Reference.md

+
+
+```mermaid
+
+graph TD;   
+  classDef Fichier fill:#ffff00;
+  classDef Configurer fill:#E0FFFF;
+  classDef Snakefile fill:#98FB98,border:#0c4c0c;
+
+
+ 
+  id0s{{`marker` sample description .dat}}-->s0;
+  id0c{{config.yaml}}-->s0;
+ id0a{{rapdirun.tsv}}-->s0;
+
+  s0[readwrite_rapidrun_demultiplexing]-->s1[assembly];
+  s1-->s2[demultiplexing];
+  s2-->s3[filtering];
+  s3-->s4[assignment];
+
+  s0--> id0b{{demultiplex.csv}};
+
+
+  id1[`run` paired-end .fastq files]-->r1(illuminapairedend);
+
+  subgraph g1[assembly]
+  r1(illuminapairedend)-->r2(remove_unaligned);
+  click r1 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/02_assembly/rules/illuminapairedend.smk";
+  click r2 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/02_assembly/rules/remove_unaligned.smk";
+  end
+  
+  r2-->id2[`run` annotated merged .fastq files];  
+  id2-->r3
+
+  subgraph g2[demultiplexing]
+  r3(assign_sequences)-->r4(split_sequences);  
+  click r3 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/03_demultiplex/rules/assign_sequences.smk";
+  click r4 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/03_demultiplex/rules/split_sequences.smk";  
+  end
+
+  r4-->id3[`projet`/`marker`/`run`/`sample` annotated .fasta files];
+  id3-->r5
+  
+  subgraph g3[filtering]
+  r5(dereplicate_samples)-->r6(goodlength_samples);
+  r6-->r7(clean_pcrerr_samples);
+  r7-->r8(rm_internal_samples);
+  
+  click r5 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/04_filter_samples/rules/dereplicate_samples.smk";
+  click r6 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/04_filter_samples/rules/goodlength_samples.smk";
+  click r7 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/04_filter_samples/rules/clean_pcrerr_samples.smk";
+  click r8 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/04_filter_samples/rules/rm_internal_samples.smk";  
+  end
+
+  r8-->id4[`projet`/`marker`/`run`/`sample` filtered .fasta files];
+  id4-->|concatenate `sample` into `run` files|id5[`projet`/`marker`/`run` .fasta files];  ;
+
+  id5-->r9;
+
+
+  subgraph g4[assignment]
+  
+  r9(dereplicate_runs)-->r10(assign_taxon);
+  r10-->r11(rm_attributes);
+  r11-->r12(sort_runs);
+  r12-->r13(table_runs);  
+  click r9 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/05_assignment/rules/dereplicate_runs.smk";
+  click r10 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/05_assignment/rules/assign_taxon.smk";
+  click r11 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/05_assignment/rules/rm_attributes.smk";
+  click r12 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/05_assignment/rules/sort_runs.smk";
+  click r13 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/05_assignment/rules/table_runs.smk";  
+  end
+
+  r13-->id6[`projet`/`marker`/`run` species occurence .tsv files];
+
+
+  
+  
+  id0a-->s1; 
+
+
+
+  id0b-->s2;
+  id0b-->s3;
+  id0b-->s4;
+
+
+  click id0c "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/tree/master/config";
+  click id0b "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/tree/master/results/01_settings"
+  click id0a "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/resources/test/all_samples.tsv";
+  click id0s "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/tree/master/resources/test/sample_description";
+
+  click id2 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/tree/master/results/02_assembly/02_remove_unaligned";
+  click id3 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/tree/master/results/03_demultiplex/02_raw";  
+  click id4 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/tree/master/results/04_filter_samples/04_filtered";
+  click id5 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/tree/master/results/05_assignment/01_runs";
+  click id6 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/tree/master/results/06_final_tables";
+
+  click s0 "https://gitlab.mbb.univ-montp2.fr/edna/snakemake_rapidrun_obitools/-/blob/master/01_settings/readwrite_rapidrun_demultiplexing.py";
+  
+  class id0a,id0b,id0c,id0s Configurer;
+  class s0,s1,s2,s3,s4,g1,g2,g3,g4 Snakefile;
+  class id1,id2,id3,id4,id5,id6 Fichier; 
+
+
+```
+
+
+# Rules
+## write demultiplex table
+### read 'rapidrun' .tsv file
+### remove blacklisted runs & projects
+### write table projet/run/sample
+demultiplex","projet", "marker","run", "plaque","sample","barcode5","barcode3","primer5","primer3","min_f","min_r","lenBarcode5","lenBarcode3"
+
+## assemble
+### Paired end alignment then keep reads with quality > 40
+### Remove unaligned sequence records
+## demultiplex
+### Assign each sequence record to the corresponding sample/marker combination
+### Split the input sequence file in a set of subfiles according to the values of attribute `sample`
+## filter samples
+### dereplicate reads into uniq sequences
+### only sequence more than 20bp with no ambiguity IUAPC with total coverage greater than 10 reads
+### Clean the sequences for PCR/sequencing errors (sequence variants)
+### Remove sequence which are classified as 'internal' by obiclean
+## concatenate samples into run
+## assignment
+### Dereplicate and merge samples together
+### Assign each sequence to a taxon
+### Some unuseful attributes can be removed at this stage
+### The sequences can be sorted by decreasing order of count
+### Generate a table final results
+
+
+
+
+