AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands
Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We first unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Then, we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training, allowing us to limit the annotation imbalance and improve binding predictions for novel proteins and ligands. We illustrate the value of AI-Bind by predicting drugs and natural compounds with binding affinity to SARS-CoV-2 viral proteins and the associated human proteins. We also validate these predictions via auto-docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. Overall, AI-Bind offers a powerful high-throughput approach to identify drug-target combinations, with the potential of becoming a powerful tool in drug discovery..
Medienart: |
Preprint |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
arXiv.org - (2021) vom: 24. Dez. Zur Gesamtaufnahme - year:2021 |
---|
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Chatterjee, Ayan [VerfasserIn] |
---|
Links: |
Volltext [kostenfrei] |
---|
Förderinstitution / Projekttitel: |
|
---|
PPN (Katalog-ID): |
XAR033302154 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | XAR033302154 | ||
003 | DE-627 | ||
005 | 20230429070454.0 | ||
007 | cr uuu---uuuuu | ||
008 | 211228s2021 xx |||||o 00| ||eng c | ||
035 | |a (DE-627)XAR033302154 | ||
035 | |a (arXiv)2112.13168 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | |a 000 |q DE-84 | |
082 | 0 | |a 570 |q DE-84 | |
100 | 1 | |a Chatterjee, Ayan |e verfasserin |4 aut | |
245 | 1 | 0 | |a AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We first unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Then, we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training, allowing us to limit the annotation imbalance and improve binding predictions for novel proteins and ligands. We illustrate the value of AI-Bind by predicting drugs and natural compounds with binding affinity to SARS-CoV-2 viral proteins and the associated human proteins. We also validate these predictions via auto-docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. Overall, AI-Bind offers a powerful high-throughput approach to identify drug-target combinations, with the potential of becoming a powerful tool in drug discovery. | ||
700 | 1 | |a Walters, Robin |e verfasserin |4 aut | |
700 | 1 | |a Shafi, Zohair |e verfasserin |4 aut | |
700 | 1 | |a Ahmed, Omair Shafi |e verfasserin |4 aut | |
700 | 1 | |a Sebek, Michael |e verfasserin |4 aut | |
700 | 1 | |a Gysi, Deisy |e verfasserin |4 aut | |
700 | 1 | |a Yu, Rose |e verfasserin |4 aut | |
700 | 1 | |a Eliassi-Rad, Tina |e verfasserin |4 aut | |
700 | 1 | |a Barabási, Albert-László |e verfasserin |4 aut | |
700 | 1 | |a Menichetti, Giulia |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t arXiv.org |g (2021) vom: 24. Dez. |
773 | 1 | 8 | |g year:2021 |g day:24 |g month:12 |
856 | 4 | 0 | |u https://arxiv.org/abs/2112.13168 |z kostenfrei |3 Volltext |
912 | |a GBV_XAR | ||
912 | |a SSG-OLC-PHA | ||
951 | |a AR | ||
952 | |j 2021 |b 24 |c 12 | ||
953 | |2 045F |a 000 | ||
953 | |2 045F |a 570 |