database.json

{
  "categories": [
    {
      "name": "类别比较",
      "count": 346,
      "subcategories": [
        {
          "name": "箱线图",
          "count": 56
        },
        {
          "name": "小提琴图",
          "count": 36
        },
        {
          "name": "柱状图",
          "count": 171
        },
        {
          "name": "云雨图",
          "count": 7
        },
        {
          "name": "气泡热图",
          "count": 125
        },
        {
          "name": "棒棒糖图",
          "count": 6
        }
      ]
    },
    {
      "name": "数据关系",
      "count": 485,
      "subcategories": [
        {
          "name": "热图",
          "count": 180
        },
        {
          "name": "散点图",
          "count": 256
        },
        {
          "name": "网络图",
          "count": 99
        },
        {
          "name": "桑基图",
          "count": 4
        },
        {
          "name": "和弦图",
          "count": 35
        },
        {
          "name": "相关性图",
          "count": 37
        }
      ]
    },
    {
      "name": "组学研究",
      "count": 233,
      "subcategories": [
        {
          "name": "火山图",
          "count": 26
        },
        {
          "name": "富集分析",
          "count": 64
        },
        {
          "name": "单细胞图",
          "count": 112
        },
        {
          "name": "系统发育树",
          "count": 43
        },
        {
          "name": "染色体分布图",
          "count": 15
        },
        {
          "name": "曼哈顿图",
          "count": 6
        }
      ]
    },
    {
      "name": "数据分布",
      "count": 73,
      "subcategories": [
        {
          "name": "山脊图",
          "count": 6
        },
        {
          "name": "密度图",
          "count": 46
        },
        {
          "name": "三元相图",
          "count": 5
        },
        {
          "name": "雷达图",
          "count": 14
        }
      ]
    }
  ],
  "figures": [
    {
      "id": "fig_ridge_ggplot2_01",
      "title": "ggplot2优雅绘制山脊图(进阶版20230208)",
      "category": "数据分布",
      "chart_type": "山脊图",
      "framework": "R",
      "packages": [
        "ggplot2",
        "ggridges",
        "viridis",
        "hrbrthemes"
      ],
      "tags": [
        "山脊图",
        "数据分布",
        "多组分布",
        "进阶图表"
      ],
      "description": "基于 ggridges 绘制的多组连续变量分布山脊图，包含自定义渐变颜色映射与透明度叠加效果。",
      "code": "library(ggplot2)\nlibrary(ggridges)\nlibrary(viridis)\n\n# 生成示例数据或加载数据\ndf <- read.csv(\"sample_density_data.csv\")\n\n# 绘制山脊图\nggplot(df, aes(x = value, y = group, fill = ..x..)) +\n  geom_density_ridges_gradient(scale = 3, rel_min_height = 0.01) +\n  scale_fill_viridis(name = \"Value\", option = \"C\") +\n  labs(title = '多组连续数据分布山脊图',\n       subtitle = '基于 ggridges 与 viridis 色盘',\n       x = '测定值 (Value)', y = '分组 (Group)') +\n  theme_ridges(font_size = 13, grid = TRUE) +\n  theme(\n    legend.position = \"right\",\n    panel.spacing = unit(0.1, \"lines\"),\n    strip.text.x = element_text(size = 8)\n  )",
      "sample_data": {
        "format": "csv",
        "columns": [
          "group",
          "value"
        ],
        "preview": [
          {
            "group": "Group_A",
            "value": 12.4
          },
          {
            "group": "Group_A",
            "value": 14.1
          },
          {
            "group": "Group_B",
            "value": 22.8
          },
          {
            "group": "Group_C",
            "value": 18.3
          }
        ]
      },
      "visual_rules": {
        "palette": "viridis (C-Option) / Magma",
