Fix: Recreate conda environment

.gitignore

@@ -19,4 +19,6 @@
 renv/*
 slurm*
 run*
-data/*
+data/*
+results/diff_exp/*
+results/ISA/

environment.yml

@@ -1,100 +1,106 @@
-name: mdd-env
+name: mdd-paper-env
 channels:
   - conda-forge
   - defaults
 dependencies:
   - _libgcc_mutex=0.1=conda_forge
-  - _openmp_mutex=4.5=1_gnu
+  - _openmp_mutex=4.5=2_gnu
   - _r-mutex=1.0.1=anacondar_1
-  - binutils_impl_linux-64=2.36.1=h193b22a_2
-  - binutils_linux-64=2.36=hf3e587d_3
+  - binutils_impl_linux-64=2.39=he00db2b_1
+  - binutils_linux-64=2.39=h5fc0e48_12
   - bwidget=1.9.14=ha770c72_1
   - bzip2=1.0.8=h7f98852_4
   - c-ares=1.18.1=h7f98852_0
-  - ca-certificates=2021.10.8=ha878542_0
-  - cairo=1.16.0=ha00ac49_1009
-  - curl=7.80.0=h494985f_1
+  - ca-certificates=2022.12.7=ha878542_0
+  - cairo=1.16.0=ha12eb4b_1010
+  - curl=7.87.0=h5eee18b_0
+  - expat=2.5.0=hcb278e6_1
   - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
   - font-ttf-inconsolata=3.000=h77eed37_0
   - font-ttf-source-code-pro=2.038=h77eed37_0
   - font-ttf-ubuntu=0.83=hab24e00_0
-  - fontconfig=2.13.1=hba837de_1005
+  - fontconfig=2.14.2=h14ed4e7_0
   - fonts-conda-ecosystem=1=0
   - fonts-conda-forge=1=0
-  - freetype=2.10.4=h0708190_1
+  - freetype=2.12.1=hca18f0e_1
   - fribidi=1.0.10=h36c2ea0_0
-  - gcc_impl_linux-64=9.4.0=h03d3576_11
-  - gcc_linux-64=9.4.0=h391b98a_3
-  - gettext=0.19.8.1=h73d1719_1008
-  - gfortran_impl_linux-64=9.4.0=h0003116_11
-  - gfortran_linux-64=9.4.0=hf0ab688_3
+  - gcc_impl_linux-64=9.5.0=h99780fb_19
+  - gcc_linux-64=9.5.0=h4258300_12
+  - gettext=0.21.1=h27087fc_0
+  - gfortran_impl_linux-64=9.5.0=hf1096a2_19
+  - gfortran_linux-64=9.5.0=hdb51d14_12
+  - git=2.34.1=pl5262hc120c5b_0
   - graphite2=1.3.13=h58526e2_1001
   - gsl=2.7=he838d99_0
-  - gxx_impl_linux-64=9.4.0=h03d3576_11
-  - gxx_linux-64=9.4.0=h0316aca_3
-  - harfbuzz=3.2.0=hb4a5f5f_0
+  - gxx_impl_linux-64=9.5.0=h99780fb_19
+  - gxx_linux-64=9.5.0=h43f449f_12
+  - harfbuzz=4.2.0=h40b6f09_0
   - icu=69.1=h9c3ff4c_0
-  - jbig=2.1=h7f98852_2003
-  - jpeg=9d=h36c2ea0_0
+  - jpeg=9e=h0b41bf4_3
   - kernel-headers_linux-64=2.6.32=he073ed8_15
-  - krb5=1.19.2=h48eae69_3
-  - ld_impl_linux-64=2.36.1=hea4e1c9_2
-  - lerc=3.0=h9c3ff4c_0
-  - libblas=3.9.0=12_linux64_openblas
-  - libcblas=3.9.0=12_linux64_openblas
-  - libcurl=7.80.0=h494985f_1
-  - libdeflate=1.8=h7f98852_0
+  - keyutils=1.6.1=h166bdaf_0
+  - krb5=1.19.3=h3790be6_0
+  - ld_impl_linux-64=2.39=hcc3a1bd_1
+  - lerc=4.0.0=h27087fc_0
+  - libblas=3.9.0=16_linux64_openblas
+  - libcblas=3.9.0=16_linux64_openblas
+  - libcurl=7.87.0=h91b91d3_0
+  - libdeflate=1.14=h166bdaf_0
   - libedit=3.1.20191231=he28a2e2_2
   - libev=4.33=h516909a_1
+  - libexpat=2.5.0=hcb278e6_1
   - libffi=3.4.2=h7f98852_5
-  - libgcc-devel_linux-64=9.4.0=hd854feb_11
-  - libgcc-ng=11.2.0=h1d223b6_11
