← Back to all news
arXiv Machine Learning

Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation

The paper introduces PT‑RAG, a retrieval‑augmented generation framework that enhances cellular perturbation response prediction by incorporating context from related perturbations. PT‑RAG uses a two‑stage retrieval process—semantic retrieval to shortlist candidate perturbations followed by a differentiable Gumbel‑Softmax selector that adapts the selection based on cell state and query perturbation. Experiments on two backbones, a frozen STATE‑style generator and a fully trained scGPT, show that PT‑RAG improves distributional similarity and predictive quality, achieving a 5.9% reduction in 2‑Wasserstein distance on cross‑cell‑type tasks.

Related stories

arXiv Machine Learning
Oct 9

Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation

The paper introduces PT‑RAG, a retrieval‑augmented generation framework that enhances deep learning models for predicting cellular transcriptional responses to gene perturbations. PT‑RAG adds a two‑stage retrieval module—semantic retrieval followed by a Gumbel‑Softmax selector—to supply contextually relevant perturbation information, improving predictive accuracy across cell types and perturbations. Experiments on STATE‑style and scGPT backbones show consistent gains, such as a 5.9% reduction in 2‑Wasserstein distance for cross‑cell‑type predictions.

By Andrea Giuseppe Di Francesco, Andrea Rubbi, Rishabh Jain, Pietro Li\`o
rag
More like this →
arXiv AI
Oct 1

CellMSA: Context Modeling for Single-Cell Representation Learning

CellMSA introduces a novel single‑cell representation learning framework that leverages a multiple‑sequence‑alignment‑inspired context model. For each target cell, it retrieves relevant cells across batches and related cell types, summarizing cross‑cell patterns into a context‑dependent gene‑pair representation that is fed into a pair‑aware encoder. Pretraining on a massive human single‑cell corpus (≈109 million cells) and subsequent benchmarks demonstrate consistent performance gains over existing methods.

By Suyuan Zhao, Minghao Liu, Yizhen Luo, Zaiqing Nie
efficiencybenchmarkssafety
More like this →
arXiv AI
Aug 18

PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data

arXiv:2608. 16419v1 Announce Type: cross Abstract: Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces.

By Zhenchao Tang, Xiaogang Xu, Tianxu Lv, Jiahui Guan, Jiale Zhou, Haohuai He, Zhi Song, Hanbo Huang, Jiehui Huang, Jiafei Wu, Zhe Liu
llmsreinforcement-learning
More like this →
arXiv AI
Oct 1

scTrilemma: Balancing Identity, Invariance, and Fidelity in Single-Cell Representation Learning

The paper introduces scTrilemma, a latent-bottleneck variational autoencoder designed to address the representation trilemma in single‑cell RNA‑seq data: preserving biological identity and state, remaining robust to nuisance context, and retaining gene‑level variation for expression analysis. scTrilemma routes expression‑derived variation to the embedding, decoder, or prior, gating gene tokens by expression and conditioning the prior on unlabeled pseudo‑bulk context, all under a single reconstruction objective without target annotations. In zero‑shot evaluations on successive CZ CELLxGENE Census releases, scTrilemma simultaneously satisfies all three demands, maintaining biological state, differential‑expression, and pathway structure across multiple disease settings, and latent interventions show context can be removed with minimal impact on other demands.

By Yunhak Oh, Yoonho Lee, Junseok Lee, Namkyeong Lee, Sang-Yeon Hwang, Yinhua Piao, Hyomin Kim, Seonghwan Kim, Jaechang Lim, Woo Youn Kim, Sungsoo Ahn, Chanyoung Park
rag
More like this →