From 56276321176f7a6e14875600e98503a4761b20ba Mon Sep 17 00:00:00 2001
From: Manuel Holtgrewe <manuel.holtgrewe@bih-charite.de>
Date: Mon, 22 Jul 2024 07:19:13 +0200
Subject: [PATCH] feat: write manifest files to output (#92) (#99)

* feat: write manifest files to output (#92)

* wi

* wip
---
 environment.yml                          |  1 +
 rules/output/annonars/alphamissense.smk  | 12 ++++++
 rules/output/annonars/cadd.smk           | 10 +++++
 rules/output/annonars/cons.smk           | 10 +++++
 rules/output/annonars/dbnsfp.smk         | 12 ++++++
 rules/output/annonars/dbscsnv.smk        | 12 ++++++
 rules/output/annonars/dbsnp.smk          | 10 +++++
 rules/output/annonars/functional.smk     | 12 ++++++
 rules/output/annonars/genes.smk          | 13 +++++++
 rules/output/annonars/gnomad_exomes.smk  | 12 ++++++
 rules/output/annonars/gnomad_genomes.smk | 12 ++++++
 rules/output/annonars/gnomad_mtdna.smk   | 12 ++++++
 rules/output/annonars/gnomad_sv.smk      | 48 ++++++++++++++++++++++++
 rules/output/annonars/helix.smk          | 12 ++++++
 rules/output/annonars/regions.smk        | 10 +++++
 rules/output/mehari/freqs.smk            | 13 +++++++
 rules/reduced/annonars.smk               | 10 +++++
 rules/reduced/hpo.smk                    | 20 ++++++++++
 rules/reduced/mehari.smk                 | 10 +++++
 19 files changed, 251 insertions(+)

