Machine learning sequence prioritization for cell type-specific enhancer design

Abstract

Recent discoveries of extreme cellular diversity in the brain warrant rapid development of technologies to access specific cell populations within heterogeneous tissue. Available approaches for engineering-targeted technologies for new neuron subtypes are low yield, involving intensive transgenic strain or virus screening. Here, we present Specific Nuclear-Anchored Independent Labeling (SNAIL), an improved virus-based strategy for cell labeling and nuclear isolation from heterogeneous tissue. SNAIL works by leveraging machine learning and other computational approaches to identify DNA sequence features that confer cell type-specific gene activation and then make a probe that drives an affinity purification-compatible reporter gene. As a proof of concept, we designed and validated two novel SNAIL probes that target parvalbumin-expressing (PV+) neurons. Nuclear isolation using SNAIL in wild-type mice is sufficient to capture characteristic open chromatin features of PV+ neurons in the cortex, striatum, and external globus pallidus. The SNAIL framework also has high utility for multispecies cell probe engineering; expression from a mouse PV+ SNAIL enhancer sequence was enriched in PV+ neurons of the macaque cortex. Expansion of this technology has broad applications in cell type-specific observation, manipulation, and therapeutics across species and disease models.

In silico prediction and in vivo testing of promoters targeting GABAergic inhibitory neurons

“… 25 , 26 Although there are limitations to the availability of the transcription factors in these databases, this approach and others (e.g., Lawler et al. 27 ) may allow elimination of the false-positive TFBSs. Another tactic would be to increase the number of non-GABAergic neuronal genes used in the GABA-v4 promoter design.…”

Anin vivomassively parallel platform for deciphering tissue-specific regulatory function

“…New AAV variants are being designed that would allow WhAMPRA libraries to be targeted to specific cell subtypes 54,55 and even non-human primate tissue 56 . As transduction efficiency improves, WhAMPRA could be paired with a methodology to isolate individual cell types 9,42 or even single-cell profiling 32 .…”

“…We cloned the candidate enhancer sequences into the plasmid backbone and then delivered the libraries into the brains of mice using retro-orbital injection of AAV-PHP.eB 37 as described in Lawler et al 42 (Fig. 1A).…”

“…High-throughput reporter assays have also been adapted to study gene regulation in cultured neurons 18,29 . However, cultured neurons fail to capture the full complexity of highly connected and regionally specialized in vivo neural tissue 30,31 .…”

MultipleXed Population Selection and Enrichment single nucleus RNA sequencing (XPoSE-seq) enables sample identity retention during transcriptional profiling of rare populations

“…Moreover, it enables precise control over population proportions prior to nucleus capture, essential for mitigating unequal sample sizes and resulting issues like unequal variance and reduced statistical power. XPoSE-seq is well positioned to support targeted multi-sample transcriptomic profiling of rare populations labelled using transgenic reporter lines, cell-type and circuit specific viral tools, or emerging enhancer-driven virus-based approaches 13,14 .…”