nanomd 0.1.0__py3-none-any.whl

nanomd/main.py

@@ -0,0 +1,24 @@
+import typer
+from .modules.gene import gene
+from .modules.isoform import isoform
+from .modules.detectMod import detectMod
+from .modules.isoformAS import isoformAS
+from .modules.nascentRNA import nascentRNA
+
+app = typer.Typer(add_completion=False)
+
+@app.callback()
+def callback():
+    """
+    nanoMD(Nanopore direct RNA sequencing Multi-dimensional analysis) was developed to synchronously analyze the changes in m6A, m5C, psi, AtoI modification sites, genes, isoforms, alternative splicing events, and nascent RNA in direct RNA sequencing data.
+    """
+
+app.command(name="gene")(gene)
+app.command(name="isoform")(isoform)
+app.command(name="isoformAS")(isoformAS)
+app.command(name="detectMod")(detectMod)
+app.command(name="nascentRNA")(nascentRNA)
+
+
+if __name__ == "__main__":
+    app()

nanomd/modules/detectMod.py

@@ -0,0 +1,58 @@
+import time
+import typer
+from typing_extensions import Annotated
+from rich.progress import Progress, SpinnerColumn, TextColumn
+from ..utils.modtools import split_mod
+from ..utils.basetools import check_path_exists
+from ..utils.abs_position import gene_feature_distance_calculator
+from ..utils.modifications import form_reads_get_modifications
+
+app = typer.Typer()
+
+@app.command()
+def detectMod(
+    input: Annotated[str, typer.Option("--input", "-i", help="Input fastq files.")],
+    sam: Annotated[str, typer.Option("--sam", "-s", help="mapping sam/bam file.")],
+    bed: Annotated[str, typer.Option("--bed", "-b", help="bed file for transcripts sites.")],
+    regions: Annotated[str, typer.Option("--regions", "-r", help="regions file for gene feature distance calculation.")],
+    output: Annotated[str, typer.Option("--output", "-o", help="Output file path.")]=".",
+    prefix: Annotated[str, typer.Option("--prefix", "-p", help="Prefix for output files.")]="prefix",
+    pvalue: Annotated[float, typer.Option("--pvalue", help="pvalue cutoff for modification sites.")]=0.98,
+    ):
+    """
+    detect modification sites in input fastq files.
+    """
+    
+    with Progress(
+        SpinnerColumn(),
+        TextColumn("[progress.description]{task.description}"),
+        transient=True,
+    ) as progress:
+        progress.add_task(description="Detecting modification start...", total=None)
+        start=time.time()
+        
+        output_file=f"{output}/{prefix}.bed"
+        progress.add_task(description="Getting modification from fq files...", total=None)
+        if not check_path_exists(output_file):
+            mod = form_reads_get_modifications(input, sam, bed, output_file, pvalue)
+            mod.get_mod_position_with_sam()
+        progress.add_task(description=f"Getting modification from fq files Done", total=None)
+
+        progress.add_task(description="Splitting modification sites...", total=None)
+        if not check_path_exists(f"{output}/{prefix}_m6A.bed"):
+            split_mod(output_file, prefix)
+        progress.add_task(description="Splitting modification sites Done", total=None)
+
+        progress.add_task(description="Calculating absolute distance...", total=None)
+        bed_file_list = [f"{output}/{prefix}_m6A.bed", f"{output}/{prefix}_m5C.bed", f"{output}/{prefix}_psi.bed", f"{output}/{prefix}_AtoI.bed"]
+        for bed_file in bed_file_list:
+            gfc_output = bed_file.replace(".bed", "_abs_dist.txt")
+            if not check_path_exists(gfc_output):
+                gfc = gene_feature_distance_calculator(bed_file, regions, gfc_output)
+                gfc.process_bed_file()
+        progress.add_task(description="Calculating absolute distance Done", total=None)
+        
+        end=time.time()
+        time_cost=f"{(end - start) // 3600}h{((end - start) % 3600) // 60}m{(end - start) % 60:.2f}s"
+        print(f"Detecting modification sites Done, time cost: {time_cost}")
+        progress.add_task(description=f"Detecting modification sites Done, time cost: {time_cost}", total=None)