-  - libgfortran-ng=11.2.0=h69a702a_11
-  - libgfortran5=11.2.0=h5c6108e_11
-  - libglib=2.70.2=h174f98d_1
-  - libgomp=11.2.0=h1d223b6_11
-  - libiconv=1.16=h516909a_0
-  - liblapack=3.9.0=12_linux64_openblas
-  - libnghttp2=1.43.0=ha19adfc_1
-  - libopenblas=0.3.18=pthreads_h8fe5266_0
-  - libpng=1.6.37=h21135ba_2
-  - libsanitizer=9.4.0=h79bfe98_11
-  - libssh2=1.10.0=ha35d2d1_2
-  - libstdcxx-devel_linux-64=9.4.0=hd854feb_11
-  - libstdcxx-ng=11.2.0=he4da1e4_11
-  - libtiff=4.3.0=h6f004c6_2
-  - libuuid=2.32.1=h7f98852_1000
-  - libwebp-base=1.2.1=h7f98852_0
+  - libgcc-devel_linux-64=9.5.0=h0a57e50_19
+  - libgcc-ng=12.2.0=h65d4601_19
+  - libgfortran-ng=12.2.0=h69a702a_19
+  - libgfortran5=12.2.0=h337968e_19
+  - libglib=2.74.1=h7a41b64_0
+  - libgomp=12.2.0=h65d4601_19
+  - libiconv=1.17=h166bdaf_0
+  - liblapack=3.9.0=16_linux64_openblas
+  - libnghttp2=1.46.0=hce63b2e_0
+  - libnsl=2.0.0=h7f98852_0
+  - libopenblas=0.3.21=pthreads_h78a6416_3
+  - libpng=1.6.39=h753d276_0
+  - libsanitizer=9.5.0=h2f262e1_19
+  - libssh2=1.10.0=haa6b8db_3
+  - libstdcxx-devel_linux-64=9.5.0=h0a57e50_19
+  - libstdcxx-ng=12.2.0=h46fd767_19
+  - libtiff=4.4.0=h82bc61c_5
+  - libuuid=2.38.1=h0b41bf4_0
+  - libwebp-base=1.3.0=h0b41bf4_0
   - libxcb=1.13=h7f98852_1004
-  - libxml2=2.9.12=h885dcf4_1
-  - libzlib=1.2.11=h36c2ea0_1013
-  - lz4-c=1.9.3=h9c3ff4c_1
+  - libxml2=2.9.14=haae042b_4
+  - libzlib=1.2.13=h166bdaf_4
   - make=4.3=hd18ef5c_1
   - ncurses=6.2=h58526e2_4
-  - openssl=3.0.0=h7f98852_2
-  - pango=1.48.10=h54213e6_2
-  - pcre=8.45=h9c3ff4c_0
-  - pcre2=10.37=h032f7d1_0
+  - openjdk=8.0.332=h166bdaf_0
+  - openssl=1.1.1t=h0b41bf4_0
+  - pango=1.50.7=hbd2fdc8_0
+  - pcre2=10.37=hc3806b6_1
+  - perl=5.32.1=2_h7f98852_perl5
   - pixman=0.40.0=h36c2ea0_0
   - pthread-stubs=0.4=h36c2ea0_1001
-  - r-base=4.1.2=hde4fec0_0
+  - r-base=4.1.2=h2553ce4_1
+  - r-rjava=1.0_6=r41h06615bd_5
   - readline=8.1=h46c0cb4_0
   - sed=4.8=he412f7d_0
   - sysroot_linux-64=2.12=he073ed8_15
-  - tk=8.6.11=h27826a3_1
+  - tk=8.6.12=h27826a3_0
   - tktable=2.10=hb7b940f_3
   - xorg-kbproto=1.0.7=h7f98852_1002
   - xorg-libice=1.0.10=h7f98852_0
   - xorg-libsm=1.2.3=hd9c2040_1000
-  - xorg-libx11=1.7.2=h7f98852_0
+  - xorg-libx11=1.8.4=h0b41bf4_0
   - xorg-libxau=1.0.9=h7f98852_0
   - xorg-libxdmcp=1.1.3=h7f98852_0
-  - xorg-libxext=1.3.4=h7f98852_1
+  - xorg-libxext=1.3.4=h0b41bf4_2
   - xorg-libxrender=0.9.10=h7f98852_1003
   - xorg-libxt=1.2.1=h7f98852_2
   - xorg-renderproto=0.11.1=h7f98852_1002
-  - xorg-xextproto=7.3.0=h7f98852_1002
+  - xorg-xextproto=7.3.0=h0b41bf4_1003
   - xorg-xproto=7.0.31=h7f98852_1007
-  - xz=5.2.5=h516909a_1
-  - zlib=1.2.11=h36c2ea0_1013
-  - zstd=1.5.1=ha95c52a_0
+  - xz=5.2.6=h166bdaf_0
+  - zlib=1.2.13=h166bdaf_4
+  - zstd=1.5.2=h3eb15da_6
+prefix: /home/iaradsouza/miniconda3/envs/mdd-paper-env

