updates to mmseq2 section made

Snakefile

@@ -87,6 +87,7 @@ rule all:
     input: expand(os.path.join(RESULTS_DIR, "assembly/{assembler}/polished/nanopolish/round_{round}/lr/merged/{barcode}/assembly_polished.fna"), assembler=ASSEMBLERS, round="01", barcode=BARCODES)
     ### RUN LATER #input: expand(os.path.join(RESULTS_DIR, "annotation/methylation/{assembler}/nanopolish/round_{round}/lr/merged/{barcode}/methylation_frequencies.tsv"), assembler=ASSEMBLERS, round="01", barcode=BARCODES)
     #input: expand(os.path.join(RESULTS_DIR, "annotation/diamond/lr/merged/{barcode}.diamond.daa"), barcode=BARCODES)
+    #input: expand(f"{RESULTS_DIR}/annotation/mmseq2/{{assembler1}}__{{assembler2}}_rbh"), zip, assembler1=["flye", "flye", "megahit"], assembler2=["megahit", "megahit_metaspades_hybrid", "megahit_metaspades_hybrid"])
 
 
 ######
@@ -1337,3 +1338,14 @@ rule mmseq2_m8_format:
         mmseqs convertalis {input.fo2} {input.fo3} {input.fo6} {output.form3} &&\
         date) &> >(tee {log})
         """
+
+rule mmseq_compare:
+    input:
+        f"{RESULTS_DIR}/annotation/mmseq2/{{assembler1}}_db",
+        f"{RESULTS_DIR}/annotation/mmseq2/{{assembler2}}_db"
+    output: 
+        f"{RESULTS_DIR}/annotation/mmseq2/{{assembler1}}__{{assembler2}}_rbh"
+    conda:
+        "cd-hit.yml"
+    shell:
+        "mmseqs rbh {input[0]} {input[1]} {output} --min-seq-id 0.9 mmseq2_tmp --threads 12"