        "font_family": "Arial / Sans",
        "aspect_ratio": "4:3",
        "theme": "theme_ridges",
        "guidelines": "1. y轴分组需按生物学顺序或中位数排序；2. scale参数控制峰高重叠程度；3. 渐变填充适合表达分布区间演变。"
      },
      "agent_context": "【Agent 绘图上下文与修改指导】\n1. 当用户数据包含多个平行处理组（>3组）且需展现连续分布趋势时，优先推荐此图。\n2. 数据列映射：x 映射到连续数值列（如表达量、表达强度），y 映射到离散分组列。\n3. 若组别过多，建议通过 scale_fill_viridis 的 option 控制颜色区分度，或者调整 scale (1.5 ~ 3.5) 防止图像过于拥挤。"
    },
    {
      "id": "fig_monocle2_heatmap_02",
      "title": "2023-3-29 ggplot修饰monocle2拟时热图",
      "category": "数据关系",
      "chart_type": "热图",
      "framework": "R",
      "packages": [
        "monocle",
        "pheatmap",
        "viridis",
        "gridExtra"
      ],
      "tags": [
        "热图",
        "拟时序",
        "单细胞",
        "Monocle2",
        "基因动态表达"
      ],
      "description": "展示单细胞RNA-seq拟时序发育轨迹中差异表达基因的渐变热图，带有细胞拟时状态与分支注释。",
      "code": "library(monocle)\nlibrary(pheatmap)\n\n# 提取拟时差异基因\nsig_gene_names <- row.names(subset(diff_test_res, qval < 0.01))\n\n# 绘制 monocle2 拟时序热图\nplot_pseudotime_heatmap(\n  cds[sig_gene_names,],\n  num_clusters = 4,\n  cores = 4,\n  show_rownames = TRUE,\n  return_heatmap = TRUE\n)",
      "sample_data": {
        "format": "rds / SingleCellExperiment",
        "columns": [
          "gene_id",
          "pseudotime",
          "cell_state",
          "expression"
        ],
        "preview": [
          {
            "gene_id": "CD4",
            "pseudotime": 0.12,
            "cell_state": "State_1",
            "expression": 2.5
          },
          {
            "gene_id": "FOXP3",
            "pseudotime": 0.85,
            "cell_state": "State_3",
            "expression": 8.1
          }
        ]
      },
      "visual_rules": {
        "palette": "Navy-White-Firebrick (Custom Red-Blue gradient)",
        "font_family": "Helvetica",
        "aspect_ratio": "16:9",
        "theme": "pheatmap_default",
        "guidelines": "1. 表达量数据需做 Z-score 标准化；2. 聚类树应标注关键差异基因模块；3. 顶部需带有拟时序 (Pseudotime) 渐变色条。"
      },
      "agent_context": "【Agent 绘图上下文与修改指导】\n1. 用于单细胞拟时轨迹分析（Monocle2/Monocle3），展现基因随发育时间轴的表达模式演变。\n2. 建议控制展示基因数在 30-100 之间，若基因过多需设置 show_rownames = FALSE 并筛选 Top 标志基因标注。"
    },
    {
      "id": "fig_time_series_line_03",
      "title": "第6章 时间序列型图表",
      "category": "数据关系",
      "chart_type": "折线图",
      "framework": "Python",
      "packages": [
        "matplotlib",
        "seaborn",
        "pandas",
        "numpy"
      ],
      "tags": [
        "折线图",
        "时间序列",
        "置信区间",
        "多曲线"
      ],
      "description": "多变量时间序列走势图，包含均值折线与标准差/置信区间阴影带。",
      "code": "import matplotlib.pyplot as plt\nimport seaborn as sns\nimport pandas as pd\n\n# 设置样式\nsns.set_theme(style=\"whitegrid\", font=\"sans-serif\")\nplt.figure(figsize=(10, 6), dpi=300)\n\n# 绘制带置信区间的折线图\nax = sns.lineplot(\n    data=df,\n    x=\"date\", y=\"value\", hue=\"category\",\n    style=\"category\", markers=True, dashes=False,\n    errorbar=(\"ci\", 95), linewidth=2.5\n)\n\nplt.title(\"多指标时间序列动态走势\", fontsize=14, fontweight='bold', pad=15)\nplt.xlabel(\"时间 (Time)\", fontsize=12)\nplt.ylabel(\"测量指标 (Metric)\", fontsize=12)\nplt.legend(title=\"类别\", frameon=True)\nplt.tight_layout()\nplt.savefig(\"time_series_output.png\", dpi=300)",
      "sample_data": {
        "format": "json",
        "columns": [
          "date",
          "value",
          "category"
        ],
        "preview": [
          {
            "date": "2026-01-01",
            "value": 105.2,
