Contrasting drugs from decoys
Sledzieski, S.; Singh, R.; Cowen, L.; Berger, B.
Show abstract
Protein language models (PLMs) have recently been proposed to advance drugtarget interaction (DTI) prediction, and have shown state-of-the-art performance on several standard benchmarks. However, a remaining challenge for all DTI prediction models (including PLM-based ones) is distinguishing true drugs from highly-similar decoys. Leveraging techniques from self-supervised contrastive learning, we introduce a second-generation PLM-based DTI model trained on triplets of proteins, drugs, and decoys (small drug-like molecules that do not bind to the protein). We show that our approach, CON-Plex, improves specificity while maintaining high prediction accuracy and generalizability to new drug classes. CON-Plex maps proteins and drugs to a shared latent space which can be interpreted to identify mutually-compatible classes of proteins and drugs. Data and code are available at https://zenodo.org/record/7127229.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- TUGDA: Task uncertainty guided domain adaptation for robust generalization of cancer drug response prediction from in vitro to in vivo settings 97%
- Topology-Driven Negative Sampling Enhances Generalizability in Protein-Protein Interaction Prediction 96%
- ProteinBERT: A universal deep-learning model of protein sequence and function 96%
Similar papers in this journal
- Accelerating protein engineering with fitness landscape modeling and reinforcement learning 96%
- TrustAffinity: accurate, reliable and scalable out-of-distribution protein-ligand binding affinity prediction using trustworthy deep learning 95%
- Evaluating generalizability of artificial intelligence models for molecular datasets 95%
Similar papers in this journal
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 97%
- Tokenized and Continuous Embedding Compressions of Protein Sequence and Structure 97%
- Single-Cell Multi-Modal GAN (scMMGAN) reveals spatial patterns in single-cell data from triple negative breast cancer 94%
Similar papers in this journal
Similar papers in this journal
"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.