Tree-aware conditional language modeling recovers mutational patterns of viral evolution

The evolutionary accessibility of a protein mutation depends on the sequence background in which it arises and its lineage history, yet most protein language models estimate sequence plausibility without explicitly considering the ordered sequence changes through which descendants arise. We developed evoPLM-Tree, a tree-aware conditional autoregressive language model that predicts descendant…

biorxiv.org ·1d ago

We haven't written up this one. bioRxiv has the full story — the link below goes straight to it.

Read the original at biorxiv.org →

More in Science

Bright people know more about wine: How higher intelligence is reflected in deep domain knowledge

Intelligent people tend to perform better at school and at work, as numerous studies have shown. But what happens in domains where incentives such as good grades or financial rewards don't apply and where socioeconomic status is not a significant factor? Wine knowledge is a case in point.

1d ago ·phys.org

Animation boosts willingness to adopt airborne disease precautions, study finds

Even as the scientific community has reached a broad consensus that infectious pathogens, such as viruses, can spread through virus-laden aerosols, one fundamental challenge remains: How can scientific evidence be transformed into public understanding—and ultimately into meaningful action for effective airborne disease control and…

1d ago ·phys.org

Tree-aware conditional language modeling recovers mutational patterns of viral evolution

More in Science

Bright people know more about wine: How higher intelligence is reflected in deep domain knowledge

Animation boosts willingness to adopt airborne disease precautions, study finds

Scientists Reconstruct Sound of Jurassic Insects

Cackle! Pop! Roar! Reptiles have a lot to say.

Analysis: Pursuing energy security with self-sufficiency, demand controls

Indonesia's shrinking digital freedom: From rubber articles to four-hour censors...