nanomd/modules/gene.py

@@ -0,0 +1,39 @@
+import time
+import typer
+from typing_extensions import Annotated
+from rich.progress import Progress, SpinnerColumn, TextColumn
+from ..utils.map import minimap2map
+
+app = typer.Typer()
+
+@app.command()
+def gene(
+    input: Annotated[str, typer.Option("--input", "-i", help="Input fastq files.")],
+    reference: Annotated[str, typer.Option("--reference", "-r", help="reference genome path.")],
+    output: Annotated[str, typer.Option("--output", "-o", help="output for output sam/bam files.")],
+    tool: Annotated[str, typer.Option("--tool", help="minimap2.")]="minimap2",
+    parms: Annotated[str, typer.Option("--parms", help="minimap2 parameters for mapping.")]="--secondary=no --cs -a",
+    threads: Annotated[int, typer.Option("--threads", "-t", help="Number of threads.")]=4,
+    ):
+    """
+    Mapping of nanopore reads to a reference genome.
+    """
+    
+    with Progress(
+        SpinnerColumn(),
+        TextColumn("[progress.description]{task.description}"),
+        transient=True,
+    ) as progress:
+        try:
+            progress.add_task(description="map reference...", total=None)
+            start=time.time()
+            minimap2map(input, reference, output, tool, parms, threads)
+            end=time.time()
+            time_cost=f"{(end - start) // 3600}h{((end - start) % 3600) // 60}m{(end - start) % 60:.2f}s"
+            print(f"map reference Done, time cost: {time_cost}")
+            progress.add_task(description=f"map reference Done, time cost: {time_cost}", total=None)
+        except Exception as e:
+            print(f"Error: {e}")
+            progress.add_task(description="map reference Failed", total=None)
+            exit(1)
+    

nanomd/modules/isoform.py

@@ -0,0 +1,39 @@
+import time
+import typer
+from typing_extensions import Annotated
+from rich.progress import Progress, SpinnerColumn, TextColumn
+from ..utils.map import minimap2map
+
+app = typer.Typer()
+
+@app.command()
+def isoform(
+    input: Annotated[str, typer.Option("--input", "-i", help="Input fastq files.")],
+    reference: Annotated[str, typer.Option("--reference", "-r", help="reference transcripts path.")],
+    output: Annotated[str, typer.Option("--output", "-o", help="output for output sam/bam files.")],
+    tool: Annotated[str, typer.Option("--tool", help="minimap2.")]="minimap2",
+    parms: Annotated[str, typer.Option("--parms", help="minimap2 parameters for mapping.")]="--secondary=no --cs -a",
+    threads: Annotated[int, typer.Option("--threads", "-t", help="Number of threads.")]=4,
+    ):
+    """
+    Mapping of nanopore reads to a reference transcripts.
+    """
+    
+    with Progress(
+        SpinnerColumn(),
+        TextColumn("[progress.description]{task.description}"),
+        transient=True,
+    ) as progress:
+        try:
+            progress.add_task(description="map reference...", total=None)
+            start=time.time()
+            minimap2map(input, reference, output, tool, parms, threads)
+            end=time.time()
+            time_cost=f"{(end - start) // 3600}h{((end - start) % 3600) // 60}m{(end - start) % 60:.2f}s"
+            print(f"map reference Done, time cost: {time_cost}")
+            progress.add_task(description=f"map reference Done, time cost: {time_cost}", total=None)
+        except Exception as e:
+            print(f"Error: {e}")
+            progress.add_task(description="map reference Failed", total=None)
+            exit(1)
+    

nanomd/modules/isoformAS.py

@@ -0,0 +1,22 @@
+import typer
+import subprocess
+from pathlib import Path
+from rich.progress import track
+from typing_extensions import Annotated
+from ..utils.map import minimap2map
+
+app = typer.Typer()
+
+@app.command()
+def isoformAS(
+    input: Annotated[str, typer.Option("--input", "-i", help="Input fastq files.")],
+    reference: Annotated[str, typer.Option("--reference", "-r", help="reference genome path.")],
+    prefix: Annotated[str, typer.Option("--prefix", "-p", help="Prefix for output files.")],
+    tool: Annotated[str, typer.Option("--tool", help="minimap2.")]="minimap2",
+    parms: Annotated[str, typer.Option("--parms", help="minimap2 parameters for mapping.")]="--secondary=no --cs -a",
+    threads: Annotated[int, typer.Option(help="Number of threads.")]=4,
+    ):
+    """
+    alternative splicing analysis.
+    """
+    minimap2map(input, reference, prefix, tool, parms, threads)