diff --git a/environment.yml b/environment.yml
index 4b735ce..44d6a60 100644
--- a/environment.yml
+++ b/environment.yml
@@ -10,6 +10,7 @@ dependencies:
   - attrs
   - cattrs
   - click
+  - hashdeep
   - loguru
   - numpy
   - pydantic
diff --git a/rules/output/annonars/alphamissense.smk b/rules/output/annonars/alphamissense.smk
index 4217671..9b3fc10 100644
--- a/rules/output/annonars/alphamissense.smk
+++ b/rules/output/annonars/alphamissense.smk
@@ -20,6 +20,9 @@ rule output_annonars_alphamissense:  # -- build AlphaMissense RocksDB with annon
         spec_yaml=(
             "output/full/annonars/alphamissense-{genome_release}-{v_alphamissense}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/alphamissense-{genome_release}-{v_alphamissense}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -58,4 +61,13 @@ rule output_annonars_alphamissense:  # -- build AlphaMissense RocksDB with annon
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/cadd.smk b/rules/output/annonars/cadd.smk
index 62c16be..f10e9bc 100644
--- a/rules/output/annonars/cadd.smk
+++ b/rules/output/annonars/cadd.smk
@@ -53,6 +53,7 @@ rule output_annonars_cadd:  # -- build CADD RocksDB with annonars
             "output/full/annonars/cadd-{genome_release}-{v_cadd}+{v_annonars}/rocksdb/IDENTITY"
         ),
         spec_yaml=("output/full/annonars/cadd-{genome_release}-{v_cadd}+{v_annonars}/spec.yaml"),
+        manifest=("output/full/annonars/cadd-{genome_release}-{v_cadd}+{v_annonars}/MANIFEST.txt"),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -93,4 +94,13 @@ rule output_annonars_cadd:  # -- build CADD RocksDB with annonars
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/cons.smk b/rules/output/annonars/cons.smk
index 3ea385d..788fe6f 100644
--- a/rules/output/annonars/cons.smk
+++ b/rules/output/annonars/cons.smk
@@ -11,6 +11,7 @@ rule output_annonars_cons:  # -- build UCSC conservation track RocksDB with anno
             "output/full/annonars/cons-{genome_release}-{v_cons}+{v_annonars}/rocksdb/IDENTITY"
         ),
         spec_yaml=("output/full/annonars/cons-{genome_release}-{v_cons}+{v_annonars}/spec.yaml"),
+        manifest=("output/full/annonars/cons-{genome_release}-{v_cons}+{v_annonars}/MANIFEST.txt"),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -37,4 +38,13 @@ rule output_annonars_cons:  # -- build UCSC conservation track RocksDB with anno
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/dbnsfp.smk b/rules/output/annonars/dbnsfp.smk
index f34ad60..1873c76 100644
--- a/rules/output/annonars/dbnsfp.smk
+++ b/rules/output/annonars/dbnsfp.smk
@@ -16,6 +16,9 @@ rule output_annonars_dbnsfp:  # -- build dbNSFP RocksDB with annonars
             "output/full/annonars/dbnsfp-{genome_release}-{v_dbnsfp}+{v_annonars}/rocksdb/IDENTITY"
         ),
         spec_yaml=("output/full/annonars/dbnsfp-{genome_release}-{v_dbnsfp}+{v_annonars}/spec.yaml"),
+        manifest=(
+            "output/full/annonars/dbnsfp-{genome_release}-{v_dbnsfp}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -59,4 +62,13 @@ rule output_annonars_dbnsfp:  # -- build dbNSFP RocksDB with annonars
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/dbscsnv.smk b/rules/output/annonars/dbscsnv.smk
index 04c1496..9490149 100644
--- a/rules/output/annonars/dbscsnv.smk
+++ b/rules/output/annonars/dbscsnv.smk
@@ -18,6 +18,9 @@ rule output_annonars_dbscsnv:  # -- build dbscSNV RocksDB with annonars
         spec_yaml=(
             "output/full/annonars/dbscsnv-{genome_release}-{v_dbscsnv}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/dbscsnv-{genome_release}-{v_dbscsnv}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -61,4 +64,13 @@ rule output_annonars_dbscsnv:  # -- build dbscSNV RocksDB with annonars
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/dbsnp.smk b/rules/output/annonars/dbsnp.smk
index 7724697..5226254 100644
--- a/rules/output/annonars/dbsnp.smk
+++ b/rules/output/annonars/dbsnp.smk
@@ -11,6 +11,7 @@ rule output_annonars_dbsnp:  # -- build dbSNP RocksDB with annonars
             "output/full/annonars/dbsnp-{genome_release}-{v_dbsnp}+{v_annonars}/rocksdb/IDENTITY"
         ),
         spec_yaml=("output/full/annonars/dbsnp-{genome_release}-{v_dbsnp}+{v_annonars}/spec.yaml"),
+        manifest=("output/full/annonars/dbsnp-{genome_release}-{v_dbsnp}+{v_annonars}/MANIFEST.txt"),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -37,4 +38,13 @@ rule output_annonars_dbsnp:  # -- build dbSNP RocksDB with annonars
