Validation

Control set

Proteins whose function is already well known. We run them through the same model as the dark proteins and compare its answer with established biology. This set will grow into a benchmark of 50–100 known proteins.

5control proteins
79correct items
11missed
12speculative
77%of 102 items correct

Correct matches known biology · Missed known function not mentioned · Speculative predicted without established evidence

ADRB2 Beta-2 adrenergic receptor

P07550

26 correct · 2 missed · 8 speculativeProtein page →
72%correct26 correct · 2 missed · 8 speculative
Molecular function
61
7 items
Biological process
1418
23 items
Cellular component
6
6 items
CorrectMissedSpeculative

Known biology

  • protein-containing complex binding · GO:0044877Correct
  • amyloid-beta binding · GO:0001540Correct
  • potassium channel regulator activity · GO:0015459Correct
  • protein homodimerization activity · GO:0042803Correct
  • amyloid-beta binding · GO:0001540Correct
  • beta2-adrenergic receptor activity · GO:0004941Correct
  • response to psychosocial stress · GO:1990911Correct
  • cell surface receptor signaling pathway · GO:0007166Correct
  • adrenergic receptor signaling pathway · GO:0071875Correct
  • negative regulation of G protein-coupled receptor signaling pathway · GO:0045744Correct
  • positive regulation of autophagosome maturation · GO:1901098Correct
  • adenylate cyclase-modulating G protein-coupled receptor signaling pathway · GO:0007188Correct
  • positive regulation of autophagosome maturation · GO:1901098Correct
  • endosome to lysosome transport · GO:0008333Correct
  • cell surface receptor signaling pathway · GO:0007166Correct
  • positive regulation of MAPK cascade · GO:0043410Correct
  • positive regulation of autophagosome maturation · GO:1901098Correct
  • negative regulation of G protein-coupled receptor signaling pathway · GO:0045744Correct
  • cellular response to amyloid-beta · GO:1904646Correct
  • receptor-mediated endocytosis · GO:0006898Correct
  • signaling receptor complex · GO:0043235Correct
  • Golgi apparatus · GO:0005794Correct
  • plasma membrane · GO:0005886Correct
  • endosome membrane · GO:0010008Correct
  • lysosome · GO:0005764Correct
  • clathrin-coated endocytic vesicle membrane · GO:0030669Correct
  • norepinephrine binding · GO:0051380Missed
  • positive regulation of glutamate receptor signaling pathway · GO:1900451Missed

Source: UniProt P07550, GO annotations (all evidence for "correct"; experimental evidence for "missed", max 2 per aspect shown)

AI prediction

  • GO:0044877 protein-containing complex bindingCorrect
  • GO:0042277 peptide bindingCorrect
  • GO:0015459 potassium channel regulator activityCorrect
  • GO:0042803 protein homodimerization activityCorrect
  • GO:0001540 amyloid-beta bindingCorrect
  • GO:0004935 adrenergic receptor activityCorrect
  • GO:0006950 response to stressCorrect
  • GO:0007166 cell surface receptor signaling pathwayCorrect
  • GO:0071875 adrenergic receptor signaling pathwayCorrect
  • GO:0045744 negative regulation of G protein-coupled receptor signaling pathwayCorrect
  • GO:0010508 positive regulation of autophagyCorrect
  • GO:0007188 adenylate cyclase-modulating G protein-coupled receptor signaling pathwayCorrect
  • GO:2000273 positive regulation of signaling receptor activitySpeculative
  • GO:0043243 positive regulation of protein-containing complex disassemblyCorrect
  • GO:0065003 protein-containing complex assemblySpeculative
  • GO:0010738 regulation of protein kinase A signalingSpeculative
  • GO:0008333 endosome to lysosome transportCorrect
  • GO:0007169 transmembrane receptor protein tyrosine kinase signaling pathwayCorrect
  • GO:0043410 positive regulation of MAPK cascadeCorrect
  • GO:2000311 regulation of AMPA receptor activitySpeculative
  • GO:1901098 positive regulation of autophagosome maturationCorrect
  • GO:0002029 desensitization of G protein-coupled receptor signaling pathwayCorrect
  • GO:0032091 negative regulation of protein bindingSpeculative
  • GO:1904646 cellular response to amyloid-betaCorrect
  • GO:0006898 receptor-mediated endocytosisCorrect
  • GO:0007190 activation of adenylate cyclase activitySpeculative
  • GO:1901653 cellular response to peptideSpeculative
  • GO:2000479 regulation of cAMP-dependent protein kinase activitySpeculative
  • GO:0043235 receptor complexCorrect
  • GO:0005794 Golgi apparatusCorrect
  • GO:0005886 plasma membraneCorrect
  • GO:0010008 endosome membraneCorrect
  • GO:0005764 lysosomeCorrect
  • GO:0030669 clathrin-coated endocytic vesicle membraneCorrect

