Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+results/test_counts/concept_f1_scores.csv filter=lfs diff=lfs merge=lfs -text
+results/valid_counts/concept_f1_scores.csv filter=lfs diff=lfs merge=lfs -text

results/test_counts/concept_f1_scores.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d36483f3a6b2d55f3412ad647865085bd2d070a34735df6a0780cd921e8615
+size 19972509

results/test_counts/heldout_all_top_pairings.csv

@@ -0,0 +1,202 @@
+concept,feature,threshold_pct,precision,recall,recall_per_domain,f1,f1_per_domain,tp,fp,tp_per_domain,is_aa_level_concept
+Zinc finger_RING-type,907,0.5,1.0,0.0231213872832369,1.0,0.0451977401129943,1.0,4.0,0.0,4.0,False
+Zinc finger_RING-type,1554,0.6,1.0,0.0231213872832369,1.0,0.0451977401129943,1.0,4.0,0.0,4.0,False
+Zinc finger_any,907,0.5,1.0,0.0231213872832369,1.0,0.0451977401129943,1.0,4.0,0.0,4.0,False
+Zinc finger_any,1554,0.6,1.0,0.0231213872832369,1.0,0.0451977401129943,1.0,4.0,0.0,4.0,False
+Domain_C-type lectin,100,0.6,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,475,0.6,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,851,0.5,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,1201,0.6,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,1434,0.5,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,1601,0.5,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,1964,0.5,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,1976,0.5,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,2262,0.5,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,2284,0.5,1.0,0.0088008800880088,1.0,0.0174482006543075,1.0,8.0,0.0,8.0,False
+Domain_C-type lectin,180,0.6,0.8888888888888888,0.0088008800880088,1.0,0.0174291938997821,0.9411764705882352,8.0,1.0,8.0,False
+Domain_C-type lectin,331,0.5,0.8888888888888888,0.0088008800880088,1.0,0.0174291938997821,0.9411764705882352,8.0,1.0,8.0,False
+Domain_C-type lectin,1603,0.5,0.8888888888888888,0.0088008800880088,1.0,0.0174291938997821,0.9411764705882352,8.0,1.0,8.0,False
+Domain_C-type lectin,2423,0.6,0.8888888888888888,0.0088008800880088,1.0,0.0174291938997821,0.9411764705882352,8.0,1.0,8.0,False
+Domain_C-type lectin,147,0.8,1.0,0.0077007700770077,0.875,0.0152838427947598,0.9333333333333332,7.0,0.0,7.0,False
+Domain_C-type lectin,986,0.5,1.0,0.0077007700770077,0.875,0.0152838427947598,0.9333333333333332,7.0,0.0,7.0,False
+Domain_C-type lectin,1917,0.5,1.0,0.0077007700770077,0.875,0.0152838427947598,0.9333333333333332,7.0,0.0,7.0,False
+Domain_C-type lectin,1302,0.15,0.8,0.0088008800880088,1.0,0.0174102285092491,0.888888888888889,8.0,2.0,8.0,False
+Domain_C-type lectin,2260,0.6,0.8,0.0088008800880088,1.0,0.0174102285092491,0.888888888888889,8.0,2.0,8.0,False
+Zinc finger_RING-type,349,0.5,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,384,0.6,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,516,0.5,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,1091,0.8,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,1095,0.6,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,1532,0.8,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,1726,0.6,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,2165,0.6,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,2368,0.5,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_RING-type,2547,0.8,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,349,0.5,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,384,0.6,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,516,0.5,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,1091,0.8,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,1095,0.6,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,1532,0.8,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,1726,0.6,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,2165,0.6,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,2368,0.5,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Zinc finger_any,2547,0.8,1.0,0.0173410404624277,0.75,0.034090909090909,0.8571428571428571,3.0,0.0,3.0,False
