LazyNet: Interpretable ODE Modeling of Sparse CRISPR Single-Cell Screens Reveals New Biological Insights
Open Access
Abstract
We present LazyNet, a compact one-step neural-ODE model for single-cell CRISPR activation/interference (A/I) that operates directly on two-snapshot (“pre → post”) measurements and yields parameters with clear mechanistic meaning. The core log–linear–exp residual block exactly represents multiplicative effects, so synergistic multi-locus responses appear as explicit components rather than opaque composites. On a 53k-cell × 18k-gene neuronal Perturb-seq matrix, a three-replica LazyNet ensemble trained under a matched 1 h budget achieved strong threshold-free ranking and competitive error (genome-wide r ≈ 0.67) while running on CPUs. For comparison, we instantiated transformer (scGPT-style) and state-space (RetNet/CellFM-style) architectures from random initialization and trained them from scratch on the same dataset and within the same 1 h cap on a GPU platform, without any large-scale pretraining or external data. Under these strictly controlled, low-data conditions, LazyNet matched or exceeded their predictive performance while using far fewer parameters and resources. A T-cell screen included only for generalization showed the same ranking advantage under the identical evaluation pipeline. Beyond prediction, LazyNet exposes directed, local elasticities; averaging Jacobians across replicas produces a consensus interaction matrix from which compact subgraphs are extracted and evaluated at the module level. The resulting networks show coherent enrichment against authoritative resources (large-scale co-expression and curated functional associations) and concordance with orthogonal GPX4-knockout proteomes, recovering known ferroptosis regulators and nominating testable links in a lysosomal–mitochondrial–immune module. These results position LazyNet as a practical option for from-scratch, low-data CRISPR A/I studies where large-scale pretraining of foundation models is not feasible.Keywords
All Related Versions
Funding Information
- Jiangsu Funding Program for Excellent Postdoctoral Talent (2024ZB546)
- Big Data Computing Center of Southeast University
- Scientific and Technological Innovation 2030 Major Projects (2021ZD0204001)
This publication has 48 references indexed in Scilit:
- How to build the virtual cell with artificial intelligence: Priorities and opportunitiesCell, 2024
- Dataset on the proteomic response during ferroptosis induction via tamoxifen induced GPX4 KO in mouse embryonic fibroblastsData in Brief, 2023
- Synthetic lethality-mediated precision oncology via the tumor transcriptomeCell, 2021
- Functional Genomics for Cancer Drug Target DiscoveryCancer Cell, 2020
- SIRT3 deficiency is resistant to autophagy‐dependent ferroptosis by inhibiting the AMPK/mTOR pathway and promoting GPX4 levelsJournal of Cellular Physiology, 2020
- Perturb-Seq: Dissecting Molecular Circuits with Scalable Single-Cell RNA Profiling of Pooled Genetic ScreensCell, 2016
- A Multiplexed Single-Cell CRISPR Screening Platform Enables Systematic Dissection of the Unfolded Protein ResponseCell, 2016
- Dissecting Immune Circuits by Linking CRISPR-Pooled Screens with Single-Cell RNA-SeqCell, 2016
- Highly Parallel Genome-wide Expression Profiling of Individual Cells Using Nanoliter DropletsCell, 2015
- Droplet Barcoding for Single-Cell Transcriptomics Applied to Embryonic Stem CellsCell, 2015