BioReason-Pro

Item by item

AspectKnown biologyAI predictionVerdict
Molecular functionprotein-containing complex binding · GO:0044877GO:0044877 protein-containing complex bindingCorrect
Molecular functionamyloid-beta binding · GO:0001540GO:0042277 peptide bindingCorrect
Molecular functionpotassium channel regulator activity · GO:0015459GO:0015459 potassium channel regulator activityCorrect
Molecular functionprotein homodimerization activity · GO:0042803GO:0042803 protein homodimerization activityCorrect
Molecular functionamyloid-beta binding · GO:0001540GO:0001540 amyloid-beta bindingCorrect
Molecular functionbeta2-adrenergic receptor activity · GO:0004941GO:0004935 adrenergic receptor activityCorrect
Biological processresponse to psychosocial stress · GO:1990911GO:0006950 response to stressCorrect
Biological processcell surface receptor signaling pathway · GO:0007166GO:0007166 cell surface receptor signaling pathwayCorrect
Biological processadrenergic receptor signaling pathway · GO:0071875GO:0071875 adrenergic receptor signaling pathwayCorrect
Biological processnegative regulation of G protein-coupled receptor signaling pathway · GO:0045744GO:0045744 negative regulation of G protein-coupled receptor signaling pathwayCorrect
Biological processpositive regulation of autophagosome maturation · GO:1901098GO:0010508 positive regulation of autophagyCorrect
Biological processadenylate cyclase-modulating G protein-coupled receptor signaling pathway · GO:0007188GO:0007188 adenylate cyclase-modulating G protein-coupled receptor signaling pathwayCorrect
Biological processNo annotation in UniProtGO:2000273 positive regulation of signaling receptor activitySpeculative
Biological processpositive regulation of autophagosome maturation · GO:1901098GO:0043243 positive regulation of protein-containing complex disassemblyCorrect
Biological processNo annotation in UniProtGO:0065003 protein-containing complex assemblySpeculative
Biological processNo annotation in UniProtGO:0010738 regulation of protein kinase A signalingSpeculative
Biological processendosome to lysosome transport · GO:0008333GO:0008333 endosome to lysosome transportCorrect
Biological processcell surface receptor signaling pathway · GO:0007166GO:0007169 transmembrane receptor protein tyrosine kinase signaling pathwayCorrect
Biological processpositive regulation of MAPK cascade · GO:0043410GO:0043410 positive regulation of MAPK cascadeCorrect
Biological processNo annotation in UniProtGO:2000311 regulation of AMPA receptor activitySpeculative
Biological processpositive regulation of autophagosome maturation · GO:1901098GO:1901098 positive regulation of autophagosome maturationCorrect
Biological processnegative regulation of G protein-coupled receptor signaling pathway · GO:0045744GO:0002029 desensitization of G protein-coupled receptor signaling pathwayCorrect
Biological processNo annotation in UniProtGO:0032091 negative regulation of protein bindingSpeculative
Biological processcellular response to amyloid-beta · GO:1904646GO:1904646 cellular response to amyloid-betaCorrect
Biological processreceptor-mediated endocytosis · GO:0006898GO:0006898 receptor-mediated endocytosisCorrect
Biological processNo annotation in UniProtGO:0007190 activation of adenylate cyclase activitySpeculative
Biological processNo annotation in UniProtGO:1901653 cellular response to peptideSpeculative
Biological processNo annotation in UniProtGO:2000479 regulation of cAMP-dependent protein kinase activitySpeculative
Cellular componentsignaling receptor complex · GO:0043235GO:0043235 receptor complexCorrect
Cellular componentGolgi apparatus · GO:0005794GO:0005794 Golgi apparatusCorrect
Cellular componentplasma membrane · GO:0005886GO:0005886 plasma membraneCorrect
Cellular componentendosome membrane · GO:0010008GO:0010008 endosome membraneCorrect
Cellular componentlysosome · GO:0005764GO:0005764 lysosomeCorrect
Cellular componentclathrin-coated endocytic vesicle membrane · GO:0030669GO:0030669 clathrin-coated endocytic vesicle membraneCorrect
Molecular functionnorepinephrine binding · GO:0051380—Missed
Biological processpositive regulation of glutamate receptor signaling pathway · GO:1900451—Missed

