← Back to all news
arXiv Machine Learning By Xudong Zhang, Jianzhe Li, Yitong Tang, Peijie Zhou

Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery

Read the original on arXiv Machine Learning →

The paper introduces Temporal Difference Active Learning (TDAL), a method that learns an acquisition function online for perturbation discovery by treating the problem as a sequential decision task. TDAL uses temporal difference learning with the Hellinger distance to weight future value and employs leave‑batch‑out to create virtual transitions, thereby addressing data scarcity. Evaluated on eight public screens involving single, double, and triple perturbations, TDAL outperforms eleven baseline methods, achieving an average rank of 1.63 and topping four tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
Sep 11

Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens

The paper introduces AssayBench-Loop, a large benchmark of 1,389 CRISPR screens across five phenotype categories, and builds on it to develop AssayLoop, a sequential experimental design framework that combines a transformer-based acquisition policy (AssayFormer) trained on historical data with LLM-derived biological priors. AssayLoop achieves a 5.67‑fold enrichment over random selection, recovering 27.7% of hits after testing only about 5% of the library, and outperforms existing adaptive-design methods and standalone LLMs. The authors also present AssayLLM, extending the approach directly to an LLM via task‑specific post‑training, and show that performance improves with more historical training data and transfers to unseen phenotype categories.

By Carl Edwards, Edward De Brouwer, Xiner Li, Namkyeong Lee, Ehsan Hajiramezanali, Anne Biton, Sara Mostafavi, Gabriele Scalia
llmsbenchmarks
More like this →
arXiv Machine Learning
Aug 24

PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction

PerturbRx is a treatment‑conditioned representation learning framework that learns latent transitions induced by drug interventions. It trains a drug‑ and dose‑conditioned transition predictor using control and treated single‑cell populations, then applies this predictor to pretreatment patient profiles to generate response features without needing post‑treatment data. On TCGA and patient‑derived xenograft benchmarks, PerturbRx outperforms other methods, demonstrating the value of perturbation‑pretrained latent transitions for patient‑level drug‑response prediction.

By Yoshitaka Inoue, Minoh Jeong, Alfred Hero, Rui Kuang, Augustin Luna
benchmarks
More like this →