Biology subjects

LeBlanc, C. J.

Publications and source records attributed to LeBlanc, C. J..

3 recordsLinked to original sources

bioRxiv2026

Machine learning guided design of strong transcriptional activation domains

Artificial intelligence has accelerated the design of structured proteins, but it remains difficult to design functional intrinsically disordered proteins because of weak structural constraints and poorly defined sequence-to-function relationships1. Activation domains (ADs), transcription factor regions that recruit coactivators, are an excellent test case for the de novo design of intrinsically disordered sequences. ADs are one of the oldest groups of functional intrinsically disordered sequences2 and designed ADs have applications in synthetic biology, biotechnology, and agriculture. We computationally generated 500,000 candidate sequences that resembled known ADs and predicted AD function with extant machine learning models, including three neural networks. From high-scoring sequences, we selected 18,750 for experimental validation in yeast. Surprisingly, >90% of the 16,770 well-measured sequences function as ADs. Sequences predicted to be active by multiple models were stronger, motivating development of a fast and accurate consensus AD predictor, MADRIGAL. A number of our designed ADs retain functionality across fungi, plants, and human cells. This work illustrates a generalizable paradigm for incorporating sequence-to-function models into the design loop to efficiently generate functional intrinsically disordered sequences.

synthetic biology↗

bioRxiv2025

Interpretable biophysical neural networks of transcriptional activation domains separate roles of protein abundance and coactivator binding

Deep neural networks have improved the accuracy of many difficult prediction tasks in biology, but it remains challenging to interpret these networks and learn molecular mechanisms. Here, we address the interpretability challenges associated with predicting transcriptional activation domains from protein sequence. Activation domains, regions within transcription factors that drive gene expression, were traditionally difficult to predict due to their sequence diversity and poor conservation. Multiple deep neural networks can now accurately predict activation domains, but these predictors are difficult to interpret. With the goal of interpretability, we designed simple neural networks that incorporated biophysical models of activation domains. The simplicity of these neural networks allowed us to visualize their parameters and directly interpret what the networks learned. The biophysical neural networks revealed two new ways that arrangement (i.e. the sequence grammar) of activation domain controlled function: 1) hydrophobic residues both increase activation domain strength and decrease protein abundance, and 2) acidic residues control both activation domain strength and protein abundance. Notably, the biophysical neural networks helped us to recognize the same signatures in complex interpreters of the deeper neural networks. We demonstrate how combining biophysical and deep neural networks maximizes both prediction accuracy and interpretability to yield insights into biological mechanisms.

systems biology↗

bioRxiv2024

Conservation of function without conservation of amino acid sequence in intrinsically disordered transcriptional activation domains

Protein function is canonically believed to be more conserved than amino acid sequence, but this idea is only well supported in folded domains, where highly diverged sequences can fold into equivalent 3D structures with identical function. Intrinsically disordered protein regions (IDRs) often experience rapid amino acid sequence divergence, but because they do not fold into stable 3D structures, it remains unknown when and how function is conserved. As a model system for studying the evolution of IDRs, we examined transcriptional activation domains, the regions of transcription factors that bind to coactivator complexes. We systematically identified activation domains on 502 homologs of the transcriptional activator Gcn4 spanning 600 MY of fungal evolution in the Ascomycota. We find that the central activation domain shows strong conservation of function without conservation of sequence. We identify the molecular mechanism for this conservation of function without conservation of sequence: evolutionary turnover (gain and loss) of acidic and aromatic residues that are important for function. We further see turnover of complete N-terminal activation domains. This turnover at two length scales confounds multiple sequence alignments, explaining why traditional comparative genomics cannot detect functional conservation of activation domains. Evolutionary turnover of key residues is likely a general mechanism for conservation of function without conservation of sequence in IDRs.

systems biology↗