CA2 Carbonic anhydrase 2

P00918

8 correct · 2 missed · 2 speculativeProtein page →
67%correct8 correct · 2 missed · 2 speculative
Molecular function
3
3 items
Biological process
122
5 items
Cellular component
4
4 items
CorrectMissedSpeculative

Known biology

  • Carbonate dehydratase (CO2 hydration) · GO:0004089Correct
  • Zinc ion binding (catalytic zinc) · GO:0008270Correct
  • Esterase activity (secondary)Correct
  • Bicarbonate transport coupling (transport metabolon)Correct
  • Cytosol · GO:0005829Correct
  • Cell membrane · GO:0005886Correct
  • Apical part of cell · GO:0045177Correct
  • Extracellular exosome · GO:0070062Correct
  • Bone resorption / osteoclast differentiation (CA2 loss causes osteopetrosis)Missed
  • pH and bicarbonate handling in kidney and eye (renal tubular acidosis, aqueous humour secretion)Missed

Source: UniProt P00918 (CAH2_HUMAN), curated GO annotation

AI prediction

  • GO:0004089 carbonate dehydratase activityCorrect
  • GO:0008270 zinc ion bindingCorrect
  • GO:0052689 carboxylic ester hydrolase activityCorrect
  • GO:0044070 regulation of monoatomic anion transportCorrect
  • GO:0005829 cytosolCorrect
  • GO:0005886 plasma membraneCorrect
  • GO:0045177 apical part of cellCorrect
  • GO:0070062 extracellular exosomeCorrect
  • GO:0007186 G protein-coupled receptor signaling pathwaySpeculative
  • GO:1904385 cellular response to angiotensinSpeculative

BioReason-Pro

Item by item

AspectKnown biologyAI predictionVerdict
Molecular functionCarbonate dehydratase (CO2 hydration) · GO:0004089GO:0004089 carbonate dehydratase activityCorrect
Molecular functionZinc ion binding (catalytic zinc) · GO:0008270GO:0008270 zinc ion bindingCorrect
Molecular functionEsterase activity (secondary)GO:0052689 carboxylic ester hydrolase activityCorrect
Biological processBicarbonate transport coupling (transport metabolon)GO:0044070 regulation of monoatomic anion transportCorrect
Cellular componentCytosol · GO:0005829GO:0005829 cytosolCorrect
Cellular componentCell membrane · GO:0005886GO:0005886 plasma membraneCorrect
Cellular componentApical part of cell · GO:0045177GO:0045177 apical part of cellCorrect
Cellular componentExtracellular exosome · GO:0070062GO:0070062 extracellular exosomeCorrect
Biological processBone resorption / osteoclast differentiation (CA2 loss causes osteopetrosis)—Missed
Biological processpH and bicarbonate handling in kidney and eye (renal tubular acidosis, aqueous humour secretion)—Missed
Biological processNo established roleGO:0007186 G protein-coupled receptor signaling pathwaySpeculative
Biological processNo established roleGO:1904385 cellular response to angiotensinSpeculative

LDHA L-lactate dehydrogenase A chain

P00338

11 correct · 0 missed · 0 speculativeProtein page →
100%correct11 correct · 0 missed · 0 speculative
Molecular function
3
3 items
Biological process
3
3 items
Cellular component
5
5 items
CorrectMissedSpeculative

