Reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing.
Mitochondria and plastids import thousands of proteins. Their experimental localisation remains a frequent task, but can be resource-intensive and sometimes impossible. Hence, hundreds of studies make use of algorithms that predict a localisation based on a protein's sequence. Their reliability...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-11-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1012575 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846151693201309696 |
|---|---|
| author | Sven B Gould Jonas Magiera Carolina García García Parth K Raval |
| author_facet | Sven B Gould Jonas Magiera Carolina García García Parth K Raval |
| author_sort | Sven B Gould |
| collection | DOAJ |
| description | Mitochondria and plastids import thousands of proteins. Their experimental localisation remains a frequent task, but can be resource-intensive and sometimes impossible. Hence, hundreds of studies make use of algorithms that predict a localisation based on a protein's sequence. Their reliability across evolutionary diverse species is unknown. Here, we evaluate the performance of common algorithms (TargetP, Localizer and WoLFPSORT) for four photosynthetic eukaryotes (Arabidopsis thaliana, Zea mays, Physcomitrium patens, and Chlamydomonas reinhardtii) for which experimental plastid and mitochondrial proteome data is available, and 171 eukaryotes using orthology inferences. The match between predictions and experimental data ranges from 75% to as low as 2%. Results worsen as the evolutionary distance between training and query species increases, especially for plant mitochondria for which performance borders on random sampling. Specificity, sensitivity and precision analyses highlight cross-organelle errors and uncover the evolutionary divergence of organelles as the main driver of current performance issues. The results encourage to train the next generation of neural networks on an evolutionary more diverse set of organelle proteins for optimizing performance and reliability. |
| format | Article |
| id | doaj-art-747313b0b5834aa8a54b82d875ed97ef |
| institution | Kabale University |
| issn | 1553-734X 1553-7358 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj-art-747313b0b5834aa8a54b82d875ed97ef2024-11-27T05:30:46ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582024-11-012011e101257510.1371/journal.pcbi.1012575Reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing.Sven B GouldJonas MagieraCarolina García GarcíaParth K RavalMitochondria and plastids import thousands of proteins. Their experimental localisation remains a frequent task, but can be resource-intensive and sometimes impossible. Hence, hundreds of studies make use of algorithms that predict a localisation based on a protein's sequence. Their reliability across evolutionary diverse species is unknown. Here, we evaluate the performance of common algorithms (TargetP, Localizer and WoLFPSORT) for four photosynthetic eukaryotes (Arabidopsis thaliana, Zea mays, Physcomitrium patens, and Chlamydomonas reinhardtii) for which experimental plastid and mitochondrial proteome data is available, and 171 eukaryotes using orthology inferences. The match between predictions and experimental data ranges from 75% to as low as 2%. Results worsen as the evolutionary distance between training and query species increases, especially for plant mitochondria for which performance borders on random sampling. Specificity, sensitivity and precision analyses highlight cross-organelle errors and uncover the evolutionary divergence of organelles as the main driver of current performance issues. The results encourage to train the next generation of neural networks on an evolutionary more diverse set of organelle proteins for optimizing performance and reliability.https://doi.org/10.1371/journal.pcbi.1012575 |
| spellingShingle | Sven B Gould Jonas Magiera Carolina García García Parth K Raval Reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing. PLoS Computational Biology |
| title | Reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing. |
| title_full | Reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing. |
| title_fullStr | Reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing. |
| title_full_unstemmed | Reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing. |
| title_short | Reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing. |
| title_sort | reliability of plastid and mitochondrial localisation prediction declines rapidly with the evolutionary distance to the training set increasing |
| url | https://doi.org/10.1371/journal.pcbi.1012575 |
| work_keys_str_mv | AT svenbgould reliabilityofplastidandmitochondriallocalisationpredictiondeclinesrapidlywiththeevolutionarydistancetothetrainingsetincreasing AT jonasmagiera reliabilityofplastidandmitochondriallocalisationpredictiondeclinesrapidlywiththeevolutionarydistancetothetrainingsetincreasing AT carolinagarciagarcia reliabilityofplastidandmitochondriallocalisationpredictiondeclinesrapidlywiththeevolutionarydistancetothetrainingsetincreasing AT parthkraval reliabilityofplastidandmitochondriallocalisationpredictiondeclinesrapidlywiththeevolutionarydistancetothetrainingsetincreasing |