Biology subjects

Kall, L.

Publications and source records attributed to Kall, L..

4 recordsLinked to original sources

bioRxiv2023

Spatial landmark detection and tissue registration with deep learning

Spatial landmarks are crucial in describing histological features between samples or sites, tracking regions of interest in microscopy, and registering tissue samples within a common coordinate framework. Although other studies have explored unsupervised landmark detection, existing methods are not well-suited for histological image data as they often require a large number of images to converge, are unable to handle non-linear deformations between tissue sections, and are ineffective for z-stack alignment, other modalities beyond image data, or multimodal data. We address these challenges by introducing a new landmark detection and registration method, utilizing neural-network-guided thin-plate splines. Our proposed method is evaluated on a diverse range of datasets, demonstrating superior performance in both accuracy and stability compared to existing approaches.

bioinformatics↗

bioRxiv2023

Automated model building and protein identification in cryo-EM maps

Interpreting electron cryo-microscopy (cryo-EM) maps with atomic models requires high levels of expertise and labour-intensive manual intervention. We present ModelAngelo, a machine-learning approach for automated atomic model building in cryo-EM maps. By combining information from the cryo-EM map with information from protein sequence and structure in a single graph neural network, ModelAngelo builds atomic models for proteins that are of similar quality as those generated by human experts. For nucleotides, ModelAngelo builds backbones with similar accuracy as humans. By using its predicted amino acid probabilities for each residue in hidden Markov model sequence searches, ModelAngelo outperforms human experts in the identification of proteins with unknown sequences. ModelAngelo will thus remove bottlenecks and increase objectivity in cryo-EM structure determination.

molecular biology↗

bioRxiv2023

Retention time and fragmentation predictors increase confidence in variant peptide identification

Precision medicine focuses on adapting care to the individual profile of patients, e.g. accounting for their unique genetic makeup. Being able to account for the effect of genetic variation on the proteome holds great promises towards this goal. However, identifying the protein products of genetic variation using mass spectrometry has proven very challenging. Here we show that the identification of variant peptides can be improved by the integration of retention time and fragmentation predictors into a unified proteogenomic pipeline. By combining these intrinsic peptide characteristics using the search-engine post-processor Percolator, we demonstrate improved discrimination power between correct and incorrect peptide-spectrum matches. Our results demonstrate that the drop in performance that is induced when expanding a protein sequence database can be compensated, and hence enabling efficient identification of genetic variation products in proteomics data. We anticipate that this enhancement of proteogenomic pipelines can provide a more refined picture of the unique proteome of patients, and thereby contribute to improving patient care.

bioinformatics↗

bioRxiv2022

Identifying Protein Haplotypes by Mass Spectrometry

The non-random distribution of alleles of common genomic variants produces haplotypes, which are fundamental in medical and population genetic studies. Consequently, protein-coding genes with different co-occurring sets of alleles can encode different amino acid sequences: protein haplotypes. These protein haplotypes are present in biological samples, and detectable by mass spectrometry, but are not accounted for in proteomic searches. Consequently, the impact of haplotypic variation on the results of proteomic searches, and the discoverability of peptides specific to haplotypes remain unknown. Here, we study how common genetic haplotypes influence the proteomic search space and investigate the possibility to match peptides containing multiple amino acid substitutions to a publicly available data set of mass spectra. We found that for 9.96 % of the discoverable amino acid substitutions encoded by common haplotypes, two or more substitutions may co-occur in the same peptide after tryptic digestion of the protein haplotypes. We identified 342 spectra that matched to such multi-variant peptides, and out of the 4,251 amino acid substitutions identified, 6.63 % were covered by multi-variant peptides. However, the evaluation of the reliability of these matches remains challenging, suggesting that refined error rate estimation procedures are needed for such complex proteomic searches. As these become available and the ability to analyze protein haplotypes increases, we anticipate that proteomics will provide new information on the consequences of common variation, across tissues and time.

bioinformatics↗