Sandra Viknander

Sandra Viknander

Auto-generated profile, based on publicly available information

Sandra Viknander

Department of Biology and Biological Engineering Chalmers University of Technology Gothenburg Sweden

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 March 2021 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
DRDonatas Repecka
Donatas Repecka
VJVykintas Jauniskis
Vykintas Jauniskis
LKLaurynas Karpus
Laurynas Karpus
ERElzbieta Rembeza
Elzbieta Rembeza
IRIrmantas Rokaitis
Irmantas Rokaitis
AZAleksej Zelezniak
Aleksej Zelezniak

22 November 2022 in Protein Science
Verified
Journal Article
Open access
GLGang Li
Gang Li
FBFilip Buric
Filip Buric
JZJan Zrimec
Jan Zrimec
SVSandra Viknander
Sandra Viknander
JNJens Nielsen
Jens Nielsen
MEMartin K. M. Engqvist
Martin K. M. Engqvist
Temperature is a fundamental environmental factor that shapes the evolution of organisms. Learning thermal determinants of protein sequences in evolution thus has profound significance for basic biology, drug discovery, and protein engineering. Here, we use a data set of over 3 million BRENDA enzymes labeled with optimal growth temperatures (OGTs) of their source organisms to train a deep neural network model (DeepET). The protein‐temperature representations learned by DeepET provide a temperature‐related statistical summary of protein sequences and capture structural properties that affect thermal stability. For prediction of enzyme optimal catalytic temperatures and protein melting temperatures via a transfer learning approach, our DeepET model outperforms classical regression models trained on rationally designed features and other deep‐learning‐based representations. DeepET thus holds promise for understanding enzyme thermal adaptation and guiding the engineering of thermostable enzymes.

4 March 2023 in bioRxiv
Verified
Preprint
Open access
PDF file
SJSean R Johnson
Sean R Johnson
XFXiaozhi Fu
Xiaozhi Fu
SVSandra Viknander
Sandra Viknander
CGClara Goldin
Clara Goldin
SMSarah Monaco
Sarah Monaco
KYKevin K. Yang
Kevin K. Yang
In recent years, generative protein sequence models have been developed to sample novel sequences. However, predicting whether generated proteins will fold and function remains challenging. We evaluate computational metrics to assess the quality of enzyme sequences produced by three contrasting generative models: ancestral sequence reconstruction, a generative adversarial network, and a protein language model. Focusing on two enzyme families, we expressed and purified over 440 natural and generated sequences with 70-90% identity to the most similar natural sequences to benchmark computational metrics for predicting in vitro enzyme activity. Over three rounds of experiments, we developed a computational filter that improved experimental success rates by 44-100%. Surprisingly, neither sequence identity to natural sequences nor AlphaFold2 residue-confidence scores were predictive of enzyme activity. The proposed metrics and models will drive protein engineering research by serving as a benchmark for generative protein sequence models and helping to select active variants to test experimentally.

12 December 2024 in Protein Science
Verified
Journal Article
Open access
FBFilip Buric
Filip Buric
SVSandra Viknander
Sandra Viknander
XFXiaozhi Fu
Xiaozhi Fu
OLOliver Lemke
Oliver Lemke
OCOriol Gracia Carmona
Oriol Gracia Carmona
AZAleksej Zelezniak
Aleksej Zelezniak
Understanding what drives protein abundance is essential to biology, medicine, and biotechnology. Driven by evolutionary selection, an amino acid sequence is tailored to meet the required abundance of a proteome, underscoring the intricate relationship between sequence and functional demand. Yet, the specific role of amino acid sequences in determining proteome abundance remains elusive. Here we show that the amino acid sequence alone encodes over half of protein abundance variation across all domains of life, ranging from bacteria to mouse and human. With an attempt to go beyond predictions, we trained a manageable‐size Transformer model to interpret latent factors predictive of protein abundances. Intuitively, the model's attention focused on the protein's structural features linked to stability and metabolic costs related to protein synthesis. To probe these relationships, we introduce MGEM (Mutation Guided by an Embedded Manifold), a methodology for guiding protein abundance through sequence modifications. We find that mutations which increase predicted abundance have significantly altered protein polarity and hydrophobicity, underscoring a connection between protein structural features and abundance. Through molecular dynamics simulations we revealed that abundance‐enhancing mutations possibly contribute to protein thermostability by increasing rigidity, which occurs at a lower synthesis cost.

4 October 2023 in bioRxiv
Verified
Preprint
Open access
PDF file
FBFilip Buric
Filip Buric
SVSandra Viknander
Sandra Viknander
XFXiaozhi Fu
Xiaozhi Fu
OLOliver Lemke
Oliver Lemke
JZJan Zrimec
Jan Zrimec
AZAleksej Zelezniak
Aleksej Zelezniak
Understanding what drives protein abundance is essential to biology, medicine, and biotechnology. Driven by evolutionary selection, the amino acid sequence is tailored to meet the required abundance of proteomes, underscoring the intricate relationship between sequence and functional demand. Yet, the specific role of amino acid sequences in determining proteome abundance remains elusive. Here, we demonstrate that the amino acid sequence predicts abundance by shaping a protein’s conformational stability. We show that increasing the abundance provides metabolic cost benefits, underscoring the evolutionary advantage of maintaining a highly abundant and stable proteome. Specifically, using a deep learning model (BERT), we predict 56% of protein abundance variation in Saccharomyces cerevisiae solely based on amino acid sequence. The model reveals latent factors linking sequence features to protein stability. To probe these relationships, we introduce MGEM (Mutation Guided by an Embedded Manifold), a methodology for guiding protein abundance through sequence modifications. We find that mutations increasing abundance significantly alter protein polarity and hydrophobicity, underscoring a connection between protein stability and abundance. Through molecular dynamics simulations and in vivo experiments in yeast, we confirm that abundance-enhancing mutations result in longer-lasting and more stable protein expression. Importantly, these sequence changes also reduce metabolic costs of protein synthesis, elucidating the evolutionary advantage of cost-effective, high-abundance, stable proteomes. Our findings support the role of amino acid sequence as a pivotal determinant of protein abundance and stability, revealing an evolutionary optimization for metabolic efficiency.

16 March 2022 in bioRxiv
Verified
Preprint
Open access
PDF file
GLGang Li
Gang Li
FBFilip Buric
Filip Buric
JZJan Zrimec
Jan Zrimec
SVSandra Viknander
Sandra Viknander
JNJens Nielsen
Jens Nielsen
MEMartin Km Engqvist
Martin Km Engqvist
Temperature is a fundamental environmental factor that shapes the evolution of organisms. Learning thermal determinants of protein sequences in evolution thus has profound significance for basic biology, drug discovery, and protein engineering. Here, we use a dataset of over 3 million enzymes labeled with optimal growth temperatures (OGT) of their source organisms to train a deep neural network model (DeepET). The protein-temperature representations learned by DeepET provide a temperature-related statistical summary of protein sequences and capture structural properties that affect thermal stability. For prediction of enzyme optimal catalytic temperatures and protein melting temperatures via a transfer learning approach, our DeepET model outperforms classical regression models trained on rationally designed features and other recent deep-learning-based representations. DeepET thus holds promise for understanding enzyme thermal adaptation and guiding the engineering of thermostable enzymes.