+Domain_C-type lectin,461,0.6,1.0,0.0066006600660066,0.75,0.0131147540983606,0.8571428571428571,6.0,0.0,6.0,False
+Domain_C-type lectin,1117,0.8,1.0,0.0066006600660066,0.75,0.0131147540983606,0.8571428571428571,6.0,0.0,6.0,False
+Domain_C-type lectin,1662,0.8,1.0,0.0066006600660066,0.75,0.0131147540983606,0.8571428571428571,6.0,0.0,6.0,False
+Domain_C-type lectin,2062,0.8,1.0,0.0066006600660066,0.75,0.0131147540983606,0.8571428571428571,6.0,0.0,6.0,False
+Domain_C-type lectin,364,0.5,0.7272727272727273,0.0088008800880088,1.0,0.017391304347826,0.8421052631578948,8.0,3.0,8.0,False
+Domain_C-type lectin,441,0.5,0.7272727272727273,0.0088008800880088,1.0,0.017391304347826,0.8421052631578948,8.0,3.0,8.0,False
+Domain_C-type lectin,788,0.5,0.7272727272727273,0.0088008800880088,1.0,0.017391304347826,0.8421052631578948,8.0,3.0,8.0,False
+Domain_C-type lectin,1128,0.6,0.7272727272727273,0.0088008800880088,1.0,0.017391304347826,0.8421052631578948,8.0,3.0,8.0,False
+Domain_C-type lectin,1438,0.8,0.7272727272727273,0.0088008800880088,1.0,0.017391304347826,0.8421052631578948,8.0,3.0,8.0,False
+Domain_C-type lectin,1956,0.0,0.7272727272727273,0.0088008800880088,1.0,0.017391304347826,0.8421052631578948,8.0,3.0,8.0,False
+Domain_C-type lectin,677,0.5,0.7777777777777778,0.0077007700770077,0.875,0.0152505446623093,0.823529411764706,7.0,2.0,7.0,False
+Domain_C-type lectin,1725,0.5,0.7777777777777778,0.0077007700770077,0.875,0.0152505446623093,0.823529411764706,7.0,2.0,7.0,False
+Domain_C-type lectin,1921,0.6,0.7777777777777778,0.0077007700770077,0.875,0.0152505446623093,0.823529411764706,7.0,2.0,7.0,False
+Domain_C-type lectin,99,0.6,0.6666666666666666,0.0088008800880088,1.0,0.017372421281216,0.8,8.0,4.0,8.0,False
+Domain_C-type lectin,193,0.5,0.6666666666666666,0.0088008800880088,1.0,0.017372421281216,0.8,8.0,4.0,8.0,False
+Domain_C-type lectin,246,0.5,0.6666666666666666,0.0088008800880088,1.0,0.017372421281216,0.8,8.0,4.0,8.0,False
+Domain_C-type lectin,458,0.15,0.6666666666666666,0.0088008800880088,1.0,0.017372421281216,0.8,8.0,4.0,8.0,False
+Domain_C-type lectin,1527,0.6,0.6666666666666666,0.0088008800880088,1.0,0.017372421281216,0.8,8.0,4.0,8.0,False
+Domain_C-type lectin,48,0.8,0.8571428571428571,0.0066006600660066,0.75,0.0131004366812227,0.7999999999999999,6.0,1.0,6.0,False
+Domain_C-type lectin,339,0.8,0.8571428571428571,0.0066006600660066,0.75,0.0131004366812227,0.7999999999999999,6.0,1.0,6.0,False
+Domain_C-type lectin,2252,0.8,0.8571428571428571,0.0066006600660066,0.75,0.0131004366812227,0.7999999999999999,6.0,1.0,6.0,False
+Domain_C-type lectin,2491,0.8,0.8571428571428571,0.0066006600660066,0.75,0.0131004366812227,0.7999999999999999,6.0,1.0,6.0,False
+Domain_C-type lectin,2529,0.5,0.8571428571428571,0.0066006600660066,0.75,0.0131004366812227,0.7999999999999999,6.0,1.0,6.0,False
+Domain_C-type lectin,97,0.6,0.6153846153846154,0.0088008800880088,1.0,0.0173535791757049,0.761904761904762,8.0,5.0,8.0,False
+Domain_C-type lectin,102,0.6,0.6153846153846154,0.0088008800880088,1.0,0.0173535791757049,0.761904761904762,8.0,5.0,8.0,False
+Domain_C-type lectin,1164,0.6,0.6153846153846154,0.0088008800880088,1.0,0.0173535791757049,0.761904761904762,8.0,5.0,8.0,False
+Domain_C-type lectin,1863,0.6,0.6153846153846154,0.0088008800880088,1.0,0.0173535791757049,0.761904761904762,8.0,5.0,8.0,False
+Zinc finger_RING-type,270,0.6,0.75,0.0173410404624277,0.75,0.0338983050847457,0.75,3.0,1.0,3.0,False
+Zinc finger_RING-type,1548,0.5,0.75,0.0173410404624277,0.75,0.0338983050847457,0.75,3.0,1.0,3.0,False
+Zinc finger_any,270,0.6,0.75,0.0173410404624277,0.75,0.0338983050847457,0.75,3.0,1.0,3.0,False
+Zinc finger_any,1548,0.5,0.75,0.0173410404624277,0.75,0.0338983050847457,0.75,3.0,1.0,3.0,False
+Domain_Ig-like V-type,1136,0.8,0.6428571428571429,0.0084985835694051,0.9,0.0167753960857409,0.75,9.0,5.0,9.0,False
