Merge pull request #4 from TattaBio/andre

Add dataset revisions
TattaBio · Jul 3, 2024 · 95b6f11 · 95b6f11
2 parents ade30a8 + 7e069a2
commit 95b6f11
Show file tree

Hide file tree

Showing 7 changed files with 34 additions and 31 deletions.
diff --git a/dgeb/tasks/bigene_mining_tasks.py b/dgeb/tasks/bigene_mining_tasks.py
@@ -43,7 +43,7 @@ class BacArchBiGeneMining(Task):
         datasets=[
             Dataset(
                 path="tattabio/bac_arch_bigene",
-                revision="main",
+                revision="d5a65e44bae43a9ba9f2fdc03056dff9c12f6631",
             )
         ],
         primary_metric_id="f1",
@@ -67,7 +67,7 @@ class ModACParalogyBiGeneMining(Task):
         datasets=[
             Dataset(
                 path="tattabio/modac_paralogy_bigene",
-                revision="main",
+                revision="241ca6397856e3360da04422d54933035b1fab87",
             )
         ],
         primary_metric_id="recall_at_5",

diff --git a/dgeb/tasks/classification_tasks.py b/dgeb/tasks/classification_tasks.py
@@ -85,7 +85,7 @@ class EnzymeCommissionClassification(Task):
         datasets=[
             Dataset(
                 path="tattabio/ec_classification",
-                revision="main",
+                revision="d83aba56d785df48bd3b4acafc536ff8c03e7d98",
             )
         ],
         primary_metric_id="f1",
@@ -105,7 +105,7 @@ class EnzymeCommissionDNAClassification(Task):
         datasets=[
             Dataset(
                 path="tattabio/ec_classification_dna",
-                revision="main",
+                revision="e78328541bb16e7cda16830d9844c09cbf4e682d",
             )
         ],
         primary_metric_id="f1",
@@ -125,7 +125,7 @@ class ConvergentEnzymesClassification(Task):
         datasets=[
             Dataset(
                 path="tattabio/convergent_enzymes",
-                revision="main",
+                revision="37f75609f54de2bc0911ccb72faf1c2f5a4285aa",
             )
         ],
         primary_metric_id="f1",
@@ -180,7 +180,12 @@ class MIBiGProteinClassification(Task):
         description="Biosynthetic Gene cluster classification using protein sequences on MIBIG dataset.",
         type="classification",
         modality=Modality.PROTEIN,
-        datasets=[Dataset(path="tattabio/mibig_classification_prot", revision="main")],
+        datasets=[
+            Dataset(
+                path="tattabio/mibig_classification_prot",
+                revision="915a7ff28dc9820e35c4d7fd03d4c8c44a88ff1f",
+            )
+        ],
         primary_metric_id="f1",
     )
 
@@ -198,7 +203,7 @@ class MIBiGDNAClassification(Task):
         datasets=[
             Dataset(
                 path="tattabio/mibig_classification_dna",
-                revision="main",
+                revision="b5ca7a76d469e4e66c46f1b655903972571e6b61",
             )
         ],
         primary_metric_id="f1",

diff --git a/dgeb/tasks/clustering_tasks.py b/dgeb/tasks/clustering_tasks.py
@@ -40,7 +40,7 @@ class RNAclustering(Task):
         datasets=[
             Dataset(
                 path="tattabio/e_coli_rnas",
-                revision="main",
+                revision="4c134bb4bdb2b0ef1d59fe10797efdfeaf318de6",
             )
         ],
         primary_metric_id="v_measure",
@@ -60,7 +60,7 @@ class MopBClustering(Task):
         datasets=[
             Dataset(
                 path="tattabio/mopb_clustering",
-                revision="main",
+                revision="eed4bfff9c5bd2dc2500c50757bfcb90425d999a",
             )
         ],
         primary_metric_id="v_measure",

