Prediction of protein-ligand binding affinity from sequencing data with interpretable machine learning
© 2022. The Author(s)..
Protein-ligand interactions are increasingly profiled at high throughput using affinity selection and massively parallel sequencing. However, these assays do not provide the biophysical parameters that most rigorously quantify molecular interactions. Here we describe a flexible machine learning method, called ProBound, that accurately defines sequence recognition in terms of equilibrium binding constants or kinetic rates. This is achieved using a multi-layered maximum-likelihood framework that models both the molecular interactions and the data generation process. We show that ProBound quantifies transcription factor (TF) behavior with models that predict binding affinity over a range exceeding that of previous resources; captures the impact of DNA modifications and conformational flexibility of multi-TF complexes; and infers specificity directly from in vivo data such as ChIP-seq without peak calling. When coupled with an assay called KD-seq, it determines the absolute affinity of protein-ligand interactions. We also apply ProBound to profile the kinetics of kinase-substrate interactions. ProBound opens new avenues for decoding biological networks and rationally engineering protein-ligand interactions.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:40 |
---|---|
Enthalten in: |
Nature biotechnology - 40(2022), 10 vom: 23. Okt., Seite 1520-1527 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Rube, H Tomas [VerfasserIn] |
---|
Links: |
---|
Themen: |
9007-49-2 |
---|
Anmerkungen: |
Date Completed 11.10.2022 Date Revised 16.11.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1038/s41587-022-01307-0 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM341289175 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM341289175 | ||
003 | DE-627 | ||
005 | 20231226011432.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1038/s41587-022-01307-0 |2 doi | |
028 | 5 | 2 | |a pubmed24n1137.xml |
035 | |a (DE-627)NLM341289175 | ||
035 | |a (NLM)35606422 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Rube, H Tomas |e verfasserin |4 aut | |
245 | 1 | 0 | |a Prediction of protein-ligand binding affinity from sequencing data with interpretable machine learning |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 11.10.2022 | ||
500 | |a Date Revised 16.11.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2022. The Author(s). | ||
520 | |a Protein-ligand interactions are increasingly profiled at high throughput using affinity selection and massively parallel sequencing. However, these assays do not provide the biophysical parameters that most rigorously quantify molecular interactions. Here we describe a flexible machine learning method, called ProBound, that accurately defines sequence recognition in terms of equilibrium binding constants or kinetic rates. This is achieved using a multi-layered maximum-likelihood framework that models both the molecular interactions and the data generation process. We show that ProBound quantifies transcription factor (TF) behavior with models that predict binding affinity over a range exceeding that of previous resources; captures the impact of DNA modifications and conformational flexibility of multi-TF complexes; and infers specificity directly from in vivo data such as ChIP-seq without peak calling. When coupled with an assay called KD-seq, it determines the absolute affinity of protein-ligand interactions. We also apply ProBound to profile the kinetics of kinase-substrate interactions. ProBound opens new avenues for decoding biological networks and rationally engineering protein-ligand interactions | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, N.I.H., Extramural | |
650 | 7 | |a Ligands |2 NLM | |
650 | 7 | |a Transcription Factors |2 NLM | |
650 | 7 | |a DNA |2 NLM | |
650 | 7 | |a 9007-49-2 |2 NLM | |
700 | 1 | |a Rastogi, Chaitanya |e verfasserin |4 aut | |
700 | 1 | |a Feng, Siqian |e verfasserin |4 aut | |
700 | 1 | |a Kribelbauer, Judith F |e verfasserin |4 aut | |
700 | 1 | |a Li, Allyson |e verfasserin |4 aut | |
700 | 1 | |a Becerra, Basheer |e verfasserin |4 aut | |
700 | 1 | |a Melo, Lucas A N |e verfasserin |4 aut | |
700 | 1 | |a Do, Bach Viet |e verfasserin |4 aut | |
700 | 1 | |a Li, Xiaoting |e verfasserin |4 aut | |
700 | 1 | |a Adam, Hammaad H |e verfasserin |4 aut | |
700 | 1 | |a Shah, Neel H |e verfasserin |4 aut | |
700 | 1 | |a Mann, Richard S |e verfasserin |4 aut | |
700 | 1 | |a Bussemaker, Harmen J |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Nature biotechnology |d 1996 |g 40(2022), 10 vom: 23. Okt., Seite 1520-1527 |w (DE-627)NLM08998398X |x 1546-1696 |7 nnns |
773 | 1 | 8 | |g volume:40 |g year:2022 |g number:10 |g day:23 |g month:10 |g pages:1520-1527 |
856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41587-022-01307-0 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 40 |j 2022 |e 10 |b 23 |c 10 |h 1520-1527 |