+Domain_C-type lectin,16,0.0,0.75,0.0066006600660066,0.75,0.0130861504907306,0.75,6.0,2.0,6.0,False
+Domain_C-type lectin,113,0.8,0.75,0.0066006600660066,0.75,0.0130861504907306,0.75,6.0,2.0,6.0,False
+Domain_C-type lectin,909,0.5,0.75,0.0066006600660066,0.75,0.0130861504907306,0.75,6.0,2.0,6.0,False
+Domain_C-type lectin,2285,0.8,0.75,0.0066006600660066,0.75,0.0130861504907306,0.75,6.0,2.0,6.0,False
+Domain_C-type lectin,2412,0.6,0.75,0.0066006600660066,0.75,0.0130861504907306,0.75,6.0,2.0,6.0,False
+Domain_C-type lectin,1108,0.15,0.6363636363636364,0.0077007700770077,0.875,0.0152173913043478,0.7368421052631579,7.0,4.0,7.0,False
+Region_Disordered,1885,0.15,0.580385288966725,0.7069866666666667,0.978494623655914,0.6374609281077181,0.7286050455900616,6628.0,4792.0,182.0,False
+Zinc finger_RING-type,2119,0.5,0.5714285714285714,0.0231213872832369,1.0,0.0444444444444444,0.7272727272727273,4.0,3.0,4.0,False
+Zinc finger_RING-type,2176,0.8,0.5714285714285714,0.0231213872832369,1.0,0.0444444444444444,0.7272727272727273,4.0,3.0,4.0,False
+Zinc finger_any,2119,0.5,0.5714285714285714,0.0231213872832369,1.0,0.0444444444444444,0.7272727272727273,4.0,3.0,4.0,False
+Zinc finger_any,2176,0.8,0.5714285714285714,0.0231213872832369,1.0,0.0444444444444444,0.7272727272727273,4.0,3.0,4.0,False
+Domain_C-type lectin,35,0.6,0.5714285714285714,0.0088008800880088,1.0,0.0173347778981581,0.7272727272727273,8.0,6.0,8.0,False
+Domain_C-type lectin,257,0.15,0.5714285714285714,0.0088008800880088,1.0,0.0173347778981581,0.7272727272727273,8.0,6.0,8.0,False
+Domain_C-type lectin,359,0.15,0.5714285714285714,0.0088008800880088,1.0,0.0173347778981581,0.7272727272727273,8.0,6.0,8.0,False
+Domain_C-type lectin,820,0.15,0.5714285714285714,0.0088008800880088,1.0,0.0173347778981581,0.7272727272727273,8.0,6.0,8.0,False
+Domain_C-type lectin,1320,0.5,0.5714285714285714,0.0088008800880088,1.0,0.0173347778981581,0.7272727272727273,8.0,6.0,8.0,False
+Domain_C-type lectin,1826,0.6,0.5714285714285714,0.0088008800880088,1.0,0.0173347778981581,0.7272727272727273,8.0,6.0,8.0,False
+Domain_C-type lectin,2205,0.15,0.5714285714285714,0.0088008800880088,1.0,0.0173347778981581,0.7272727272727273,8.0,6.0,8.0,False
+Domain_Ig-like V-type,460,0.6,0.6666666666666666,0.0075542965061378,0.8,0.0149393090569561,0.7272727272727272,8.0,4.0,8.0,False
+Compositional bias_Acidic residues,790,0.8,0.8529411764705882,0.1269146608315098,0.6153846153846154,0.2209523809523809,0.7149460708782742,58.0,10.0,16.0,False
+Domain_C-type lectin,383,0.8,0.8333333333333334,0.0055005500550055,0.625,0.0109289617486338,0.7142857142857143,5.0,1.0,5.0,False
+Domain_C-type lectin,703,0.5,0.8333333333333334,0.0055005500550055,0.625,0.0109289617486338,0.7142857142857143,5.0,1.0,5.0,False
+Domain_C-type lectin,450,0.6,0.6666666666666666,0.0066006600660066,0.75,0.0130718954248366,0.7058823529411765,6.0,3.0,6.0,False
+Domain_C-type lectin,454,0.5,0.6666666666666666,0.0066006600660066,0.75,0.0130718954248366,0.7058823529411765,6.0,3.0,6.0,False
+Domain_C-type lectin,31,0.15,0.5333333333333333,0.0088008800880088,1.0,0.0173160173160173,0.6956521739130436,8.0,7.0,8.0,False
+Domain_C-type lectin,119,0.5,0.5333333333333333,0.0088008800880088,1.0,0.0173160173160173,0.6956521739130436,8.0,7.0,8.0,False
+Domain_C-type lectin,1954,0.5,0.5333333333333333,0.0088008800880088,1.0,0.0173160173160173,0.6956521739130436,8.0,7.0,8.0,False
+Domain_C-type lectin,2172,0.15,0.5333333333333333,0.0088008800880088,1.0,0.0173160173160173,0.6956521739130436,8.0,7.0,8.0,False
+Domain_C-type lectin,2349,0.15,0.5333333333333333,0.0088008800880088,1.0,0.0173160173160173,0.6956521739130436,8.0,7.0,8.0,False
+Domain_Ig-like V-type,12,0.6,0.5625,0.0084985835694051,0.9,0.0167441860465116,0.6923076923076923,9.0,7.0,9.0,False
+Domain_C-type lectin,90,0.6,0.5384615384615384,0.0077007700770077,0.875,0.0151843817787418,0.6666666666666667,7.0,6.0,7.0,False
+Domain_C-type lectin,1753,0.6,0.5384615384615384,0.0077007700770077,0.875,0.0151843817787418,0.6666666666666667,7.0,6.0,7.0,False