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/functional.smk b/rules/output/annonars/functional.smk
index c4a6d13..325d2c0 100644
--- a/rules/output/annonars/functional.smk
+++ b/rules/output/annonars/functional.smk
@@ -39,6 +39,9 @@ rule output_annonars_functional:  # -- build annonars functional RocksDB file
         spec_yaml=(
             "output/full/annonars/functional-{genome_release}-{v_refseq}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/functional-{genome_release}-{v_refseq}+{v_annonars}/MANIFEST.txt"
+        ),
     wildcard_constraints:
         v_refseq=RE_VERSION,
         v_annonars=RE_VERSION,
@@ -64,4 +67,13 @@ rule output_annonars_functional:  # -- build annonars functional RocksDB file
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/genes.smk b/rules/output/annonars/genes.smk
index e72b8e7..d461f6f 100644
--- a/rules/output/annonars/genes.smk
+++ b/rules/output/annonars/genes.smk
@@ -28,6 +28,10 @@ rule output_annonars_genes:  # -- build annonars genes RocksDB file
             "output/full/annonars/genes-{v_acmg_sf}+{v_gnomad_constraints}+{v_dbnsfp}+{v_hpo}+{date}+{v_annonars}/"
             "spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/genes-{v_acmg_sf}+{v_gnomad_constraints}+{v_dbnsfp}+{v_hpo}+{date}+{v_annonars}/"
+            "MANIFEST.txt"
+        ),
     wildcard_constraints:
         v_acmg_sf=RE_VERSION,
         v_gnomad_constraints=RE_VERSION,
@@ -73,4 +77,13 @@ rule output_annonars_genes:  # -- build annonars genes RocksDB file
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/gnomad_exomes.smk b/rules/output/annonars/gnomad_exomes.smk
index 0376970..a4e1291 100644
--- a/rules/output/annonars/gnomad_exomes.smk
+++ b/rules/output/annonars/gnomad_exomes.smk
@@ -13,6 +13,9 @@ rule output_annonars_gnomad_exomes:  # -- build gnomAD-exomes RocksDB with annon
         spec_yaml=(
             "output/full/annonars/gnomad-exomes-{genome_release}-{v_gnomad}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/gnomad-exomes-{genome_release}-{v_gnomad}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -55,4 +58,13 @@ rule output_annonars_gnomad_exomes:  # -- build gnomAD-exomes RocksDB with annon
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/gnomad_genomes.smk b/rules/output/annonars/gnomad_genomes.smk
index 673f574..07c4825 100644
--- a/rules/output/annonars/gnomad_genomes.smk
+++ b/rules/output/annonars/gnomad_genomes.smk
@@ -13,6 +13,9 @@ rule output_annonars_gnomad_genomes:  # -- build gnomAD-genomes RocksDB with ann
         spec_yaml=(
             "output/full/annonars/gnomad-genomes-{genome_release}-{v_gnomad}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/gnomad-genomes-{genome_release}-{v_gnomad}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -55,4 +58,13 @@ rule output_annonars_gnomad_genomes:  # -- build gnomAD-genomes RocksDB with ann
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/gnomad_mtdna.smk b/rules/output/annonars/gnomad_mtdna.smk
index bfbb712..befa299 100644
--- a/rules/output/annonars/gnomad_mtdna.smk
+++ b/rules/output/annonars/gnomad_mtdna.smk
@@ -13,6 +13,9 @@ rule output_annonars_gnomad_mtdna:  # -- build gnomAD-mtDNA RocksDB with annonar
         spec_yaml=(
             "output/full/annonars/gnomad-mtdna-{genome_release}-{v_gnomad}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/gnomad-mtdna-{genome_release}-{v_gnomad}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -40,4 +43,13 @@ rule output_annonars_gnomad_mtdna:  # -- build gnomAD-mtDNA RocksDB with annonar
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/gnomad_sv.smk b/rules/output/annonars/gnomad_sv.smk
index 7f52a9f..b5f1473 100644
--- a/rules/output/annonars/gnomad_sv.smk
+++ b/rules/output/annonars/gnomad_sv.smk
@@ -12,6 +12,9 @@ rule output_annonars_gnomad_sv_grch37_exac:  # -- build gnomAD-SV RocksDB with a
             "output/full/annonars/gnomad-sv-exomes-grch37-{v_gnomad}+{v_annonars}/rocksdb/IDENTITY",
         ),
         spec_yaml=("output/full/annonars/gnomad-sv-exomes-grch37-{v_gnomad}+{v_annonars}/spec.yaml"),
+        manifest=(
+            "output/full/annonars/gnomad-sv-exomes-grch37-{v_gnomad}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -39,6 +42,15 @@ rule output_annonars_gnomad_sv_grch37_exac:  # -- build gnomAD-SV RocksDB with a
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
 
