He, A. Y. | Search bioRxiv

bioRxiv2024

Training deep learning models on personalized genomic sequences improves variant effect prediction

Sequence-to-function models have broad applications in interpreting the molecular impact of genetic variation, yet have been criticized for poor performance in this task. Here we show that training models on functional genomic data with matched personal genomes improves their performance at variant effect prediction. Variant effect representations are retained even when fine tuning models to unseen cellular contexts and experimental readouts. Our results have implications for interpreting trait-associated genetic variation.

bioinformatics↗

bioRxiv2024

Dissection of core promoter syntax through single nucleotide resolution modeling of transcription initiation

How the DNA sequence of cis-regulatory elements encode transcription initiation patterns remains poorly understood. Here we introduce CLIPNET, a deep learning model trained on population-scale PRO-cap data that predicts the position and quantity of transcription initiation with single nucleotide resolution from DNA sequence more accurately than existing approaches. Interpretation of CLIPNET revealed a complex regulatory syntax consisting of DNA-protein interactions in five major positions between -200 and +50 bp relative to the transcription start site, as well as more subtle positional preferences among transcriptional activators. Transcriptional activator and core promoter motifs work non-additively to encode distinct aspects of initiation, with the former driving initiation quantity and the latter initiation position. We identified core promoter motifs that explain initiation patterns in the majority of promoters and enhancers, including DPR motifs and AT-rich TBP binding sequences in TATA-less promoters. Our results provide insights into the sequence architecture governing transcription initiation.

genomics↗