renv.lock

@@ -905,6 +905,21 @@
         "S4Vectors"
       ]
     },
+    "TreeAndLeaf": {
+      "Package": "TreeAndLeaf",
+      "Version": "1.6.1",
+      "Source": "Bioconductor",
+      "git_url": "https://git.bioconductor.org/packages/TreeAndLeaf",
+      "git_branch": "RELEASE_3_14",
+      "git_last_commit": "171d519",
+      "git_last_commit_date": "2021-10-27",
+      "Hash": "b8f10ab9082a4c3cbcc136006706ef4e",
+      "Requirements": [
+        "RedeR",
+        "ape",
+        "igraph"
+      ]
+    },
     "UpSetR": {
       "Package": "UpSetR",
       "Version": "1.4.0",
@@ -2156,12 +2171,13 @@
       "Package": "ggtree",
       "Version": "3.2.1",
       "Source": "Bioconductor",
+      "RemoteType": "bioconductor",
       "Remotes": "GuangchuangYu/treeio",
       "git_url": "https://git.bioconductor.org/packages/ggtree",
       "git_branch": "RELEASE_3_14",
       "git_last_commit": "d3747e6",
       "git_last_commit_date": "2021-11-14",
-      "Hash": "f156c85173024c88e2fdfd63ccca3fd7",
+      "Hash": "5711c057a04e53ed1c70909939dd9ad9",
       "Requirements": [
         "ape",
         "aplot",
@@ -3291,6 +3307,14 @@
         "reshape2"
       ]
     },
+    "rJava": {
+      "Package": "rJava",
+      "Version": "1.0-6",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Hash": "0415819f6baa75d86d52483f7292b623",
+      "Requirements": []
+    },
     "ranger": {
       "Package": "ranger",
       "Version": "0.13.1",
@@ -4237,6 +4261,27 @@
       "Hash": "e2e5fb1a74fbb68b27d6efc5372635dc",
       "Requirements": []
     },
+    "xlsx": {
+      "Package": "xlsx",
+      "Version": "0.6.5",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Hash": "d24d579f59a3b6da1e1cf4660425443e",
+      "Requirements": [
+        "rJava",
+        "xlsxjars"
+      ]
+    },
+    "xlsxjars": {
+      "Package": "xlsxjars",
+      "Version": "0.6.1",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Hash": "4c4b3bc29a916f33f1298dd951133351",
+      "Requirements": [
+        "rJava"
+      ]
+    },
     "xml2": {
       "Package": "xml2",
       "Version": "1.3.3",

scripts/compile_DTU.R

@@ -0,0 +1,42 @@
+library(dplyr)
+library(purrr)
+library(IsoformSwitchAnalyzeR)
+
+# 1. Get all results from ISA ------
+
+files <-
+  list.files(
+    "results/ISA/",
+    pattern = "pass2",
+    recursive = T,
+    full.names = T
+  )
+isa_df <- map_dfr(files, ~ {
+  load(.x)
+  SwitchList_2$isoformFeatures
+})
+
+# 2. Filter results by conditions and save full result -----
+
+condition_1_male <- grepl("CTRL_male", isa_df$condition_1)
+condition_2_male <- grepl("MDD_male", isa_df$condition_2)
+condition_1_female <- grepl("CTRL_female", isa_df$condition_1)
+condition_2_female <- grepl("MDD_female", isa_df$condition_2)
+
+isa_df <- isa_df[(condition_1_male & condition_2_male) |
+                   (condition_1_female & condition_2_female), ]
+
+save(isa_df, file = "results/ISA/DTU_df.rda")
+
+# 3. Get dataframe with biotypes ----
+
+dtu_w_biotypes <- isa_df %>%
+  mutate(
+    gene_id = gsub("\\.\\d+", "", gene_id),
+    isoform_id = gsub("\\.\\d+", "", isoform_id)
+  ) %>%
+  filter(isoform_switch_q_value <= 0.05) %>%
+  mutate(group = gsub("_CTRL", "", condition_1)) %>%
+  dplyr::select(isoform_id, iso_biotype, group)
+
+readr::write_csv(dtu_w_biotypes, file = "results/ISA/dtu_w_biotype.csv")