diff --git a/dgeb/tasks/eds_tasks.py b/dgeb/tasks/eds_tasks.py
@@ -64,11 +64,11 @@ class RpobBacPhylogeny(Task):
         datasets=[
             Dataset(
                 path="tattabio/rpob_bac_phylogeny_sequences",
-                revision="main",
+                revision="b833ef8d8d873ea5387540562873f41d073d3e03",
             ),
             Dataset(
                 path="tattabio/rpob_bac_phylogeny_distances",
-                revision="main",
+                revision="0594e1501ac9fd0e3de49257b8ec318c2a0ea6f7",
             ),
         ],
         primary_metric_id="top_corr",
@@ -88,11 +88,11 @@ class RpobArchPhylogeny(Task):
         datasets=[
             Dataset(
                 path="tattabio/rpob_arch_phylogeny_sequences",
-                revision="main",
+                revision="10de75b9f5ad12340d629fd1ad015ef4319d6ee4",
             ),
             Dataset(
                 path="tattabio/rpob_arch_phylogeny_distances",
-                revision="main",
+                revision="2a585f0e135fe74b8ae6d31e7801c6031b0dcc18",
             ),
         ],
         primary_metric_id="top_corr",
@@ -112,11 +112,11 @@ class FeFePhylogeny(Task):
         datasets=[
             Dataset(
                 path="tattabio/fefe_phylogeny_sequences",
-                revision="main",
+                revision="bce06d79d9ce58413e7bcbed6943905d1afb8b26",
             ),
             Dataset(
                 path="tattabio/fefe_phylogeny_distances",
-                revision="main",
+                revision="d6357cee9b4071a8dcdeef54083006f0d5e94fd2",
             ),
         ],
         primary_metric_id="top_corr",
@@ -136,11 +136,11 @@ class Bac16SPhylogeny(Task):
         datasets=[
             Dataset(
                 path="tattabio/bac_16S_sequences",
-                revision="main",
+                revision="efde1456b86748909cbcfecb07d783756d570aa3",
             ),
             Dataset(
                 path="tattabio/bac_16S_distances",
-                revision="main",
+                revision="5c8ba5dfa600bb930d34af2fbc2b17f0acab62d3",
             ),
         ],
         primary_metric_id="top_corr",
@@ -160,11 +160,11 @@ class Arch16SPhylogeny(Task):
         datasets=[
             Dataset(
                 path="tattabio/arch_16S_sequences",
-                revision="main",
+                revision="e0f0b5d5bd4b08a329b08c2bf4cc800781dff7f0",
             ),
             Dataset(
                 path="tattabio/arch_16S_distances",
-                revision="main",
+                revision="b0356b632a954be70cefd57e3a02e7e1ccd34408",
             ),
         ],
         primary_metric_id="top_corr",
@@ -184,11 +184,11 @@ class Euk18SPhylogeny(Task):
         datasets=[
             Dataset(
                 path="tattabio/euk_18S_sequences",
-                revision="main",
+                revision="5174cb3b2c5c46b61307fd1c2c08f5c432655196",
             ),
             Dataset(
                 path="tattabio/euk_18S_distances",
-                revision="main",
+                revision="c4cea4fbb1185d08e0e01fd28ffb8b06a25025da",
             ),
         ],
         primary_metric_id="top_corr",

diff --git a/dgeb/tasks/pair_classification_tasks.py b/dgeb/tasks/pair_classification_tasks.py
@@ -46,7 +46,7 @@ class EcoliOperon(Task):
         datasets=[
             Dataset(
                 path="tattabio/ecoli_operonic_pair",
-                revision="main",
+                revision="a62c01143a842696fc8200b91c1acb825e8cb891",
             )
         ],
         primary_metric_id="top_ap",
@@ -66,7 +66,7 @@ class CyanoOperonPair(Task):
         datasets=[
             Dataset(
                 path="tattabio/cyano_operonic_pair",
-                revision="main",
+                revision="eeb4cb71ec2a4ff688af9de7c0662123577d32ec",
             )
         ],
         primary_metric_id="top_ap",
@@ -86,7 +86,7 @@ class VibrioOperonPair(Task):
         datasets=[
             Dataset(
                 path="tattabio/vibrio_operonic_pair",
-                revision="main",
+                revision="24781b12b45bf81a079a6164ef0d2124948c1878",
             )
         ],
         primary_metric_id="top_ap",

diff --git a/dgeb/tasks/retrieval_tasks.py b/dgeb/tasks/retrieval_tasks.py
@@ -58,12 +58,12 @@ class ArchRetrieval(Task):
         datasets=[
             Dataset(
                 path="tattabio/arch_retrieval",
-                revision="main",
+                revision="a19124322604a21b26b1b3c13a1bd0b8a63c9f7b",
             ),
             Dataset(
                 path="tattabio/arch_retrieval_qrels",
                 description="Relevance between query and corpus proteins",
-                revision="main",
+                revision="3f142f2f9a0995d56c6e77188c7251761450afcf",
             ),
         ],
         primary_metric_id="map_at_5",
@@ -83,12 +83,12 @@ class EukRetrieval(Task):
         datasets=[
             Dataset(
                 path="tattabio/euk_retrieval",
-                revision="main",
+                revision="c93dc56665cedd19fbeaea9ace146f2474c895f0",
             ),
             Dataset(
                 path="tattabio/euk_retrieval_qrels",
                 description="Relevance between query and corpus proteins",
-                revision="main",
+                revision="a5aa01e9b9738074aba57fc07434e352c4c71e4b",
             ),
         ],
         primary_metric_id="map_at_5",

diff --git a/dgeb/tasks/tasks.py b/dgeb/tasks/tasks.py
@@ -1,6 +1,4 @@
-"""Task functions for evaluation.
-# TODO: Add dataset revisions.
-"""
+"""Task abstract class for evaluation and results."""
 
 import logging
 from abc import ABC, abstractmethod