Known biology

  • L-lactate dehydrogenase (NAD+) activity · GO:0004459Correct
  • identical protein binding · GO:0042802Correct
  • cadherin binding · GO:0045296Correct
  • lactate metabolic process · GO:0006089Correct
  • glycolytic process · GO:0006096Correct
  • substantia nigra development · GO:0021762Correct
  • cytosol · GO:0005829Correct
  • membrane · GO:0016020Correct
  • extracellular exosome · GO:0070062Correct
  • oxidoreductase complex · GO:1990204Correct
  • nucleus · GO:0005634Correct

Source: UniProt P00338, GO annotations (all evidence for "correct"; experimental evidence for "missed", max 2 per aspect shown)

AI prediction

  • GO:0004457 lactate dehydrogenase activityCorrect
  • GO:0042802 identical protein bindingCorrect
  • GO:0045296 cadherin bindingCorrect
  • GO:0006089 lactate metabolic processCorrect
  • GO:0006090 pyruvate metabolic processCorrect
  • GO:0021762 substantia nigra developmentCorrect
  • GO:0005829 cytosolCorrect
  • GO:0016020 membraneCorrect
  • GO:0070062 extracellular exosomeCorrect
  • GO:1990204 oxidoreductase complexCorrect
  • GO:0005634 nucleusCorrect

BioReason-Pro

Item by item

AspectKnown biologyAI predictionVerdict
Molecular functionL-lactate dehydrogenase (NAD+) activity · GO:0004459GO:0004457 lactate dehydrogenase activityCorrect
Molecular functionidentical protein binding · GO:0042802GO:0042802 identical protein bindingCorrect
Molecular functioncadherin binding · GO:0045296GO:0045296 cadherin bindingCorrect
Biological processlactate metabolic process · GO:0006089GO:0006089 lactate metabolic processCorrect
Biological processglycolytic process · GO:0006096GO:0006090 pyruvate metabolic processCorrect
Biological processsubstantia nigra development · GO:0021762GO:0021762 substantia nigra developmentCorrect
Cellular componentcytosol · GO:0005829GO:0005829 cytosolCorrect
Cellular componentmembrane · GO:0016020GO:0016020 membraneCorrect
Cellular componentextracellular exosome · GO:0070062GO:0070062 extracellular exosomeCorrect
Cellular componentoxidoreductase complex · GO:1990204GO:1990204 oxidoreductase complexCorrect
Cellular componentnucleus · GO:0005634GO:0005634 nucleusCorrect

SLC2A1 Solute carrier family 2, facilitated glucose transporter member 1 (GLUT1)

P11166

22 correct · 4 missed · 2 speculativeProtein page →
79%correct22 correct · 4 missed · 2 speculative
Molecular function
52
7 items
Biological process
92
11 items
Cellular component
82
10 items
CorrectMissedSpeculative

Known biology

  • dehydroascorbic acid transmembrane transporter activity · GO:0033300Correct
  • long-chain fatty acid transmembrane transporter activity · GO:0005324Correct
  • identical protein binding · GO:0042802Correct
  • D-glucose transmembrane transporter activity · GO:0055056Correct
  • D-glucose transmembrane transporter activity · GO:0055056Correct
  • L-ascorbic acid metabolic process · GO:0019852Correct
  • L-ascorbic acid metabolic process · GO:0019852Correct
  • D-glucose transmembrane transporter activity · GO:0055056Correct
  • D-glucose import across plasma membrane · GO:0098708Correct
  • central nervous system development · GO:0007417Correct
  • L-ascorbic acid metabolic process · GO:0019852Correct
  • transport across blood-brain barrier · GO:0150104Correct
  • long-chain fatty acid import across plasma membrane · GO:0015911Correct
  • D-glucose transmembrane transport · GO:1904659Correct
  • blood microparticle · GO:0072562Correct
  • midbody · GO:0030496Correct
  • apical plasma membrane · GO:0016324Correct
  • apical plasma membrane · GO:0016324Correct
  • extracellular exosome · GO:0070062Correct
  • basolateral plasma membrane · GO:0016323Correct
  • Golgi membrane · GO:0000139Correct
  • cortical actin cytoskeleton · GO:0030864Correct
  • glucose transporter complex · GO:1990350Missed
  • melanosome · GO:0042470Missed
  • photoreceptor cell maintenance · GO:0045494Missed
  • protein-containing complex assembly · GO:0065003Missed