 
@@ -55,6 +67,9 @@ rule output_annonars_gnomad_sv_grch37_gnomad_sv2:  # -- build gnomAD-SV RocksDB
         spec_yaml=(
             "output/full/annonars/gnomad-sv-genomes-grch37-{v_gnomad}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/gnomad-sv-genomes-grch37-{v_gnomad}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -82,6 +97,15 @@ rule output_annonars_gnomad_sv_grch37_gnomad_sv2:  # -- build gnomAD-SV RocksDB
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
 
 
@@ -96,6 +120,9 @@ rule output_annonars_gnomad_sv_grch38_gnomad_cnv4:  # -- build gnomAD-SV RocksDB
             "output/full/annonars/gnomad-sv-exomes-grch38-{v_gnomad}+{v_annonars}/rocksdb/IDENTITY",
         ),
         spec_yaml=("output/full/annonars/gnomad-sv-exomes-grch38-{v_gnomad}+{v_annonars}/spec.yaml"),
+        manifest=(
+            "output/full/annonars/gnomad-sv-exomes-grch38-{v_gnomad}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -123,6 +150,15 @@ rule output_annonars_gnomad_sv_grch38_gnomad_cnv4:  # -- build gnomAD-SV RocksDB
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
 
 
@@ -136,6 +172,9 @@ rule output_annonars_gnomad_sv_grch38_gnomad_sv4:  # -- build gnomAD-SV RocksDB
         spec_yaml=(
             "output/full/annonars/gnomad-sv-genomes-grch38-{v_gnomad}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/annonars/gnomad-sv-genomes-grch38-{v_gnomad}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -164,4 +203,13 @@ rule output_annonars_gnomad_sv_grch38_gnomad_sv4:  # -- build gnomAD-SV RocksDB
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/helix.smk b/rules/output/annonars/helix.smk
index 378ef69..b2db8c7 100644
--- a/rules/output/annonars/helix.smk
+++ b/rules/output/annonars/helix.smk
@@ -13,6 +13,9 @@ rule output_annonars_helixmtdb:  # -- build HelixMtDb RocksDB with annonars
         spec_yaml=(
             "output/full/annonars/helixmtdb-{genome_release}-{v_helixmtdb}+{v_annonars}/spec.yaml",
         ),
+        manifest=(
+            "output/full/annonars/helixmtdb-{genome_release}-{v_helixmtdb}+{v_annonars}/MANIFEST.txt",
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -39,4 +42,13 @@ rule output_annonars_helixmtdb:  # -- build HelixMtDb RocksDB with annonars
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/annonars/regions.smk b/rules/output/annonars/regions.smk
index 1084571..fc17892 100644
--- a/rules/output/annonars/regions.smk
+++ b/rules/output/annonars/regions.smk
@@ -25,6 +25,7 @@ rule output_annonars_regions:  # -- build annonars regions RocksDB file
             "output/full/annonars/regions-{genome_release}-{date}+{v_annonars}/" "rocksdb/IDENTITY"
         ),
         spec_yaml=("output/full/annonars/regions-{genome_release}-{date}+{v_annonars}/spec.yaml"),
+        manifest=("output/full/annonars/regions-{genome_release}-{date}+{v_annonars}/MANIFEST.txt"),
     wildcard_constraints:
         v_refseq=RE_VERSION,
         v_annonars=RE_VERSION,
@@ -49,4 +50,13 @@ rule output_annonars_regions:  # -- build annonars regions RocksDB file
             --value v_annonars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/output/mehari/freqs.smk b/rules/output/mehari/freqs.smk
index b1f7483..2a5ebe2 100644
--- a/rules/output/mehari/freqs.smk
+++ b/rules/output/mehari/freqs.smk
@@ -18,6 +18,10 @@ rule output_mehari_freqs_build:  # -- build frequency tables for mehari
             "output/full/mehari/freqs-{genome_release}-{v_gnomad_genomes}+{v_gnomad_exomes}+"
             "{v_gnomad_mtdna}+{v_helixmtdb}+{v_annonars}/spec.yaml"
         ),
+        manifest=(
+            "output/full/mehari/freqs-{genome_release}-{v_gnomad_genomes}+{v_gnomad_exomes}+"
+            "{v_gnomad_mtdna}+{v_helixmtdb}+{v_annonars}/MANIFEST.txt"
+        ),
     threads: int(os.environ.get("THREADS_ANNONARS_IMPORT", "96"))
     resources:
         runtime=os.environ.get("RUNTIME_ANNONARS_IMPORT", "48h"),
@@ -79,4 +83,13 @@ rule output_mehari_freqs_build:  # -- build frequency tables for mehari
             --value v_annovars={wildcards.v_annonars} \
             --value v_downloader={PV.downloader} \
         > {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/reduced/annonars.smk b/rules/reduced/annonars.smk
index 67c0b61..433de9a 100644
--- a/rules/reduced/annonars.smk
+++ b/rules/reduced/annonars.smk
@@ -32,6 +32,7 @@ rule subset_annonars:  # -- create exomes subset
     output:
         rocksdb_identity="output/reduced-{set_name}/annonars/{name}-{genome_release}-{version_multi}/rocksdb/IDENTITY",
         spec_yaml="output/reduced-{set_name}/annonars/{name}-{genome_release}-{version_multi}/spec.yaml",
+        manifest="output/reduced-{set_name}/annonars/{name}-{genome_release}-{version_multi}/MANIFEST.txt",
     wildcard_constraints:
         name=RE_NAME,
         genome_release=RE_GENOME,
@@ -51,4 +52,13 @@ rule subset_annonars:  # -- create exomes subset
             --path-beds {input.bed}
 
