diff --git a/ingest/bin/gene-coverage.py b/ingest/bin/gene-coverage.py
index c7e77d8..dec3d89 100644
--- a/ingest/bin/gene-coverage.py
+++ b/ingest/bin/gene-coverage.py
@@ -53,7 +53,7 @@ def G_and_F_coverage(alignment, indices_G, indices_F):
             F_coverage[accession].append(coverages_F.get(accession, 0.00))
             genome_coverage[accession].append(coverage_genome.get(accession, 0.00))
 
-    metadata_files = ["data/b/metadata_no_covg.tsv", "data/a/metadata_no_covg.tsv"]
+    metadata_files = ["data/b/metadata_sorted.tsv", "data/a/metadata_sorted.tsv"]
     outputs = ["data/b/metadata.tsv", "data/a/metadata.tsv"]
 
     # this part of the script reads the already separated a and b metadata and adds the F and G covg values to the correct row based on accession
diff --git a/ingest/bin/sort.py b/ingest/bin/sort.py
index 33e9c30..1bc1bf1 100644
--- a/ingest/bin/sort.py
+++ b/ingest/bin/sort.py
@@ -59,8 +59,8 @@ def get_similarity(alignment, reference):
             elif a_or_b[record.id]=='B':
                 b_sequences.append(record)
 
-    SeqIO.write(a_sequences, "data/a/sequences_notdedup.fasta","fasta")
-    SeqIO.write(b_sequences, "data/b/sequences_notdedup.fasta", "fasta")
+    SeqIO.write(a_sequences, "data/a/sequences.fasta","fasta")
+    SeqIO.write(b_sequences, "data/b/sequences.fasta", "fasta")
 
     metadata = pd.read_csv("data/metadata.tsv", sep="\t", index_col='accession')
     original_columns = metadata.columns
@@ -71,5 +71,5 @@ def get_similarity(alignment, reference):
                               columns=original_columns)
     b_metadata = pd.DataFrame(data=metadata.loc[metadata['type']=='B'],
                               columns=original_columns)
-    a_metadata.to_csv('data/a/metadata_notdedup.tsv', sep="\t")
-    b_metadata.to_csv('data/b/metadata_notdedup.tsv', sep="\t")
+    a_metadata.to_csv('data/a/metadata_sorted.tsv', sep="\t")
+    b_metadata.to_csv('data/b/metadata_sorted.tsv', sep="\t")
diff --git a/ingest/workflow/snakemake_rules/sort.smk b/ingest/workflow/snakemake_rules/sort.smk
index b246f71..2b73e23 100644
--- a/ingest/workflow/snakemake_rules/sort.smk
+++ b/ingest/workflow/snakemake_rules/sort.smk
@@ -58,40 +58,22 @@ rule sort:
         metadata_a = expand("data/a/{time}_metadata.tsv", time=TIME)
     output:
         sequences_a = "data/a/sequences.fasta",
-        metadata_a = "data/a/metadata_notdedup.tsv",
+        metadata_a = "data/a/metadata_sorted.tsv",
         sequences_b = "data/b/sequences.fasta",
-        metadata_b = "data/b/metadata_notdedup.tsv"
+        metadata_b = "data/b/metadata_sorted.tsv"
     shell:
         """
         python bin/sort.py
         """
 
-rule deduplication:
-    input:
-        metadata_a = rules.sort.output.metadata_a,
-        metadata_b = rules.sort.output.metadata_b
-    output:
-        dedup_metadata_a = "data/a/metadata_no_covg.tsv",
-        dedup_metadata_b = "data/b/metadata_no_covg.tsv"
-    shell:
-        """
-        python bin/metadata_dedup.py \
-            --metadata-original {input.metadata_a} \
-            --metadata-output {output.dedup_metadata_a}
-
-        python bin/metadata_dedup.py \
-            --metadata-original {input.metadata_b} \
-            --metadata-output {output.dedup_metadata_b}
-        """
-
 rule coverage:
     input:
         alignment_a = expand("data/a/{time}_sequences.aligned.fasta", time=TIME),
         alignment_b = expand("data/b/{time}_sequences.aligned.fasta", time=TIME),
         metadata_b = expand("data/b/{time}_metadata.tsv", time=TIME),
         metadata_a = expand("data/a/{time}_metadata.tsv", time=TIME),
-        dedup_metadata_a = rules.deduplication.output.dedup_metadata_a,
-        dedup_metadata_b = rules.deduplication.output.dedup_metadata_b
+        sorted_metadata_a = "data/a/metadata_sorted.tsv",
+        sorted_metadata_b = "data/b/metadata_sorted.tsv"
     output:
         metadata_a = "data/a/metadata.tsv",
         metadata_b = "data/b/metadata.tsv"