Active machine learning-driven experimentation to determine compound effects on protein patterns
Abstract
High throughput screening determines the effects of many conditions on a given biological target. Currently, to estimate the effects of those conditions on other targets requires either strong modeling assumptions (e.g. similarities among targets) or separate screens. Ideally, data-driven experimentation could be used to learn accurate models for many conditions and targets without doing all possible experiments. We have previously described an active machine learning algorithm that can iteratively choose small sets of experiments to learn models of multiple effects. We now show that, with no prior knowledge and with liquid handling robotics and automated microscopy under its control, this learner accurately learned the effects of 48 chemical compounds on the subcellular localization of 48 proteins while performing only 29% of all possible experiments. The results represent the first practical demonstration of the utility of active learning-driven biological experimentation in which the set of possible phenotypes is unknown in advance.
Article and author information
Author details
Copyright
© 2016, Naik et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 7,106
- views
-
- 1,236
- downloads
-
- 43
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Further reading
-
- Cell Biology
Polynucleotide kinase phosphatase (PNKP) has enzymatic activities as 3′-phosphatase and 5′-kinase of DNA ends to promote DNA ligation and repair. Here, we show that cyclin-dependent kinases (CDKs) regulate the phosphorylation of threonine 118 (T118) in PNKP. This phosphorylation allows recruitment to the gapped DNA structure found in single-strand DNA (ssDNA) nicks and/or gaps between Okazaki fragments (OFs) during DNA replication. T118A (alanine)-substituted PNKP-expressing cells exhibited an accumulation of ssDNA gaps in S phase and accelerated replication fork progression. Furthermore, PNKP is involved in poly (ADP-ribose) polymerase 1 (PARP1)-dependent replication gap filling as part of a backup pathway in the absence of OFs ligation. Altogether, our data suggest that CDK-mediated PNKP phosphorylation at T118 is important for its recruitment to ssDNA gaps to proceed with OFs ligation and its backup repairs via the gap-filling pathway to maintain genome stability.
-
- Cell Biology
Chronic kidney disease (CKD) and atherosclerotic heart disease, frequently associated with dyslipidemia and hypertension, represent significant health concerns. We investigated the interplay among these conditions, focusing on the role of oxidized low-density lipoprotein (oxLDL) and angiotensin II (Ang II) in renal injury via G protein αq subunit (Gq) signaling. We hypothesized that oxLDL enhances Ang II-induced Gq signaling via the AT1 (Ang II type 1 receptor)-LOX1 (lectin-like oxLDL receptor) complex. Based on CHO and renal cell model experiments, oxLDL alone did not activate Gq signaling. However, when combined with Ang II, it significantly potentiated Gq-mediated inositol phosphate 1 production and calcium influx in cells expressing both LOX-1 and AT1 but not in AT1-expressing cells. This suggests a critical synergistic interaction between oxLDL and Ang II in the AT1-LOX1 complex. Conformational studies using AT1 biosensors have indicated a unique receptor conformational change due to the oxLDL-Ang II combination. In vivo, wild-type mice fed a high-fat diet with Ang II infusion presented exacerbated renal dysfunction, whereas LOX-1 knockout mice did not, underscoring the pathophysiological relevance of the AT1-LOX1 interaction in renal damage. These findings highlight a novel mechanism of renal dysfunction in CKD driven by dyslipidemia and hypertension and suggest the therapeutic potential of AT1-LOX1 receptor complex in patients with these comorbidities.