Evidence item

The abstract reports largely species-specific motif combinations and loss of cross-species predictive power for models trained on individual cell types within a family, indicating rapidly evolving cell-type regulatory syntax. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 24341

Source: Flexible use of conserved motifs constrains genome access in cell type evolution · locator {} · excerpt hash sha256:b354f975992e9fd2d73a8e8092028e1b1d3dcd94702a8109878402c4136a63e0

Exact excerpt

However, combinatorial relationships among these motifs preferred by individual cell types are largely species specific. Deep-learning models trained on one species accurately predict family-level chromatin accessibility in distantly related species, albeit frequently rely on different motifs from shared vocabularies to reach convergent predictions. By contrast, models trained on individual cell types within a family lose cross-species predictive power, indicating that the regulatory syntax governing cell type-level identity evolves rapidly.

Linked claims

Claim	Direction	Relevance	Steps	Counted
d4a13ee9	SUPPORT	DIRECT	0	yes

Audits

None.