nanomd/modules/nascentRNA.py

@@ -0,0 +1,22 @@
+import typer
+import subprocess
+from pathlib import Path
+from rich.progress import track
+from typing_extensions import Annotated
+from ..utils.map import minimap2map
+
+app = typer.Typer()
+
+@app.command()
+def nascentRNA(
+    input: Annotated[str, typer.Option("--input", "-i", help="Input fastq files.")],
+    reference: Annotated[str, typer.Option("--reference", "-r", help="reference genome path.")],
+    prefix: Annotated[str, typer.Option("--prefix", "-p", help="Prefix for output files.")],
+    tool: Annotated[str, typer.Option("--tool", help="minimap2.")]="minimap2",
+    parms: Annotated[str, typer.Option("--parms", help="minimap2 parameters for mapping.")]="--secondary=no --cs -a",
+    threads: Annotated[int, typer.Option(help="Number of threads.")]=4,
+    ):
+    """
+    Detect nascent RNA of nanopore reads.
+    """
+    minimap2map(input, reference, prefix, tool, parms, threads)

nanomd/scripts/m6a.sh

@@ -0,0 +1,23 @@
+
+conda activate mines
+
+cat m6A.bed|sort -k1,1 -k2,2n > m6a.sorted.bed
+
+perl ~/soft/metaPlotR/annotate_bed_file.pl --bed ./m6a.sorted.bed --bed2 ~/Refernce/human_ensembl_genome/91/hg38_annot.sorted.bed > annot_m6a.sorted.bed
+
+perl ~/soft/metaPlotR/rel_and_abs_dist_calc.pl --bed ./annot_m6a.sorted.bed --regions ~/Refernce/human_ensembl_genome/91/region_sizes.txt > m6a.dist.measures.txt
+
+cat Treat.mod.bed | awk -F "\t" '$4 > 0.95 {file="Treat/" $7 ".bed"; print $0 > file}'
+
+cat Control.mod.bed | awk -F "\t" '$4 > 0.95 {file="Control/" $7 ".bed"; print $0 > file}'
+
+cat Treat.mod.bed | awk -F "\t" '$4 >= 0.9 {file="treat_" $7 ".bed"; print $0 > file}'
+
+cat Control.mod.bed | awk -F "\t" '$4 >= 0.9 {file="control_" $7 ".bed"; print $0 > file}'
+
+awk '!seen[$4]++ {first[$4]=$0} {count[$4]++} END {for (key in count) print first[key], count[key]}' treat_m6A.bed > treat_m6A.uniq.bed
+
+nohup python ./split.py -i Treat.mod.bed -p treat -v 0.6 &
+nohup python ./split.py -i WT.mod.bed -p wt -v 0.6 &
+
+R CMD INSTALL legendBaseModel_0.0.6.tar.gz