            "category": "Control"
          },
          {
            "date": "2026-01-02",
            "value": 112.8,
            "category": "Treatment"
          }
        ]
      },
      "visual_rules": {
        "palette": "Set2 / Colorblind-friendly",
        "font_family": "DejaVu Sans",
        "aspect_ratio": "5:3",
        "theme": "sns.set_theme(style='whitegrid')",
        "guidelines": "1. 置信区间阴影设置透明度 alpha=0.2；2. 针对离散采样点配置数据点标记 (markers=True)。"
      },
      "agent_context": "【Agent 绘图上下文与修改指导】\n1. 适用于连续时间点、实验周期或动态监测量（如动物体重变化、临床随访指标）。\n2. x 轴自动解析日期或数值点，若类别多于 5 个，建议改用面板分图 (facet_grid)。"
    },
    {
      "id": "fig_density_mean_04",
      "title": "密度图+分组标记+均值线",
      "category": "数据分布",
      "chart_type": "密度图",
      "framework": "R",
      "packages": [
        "ggplot2",
        "dplyr",
        "gghalves"
      ],
      "tags": [
        "密度图",
        "数据分布",
        "分组对比",
        "均值线"
      ],
      "description": "多组数据重叠概率密度图，每组叠加虚线标示均值与文本注释。",
      "code": "library(ggplot2)\nlibrary(dplyr)\n\n# 计算各组均值\nmu <- df %>%\n  group_by(group) %>%\n  summarise(grp.mean = mean(value))\n\n# 绘制密度图\nggplot(df, aes(x = value, fill = group, color = group)) +\n  geom_density(alpha = 0.4, linewidth = 0.8) +\n  geom_vline(data = mu, aes(xintercept = grp.mean, color = group),\n             linetype = \"dashed\", linewidth = 1) +\n  scale_fill_manual(values = c(\"#E69F00\", \"#56B4E9\", \"#009E73\")) +\n  scale_color_manual(values = c(\"#E69F00\", \"#56B4E9\", \"#009E73\")) +\n  labs(title = \"组间概率密度分布与均值对比\",\n       x = \"测量指标 (Body Mass)\", y = \"概率密度 (Density)\") +\n  theme_minimal(base_size = 14) +\n  theme(legend.position = \"top\")",
      "sample_data": {
        "format": "csv",
        "columns": [
          "group",
          "value"
        ],
        "preview": [
          {
            "group": "Adelie",
            "value": 3700
          },
          {
            "group": "Chinstrap",
            "value": 3733
          },
          {
            "group": "Gentoo",
            "value": 5076
          }
        ]
      },
      "visual_rules": {
        "palette": "Okabe-Ito Colorblind Safe Palette",
        "font_family": "Arial",
        "aspect_ratio": "4:3",
        "theme": "theme_minimal",
        "guidelines": "1. 使用半透明 alpha (0.3-0.5) 避免重叠遮挡；2. 必须包含组均值虚线 (dashed vline)。"
      },
      "agent_context": "【Agent 绘图上下文与修改指导】\n1. 当用户需要对比 2-4 个平行组的概率分布形态及中心位置时最佳。\n2. 自动计算各组 Mean 或 Median 并标注垂直切线。"
    },
    {
      "id": "fig_volcano_omics_05",
      "title": "高水平发表级火山图 (Volcano Plot)",
      "category": "组学研究",
      "chart_type": "火山图",
      "framework": "R",
      "packages": [
        "EnhancedVolcano",
        "ggplot2",
        "ggrepel"
      ],
      "tags": [
        "火山图",
        "组学研究",
        "差异表达",
        "转录组",
        "Top基因标注"
      ],
      "description": "转录组/蛋白组差异分析标配火山图，清晰标注显著上调、下调基因及 Top Label。",
      "code": "library(EnhancedVolcano)\n\nEnhancedVolcano(res,\n  lab = rownames(res),\n  x = 'log2FoldChange',\n  y = 'pvalue',\n  pCutoff = 10e-6,\n  FCcutoff = 1.5,\n  pointSize = 3.0,\n  labSize = 4.0,\n  col=c('black', 'black', 'blue', 'red'),\n  colAlpha = 0.8,\n  legendPosition = 'right',\n  title = '差异基因火山图 (Volcano Plot)',\n  subtitle = 'Significant Up/Down Regulated Genes'\n)",
      "sample_data": {
        "format": "csv",
        "columns": [
          "gene_symbol",
          "log2FoldChange",
          "pvalue",
          "padj"
        ],
        "preview": [
          {
            "gene_symbol": "TP53",