+Zinc finger_RING-type,1004,0.5,0.5,0.0231213872832369,1.0,0.0441988950276243,0.6666666666666666,4.0,4.0,4.0,False
+Zinc finger_RING-type,1620,0.8,0.5,0.0231213872832369,1.0,0.0441988950276243,0.6666666666666666,4.0,4.0,4.0,False
+Zinc finger_RING-type,1834,0.15,0.5,0.0231213872832369,1.0,0.0441988950276243,0.6666666666666666,4.0,4.0,4.0,False
+Zinc finger_any,1004,0.5,0.5,0.0231213872832369,1.0,0.0441988950276243,0.6666666666666666,4.0,4.0,4.0,False
+Zinc finger_any,1620,0.8,0.5,0.0231213872832369,1.0,0.0441988950276243,0.6666666666666666,4.0,4.0,4.0,False
+Zinc finger_any,1834,0.15,0.5,0.0231213872832369,1.0,0.0441988950276243,0.6666666666666666,4.0,4.0,4.0,False
+Domain_C-type lectin,326,0.5,0.5,0.0088008800880088,1.0,0.0172972972972972,0.6666666666666666,8.0,8.0,8.0,False
+Domain_C-type lectin,599,0.0,0.5,0.0088008800880088,1.0,0.0172972972972972,0.6666666666666666,8.0,8.0,8.0,False
+Domain_C-type lectin,877,0.15,0.5,0.0088008800880088,1.0,0.0172972972972972,0.6666666666666666,8.0,8.0,8.0,False
+Domain_C-type lectin,1657,0.5,0.5,0.0088008800880088,1.0,0.0172972972972972,0.6666666666666666,8.0,8.0,8.0,False
+Domain_C-type lectin,2447,0.5,0.5,0.0088008800880088,1.0,0.0172972972972972,0.6666666666666666,8.0,8.0,8.0,False
+Zinc finger_RING-type,159,0.6,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_RING-type,540,0.6,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_RING-type,1319,0.6,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_RING-type,1534,0.6,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_RING-type,1675,0.8,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_RING-type,2299,0.8,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_any,159,0.6,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_any,540,0.6,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_any,1319,0.6,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_any,1534,0.6,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_any,1675,0.8,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Zinc finger_any,2299,0.8,0.6,0.0173410404624277,0.75,0.0337078651685393,0.6666666666666665,3.0,2.0,3.0,False
+Domain_C-type lectin,367,0.8,0.6,0.0066006600660066,0.75,0.0130576713819368,0.6666666666666665,6.0,4.0,6.0,False
+Domain_C-type lectin,1489,0.6,0.6,0.0066006600660066,0.75,0.0130576713819368,0.6666666666666665,6.0,4.0,6.0,False
+Domain_C-type lectin,2123,0.6,0.6,0.0066006600660066,0.75,0.0130576713819368,0.6666666666666665,6.0,4.0,6.0,False
+Region_Disordered,1687,0.15,0.6397296503085512,0.2322133333333333,0.6774193548387096,0.3407419001408671,0.6580352644836271,2177.0,1226.0,126.0,False
+Coiled coil,774,0.5,0.696078431372549,0.0507868383404864,0.6111111111111112,0.0946666666666666,0.6508333333333334,71.0,31.0,11.0,False
+Domain_C-type lectin,79,0.6,0.4705882352941176,0.0088008800880088,1.0,0.0172786177105831,0.6399999999999999,8.0,9.0,8.0,False
+Domain_C-type lectin,382,0.8,0.4705882352941176,0.0088008800880088,1.0,0.0172786177105831,0.6399999999999999,8.0,9.0,8.0,False
+Domain_C-type lectin,2186,0.5,0.4705882352941176,0.0088008800880088,1.0,0.0172786177105831,0.6399999999999999,8.0,9.0,8.0,False
+Domain_C-type lectin,2382,0.6,0.4705882352941176,0.0088008800880088,1.0,0.0172786177105831,0.6399999999999999,8.0,9.0,8.0,False
+Domain_C-type lectin,2159,0.5,0.5,0.0077007700770077,0.875,0.0151679306608884,0.6363636363636364,7.0,7.0,7.0,False
+Domain_C-type lectin,1101,0.8,0.5454545454545454,0.0066006600660066,0.75,0.0130434782608695,0.631578947368421,6.0,5.0,6.0,False
+Domain_C-type lectin,2506,0.6,0.5454545454545454,0.0066006600660066,0.75,0.0130434782608695,0.631578947368421,6.0,5.0,6.0,False
+Domain_Ig-like V-type,312,0.6,0.4545454545454545,0.0094428706326723,1.0,0.0185013876040703,0.625,10.0,12.0,10.0,False
+Domain_Ig-like V-type,905,0.0,0.4545454545454545,0.0094428706326723,1.0,0.0185013876040703,0.625,10.0,12.0,10.0,False
+Domain_C-type lectin,471,0.8,0.625,0.0055005500550055,0.625,0.0109051254089422,0.625,5.0,3.0,5.0,False
+Coiled coil,1783,0.5,0.6386554621848739,0.0543633762517882,0.6111111111111112,0.1001977587343441,0.6245797534553604,76.0,43.0,11.0,False
+Coiled coil,2442,0.15,0.5204081632653061,0.0729613733905579,0.7777777777777778,0.1279799247176913,0.6235807860262008,102.0,94.0,14.0,False
+Domain_Ig-like V-type,1950,0.8,0.5,0.0075542965061378,0.8,0.0148837209302325,0.6153846153846154,8.0,8.0,8.0,False
+Domain_C-type lectin,897,0.5,0.8,0.0044004400440044,0.5,0.0087527352297593,0.6153846153846154,4.0,1.0,4.0,False
+Zinc finger_RING-type,2277,0.5,0.4444444444444444,0.0231213872832369,1.0,0.0439560439560439,0.6153846153846153,4.0,5.0,4.0,False
+Zinc finger_any,2277,0.5,0.4444444444444444,0.0231213872832369,1.0,0.0439560439560439,0.6153846153846153,4.0,5.0,4.0,False
+Domain_C-type lectin,162,0.6,0.4444444444444444,0.0088008800880088,1.0,0.0172599784250269,0.6153846153846153,8.0,10.0,8.0,False
+Domain_C-type lectin,596,0.6,0.4444444444444444,0.0088008800880088,1.0,0.0172599784250269,0.6153846153846153,8.0,10.0,8.0,False
+Domain_C-type lectin,1250,0.5,0.4444444444444444,0.0088008800880088,1.0,0.0172599784250269,0.6153846153846153,8.0,10.0,8.0,False
+Domain_C-type lectin,2211,0.6,0.4444444444444444,0.0088008800880088,1.0,0.0172599784250269,0.6153846153846153,8.0,10.0,8.0,False
+Domain_C-type lectin,1685,0.5,0.4666666666666667,0.0077007700770077,0.875,0.0151515151515151,0.608695652173913,7.0,8.0,7.0,False
+Domain_Ig-like V-type,972,0.6,0.4347826086956521,0.0094428706326723,1.0,0.0184842883548983,0.6060606060606061,10.0,13.0,10.0,False
+Zinc finger_RING-type,550,0.6,0.5,0.0173410404624277,0.75,0.0335195530726256,0.6,3.0,3.0,3.0,False
+Zinc finger_RING-type,1197,0.5,0.5,0.0173410404624277,0.75,0.0335195530726256,0.6,3.0,3.0,3.0,False
+Zinc finger_any,550,0.6,0.5,0.0173410404624277,0.75,0.0335195530726256,0.6,3.0,3.0,3.0,False
+Zinc finger_any,1197,0.5,0.5,0.0173410404624277,0.75,0.0335195530726256,0.6,3.0,3.0,3.0,False
+Domain_C-type lectin,858,0.8,0.5,0.0066006600660066,0.75,0.013029315960912,0.6,6.0,6.0,6.0,False
+Domain_C-type lectin,2118,0.8,0.5,0.0066006600660066,0.75,0.013029315960912,0.6,6.0,6.0,6.0,False
+Domain_C-type lectin,2370,0.6,0.5,0.0066006600660066,0.75,0.013029315960912,0.6,6.0,6.0,6.0,False
+Domain_Ig-like V-type,2068,0.6,0.4166666666666667,0.0094428706326723,1.0,0.0184672206832871,0.5882352941176471,10.0,14.0,10.0,False
+Domain_C-type lectin,2223,0.15,0.4375,0.0077007700770077,0.875,0.0151351351351351,0.5833333333333334,7.0,9.0,7.0,False
+Region_Disordered,790,0.15,0.4191987613702341,0.23104,0.9086021505376344,0.2978957502406821,0.5737078392820618,2166.0,3001.0,169.0,False
+Region_Disordered,667,0.5,0.4281904761904762,0.1198933333333333,0.8602150537634409,0.1873333333333333,0.571770121958974,1124.0,1501.0,160.0,False
+Zinc finger_RING-type,872,0.6,0.6666666666666666,0.0115606936416184,0.5,0.0227272727272727,0.5714285714285715,2.0,1.0,2.0,False
+Zinc finger_RING-type,2038,0.8,0.6666666666666666,0.0115606936416184,0.5,0.0227272727272727,0.5714285714285715,2.0,1.0,2.0,False
+Zinc finger_RING-type,2201,0.5,0.6666666666666666,0.0115606936416184,0.5,0.0227272727272727,0.5714285714285715,2.0,1.0,2.0,False
+Zinc finger_any,872,0.6,0.6666666666666666,0.0115606936416184,0.5,0.0227272727272727,0.5714285714285715,2.0,1.0,2.0,False
+Zinc finger_any,2038,0.8,0.6666666666666666,0.0115606936416184,0.5,0.0227272727272727,0.5714285714285715,2.0,1.0,2.0,False
+Zinc finger_any,2201,0.5,0.6666666666666666,0.0115606936416184,0.5,0.0227272727272727,0.5714285714285715,2.0,1.0,2.0,False
+Domain_C-type lectin,415,0.5,0.4,0.0088008800880088,1.0,0.0172228202368137,0.5714285714285715,8.0,12.0,8.0,False
+Domain_C-type lectin,1107,0.5,0.4,0.0088008800880088,1.0,0.0172228202368137,0.5714285714285715,8.0,12.0,8.0,False
+Domain_C-type lectin,463,0.5,0.4615384615384615,0.0066006600660066,0.75,0.0130151843817787,0.5714285714285714,6.0,7.0,6.0,False
