| 1. |
- Repecka, Donatas, et al.
(författare)
-
Expanding functional protein sequence spaces using generative adversarial networks
- 2021
-
Ingår i: Nature Machine Intelligence. - : Springer Science and Business Media LLC. - 2522-5839. ; 3:4, s. 324-333
-
Tidskriftsartikel (refereegranskat)abstract
- De novo protein design for catalysis of any desired chemical reaction is a long-standing goal in protein engineering because of the broad spectrum of technological, scientific and medical applications. However, mapping protein sequence to protein function is currently neither computationally nor experimentally tangible. Here, we develop ProteinGAN, a self-attention-based variant of the generative adversarial network that is able to ‘learn’ natural protein sequence diversity and enables the generation of functional protein sequences. ProteinGAN learns the evolutionary relationships of protein sequences directly from the complex multidimensional amino-acid sequence space and creates new, highly diverse sequence variants with natural-like physical properties. Using malate dehydrogenase (MDH) as a template enzyme, we show that 24% (13 out of 55 tested) of the ProteinGAN-generated and experimentally tested sequences are soluble and display MDH catalytic activity in the tested conditions in vitro, including a highly mutated variant of 106 amino-acid substitutions. ProteinGAN therefore demonstrates the potential of artificial intelligence to rapidly generate highly diverse functional proteins within the allowed biological constraints of the sequence space.
|
|
| 2. |
- Rembeza, Elzbieta, 1990, et al.
(författare)
-
Adaptation of a Microfluidic qPCR System for Enzyme Kinetic Studies
- 2021
-
Ingår i: ACS Omega. - : American Chemical Society (ACS). - 2470-1343. ; 6:3, s. 1985-1990
-
Tidskriftsartikel (refereegranskat)abstract
- Microfluidic platforms offer a drastic increase in throughput while minimizing sample usage and hands-on time, which make them important tools for large-scale biological studies. A range of such systems have been developed for enzyme activity studies, although their complexity largely hinders their application to the wider scientific community. Here, we present adaptation of an easy-to-use commercial microfluidic qPCR system for performing enzyme kinetic studies. We demonstrate the functionality of the Fluidigm Biomark HD system (the Fluidigm system) by determining the kinetic properties of three oxidases in a resorufin-based fluorescence assay. The results obtained in the microfluidic system proved reproducible and comparable to the ones obtained in a standard microplate-based assay. With a wide range of easy-to-use, off-the-shelf components, the microfluidic system presents itself as a simple and customizable platform for high-throughput enzyme activity studies.
|
|
| 3. |
- Rembeza, Elzbieta, 1990, et al.
(författare)
-
Discovery of Two Novel Oxidases Using a High-Throughput Activity Screen
- 2022
-
Ingår i: ChemBioChem. - : Wiley. - 1439-7633 .- 1439-4227. ; 23:2
-
Tidskriftsartikel (refereegranskat)abstract
- Discovery of novel enzymes is a challenging task, yet a crucial one, due to their increasing relevance as chemical catalysts and biotechnological tools. In our work we present a high-throughput screening approach to discovering novel activities. A screen of 96 putative oxidases with 23 substrates led to the discovery of two new enzymes. The first enzyme, N-acetyl-D-hexosamine oxidase (EC 1.1.3.29) from Ralstonia solanacearum, is a vanillyl alcohol oxidase-like flavoprotein displaying the highest activity with N-acetylglucosamine and N-acetylgalactosamine. Before our discovery of the enzyme, its activity was an orphan one - experimentally characterized but lacking the link to amino acid sequence. The second enzyme, from an uncultured marine euryarchaeota, is a long-chain alcohol oxidase (LCAO, EC 1.1.3.20) active with a range of fatty alcohols, with 1-dodecanol being the preferred substrate. The enzyme displays no sequence similarity to previously characterised LCAOs, and thus is a completely novel representative of a protein with such activity.
|
|
| 4. |
- Rembeza, Elzbieta, 1990
(författare)
-
Experimental and computational exploration of enzyme sequence space
- 2021
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Millions of enzymes with desirable features or new exciting activities can be found in organisms occupying diverse niches all around the earth. However, enzyme studies tend to be biased towards characterisation of representatives from eukaryotes, model organisms, or disease-causing bacteria. As such, a large number of enzymes still remains underexplored. The so-called sequence space of proteins - all possible protein sequences - is even greater when we include not only natural sequences, but also the ones designed by human or artificial intelligence. This thesis explores various reasons, approaches, and outcomes of investigation of large enzymatic sequence spaces. In the first part of my work, I focused on investigation of a natural sequence space of oxidases using a high-throughput activity profiling platform. A functional screen of an industrially important class of enzymes, S-2-hydroxyacid oxidases (EC 1.1.3.15), revealed that nearly 80% of the class is misannotated. Further exploration of annotations to public databases indicated that similar errors of annotations can be found in other enzyme classes. A broader activity profiling of 1.1.3.x oxidases resulted in the discovery of two novel microbial enzymes: N-acetyl-hexosamine oxidase, and a novel type of long-chain alcohol oxidase. Natural enzymes often need to be improved in order to be industrially applied, for example to become more stable, or accept non-natural substrates. A novel, and constantly developing, approach for enzyme design involves the use of machine learning (ML) tools. Second part of my work focused on screening an enzyme sequence space designed by generative adversarial networks. Our work proved that ML methods can generate fully functional enzymes that mimic sequences present in nature. Enzyme assays are necessary to get a full understanding of how enzymes work. Traditional kinetic assays are time- and reagent-consuming and as a result a limited number of variants and conditions are being tested for each target. In my final work I described a novel approach for enzyme kinetic studies, by adaptation of a microfluidic qPCR device.
|
|
| 5. |
- Rembeza, Elzbieta, 1990, et al.
(författare)
-
Experimental and computational investigation of enzyme functional annotations uncovers misannotation in the EC 1.1.3.15 enzyme class
- 2021
-
Ingår i: PLoS Computational Biology. - : Public Library of Science (PLoS). - 1553-734X .- 1553-7358. ; 17:9
-
Tidskriftsartikel (refereegranskat)abstract
- Only a small fraction of genes deposited to databases have been experimentally characterised. The majority of proteins have their function assigned automatically, which can result in erroneous annotations. The reliability of current annotations in public databases is largely unknown; experimental attempts to validate the accuracy within individual enzyme classes are lacking. In this study we performed an overview of functional annotations to the BRENDA enzyme database. We first applied a high-throughput experimental platform to verify functional annotations to an enzyme class of S-2-hydroxyacid oxidases (EC 1.1.3.15). We chose 122 representative sequences of the class and screened them for their predicted function. Based on the experimental results, predicted domain architecture and similarity to previously characterised S-2-hydroxyacid oxidases, we inferred that at least 78% of sequences in the enzyme class are misannotated. We experimentally confirmed four alternative activities among the misannotated sequences and showed that misannotation in the enzyme class increased over time. Finally, we performed a computational analysis of annotations to all enzyme classes in the BRENDA database, and showed that nearly 18% of all sequences are annotated to an enzyme class while sharing no similarity or domain architecture to experimentally characterised representatives. We showed that even well-studied enzyme classes of industrial relevance are affected by the problem of functional misannotation. Copyright:
|
|
| 6. |
|
|