Source: UniProt P11166, GO annotations (all evidence for "correct"; experimental evidence for "missed", max 2 per aspect shown)

AI prediction

  • GO:0090482 vitamin transmembrane transporter activityCorrect
  • GO:0005324 long-chain fatty acid transporter activityCorrect
  • GO:0042802 identical protein bindingCorrect
  • GO:0043621 protein self-associationSpeculative
  • GO:0015149 hexose transmembrane transporter activityCorrect
  • GO:0005355 glucose transmembrane transporter activitySpeculative
  • GO:0055056 D-glucose transmembrane transporter activityCorrect
  • GO:0005996 monosaccharide metabolic processCorrect
  • GO:0005975 carbohydrate metabolic processCorrect
  • GO:0034219 carbohydrate transmembrane transportCorrect
  • GO:0098704 carbohydrate import across plasma membraneCorrect
  • GO:0007417 central nervous system developmentCorrect
  • GO:0019852 L-ascorbic acid metabolic processCorrect
  • GO:0150104 transport across blood-brain barrierCorrect
  • GO:0044539 long-chain fatty acid import into cellCorrect
  • GO:1904659 glucose transmembrane transportCorrect
  • GO:0072562 blood microparticleCorrect
  • GO:0030496 midbodyCorrect
  • GO:0045177 apical part of cellCorrect
  • GO:0016324 apical plasma membraneCorrect
  • GO:0070062 extracellular exosomeCorrect
  • GO:0016323 basolateral plasma membraneCorrect
  • GO:0000139 Golgi membraneCorrect
  • GO:0030864 cortical actin cytoskeletonCorrect

BioReason-Pro

Item by item

AspectKnown biologyAI predictionVerdict
Molecular functiondehydroascorbic acid transmembrane transporter activity · GO:0033300GO:0090482 vitamin transmembrane transporter activityCorrect
Molecular functionlong-chain fatty acid transmembrane transporter activity · GO:0005324GO:0005324 long-chain fatty acid transporter activityCorrect
Molecular functionidentical protein binding · GO:0042802GO:0042802 identical protein bindingCorrect
Molecular functionNo annotation in UniProtGO:0043621 protein self-associationSpeculative
Molecular functionD-glucose transmembrane transporter activity · GO:0055056GO:0015149 hexose transmembrane transporter activityCorrect
Molecular functionNo annotation in UniProtGO:0005355 glucose transmembrane transporter activitySpeculative
Molecular functionD-glucose transmembrane transporter activity · GO:0055056GO:0055056 D-glucose transmembrane transporter activityCorrect
Biological processL-ascorbic acid metabolic process · GO:0019852GO:0005996 monosaccharide metabolic processCorrect
Biological processL-ascorbic acid metabolic process · GO:0019852GO:0005975 carbohydrate metabolic processCorrect
Biological processD-glucose transmembrane transporter activity · GO:0055056GO:0034219 carbohydrate transmembrane transportCorrect
Biological processD-glucose import across plasma membrane · GO:0098708GO:0098704 carbohydrate import across plasma membraneCorrect
Biological processcentral nervous system development · GO:0007417GO:0007417 central nervous system developmentCorrect
Biological processL-ascorbic acid metabolic process · GO:0019852GO:0019852 L-ascorbic acid metabolic processCorrect
Biological processtransport across blood-brain barrier · GO:0150104GO:0150104 transport across blood-brain barrierCorrect
Biological processlong-chain fatty acid import across plasma membrane · GO:0015911GO:0044539 long-chain fatty acid import into cellCorrect
Biological processD-glucose transmembrane transport · GO:1904659GO:1904659 glucose transmembrane transportCorrect
Cellular componentblood microparticle · GO:0072562GO:0072562 blood microparticleCorrect
Cellular componentmidbody · GO:0030496GO:0030496 midbodyCorrect
Cellular componentapical plasma membrane · GO:0016324GO:0045177 apical part of cellCorrect
Cellular componentapical plasma membrane · GO:0016324GO:0016324 apical plasma membraneCorrect
Cellular componentextracellular exosome · GO:0070062GO:0070062 extracellular exosomeCorrect
Cellular componentbasolateral plasma membrane · GO:0016323GO:0016323 basolateral plasma membraneCorrect
Cellular componentGolgi membrane · GO:0000139GO:0000139 Golgi membraneCorrect
Cellular componentcortical actin cytoskeleton · GO:0030864GO:0030864 cortical actin cytoskeletonCorrect
Cellular componentglucose transporter complex · GO:1990350—Missed
Cellular componentmelanosome · GO:0042470—Missed
Biological processphotoreceptor cell maintenance · GO:0045494—Missed
Biological processprotein-containing complex assembly · GO:0065003—Missed

