Graph representation learning in biomedicine and healthcare
Networks—or graphs—are universal descriptors of systems of interacting elements. In
biomedicine and healthcare, they can represent, for example, molecular interactions …
biomedicine and healthcare, they can represent, for example, molecular interactions …
[HTML][HTML] The language of proteins: NLP, machine learning & protein sequences
Natural language processing (NLP) is a field of computer science concerned with automated
text and language analysis. In recent years, following a series of breakthroughs in deep and …
text and language analysis. In recent years, following a series of breakthroughs in deep and …
Evolutionary-scale prediction of atomic-level protein structure with a language model
Recent advances in machine learning have leveraged evolutionary information in multiple
sequence alignments to predict protein structure. We demonstrate direct inference of full …
sequence alignments to predict protein structure. We demonstrate direct inference of full …
Large language models generate functional protein sequences across diverse families
Deep-learning language models have shown promise in various biotechnological
applications, including protein design and engineering. Here we describe ProGen, a …
applications, including protein design and engineering. Here we describe ProGen, a …
[PDF][PDF] Language models of protein sequences at the scale of evolution enable accurate structure prediction
Large language models have recently been shown to develop emergent capabilities with
scale, going beyond simple pattern matching to perform higher level reasoning and …
scale, going beyond simple pattern matching to perform higher level reasoning and …
DeepLoc 2.0: multi-label subcellular localization prediction using protein language models
V Thumuluri, JJ Almagro Armenteros… - Nucleic acids …, 2022 - academic.oup.com
The prediction of protein subcellular localization is of great relevance for proteomics
research. Here, we propose an update to the popular tool DeepLoc with multi-localization …
research. Here, we propose an update to the popular tool DeepLoc with multi-localization …
High-resolution de novo structure prediction from primary sequence
Recent breakthroughs have used deep learning to exploit evolutionary information in
multiple sequence alignments (MSAs) to accurately predict protein structures. However …
multiple sequence alignments (MSAs) to accurately predict protein structures. However …
Promptaid: Prompt exploration, perturbation, testing and iteration using visual analytics for large language models
Large Language Models (LLMs) have gained widespread popularity due to their ability to
perform ad-hoc Natural Language Processing (NLP) tasks with a simple natural language …
perform ad-hoc Natural Language Processing (NLP) tasks with a simple natural language …
Language models enable zero-shot prediction of the effects of mutations on protein function
Modeling the effect of sequence variation on function is a fundamental problem for
understanding and designing proteins. Since evolution encodes information about function …
understanding and designing proteins. Since evolution encodes information about function …
Rethinking attention with performers
We introduce Performers, Transformer architectures which can estimate regular (softmax)
full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to …
full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to …