+Domain_C-type lectin,474,0.5,0.4615384615384615,0.0066006600660066,0.75,0.0130151843817787,0.5714285714285714,6.0,7.0,6.0,False
+Domain_C-type lectin,499,0.5,0.4615384615384615,0.0066006600660066,0.75,0.0130151843817787,0.5714285714285714,6.0,7.0,6.0,False
+Domain_C-type lectin,812,0.5,0.4615384615384615,0.0066006600660066,0.75,0.0130151843817787,0.5714285714285714,6.0,7.0,6.0,False
+Domain_C-type lectin,1818,0.6,0.4615384615384615,0.0066006600660066,0.75,0.0130151843817787,0.5714285714285714,6.0,7.0,6.0,False
+Coiled coil,2475,0.15,0.532051282051282,0.0593705293276108,0.6111111111111112,0.1068211068211068,0.5688473520249222,83.0,73.0,11.0,False
+Domain_Ig-like V-type,1455,0.6,0.3846153846153846,0.0094428706326723,1.0,0.0184331797235023,0.5555555555555556,10.0,16.0,10.0,False
+Region_Disordered,754,0.6,0.5035294117647059,0.06848,0.6129032258064516,0.1205633802816901,0.5528587939356857,642.0,633.0,114.0,False
+Domain_Ig-like V-type,156,0.15,0.4210526315789473,0.0075542965061378,0.8,0.0148423005565862,0.5517241379310345,8.0,11.0,8.0,False
+Zinc finger_RING-type,478,0.6,0.4285714285714285,0.0173410404624277,0.75,0.0333333333333333,0.5454545454545454,3.0,4.0,3.0,False
+Zinc finger_RING-type,1178,0.15,0.4285714285714285,0.0173410404624277,0.75,0.0333333333333333,0.5454545454545454,3.0,4.0,3.0,False
+Zinc finger_any,478,0.6,0.4285714285714285,0.0173410404624277,0.75,0.0333333333333333,0.5454545454545454,3.0,4.0,3.0,False
+Zinc finger_any,1178,0.15,0.4285714285714285,0.0173410404624277,0.75,0.0333333333333333,0.5454545454545454,3.0,4.0,3.0,False
+Domain_C-type lectin,161,0.15,0.4285714285714285,0.0066006600660066,0.75,0.0130010834236186,0.5454545454545454,6.0,8.0,6.0,False
+Domain_C-type lectin,1377,0.5,0.4285714285714285,0.0066006600660066,0.75,0.0130010834236186,0.5454545454545454,6.0,8.0,6.0,False
+Domain_C-type lectin,1587,0.6,0.4285714285714285,0.0066006600660066,0.75,0.0130010834236186,0.5454545454545454,6.0,8.0,6.0,False
+Domain_C-type lectin,713,0.5,1.0,0.0033003300330033,0.375,0.006578947368421,0.5454545454545454,3.0,0.0,3.0,False
+Domain_C-type lectin,1224,0.6,0.3888888888888889,0.0077007700770077,0.875,0.0151024811218985,0.5384615384615385,7.0,11.0,7.0,False
+Domain_C-type lectin,1944,0.0,0.3636363636363636,0.0088008800880088,1.0,0.0171858216970998,0.5333333333333333,8.0,14.0,8.0,False
+Domain_C-type lectin,2543,0.0,0.5714285714285714,0.0044004400440044,0.5,0.0087336244541484,0.5333333333333333,4.0,3.0,4.0,False
+Domain_Ig-like V-type,2187,0.5,0.3571428571428571,0.0094428706326723,1.0,0.0183992640294388,0.5263157894736842,10.0,18.0,10.0,False
+Region_Disordered,949,0.8,0.484090909090909,0.04544,0.5698924731182796,0.0830814236957581,0.5234992696329616,426.0,454.0,106.0,False
+Domain_C-type lectin,643,0.15,0.4,0.0066006600660066,0.75,0.0129870129870129,0.5217391304347827,6.0,9.0,6.0,False
+Domain_C-type lectin,1586,0.6,0.4,0.0066006600660066,0.75,0.0129870129870129,0.5217391304347827,6.0,9.0,6.0,False
+Domain_Ig-like V-type,896,0.5,0.36,0.0084985835694051,0.9,0.0166051660516605,0.5142857142857143,9.0,16.0,9.0,False

results/test_counts/heldout_top_pairings.csv

@@ -0,0 +1,50 @@
+,concept,feature,threshold_pct,precision,recall,recall_per_domain,f1,f1_per_domain,tp,fp,tp_per_domain,is_aa_level_concept
+143,Domain_C-type lectin,246,0.5,0.6666666666666666,0.0088008800880088,1.0,0.017372421281216,0.8,8.0,4.0,8.0,False
+172,Zinc finger_RING-type,270,0.6,0.75,0.0173410404624277,0.75,0.0338983050847457,0.75,3.0,1.0,3.0,False
+177,Zinc finger_any,270,0.6,0.75,0.0173410404624277,0.75,0.0338983050847457,0.75,3.0,1.0,3.0,False
+152,Region_Disordered,1885,0.15,0.580385288966725,0.7069866666666667,0.978494623655914,0.6374609281077181,0.7286050455900616,6628.0,4792.0,182.0,False
+108,Compositional bias_Acidic residues,790,0.8,0.8529411764705882,0.1269146608315098,0.6153846153846154,0.2209523809523809,0.7149460708782742,58.0,10.0,16.0,False
+122,Domain_Ig-like V-type,12,0.6,0.5625,0.0084985835694051,0.9,0.0167441860465116,0.6923076923076923,9.0,7.0,9.0,False
