cat("\nTherapy development timeline:\n")
timeline_span <- max(therapy_milestones$year) - min(therapy_milestones$year)
avg_impact <- mean(therapy_milestones$impact)
cat("  Development span:", timeline_span, "years\n")
cat("  Average clinical impact:", round(avg_impact, 1), "/10\n")

# Identify highest impact therapies
high_impact <- therapy_milestones[therapy_milestones$impact >= 9, ]
cat("  Major breakthroughs (impact ≥ 9):\n")
for(i in 1:nrow(high_impact)) {
    cat("    ", high_impact$year[i], ":", high_impact$milestone[i], "\n")
}