            "log2FoldChange": 2.8,
            "pvalue": 1.2e-08,
            "padj": 3.4e-07
          },
          {
            "gene_symbol": "EGFR",
            "log2FoldChange": -3.1,
            "pvalue": 5.6e-09,
            "padj": 1.1e-07
          }
        ]
      },
      "visual_rules": {
        "palette": "Red (Up) / Blue (Down) / Grey (NS)",
        "font_family": "Arial",
        "aspect_ratio": "1:1",
        "theme": "EnhancedVolcano_theme",
        "guidelines": "1. 设置 log2FC cutoff (如 1.0 或 1.5) 与 p-value cutoff (如 0.05 或 1e-5)；2. 顶部显著基因使用 ggrepel 避让文本标签。"
      },
      "agent_context": "【Agent 绘图上下文与修改指导】\n1. RNA-seq / Proteomics / Metabolomics 差异表达分析的首选可视化方案。\n2. Agent 需要自动检测用户数据中的 log2FC 列和 pvalue/padj 列，并自动进行缺失值剔除。"
    },
    {
      "id": "fig_raincloud_06",
      "title": "云雨图 (Raincloud Plot - 半小提琴+箱线图+散点)",
      "category": "类别比较",
      "chart_type": "云雨图",
      "framework": "R",
      "packages": [
        "ggplot2",
        "ggdist",
        "gghalves"
      ],
      "tags": [
        "云雨图",
        "类别比较",
        "分布+散点",
        "顶刊图表"
      ],
      "description": "结合半透明概率密度（云）、箱线图（中位数）与原始样本散点（雨滴）的高信息量比较图。",
      "code": "library(ggplot2)\nlibrary(ggdist)\n\nggplot(df, aes(x = group, y = value, fill = group)) +\n  # 1. 云：密度图\n  stat_halfeye(\n    adjust = 0.5,\n    width = 0.6,\n    .width = 0,\n    justification = -0.2,\n    point_colour = NA\n  ) +\n  # 2. 箱线图\n  geom_boxplot(\n    width = 0.15,\n    outlier.shape = NA,\n    alpha = 0.5\n  ) +\n  # 3. 雨：散点\n  stat_dots(\n    side = \"left\",\n    justification = 1.1,\n    binwidth = 0.2\n  ) +\n  scale_fill_brewer(palette = \"Set2\") +\n  theme_minimal() +\n  labs(title = \"云雨图 (Raincloud Plot)\", x = \"实验组别\", y = \"测量值\")",
      "sample_data": {
        "format": "csv",
        "columns": [
          "group",
          "value"
        ],
        "preview": [
          {
            "group": "Control",
            "value": 15.2
          },
          {
            "group": "Drug_A",
            "value": 28.4
          },
          {
            "group": "Drug_B",
            "value": 34.1
          }
        ]
      },
      "visual_rules": {
        "palette": "RColorBrewer Set2 / Pastel",
        "font_family": "Arial",
        "aspect_ratio": "4:3",
        "theme": "theme_minimal",
        "guidelines": "1. 密度分布靠右，原始点阵靠左；2. 展现真实数据样本量的同时兼顾总体分布形状。"
      },
      "agent_context": "【Agent 绘图上下文与修改指导】\n1. 适合替代传统柱状图/小提琴图，展示小样本到中样本数据（N=10~100）。\n2. 提供最全面的原始数据真实分布表达。"
    },
    {
      "id": "fig_961f9a6e",
      "title": "Python Seaborn 双曼哈顿图 (Manhattan Plot)",
      "category": "组学研究",
      "chart_type": "曼哈顿图",
      "framework": "Python",
      "packages": [],
      "tags": [
        "曼哈顿图",
        "GWAS",
        "组学研究",
        "Python"
      ],
      "description": "用于全基因组关联分析 (GWAS) SNP 显著性分布的双向对比曼哈顿图。",
      "code": "import seaborn as sns...",
      "sample_data": {},
      "visual_rules": {},
      "agent_context": "暂无特定 Agent 上下文指导。"
    },
    {
      "id": "fig_3f6ec8b1",
      "title": "Python Seaborn 双曼哈顿图 (Manhattan Plot)",
      "category": "组学研究",
      "chart_type": "曼哈顿图",
      "framework": "Python",
      "packages": [],
      "tags": [
        "曼哈顿图",
        "GWAS",
        "组学研究",
        "Python"
      ],
      "description": "用于全基因组关联分析 (GWAS) SNP 显著性分布的双向对比曼哈顿图。",
      "code": "import seaborn as sns...",
      "sample_data": {},
      "visual_rules": {},
      "agent_context": "暂无特定 Agent 上下文指导。"
    }
  ]
}