nanomd/scripts/metaplot.R

@@ -0,0 +1,133 @@
+#!/opt/conda/bin/Rscript
+options(repos=structure(c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")))  
+if (!requireNamespace("optparse", quietly = TRUE))
+  install.packages("optparse")
+library(optparse)
+option_list <- list(
+    make_option(c("-i", "--input"), type = "character", default = FALSE,
+                help = "input file path"),
+    make_option(c("-o", "--output"), type = "character", default = FALSE,
+              help = "output file path"),
+    make_option(c("-p", "--prefix"), type = "character", default = FALSE,
+              help = "prefix of output file"),
+    make_option(c("-t", "--type"), type = "character", default = FALSE,
+              help = "type of mod (m6A, m5C, AtoI, psi, etc.)")
+)
+opt_parser <- OptionParser(option_list = option_list)
+opt <- parse_args(opt_parser)
+
+input  <-  opt$input
+output <- opt$output
+prefix <- opt$prefix
+type <- opt$type
+
+# library packages
+library(dplyr)
+library(purrr)
+library(scales)
+library(ggplot2)
+library(magrittr)
+library(legendBaseModel)
+
+plot_metagene_Rd <- function(input_data, output_path, prefix, mod_type = "m6A") {
+    ifelse(dir.exists(output_path), "Dir exist alreadly!", dir.create(output_path, recursive = TRUE))
+    tryCatch({
+    # START
+    cat(crayon::green(paste0(prefix, " Start ploting Metagene\n")))
+    colour_fill <- c("black", "red")
+    names(colour_fill) <- input_data$group  %>% unique()
+    p1 <- ggplot(input_data, aes(x=value))+
+        geom_line(aes(colour = group), stat = "density", adjust = 2) +
+        scale_colour_manual(values=colour_fill) +
+        geom_vline(xintercept = 1:2, col = "red", linetype="dashed") + 
+        annotate("text", x = 0.5, y = -0.14, label = "5'UTR") +
+        annotate("text", x = 1.5, y = -0.14, label = "CDS") +
+        annotate("text", x = 2.5, y = -0.14, label = "3'UTR")  +
+        annotate("rect", xmin = 0, xmax = 1, ymin = -0.08, ymax = -0.04, alpha = .99, colour = "black")+
+        annotate("rect", xmin = 2, xmax = 3, ymin = -0.08, ymax = -0.04, alpha = .99, colour = "black")+
+        annotate("rect", xmin = 1, xmax = 2, ymin = -0.12, ymax = 0, alpha = .2, colour = "black") +
+        xlab(paste0(mod_type, " metagene")) +
+        ylab("Frequency") +
+        guides(colour = guide_legend(title = NULL)) +
+        theme_bw() +
+        theme(legend.position = c(1, 1), legend.justification = c(1, 1)) +
+        theme(legend.background = element_blank()) 
+    ggsave(paste0(output_path, "/", prefix, "_", mod_type, "_metagene.pdf"), p1, width = 8, height = 6)
+    ggsave(paste0(output_path, "/", prefix, "_", mod_type, "_metagene.png"), p1, width = 8, height = 6)
+    ggsave(paste0(output_path, "/", prefix, "_", mod_type, "_metagene.tiff"), p1, width = 8, height = 6)
+
+    cat(crayon::green(paste0(prefix, " Metagene analysis done\n")))
+    # END
+    return("sucess")},
+    error = function(e){print(e$message);message(return("failled"))})
+}
+restructure_coord <- function(input_path, group, type) {
+    if (type == "m6A") {
+        m6a.dist <- read.delim(input_path, header = T) %>%
+            dplyr::filter(utr5_size > utr3_size) %>% 
+            dplyr::mutate(
+                trx_len = utr5_size + cds_size + utr3_size)
+    } else if (type == "m5C") {
+        m6a.dist <- read.delim(input_path, header = T) %>%
+            dplyr::filter(cds_size > utr3_size & utr3_size > utr5_size) %>% 
+            dplyr::mutate(
+                trx_len = utr5_size + cds_size + utr3_size)
+    } else if (type == "psi") {
+        m6a.dist <- read.delim(input_path, header = T) %>%
+            dplyr::filter(cds_size > utr3_size & utr3_size > utr5_size) %>% 
+            dplyr::mutate(
+                trx_len = utr5_size + cds_size + utr3_size)
+    } else if (type == "AtoI") {
+        m6a.dist <- read.delim(input_path, header = T) %>% 
+            dplyr::filter(cds_size > utr3_size & utr3_size > utr5_size) %>% 
+            dplyr::mutate(
+                trx_len = utr5_size + cds_size + utr3_size)
+    }
+
+    temp.df <- m6a.dist %>%
+        dplyr::select(c("gene_name", "refseqID", "trx_len")) %>%
+        dplyr::rename(setNames(colnames(.), c("gene_name", "gid", "trx_len"))) %$%
+        .[order(.$gene_name, .$gid, -.$trx_len), ] %$%
+        .[!duplicated(.$gene_name), ]
+
+    m6a.dist <- m6a.dist[m6a.dist$refseqID %in% temp.df$gid, ]
+    utr5.SF <- median(m6a.dist$utr5_size, na.rm = T)/median(m6a.dist$cds_size, na.rm = T)
+    utr3.SF <- median(m6a.dist$utr3_size, na.rm = T)/median(m6a.dist$cds_size, na.rm = T)
+    # print(paste0("utr5.SF: ", utr5.SF, " utr3.SF: ", utr3.SF))
+    utr5.m6a.dist <- m6a.dist[m6a.dist$rel_location < 1, ]
+    cds.m6a.dist <- m6a.dist[m6a.dist$rel_location < 2 & m6a.dist$rel_location >= 1, ]
+    utr3.m6a.dist <- m6a.dist[m6a.dist$rel_location >= 2 & m6a.dist$rel_location < 3, ]
+    utr5.m6a.dist$rel_location <- scales::rescale(utr5.m6a.dist$rel_location, to = c(1-utr5.SF, 1), from = c(0, 1))
+    utr3.m6a.dist$rel_location <- scales::rescale(utr3.m6a.dist$rel_location, to = c(2, 2+utr3.SF), from = c(2, 3))
+    m6a.metagene.coord <- c(utr5.m6a.dist$rel_location, cds.m6a.dist$rel_location, utr3.m6a.dist$rel_location)
+
+    m6a_data <- data.frame("value"= m6a.metagene.coord) %>% 
+        dplyr::mutate("group"= group)
+    return(m6a_data)
+}
+auto_meta_plot <- function(input_path, output_path, prefix, mod_type = "m6A") {
+    # test
+    # 2. check output path
+    options(warn = -1)
+    ifelse(dir.exists(output_path), "Dir exist alreadly!", dir.create(output_path, recursive = TRUE))
+    tryCatch({
+    # START
+    sample_all <- legendBaseModel::make_sample_sheet(input_path, paste0("_", mod_type, "_abs_dist.txt")) %>%
+        dplyr::mutate(
+            group = sample,
+            type = mod_type,
+            dist_measures = purrr::pmap(list(sample_path, group, type), restructure_coord)
+        ) %>% 
+        dplyr::mutate(
+            output_plot = output_path,
+            prefix_plot = paste0(prefix, group),
+            plot_meta <- purrr::pmap(list(dist_measures, output_plot, prefix_plot, type), plot_metagene_Rd)
+        )
+    # END
+    return("sucess")},
+    error = function(e){print(e$message);message(return("failled"))})
+}
+
+
+# main run
+auto_meta_plot(input, output, prefix, type)

