A multitask neural network trained on embeddings from ESMFold can accurately rank order clinical outcomes for different cystic fibrosis mutations
Drysdale, E.
Show abstract
Advancements in AI-based protein structure prediction have opened new research avenues in computational biology. Previous work has shown mixed results when the predicted 3D structure or model embeddings have been used as features for predicting phenotypes. Many existing tools which predict the pathogenicity of variants (e.g. SIFT 4G, Polyphen-2, REVEL, LYRUS) have incorporated structural protein features, but have shown mixed success when applied to mutations on the CFTR gene. This paper explores whether embeddings from the ESM-Fold model, which predicts the 3D structure of a protein from an amino acid sequence, can be used to predict clinical outcomes for different Cystic Fibrosis (CF) genotypes found in the CFTR2 database. A neural network model trained on these embeddings is able to obtain both non-trivial and statistically significant correlations on CF-related phenotypes (sweat chloride, pancreatic insufficiency, and infection rates). Overall, AI-based protein structure prediction models show a promising ability to assess the relative severity of CFTR-based mutations on key phenotypic outcomes associated with CF. The entire processing and analysis pipeline for this work can be found at this repo.
Matching journals
The top 11 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Deep representation learning for clustering longitudinal survival data from electronic health records 92%
- Convolutional neural networks quantify antibiotic resistance in Mycobacterium tuberculosis with diagnostic grade accuracy and predict treatment response 92%
- Simulation of undiagnosed patients with novel genetic conditions 91%
Similar papers in this journal
- Antisense oligonucleotide-based drug development for Cystic Fibrosis patients carrying the 3849+10kb C-to-T splicing mutation 89%
- The influence of highly effective modulator therapies on the sputum proteome in cystic fibrosis 89%
- FDA-Approved Drug Screening in Patient-Derived Organoids Demonstrates Potential of Drug Repurposing for Rare Cystic Fibrosis Genotypes 89%
Similar papers in this journal
- ProteinBERT: A universal deep-learning model of protein sequence and function 92%
- Beyond the Leaderboard: Leveraging Predictive Modeling for Protein-Ligand Insights and Discovery 91%
- CaLMPhosKAN: Prediction of General Phosphorylation Sites in Proteins via Fusion of Codon Aware Embeddings with Amino Acid Aware Embeddings and Wavelet-based Kolmogorov Arnold Network 91%
Similar papers in this journal
- Biobank-scale methods and projections for sparse polygenic prediction from machine learning 92%
- The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients 92%
- Medium-sized protein language models perform well at transfer learning on realistic datasets 92%
Similar papers in this journal
- Semantical and Geometrical Protein Encoding Toward Enhanced Bioactivity and Thermostability 91%
- Discovery of runs-of-homozygosity diplotype clusters and their associations with diseases in UK Biobank 90%
- PARROT: a flexible recurrent neural network framework for analysis of large protein datasets 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.