PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction
Scarce data and tumor heterogeneity limit patient-level cancer treatment-response prediction. Existing approaches predict response from pretreatment molecular profiles and drug representations, without explicitly modeling the molecular changes expected under treatment. We propose PerturbRx, a treatment-conditioned representation learning framework that learns intervention-induced latent transitions and uses them as patient-drug response features. PerturbRx trains a drug- and dose-conditioned transition predictor from context-matched but cell-unpaired control and treated single-cell populations
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%AI in chemogenomics: Predicting drug-target interactions at scale - Drug Discovery News →
- PossiblePossibly related (embedding) · 49%Explainable machine learning to predict immunotherapy outcomes in metastatic renal cell carcinoma - Meet-URO 15-AI study - Nature →
- PossiblePossibly related (embedding) · 48%Machine learning for drug metabolism prediction: CYPs, Phase II enzymes, and metabolite ID - Drug Discovery News →
- PossiblePossibly related (embedding) · 48%Patient-Reported Outcomes, Machine Learning May Predict Breast Cancer Recurrence Earlier - Pharmacy Times →
- PossiblePossibly related (embedding) · 47%Artificial intelligence in oncology drug discovery: from target identification to therapeutic molecule generation - EurekAlert! →
- FuzzyOverlapping authors or contributors · 62%esengine/DeepSeek-Reasonix →
“Shared author/contributor keys: hero”
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “PerturbRx: Learning Treatment-Conditioned Latent Transitions” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Yoshitaka Inoue →
“PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction”