# 7th Place Solution: The "Blind" MLP, and LOO Augmentation

First, a massive thank you to
Myllia Biotechnology
and the Virtual Cell Research Community for organizing such an elegant and uniquely challenging competition. The novel evaluation metric and the strict one-submission-per-day limit made this an incredible test of disciplined, hypothesis-driven data science.
I’m excited to share my team's 7th Place solution (Public LB: 4.090 / Private LB: 3.3075).
🧬 Extremely Short Summary of Our Approach
Our core philosophy was that
data augmentation would outperform complex architecture
. We utilized a very simple
"Blind" LightMLP
(~2.5M params) that takes only a gene index as input, and powered it with two major augmentation pipelines:
3-Tier PseudoBulk:
Bootstrapping single-cell data to multiply our 80 ground-truth samples.
Leave-One-Out (LOO) Synthetic Perturbations (The Breakthrough):
Simulating knockouts genome-wide by finding control cells where specific genes are naturally low-expressed. This generated ~15,000 synthetic perturbation samples, teaching the model to generalize across all 5,127 genes.
External Data as Regularization:
We used Replogle K562 data
only
to add beneficial noise and prevent overfitting, rather than as input features.
🔬 An Interesting Divergence in Modeling Strategy
The grand vision of virtual cell models is to learn deep mechanistic rules to predict specific perturbation outcomes. However, a fascinating takeaway from our approach is how we navigated the competition's extreme low-data regime (80 training perturbations predicting 120 completely disjoint, unseen targets).
We found that in this highly constrained environment, models attempting to learn perturbation-specific rules severely overfit the training data. Ultimately, our winning strategy leaned into a different biological prior:
predicting a highly robust,
shared
transcriptomic response
based on the covariance structure of the training data.
Aside from manually correcting the delta of the knocked-out gene itself, our model predicts the exact same generalized cellular response for every perturbation. It highlights a profound lesson in computational biology: when perturbation data is sparse, a strong, generalized biological prior is currently the safest path to generalization.
🔗 Deep Dive & Source Code
Our final solution was the result of 24 carefully documented iterations. If you want to see the full evolutionary journey—including our experiments with external data, and a deep dive into an interesting inverse correlation we discovered between our CV and LB scores—please visit the repository!
Full Write-up & Source Code:
[https://github.com/DrGM87/Myllia-Challenge](https://github.com/DrGM87/Myllia-Challenge)
Thank you again to the organizers for providing such a phenomenal dataset and pushing the boundaries of what virtual cell models can achieve!