+195,Coiled coil,2442,0.15,0.5204081632653061,0.0729613733905579,0.7777777777777778,0.1279799247176913,0.6235807860262008,102.0,94.0,14.0,False
+135,Domain_EF-hand 2,670,0.15,0.3235294117647059,0.0238095238095238,0.8461538461538461,0.0443548387096774,0.4680851063829787,11.0,23.0,11.0,False
+184,Helix,41,0.0,0.3629548517520216,0.2302431204915843,0.6081223628691983,0.2817536862065584,0.4545899311382231,4309.0,7563.0,1153.0,False
+189,Beta strand,961,0.0,0.3810222036028488,0.2375293810394358,0.5381889763779527,0.2926319176319176,0.4461693987198283,3638.0,5910.0,1367.0,False
+75,Transit peptide_Mitochondrion,1935,0.15,0.3709677419354839,0.0558252427184466,0.5384615384615384,0.0970464135021097,0.4392905866302865,23.0,39.0,7.0,False
+80,Transit peptide_any,1935,0.15,0.3709677419354839,0.0558252427184466,0.5384615384615384,0.0970464135021097,0.4392905866302865,23.0,39.0,7.0,False
+150,Domain_EF-hand 3,670,0.8,0.2857142857142857,0.0210526315789473,0.75,0.0392156862745098,0.4137931034482759,6.0,15.0,6.0,False
+168,Region_Alpha-3,1922,0.8,0.238095238095238,0.0108695652173913,1.0,0.0207900207900207,0.3846153846153846,5.0,16.0,5.0,False
+128,Domain_Ig-like C1-type,1922,0.8,0.2857142857142857,0.0059940059940059,0.5454545454545454,0.0117416829745596,0.3749999999999999,6.0,15.0,6.0,False
+103,Compositional bias_Basic residues,754,0.8,0.2297872340425532,0.2,0.9444444444444444,0.2138613861386138,0.3696396215019126,54.0,181.0,17.0,False
+96,Compositional bias_Low complexity,1885,0.5,0.1888619854721549,0.3227586206896551,0.7906976744186046,0.2382892057026476,0.3048976776270407,234.0,1005.0,34.0,False
+3,Active site_Proton acceptor,8,0.6,0.5,0.2,0.2,0.2857142857142857,0.2857142857142857,3.0,3.0,0.0,True
+130,Domain_EF-hand 1,2188,0.15,0.1714285714285714,0.0124223602484472,0.4615384615384615,0.0231660231660231,0.25,6.0,29.0,6.0,False
+16,Glycosylation_N-linked (GlcNAc...) asparagine,1111,0.8,0.1331142152834839,0.782608695652174,0.782608695652174,0.2275280898876404,0.2275280898876404,162.0,1055.0,0.0,True
+26,Glycosylation_any,1111,0.8,0.1331142152834839,0.7534883720930232,0.7534883720930232,0.2262569832402234,0.2262569832402234,162.0,1055.0,0.0,True
+118,Compositional bias_Pro residues,2124,0.8,0.2857142857142857,0.0205128205128205,0.1818181818181818,0.0382775119617224,0.2222222222222222,4.0,10.0,2.0,False
+88,Compositional bias_Basic and acidic residues,2394,0.8,0.1739130434782608,0.0208023774145616,0.2894736842105263,0.0371599203715992,0.2172839506172839,28.0,133.0,22.0,False
+31,Modified residue_Phosphoserine,949,0.8,0.1397727272727272,0.2808219178082192,0.2808219178082192,0.1866464339908952,0.1866464339908952,123.0,757.0,0.0,True
+157,Region_Connecting peptide,357,0.15,0.125,0.0163934426229508,0.2,0.0289855072463768,0.1538461538461538,2.0,14.0,2.0,False
+93,Compositional bias_Polar residues,2008,0.8,0.1232876712328767,0.0143540669856459,0.1904761904761904,0.0257142857142857,0.1496881496881497,9.0,64.0,8.0,False
+111,Compositional bias_Gly residues,1885,0.5,0.0686037126715092,0.5704697986577181,1.0,0.1224783861671469,0.1283987915407854,85.0,1154.0,9.0,False
+162,Region_Alpha-2,2474,0.8,0.0833333333333333,0.0026990553306342,0.25,0.0052287581699346,0.125,2.0,22.0,2.0,False
+60,Modified residue_N-acetylmethionine,1304,0.15,0.0663716814159292,1.0,1.0,0.1244813278008298,0.1244813278008298,30.0,422.0,0.0,True
+163,Region_Alpha-1,1252,0.0,0.08,0.0027624309392265,0.25,0.0053404539385847,0.1212121212121212,2.0,23.0,2.0,False
+8,Active site_any,636,0.0,0.375,0.0652173913043478,0.0652173913043478,0.111111111111111,0.111111111111111,3.0,5.0,0.0,True
+68,Modified residue_N-acetylserine,1776,0.15,0.1,0.1176470588235294,0.1176470588235294,0.1081081081081081,0.1081081081081081,2.0,18.0,0.0,True
+139,Domain_Ig-like C2-type,537,0.0,0.0588235294117647,0.005736137667304,0.5,0.0104529616724738,0.1052631578947368,3.0,48.0,3.0,False