nanomd/scripts/newRNA.R

@@ -0,0 +1,65 @@
+#!/user/bin/Rscript
+options(repos=structure(c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")))  
+if (!requireNamespace("optparse", quietly = TRUE))
+  # install.packages("optparse",repos="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")
+  install.packages("optparse")
+library(optparse)
+option_list <- list(
+  make_option(c("-i", "--input"), type = "character", default = FALSE,
+              help = "You input file "),
+  make_option(c("-s", "--species"), type = "character", default = FALSE,
+              help = "You species in [human,mouse] "), 
+  make_option(c("-o", "--outputDir"), type = "character", default = FALSE,
+              help = "Your outputDir ")
+)
+opt_parser = OptionParser(option_list = option_list);
+opt = parse_args(opt_parser);
+
+# 1.library package
+library(modelr)
+library(magrittr)
+library(tidyverse)
+library(rstudioapi)
+options(na.action = na.warn)
+# vignette("dplyr" ,package = "dplyr")
+# 2.glob function
+# 1.add analysis function
+#get the file path
+fun_path_ <- dirname(getSourceEditorContext()$path)
+source(paste0(fun_path_, "/fun/basis_fun.R"), encoding = "UTF-8")
+source(paste0(fun_path_, "/fun/unique_fun.R"), encoding = "UTF-8")
+
+# 2.global variables
+
+# input_  <-  path_clean(opt$input)
+# species <- choose_species(opt$species)
+# output_ <- path_clean(opt$outputDir)
+
+## run chenyiping's m6a DEA
+input_  <-  path_clean("./1-output/20221027_newRNA/input/")
+species <- choose_species("human")
+output_ <- path_clean("./1-output/20221027_newRNA/all_newRNA_results3")
+
+run_data <- data.frame(
+    group=c("newRNA"), 
+    input = input_,
+    output = output_) %>% 
+    mutate(
+        ipath = paste0(input, "/newRNA_counts_matrix.tsv"),
+        newRNA_DE = pmap(list(ipath, output, group), newRNA_DE_Rd))
+
+run_data <- data.frame(
+    group=c("allRNA"), 
+    input = input_,
+    output = output_) %>% 
+    mutate(
+        ipath = paste0(input, "/newRNA_counts_matrix.tsv"),
+        newRNA_DE = pmap(list(ipath, output, group), newRNA_DE_Rd))
+
+run_data <- data.frame(
+    group=c("allRNA"), 
+    input = input_,
+    output = output_) %>% 
+    mutate(
+        ipath = paste0(input, "/newRNA_counts_matrix.tsv"),
+        newRNA_DE = pmap(list(ipath, output, group), newRNA_DE_Rd))