← Browse entries

Akt

D. melanogaster

Akt kinase

What the model saw

Gene: Akt
Organism: Drosophila melanogaster
Known functions: Akt kinase. ATP binding. protein binding. protein kinase activity. protein serine kinase activity. protein serine/threonine kinase activity.
View unredacted entry
Akt kinase. ATP binding. protein binding. protein kinase activity. protein serine kinase activity. protein serine/threonine kinase activity.

Solver output

Predicted influence
Anti-longevity
Confidence
88%
Mechanism
Deregulated nutrient sensing
Reasoning

Akt (also known as PKB) is the central serine/threonine kinase of the insulin/IGF-1 signaling (IIS) pathway. In Drosophila, Akt phosphorylates and inactivates FOXO (dFOXO), a transcription factor that promotes stress resistance, autophagy, and longevity-associated gene expression. Elevated IIS/Akt activity suppresses dFOXO nuclear localization, thereby reducing expression of protective genes and shortening lifespan. Conversely, reduced Akt activity or loss-of-function extends lifespan in flies, consistent with findings across multiple model organisms. Akt also phosphorylates and activates TOR complex signaling (via TSC1/2 inhibition), further amplifying nutrient-sensing pathways that are well-established drivers of aging when chronically active. Thus, the normal (wild-type) function of Akt opposes longevity by sustaining IIS-driven suppression of FOXO and activation of TORC1.

Key pathways
Insulin/IGF-1 signaling (IIS) → Akt → dFOXO suppressionAkt → TSC1/2 inhibition → TORC1 activationNutrient sensing / mTOR pathway
Longevity influence
Pro-longevity
Lifespan effect
Decrease

GenAge curators classify each gene's normal function as promoting (Pro-Longevity) or opposing (Anti-Longevity) longevity, based on synthesis across studies. Loss-of-function effects can vary from this depending on the manipulation.

Advisor judgment

The advisor flagged this ground-truth label as potentially questionable.
Answer
Incorrect
Mechanism
Incorrect
Reasoning quality
3/5
Failure mode
Confident wrong
Notes

The model predicted anti_longevity with high confidence (0.88), but the ground truth is pro_longevity. The model's reasoning is mechanistically coherent in describing how Akt suppresses FOXO and activates TORC1, which are indeed established aging-related pathways. However, the model conflated "reduced Akt activity extends lifespan" with "Akt is anti-longevity," which is the standard IIS narrative. In Drosophila, the GenAge classification of Akt as pro_longevity likely reflects that some level of Akt activity is required for normal survival/longevity, or that overexpression/activation studies in specific tissues (e.g., muscle or nervous system) can extend lifespan. The model's reasoning is one-sided and ignores the complexity that Akt can be pro-longevity in certain contexts in Drosophila. The model was confidently wrong about the direction of effect.

Raw API responses

solver

{
  "reasoning": "Akt (also known as PKB) is the central serine/threonine kinase of the insulin/IGF-1 signaling (IIS) pathway. In Drosophila, Akt phosphorylates and inactivates FOXO (dFOXO), a transcription factor that promotes stress resistance, autophagy, and longevity-associated gene expression. Elevated IIS/Akt activity suppresses dFOXO nuclear localization, thereby reducing expression of protective genes and shortening lifespan. Conversely, reduced Akt activity or loss-of-function extends lifespan in flies, consistent with findings across multiple model organisms. Akt also phosphorylates and activates TOR complex signaling (via TSC1/2 inhibition), further amplifying nutrient-sensing pathways that are well-established drivers of aging when chronically active. Thus, the normal (wild-type) function of Akt opposes longevity by sustaining IIS-driven suppression of FOXO and activation of TORC1.",
  "confidence": 0.88,
  "key_pathways": [
    "Insulin/IGF-1 signaling (IIS) → Akt → dFOXO suppression",
    "Akt → TSC1/2 inhibition → TORC1 activation",
    "Nutrient sensing / mTOR pathway"
  ],
  "mechanism_class": "deregulated_nutrient_sensing",
  "longevity_influence": "anti_longevity"
}

advisor

{
  "notes": "The model predicted anti_longevity with high confidence (0.88), but the ground truth is pro_longevity. The model's reasoning is mechanistically coherent in describing how Akt suppresses FOXO and activates TORC1, which are indeed established aging-related pathways. However, the model conflated \"reduced Akt activity extends lifespan\" with \"Akt is anti-longevity,\" which is the standard IIS narrative. In Drosophila, the GenAge classification of Akt as pro_longevity likely reflects that some level of Akt activity is required for normal survival/longevity, or that overexpression/activation studies in specific tissues (e.g., muscle or nervous system) can extend lifespan. The model's reasoning is one-sided and ignores the complexity that Akt can be pro-longevity in certain contexts in Drosophila. The model was confidently wrong about the direction of effect.",
  "failure_mode": "confident_wrong",
  "answer_correct": false,
  "mechanism_correct": false,
  "reasoning_quality": 3,
  "ground_truth_questionable": true
}