+43,Modified residue_Phosphotyrosine,541,0.15,0.086021505376344,0.1269841269841269,0.1269841269841269,0.1025641025641025,0.1025641025641025,8.0,85.0,0.0,True
+199,Lipidation,2050,0.0,0.0806451612903225,0.0925925925925925,0.0909090909090909,0.0862068965517241,0.0854700854700854,5.0,57.0,5.0,False
+52,Modified residue_N6-lactoyllysine,754,0.8,0.0468085106382978,0.2291666666666666,0.2291666666666666,0.07773851590106,0.07773851590106,11.0,224.0,0.0,True
+55,Modified residue_N-acetylalanine,847,0.5,0.0379241516966067,0.59375,0.59375,0.0712945590994371,0.0712945590994371,19.0,482.0,0.0,True
+35,Modified residue_N6-acetyllysine,827,0.6,0.0331922099915326,0.9289099526066352,0.9289099526066352,0.0640941792020928,0.0640941792020928,196.0,5709.0,0.0,True
+180,Turn,1410,0.15,0.0480887792848335,0.021081081081081,0.0636704119850187,0.0293122886133032,0.054793388429752,39.0,772.0,34.0,False
+39,Modified residue_Phosphothreonine,1251,0.5,0.0221005280657148,0.9416666666666668,0.9416666666666668,0.0431874641696923,0.0431874641696923,113.0,5000.0,0.0,True
+69,Modified residue_Cysteine methyl ester,2484,0.0,0.0158730158730158,0.1428571428571428,0.1428571428571428,0.0285714285714285,0.0285714285714285,1.0,62.0,0.0,True
+21,Glycosylation_O-linked (GalNAc...) threonine,2008,0.8,0.0136986301369863,0.2,0.2,0.0256410256410256,0.0256410256410256,1.0,72.0,0.0,True
+58,Modified residue_N6-crotonyllysine,2480,0.15,0.0108695652173913,0.054054054054054,0.054054054054054,0.0180995475113122,0.0180995475113122,2.0,182.0,0.0,True
+47,Modified residue_N6-(2-hydroxyisobutyryl)lysine,2480,0.15,0.0108695652173913,0.0384615384615384,0.0384615384615384,0.0169491525423728,0.0169491525423728,2.0,182.0,0.0,True
+66,Modified residue_N6-butyryllysine,2480,0.15,0.0054347826086956,0.0454545454545454,0.0454545454545454,0.0097087378640776,0.0097087378640776,1.0,183.0,0.0,True
+64,Modified residue_N6-(beta-hydroxybutyryl)lysine,2480,0.15,0.0054347826086956,0.037037037037037,0.037037037037037,0.0094786729857819,0.0094786729857819,1.0,183.0,0.0,True
+73,Modified residue_Symmetric dimethylarginine,754,0.6,0.0039215686274509,0.5,0.5,0.0077821011673151,0.0077821011673151,5.0,1270.0,0.0,True
+45,Modified residue_N6-succinyllysine,1255,0.15,0.0014492753623188,0.0153846153846153,0.0153846153846153,0.0026490066225165,0.0026490066225165,1.0,689.0,0.0,True
+7,Active site_Charge relay system,325,0.5,0.0006872852233676,0.1111111111111111,0.1111111111111111,0.0013661202185792,0.0013661202185792,1.0,1454.0,0.0,True

results/test_counts/shard_4_counts.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60fb48a6164dfc44985c096936c62e95ed81f0ab576321597a37d78b75d29b7
+size 943748

results/test_counts/shard_5_counts.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de70ca3f12f6a16d23575edd00fe3cc8fbf6d1443981d2a116173efe798d6659
+size 955302

results/test_counts/shard_6_counts.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce11913697c8b2a4209c70192ac089f1680d717814d505470173a8e8de92281a
+size 1001342

results/test_counts/shard_7_counts.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b23bcc9ea8d41768b6a7c8745e4ab48e218c572e7cab8dc9d51ed0994b5ceaa
+size 987815

results/valid_counts/concept_f1_scores.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e416ad9deb6eb93062df81a48b44eb1a1a283a9b6c44d548b578112c3b2ad8a
+size 21215215

results/valid_counts/shard_0_counts.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31bfe4dc118c6dbd4e668e5b451a7d10e92d307fad9dd69eadcac8f714bd6771
+size 867507

results/valid_counts/shard_1_counts.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3103eb2fcab2476631c59d15166a3273e5d29270614eb14f5b5001c80eeb8d9f
+size 953961

results/valid_counts/shard_2_counts.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30f8bc27dfda31eed26c1a2efde085cb967dab6db36afc2660719d878ee4ec9
+size 986375

results/valid_counts/shard_3_counts.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afee3166f1bc8fd9e3d3b1a4075acb3e8750b80a9e7eebd220ab2c983c73d9ff
+size 1043919