scripts/summarise_biotypes.R

@@ -0,0 +1,89 @@
+library(dplyr)
+library(purrr)
+library(ggplot2)
+library(rtracklayer)
+library(GenomicFeatures)
+
+# 1. Carregando GTF ---------------------------------------
+gtf <- "./data/Homo_sapiens.GRCh38.97.chr_patch_hapl_scaff.gtf.gz"
+
+gtf_data <- import(gtf)
+
+# 2. Lendo DGE/DTE e pegando os biotipos ---------------------------------------
+load("./results/diff_exp/diff_df.rda")
+
+dge_genes <- diff_df %>%
+  filter(type == "DGE")
+
+# 2.1. Pegando biotipo dos DGE ---------------------------------------
+dge_w_biotype <- gtf_data[, c("gene_id", "gene_biotype")] %>%
+  as.data.frame() %>%
+  filter(gene_id %in% dge_genes$gene) %>%
+  dplyr::select(gene_id, gene_biotype) %>%
+  right_join(dge_genes, by = c("gene_id" = "gene")) %>%
+  distinct() %>% 
+  dplyr::select(gene_id, gene_biotype, group)
+
+readr::write_csv(dge_w_biotype, "results/diff_exp/dge_w_biotype.csv")
+
+# 2.2. Pegando biotipo dos DTE ---------------------------------------
+load("./results/diff_exp/diff_tx_corrected.rda")
+
+dte_genes <- df_res_padj_tx %>%
+  dplyr::select(txID, transcript, group) %>%
+  filter(transcript < 0.01)
+
+dte_w_biotype <-
+  gtf_data[, c("transcript_id", "transcript_biotype")] %>%
+  as.data.frame() %>%
+  filter(transcript_id %in% dte_genes$txID) %>%
+  dplyr::select(transcript_id, transcript_biotype) %>%
+  right_join(dte_genes, by = c("transcript_id" = "txID")) %>%
+  distinct() %>% 
+  dplyr::select(transcript_id, transcript_biotype, group)
+
+readr::write_csv(dte_w_biotype, "results/diff_exp/dte_w_biotype.csv")
+
+# 2.3. Pegando biotipo dos DTU ---------------------------------------
+
+dtu_w_biotype <- readr::read_csv("results/ISA/dtu_w_biotype.csv")
+
+# 3. Plotando as porcentagens ---------------------------------------
+plot_biotype_bar <- function(data, id_col, n_col) {
+
+  id_col <- enquo(id_col)
+  n_col <- enquo(n_col)
+
+  data %>% 
+    ggplot(aes(x = reorder(!!id_col, dplyr::desc(!!n_col)), y = !!n_col)) +
+    geom_col() +
+    scale_y_continuous(labels = scales::percent_format(scale = 1)) +
+    coord_flip() +
+    labs(
+      y = "Porcentagem de Genes",
+      x = "Biotipo",
+    )
+
+}
+
+dge_plot <- dge_w_biotype %>% 
+  group_by(gene_biotype) %>% 
+  summarise(biotype_n = n() / length(unique(dge_w_biotype$gene_id)) * 100) %>% 
+  ungroup() %>% 
+  plot_biotype_bar(. , id_col = gene_biotype, n_col = biotype_n)
+
+dte_plot <- dte_w_biotype %>%
+  group_by(transcript_biotype) %>%
+  summarise(biotype_n = n() / length(unique(dte_w_biotype$transcript_id))* 100) %>%
+  ungroup() %>%
+  plot_biotype_bar(., id_col = transcript_biotype, n_col = biotype_n)
+
+dtu_plot <- dtu_w_biotype %>%
+  group_by(iso_biotype) %>%
+  summarise(biotype_n = n() / length(unique(dtu_w_biotype$isoform_id))* 100) %>%
+  ungroup() %>%
+  plot_biotype_bar(., id_col = iso_biotype, n_col = biotype_n)
+
+ggsave(dge_plot, filename = "results/diff_exp/dge_biotypes.pdf")
+ggsave(dte_plot, filename = "results/diff_exp/dte_biotypes.pdf")
+ggsave(dtu_plot, filename = "results/diff_exp/dtu_biotypes.pdf")