small adjustments

Author: weichan

config/config_CD19_28z.yml

@@ -1,5 +1,5 @@
 # Long-read data
-experiment: "28z"
+experiment: "28z_with_mod"
 samples:
     MK028_28z: "/home/weichan/permanent/Projects/VIS/Data/VIS_MPX_pooled/VIS_MPX_MK028_28z_pooled.bam"
     MK014_28z: "/home/weichan/permanent/Projects/VIS/Data/VIS_MPX_pooled/VIS_MPX_MK014_28z_pooled.bam"
@@ -27,26 +27,30 @@ ref_genome_ctrl: "/home/weichan/permanent/Projects/VIS/Data/VIS_Magdeburg_withBa
 #ucsc_H3K27Ac: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_LayeredH3K27Ac_02_24"
 #ucsc_H3K4Me3: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_LayeredH3K4Me3_02_24"
 #ucsc_DNaseH: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_DNaseClusters_02_24_cut"
-ucsc_TF: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_TFClusters_processed.bed"
+annotate_ucsc_tf: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_TFClusters_processed.bed"
 #annotation_1: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_GENCODEV44_processed.bed"
-annotation_1: "/home/weichan/permanent/Projects/VIS/dev/UCSC/new_UCSC_GENCODEV44_processed.bed"
+annotate_gencode: "/home/weichan/permanent/Projects/VIS/dev/UCSC/new_UCSC_GENCODEV44_processed.bed"
 #ucsc_Genes_gtf: "/home/weichan/permanent/Projects/VIS/dev/UCSC/gencode.v44.annotation.gtf"
 #ucsc exons
-ucsc_exons: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_GENCODE_V44_Exons"
-ucsc_introns: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_GENCODE_V44_Introns"
+annotate_ucsc_exons: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_GENCODE_V44_Exons"
+annotate_ucsc_introns: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_GENCODE_V44_Introns"
+#promoters
+annotate_ucsc_promoter: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_Promoters_EPDnew"
+#enhancer
+annotate_ucsc_enhancer: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_VISTA_Enhancer_02_2025.bed"
+#enhancer fantom5
+annotate_fantom5_enhancer: "/home/weichan/permanent/Projects/VIS/dev/FANTOM5/F5.hg38.enhancers.bed"
 #sedb
 #sedb_cd4: "/home/weichan/permanent/Projects/VIS/dev/SEdb/sedb_cd4_closest_gene.bed"
 #sedb_cd8: "/home/weichan/permanent/Projects/VIS/dev/SEdb/sedb_cd8_closest_gene.bed"
 #tss
 #ucsc_tss: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_TSS_peaks_processed_sorted.bed"
 #miRNA
-#ucsc_mirna: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_miRNA_processed_sorted.bed"
+annotate_ucsc_mirna: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_miRNA_processed_sorted.bed"
 #cancer genes
-cosmic_genes: "/home/weichan/permanent/Projects/VIS/dev/COSMIC/Cosmic_CancerGeneCensus_Tsv_v101_GRCh38/Cosmic_CancerGeneCensus_v101_GRCh38_processed.bed"
-#promoters
-ucsc_promoter: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_Promoters_EPDnew"
+annotate_cosmic_genes: "/home/weichan/permanent/Projects/VIS/dev/COSMIC/Cosmic_CancerGeneCensus_Tsv_v101_GRCh38/Cosmic_CancerGeneCensus_v101_GRCh38_processed.bed"
 #hiC
-encode_hic: "/home/weichan/permanent/Projects/VIS/dev/ENCODE/HiC_Tcells/HiC_processed.bed"
+annotate_encode_hic: "/home/weichan/permanent/Projects/VIS/dev/ENCODE/HiC_Tcells/HiC_processed.bed"
 #VIS detection
 detection: "rules/detection.smk"
 #qc rule collection
@@ -61,3 +65,6 @@ downstream: "rules/downstream.smk"
 #epigenetics: "rules/epigenetics.smk"
 #variants rule collection WIP
 #variants: "rules/variants.smk"
+base_modifications: "rules/base_modifications.smk"
+plot_functional_genomics: "rules/plot_functional_genomics.smk"
+threads: 10

config/config_CD19_BBz.yml

@@ -1,5 +1,5 @@
 # Long-read data
-experiment: "annotation_test_cmod"
+experiment: "BBz_with_mod"
 samples:
     MK028_BBz: "/home/weichan/permanent/Projects/VIS/Data/VIS_MPX_pooled/VIS_MPX_MK028_BBz_pooled.bam"
     MK014_BBz: "/home/weichan/permanent/Projects/VIS/Data/VIS_MPX_pooled/VIS_MPX_MK014_BBz_pooled.bam"
@@ -36,6 +36,10 @@ annotate_ucsc_exons: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_GENCODE
 annotate_ucsc_introns: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_GENCODE_V44_Introns"
 #promoters
 annotate_ucsc_promoter: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_Promoters_EPDnew"
+#enhancer fantom5
+annotate_fantom5_enhancer: "/home/weichan/permanent/Projects/VIS/dev/FANTOM5/F5.hg38.enhancers.bed"
+#enhancer refTSS
+annotate_refTSS_tss: "/home/weichan/permanent/Projects/VIS/dev/refTSS/refTSS_v4.1_human_coordinate.hg38.bed"
 #enhancer
 annotate_ucsc_enhancer: "/home/weichan/permanent/Projects/VIS/dev/UCSC/UCSC_VISTA_Enhancer_02_2025.bed"
 #sedb

workflow/Snakefile

@@ -3,9 +3,9 @@ import os
 from pathlib import Path
 
 env_name = os.getenv('CONDA_DEFAULT_ENV')
-print(f"Current environment (should be either 'VIS_minimal' or 'VIS_full'): {env_name}")
+#print(f"Current environment (should be either 'VIS_minimal' or 'VIS_full'): {env_name}")
 
-CONFIG = "config/config_CD19_BBz.yml"
+CONFIG = "config/config_CD19_28z.yml"
 configfile: CONFIG
 #SRC=config["source_dir"] #only in use for r script scirp, will be removed sooner or later
 SAMPLES = expand(config["samples"]) 
@@ -65,4 +65,4 @@ rule all:
 		#expand(f"{outdir}/intermediate/blastn/Filtered_Annotated_{fragmentsize}_InsertionMatches_{{sample}}.gff", sample=SAMPLES),
 		#expand(f"{outdir}/final/functional_genomics/localization/{fragmentsize}_{{sample}}", sample=SAMPLES),
 		# for msa
-		#expand(f"{outdir}/intermediate/fasta/Inserted_sequence_{{sample}}.fa", sample=SAMPLES)
+		#expand(f"{outdir}/intermediate/fasta/Inserted_sequence_{{sample}}.fa", sample=SAMPLES)

workflow/rules/base_modifications.smk

@@ -26,7 +26,7 @@ rule readnames_final:
 rule only_keep_filtered_insertions:
 	input:
 		isobam=f"{outdir}/intermediate/mapping/Precut_{{sample}}_sorted.bam",
-		readnames=f"{outdir}/intermediate/cmod/final_insertion_readnames_{{sample}}.txt"
+		readnames=f"{outdir}/intermediate/base_modifications/final_insertion_readnames_{{sample}}.txt"
 	log:
 		log=f"{outdir}/intermediate/log/base_modifications/only_keep_filtered_insertions/{{sample}}.log"
 	output:

workflow/rules/functional_genomics.smk

@@ -35,7 +35,7 @@ rule calc_distance_to_elements:
     output:
         f"{outdir}/final/functional_genomics/Functional_distances_to_Insertions_{{sample}}.bed"
     run:
-        vhf.calculate_element_distance(input.insertions, output[0], log.log, params.annotation_files)
+        vhf_fg.calculate_element_distance(input.insertions, output[0], log.log, params.annotation_files)
 
 #kinda 'hacky' solution for flexibility: Now it does not matter if one annotation or 20 are defined. 
 rule annotation_overlap_insertion: