Reproducibility crisis in ML science: Only 7 of 32 PPI methods re-trainable
anshulkundaje · x · 2026-08-17
A survey of Protein-Protein Interaction (PPI) prediction methods highlights a severe reproducibility crisis in ML-based science:
- Low code availability: Only 12 out of 32 PPI prediction methods had source code available.
- High barrier to re-training: Among those, only 7 could be re-trained with reasonable effort.
- Benchmarking: The study compared these methods against 8 baseline ML models.
More from Research
- Transformer trained on flying bat recordings yields hippocampus 'digital twin' revealing hidden structure — patrickmineault · 2026-10-16
- One year of Recursive Language Models: GPT-5-mini beats GPT-5 by 110% on 132k-token tasks, cheaper too — a1zhang · 2026-10-16
- MIT PhD Sharut Gupta joins DeepMind; Isola hails her representational alignment defense talk — phillip_isola · 2026-10-16
- 36 primitives, just 10 parameters each: a remarkably precise T-pose body fit — letandrewcook · 2026-10-16
- Interp researcher pushes back: if you can't simulate a neuron, you haven't explained it — nabla_theta · 2026-10-16
- MLP-Splatting (ECCV 2026) code released: MLPs as light-field primitives instead of Gaussians — AjdDavison · 2026-10-16