PandoGen: Generating complete instances of future SARS-CoV-2 sequences using Deep Learning.
One of the challenges in a viral pandemic is the emergence of novel variants with different phenotypical characteristics. An ability to forecast future viral individuals at the sequence level enables advance preparation by characterizing the sequences and closing vulnerabilities in current preventat...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011790&type=printable |
| _version_ | 1797326208070844416 |
|---|---|
| author | Anand Ramachandran Steven S Lumetta Deming Chen |
| author_facet | Anand Ramachandran Steven S Lumetta Deming Chen |
| author_sort | Anand Ramachandran |
| collection | DOAJ |
| description | One of the challenges in a viral pandemic is the emergence of novel variants with different phenotypical characteristics. An ability to forecast future viral individuals at the sequence level enables advance preparation by characterizing the sequences and closing vulnerabilities in current preventative and therapeutic methods. In this article, we explore, in the context of a viral pandemic, the problem of generating complete instances of undiscovered viral protein sequences, which have a high likelihood of being discovered in the future using protein language models. Current approaches to training these models fit model parameters to a known sequence set, which does not suit pandemic forecasting as future sequences differ from known sequences in some respects. To address this, we develop a novel method, called PandoGen, to train protein language models towards the pandemic protein forecasting task. PandoGen combines techniques such as synthetic data generation, conditional sequence generation, and reward-based learning, enabling the model to forecast future sequences, with a high propensity to spread. Applying our method to modeling the SARS-CoV-2 Spike protein sequence, we find empirically that our model forecasts twice as many novel sequences with five times the case counts compared to a model that is 30× larger. Our method forecasts unseen lineages months in advance, whereas models 4× and 30× larger forecast almost no new lineages. When trained on data available up to a month before the onset of important Variants of Concern, our method consistently forecasts sequences belonging to those variants within tight sequence budgets. |
| first_indexed | 2024-03-08T06:20:07Z |
| format | Article |
| id | doaj.art-26ff7579ec0d47c5b2adeb9fbbe90a07 |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-03-08T06:20:07Z |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-26ff7579ec0d47c5b2adeb9fbbe90a072024-02-04T05:30:48ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582024-01-01201e101179010.1371/journal.pcbi.1011790PandoGen: Generating complete instances of future SARS-CoV-2 sequences using Deep Learning.Anand RamachandranSteven S LumettaDeming ChenOne of the challenges in a viral pandemic is the emergence of novel variants with different phenotypical characteristics. An ability to forecast future viral individuals at the sequence level enables advance preparation by characterizing the sequences and closing vulnerabilities in current preventative and therapeutic methods. In this article, we explore, in the context of a viral pandemic, the problem of generating complete instances of undiscovered viral protein sequences, which have a high likelihood of being discovered in the future using protein language models. Current approaches to training these models fit model parameters to a known sequence set, which does not suit pandemic forecasting as future sequences differ from known sequences in some respects. To address this, we develop a novel method, called PandoGen, to train protein language models towards the pandemic protein forecasting task. PandoGen combines techniques such as synthetic data generation, conditional sequence generation, and reward-based learning, enabling the model to forecast future sequences, with a high propensity to spread. Applying our method to modeling the SARS-CoV-2 Spike protein sequence, we find empirically that our model forecasts twice as many novel sequences with five times the case counts compared to a model that is 30× larger. Our method forecasts unseen lineages months in advance, whereas models 4× and 30× larger forecast almost no new lineages. When trained on data available up to a month before the onset of important Variants of Concern, our method consistently forecasts sequences belonging to those variants within tight sequence budgets.https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011790&type=printable |
| spellingShingle | Anand Ramachandran Steven S Lumetta Deming Chen PandoGen: Generating complete instances of future SARS-CoV-2 sequences using Deep Learning. PLoS Computational Biology |
| title | PandoGen: Generating complete instances of future SARS-CoV-2 sequences using Deep Learning. |
| title_full | PandoGen: Generating complete instances of future SARS-CoV-2 sequences using Deep Learning. |
| title_fullStr | PandoGen: Generating complete instances of future SARS-CoV-2 sequences using Deep Learning. |
| title_full_unstemmed | PandoGen: Generating complete instances of future SARS-CoV-2 sequences using Deep Learning. |
| title_short | PandoGen: Generating complete instances of future SARS-CoV-2 sequences using Deep Learning. |
| title_sort | pandogen generating complete instances of future sars cov 2 sequences using deep learning |
| url | https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011790&type=printable |
| work_keys_str_mv | AT anandramachandran pandogengeneratingcompleteinstancesoffuturesarscov2sequencesusingdeeplearning AT stevenslumetta pandogengeneratingcompleteinstancesoffuturesarscov2sequencesusingdeeplearning AT demingchen pandogengeneratingcompleteinstancesoffuturesarscov2sequencesusingdeeplearning |