         cp {input.spec_yaml} {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/reduced/hpo.smk b/rules/reduced/hpo.smk
index b182c94..374ef6d 100644
--- a/rules/reduced/hpo.smk
+++ b/rules/reduced/hpo.smk
@@ -16,6 +16,7 @@ rule subset_viguno_pheno_exomes:  # -- create exomes subset
         phenotype_to_genes="output/reduced-exomes/viguno/hpo-{v_hpo}+{v_viguno}/phenotype_to_genes.txt",
         bin="output/reduced-exomes/viguno/hpo-{v_hpo}+{v_viguno}/hpo.bin",
         spec_yaml="output/reduced-exomes/viguno/hpo-{v_hpo}+{v_viguno}/spec.yaml",
+        manifest="output/reduced-exomes/viguno/hpo-{v_hpo}+{v_viguno}/MANIFEST.txt",
     wildcard_constraints:
         v_hpo=RE_VERSION,
         v_viguno=RE_VERSION,
@@ -26,6 +27,15 @@ rule subset_viguno_pheno_exomes:  # -- create exomes subset
         cp -a {input.phenotype_to_genes} {output.phenotype_to_genes}
         cp -a {input.bin} {output.bin}
         cp -a {input.spec_yaml} {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
 
 
@@ -42,6 +52,7 @@ rule subset_worker_pheno_dev:  # -- create development subset
         phenotype_to_genes="output/reduced-dev/viguno/hpo-{v_hpo}+{v_viguno}/phenotype_to_genes.txt",
         bin="output/reduced-dev/viguno/hpo-{v_hpo}+{v_viguno}/hpo.bin",
         spec_yaml="output/reduced-dev/viguno/hpo-{v_hpo}+{v_viguno}/spec.yaml",
+        manifest="output/reduced-dev/viguno/hpo-{v_hpo}+{v_viguno}/MANIFEST.txt",
     wildcard_constraints:
         v_hpo=RE_VERSION,
         v_viguno=RE_VERSION,
@@ -55,4 +66,13 @@ rule subset_worker_pheno_dev:  # -- create development subset
         cp -a {input.phenotype_to_genes} {output.phenotype_to_genes}
         cp -a {input.bin} {output.bin}
         cp -a {input.spec_yaml} {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """
diff --git a/rules/reduced/mehari.smk b/rules/reduced/mehari.smk
index e7a1b16..5881f9d 100644
--- a/rules/reduced/mehari.smk
+++ b/rules/reduced/mehari.smk
@@ -32,6 +32,7 @@ rule subset_mehari:  # -- create exomes subset
     output:
         rocksdb_identity="output/reduced-{set_name}/mehari/freqs-{genome_release}-{version_multi}/rocksdb/IDENTITY",
         spec_yaml="output/reduced-{set_name}/mehari/freqs-{genome_release}-{version_multi}/spec.yaml",
+        manifest="output/reduced-{set_name}/mehari/freqs-{genome_release}-{version_multi}/MANIFEST.txt",
     wildcard_constraints:
         genome_release=RE_GENOME,
         v_hpo=RE_VERSION,
@@ -48,4 +49,13 @@ rule subset_mehari:  # -- create exomes subset
             --path-beds {input.bed}
 
         cp {input.spec_yaml} {output.spec_yaml}
+
+        export TMPDIR=$(mktemp -d)
+        pushd $(dirname {output.spec_yaml})
+        rm -f MANIFEST.txt
+        hashdeep -l -r . >$TMPDIR/MANIFEST.txt
+        CHECKSUM=$(sha256sum $TMPDIR/MANIFEST.txt | cut -d ' ' -f 1)
+        echo "## EOF SHA256=$CHECKSUM" >> $TMPDIR/MANIFEST.txt
+        cp $TMPDIR/MANIFEST.txt MANIFEST.txt
+        popd
         """