VIM Vimentin

P08670

12 correct · 3 missed · 0 speculativeProtein page →
80%correct12 correct · 3 missed · 0 speculative
Molecular function
61
7 items
Biological process
5
5 items
Cellular component
12
3 items
CorrectMissedSpeculative

Known biology

  • molecular adaptor activity · GO:0060090Correct
  • structural constituent of cytoskeleton · GO:0005200Correct
  • identical protein binding · GO:0042802Correct
  • scaffold protein binding · GO:0097110Correct
  • protein domain specific binding · GO:0019904Correct
  • double-stranded RNA binding · GO:0003725Correct
  • positive regulation of collagen biosynthetic process · GO:0032967Correct
  • regulation of mRNA stability · GO:0043488Correct
  • cellular response to lipopolysaccharide · GO:0071222Correct
  • positive regulation of gene expression · GO:0010628Correct
  • cellular response to muramyl dipeptide · GO:0071225Correct
  • intermediate filament cytoskeleton · GO:0045111Correct
  • cytosol · GO:0005829Missed
  • extracellular exosome · GO:0070062Missed
  • keratin filament binding · GO:1990254Missed

Source: UniProt P08670, GO annotations (all evidence for "correct"; experimental evidence for "missed", max 2 per aspect shown)

AI prediction

  • GO:0060090 molecular adaptor activityCorrect
  • GO:0005200 structural constituent of cytoskeletonCorrect
  • GO:0042802 identical protein bindingCorrect
  • GO:0097110 scaffold protein bindingCorrect
  • GO:0019904 protein domain specific bindingCorrect
  • GO:0003725 double-stranded RNA bindingCorrect
  • GO:0032967 positive regulation of collagen biosynthetic processCorrect
  • GO:0043488 regulation of mRNA stabilityCorrect
  • GO:0071222 cellular response to lipopolysaccharideCorrect
  • GO:0045727 positive regulation of translationCorrect
  • GO:0032495 response to muramyl dipeptideCorrect
  • GO:0045111 intermediate filament cytoskeletonCorrect

BioReason-Pro

Item by item

AspectKnown biologyAI predictionVerdict
Molecular functionmolecular adaptor activity · GO:0060090GO:0060090 molecular adaptor activityCorrect
Molecular functionstructural constituent of cytoskeleton · GO:0005200GO:0005200 structural constituent of cytoskeletonCorrect
Molecular functionidentical protein binding · GO:0042802GO:0042802 identical protein bindingCorrect
Molecular functionscaffold protein binding · GO:0097110GO:0097110 scaffold protein bindingCorrect
Molecular functionprotein domain specific binding · GO:0019904GO:0019904 protein domain specific bindingCorrect
Molecular functiondouble-stranded RNA binding · GO:0003725GO:0003725 double-stranded RNA bindingCorrect
Biological processpositive regulation of collagen biosynthetic process · GO:0032967GO:0032967 positive regulation of collagen biosynthetic processCorrect
Biological processregulation of mRNA stability · GO:0043488GO:0043488 regulation of mRNA stabilityCorrect
Biological processcellular response to lipopolysaccharide · GO:0071222GO:0071222 cellular response to lipopolysaccharideCorrect
Biological processpositive regulation of gene expression · GO:0010628GO:0045727 positive regulation of translationCorrect
Biological processcellular response to muramyl dipeptide · GO:0071225GO:0032495 response to muramyl dipeptideCorrect
Cellular componentintermediate filament cytoskeleton · GO:0045111GO:0045111 intermediate filament cytoskeletonCorrect
Cellular componentcytosol · GO:0005829—Missed
Cellular componentextracellular exosome · GO:0070062—Missed
Molecular functionkeratin filament binding · GO:1990254—Missed