← Browse entries

hsp104

S. pombe

heat shock protein Hsp104

What the model saw

Gene: hsp104
Organism: Schizosaccharomyces pombe
Known functions: heat shock protein Hsp104. ATP binding. ATP hydrolysis activity. ATP-dependent protein disaggregase activity. misfolded protein binding. protein-folding chaperone binding. unfolded protein binding.
View unredacted entry
heat shock protein Hsp104. ATP binding. ATP hydrolysis activity. ATP-dependent protein disaggregase activity. misfolded protein binding. protein-folding chaperone binding. unfolded protein binding.

Solver output

Predicted influence
Pro-longevity
Confidence
85%
Mechanism
Loss of proteostasis
Reasoning

Hsp104 is an AAA+ ATPase disaggregase that uses ATP hydrolysis to solubilize and reactivate aggregated and misfolded proteins, directly maintaining proteostasis. By binding misfolded and unfolded proteins and cooperating with other chaperones (Hsp70/Hsp40), it clears toxic protein aggregates that accumulate with age. Loss of disaggregase activity leads to accumulation of amyloid-like aggregates and damaged proteins, a hallmark of cellular aging. In yeast, Hsp104 is well-established as a pro-longevity factor: it is required for asymmetric segregation of protein aggregates during cell division, ensuring that daughter cells receive fewer damaged proteins, and its activity directly counteracts the proteotoxic stress that drives aging. Its ATP-dependent protein disaggregation function is the primary molecular mechanism opposing age-related proteostasis collapse.

Key pathways
protein disaggregation and refoldingchaperone-mediated proteostasisasymmetric inheritance of protein aggregates
Longevity influence
Anti-longevity
Lifespan effect
Increase

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

Answer
Incorrect
Mechanism
Incorrect
Reasoning quality
3/5
Failure mode
Confident wrong
Notes

The model predicted pro_longevity with high confidence (0.85), but the ground truth is anti_longevity. The model's reasoning is based on well-known functions of Hsp104 in S. cerevisiae (budding yeast), where it is indeed a pro-longevity factor involved in asymmetric segregation of protein aggregates. However, in S. pombe (fission yeast), hsp104 appears to have an anti-longevity role. The model failed to account for organism-specific differences between S. cerevisiae and S. pombe. Fission yeast divides symmetrically (unlike budding yeast), so the asymmetric inheritance argument doesn't apply in the same way. The mechanistic reasoning, while coherent for S. cerevisiae, is incorrect for S. pombe. The model was confidently wrong and did not flag the organism-specific uncertainty.

Raw API responses

solver

{
  "reasoning": "Hsp104 is an AAA+ ATPase disaggregase that uses ATP hydrolysis to solubilize and reactivate aggregated and misfolded proteins, directly maintaining proteostasis. By binding misfolded and unfolded proteins and cooperating with other chaperones (Hsp70/Hsp40), it clears toxic protein aggregates that accumulate with age. Loss of disaggregase activity leads to accumulation of amyloid-like aggregates and damaged proteins, a hallmark of cellular aging. In yeast, Hsp104 is well-established as a pro-longevity factor: it is required for asymmetric segregation of protein aggregates during cell division, ensuring that daughter cells receive fewer damaged proteins, and its activity directly counteracts the proteotoxic stress that drives aging. Its ATP-dependent protein disaggregation function is the primary molecular mechanism opposing age-related proteostasis collapse.",
  "confidence": 0.85,
  "key_pathways": [
    "protein disaggregation and refolding",
    "chaperone-mediated proteostasis",
    "asymmetric inheritance of protein aggregates"
  ],
  "mechanism_class": "loss_of_proteostasis",
  "longevity_influence": "pro_longevity"
}

advisor

{
  "notes": "The model predicted pro_longevity with high confidence (0.85), but the ground truth is anti_longevity. The model's reasoning is based on well-known functions of Hsp104 in S. cerevisiae (budding yeast), where it is indeed a pro-longevity factor involved in asymmetric segregation of protein aggregates. However, in S. pombe (fission yeast), hsp104 appears to have an anti-longevity role. The model failed to account for organism-specific differences between S. cerevisiae and S. pombe. Fission yeast divides symmetrically (unlike budding yeast), so the asymmetric inheritance argument doesn't apply in the same way. The mechanistic reasoning, while coherent for S. cerevisiae, is incorrect for S. pombe. The model was confidently wrong and did not flag the organism-specific uncertainty.",
  "failure_mode": "confident_wrong",
  "answer_correct": false,
  "mechanism_correct": false,
  "reasoning_quality": 3,
  "ground_truth_questionable": false
}