Bioactivity descriptors for uncharacterized compounds

Bertoni, Martino; Duran‐Frigola, Miquel; Badia-i-Mompel, Pau; Pauls, Eduardo; Orozco-Ruiz, Modesto; Guitart-Pla, Oriol; Alcalde, Víctor; Dı́az, Vı́ctor M.; Berenguer‐Llergo, Antoni; Herreros, Antonio Garcı́a de; Aloy, Patrick

doi:10.1101/2020.07.21.214197

Cited by 5 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of deep learning on fragmentation mass spectrometry data though, has only just begun to enter the stage [13]. The first promising applications include the prediction of compound classes from MS/MS spectra [31] or from (predicted) molecular fingerprints [32,33], the prediction of bioactivity signatures [34], the prediction of parts of molecular fingerprints [11,12], as well as the prediction of the structural similarity from MS/MS spectra and chemical formula [14]. With MS2DeepScore, we show for the first time that neural networks can also be used to predict structural similarity scores, i.e., to obtain a chemical-driven measure, from MS/MS spectra without requiring a known molecular formula or other metadata.…”

Section: Discussionmentioning

confidence: 99%

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

et al. 2021

View full text Add to dashboard Cite

Mass spectrometry data is one of the key sources of information in many workflows in medicine and across the life sciences. Mass fragmentation spectra are generally considered to be characteristic signatures of the chemical compound they originate from, yet the chemical structure itself usually cannot be easily deduced from the spectrum. Often, spectral similarity measures are used as a proxy for structural similarity but this approach is strongly limited by a generally poor correlation between both metrics. Here, we propose MS2DeepScore: a novel Siamese neural network to predict the structural similarity between two chemical structures solely based on their MS/MS fragmentation spectra. Using a cleaned dataset of > 100,000 mass spectra of about 15,000 unique known compounds, we trained MS2DeepScore to predict structural similarity scores for spectrum pairs with high accuracy. In addition, sampling different model varieties through Monte-Carlo Dropout is used to further improve the predictions and assess the model’s prediction uncertainty. On 3600 spectra of 500 unseen compounds, MS2DeepScore is able to identify highly-reliable structural matches and to predict Tanimoto scores for pairs of molecules based on their fragment spectra with a root mean squared error of about 0.15. Furthermore, the prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1. Furthermore, we demonstrate that MS2DeepScore outperforms classical spectral similarity measures in retrieving chemically related compound pairs from large mass spectral datasets, thereby illustrating its potential for spectral library matching. Finally, MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra. Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity measures have great potential for a range of metabolomics data processing pipelines.

show abstract

Section: Discussionmentioning

confidence: 99%

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The application of deep learning on fragmentation mass spectrometry data though, has only just begun to enter the stage. The first promising applications include the prediction of compound classes from MS/MS spectra 27 or from (predicted) molecular fingerprints 28,29 , the prediction of bioactivity signatures 30 , the prediction of parts of molecular fingerprints 13,14 , as well as the prediction of the structural similarity from MS/MS spectra and chemical formula 15 . With MS2DeepScore, we show for the first time that neural networks can also be used to predict structural similarity scores, i.e.…”

Section: Discussionmentioning

confidence: 99%

MS2DeepScore - a novel deep learning similarity measure for mass fragmentation spectrum comparisons

Huber

Burg

et al. 2021

Preprint

View full text Add to dashboard Cite

Mass spectrometry data is one of the key sources of information in many workflows in medicine and across the life sciences. Mass fragmentation spectra are considered characteristic signatures of the chemical compound they originate from, yet the chemical structure itself usually cannot be easily deduced from the spectrum. Often, spectral similarity measures are used as a proxy for structural similarity but this approach is strongly limited by a generally poor correlation between both metrics. Here, we propose MS2DeepScore: a novel Siamese neural network to predict the structural similarity between two chemical structures solely based on their MS/MS fragmentation spectra. Using a cleaned dataset of >100,000 mass spectra of about 15,000 unique known compounds, MS2DeepScore learns to predict structural similarity scores for spectrum pairs with high accuracy. In addition, sampling different model varieties through Monte-Carlo Dropout is used to further improve the predictions and assess the model's prediction uncertainty. On 3,600 spectra of 500 unseen compounds, MS2DeepScore is able to identify highly-reliable structural matches and predicts Tanimoto scores with a root mean squared error of about 0.15. The prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1. We demonstrate that MS2DeepScore outperforms classical spectral similarity measures in retrieving chemically related compound pairs from large mass spectral datasets, thereby illustrating its potential for spectral library matching. Finally, MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra. Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity metrics have great potential for a range of metabolomics data processing pipelines.

show abstract

“…As a machine-learning method, we used an ensemble-based approach (extra-trees classifiers) and, as features, we used CC signatures. Ensemble-based methods applied to CC signatures have shown exceptional performance across a wide range of benchmarking tasks ( 95 ). In a stratified 5-fold cross-validation, we obtained ROC AUC > 0.918, 0.874, 0.774, 0.690 and 0.874 for BBP, BACE, Aβ40, Aβ42 and Aβ ratio models, respectively.…”

Section: Methodsmentioning

confidence: 99%

Identification and drug-induced reversion of molecular signatures of Alzheimer’s disease onset and progression inApp^NL-G-F,App^NL-Fand 3xTg-AD mouse models

Pauls

Bayod

Mateo

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Alzheimers disease (AD) is the most common form of dementia. Over fifty years of intense research have revealed many key elements of the biology of this neurodegenerative disorder. However, our understanding of the molecular bases of the disease is still incomplete, and the medical treatments available for AD are mainly symptomatic and hardly effective. Indeed, the robustness of biological systems has revealed that the modulation of a single target is unlikely to yield the desired outcome and we should therefore move from gene-centric to systemic therapeutic strategies. Here we present the complete characterization of three murine models of AD at different stages of the disease (i.e. onset, progression and advanced). To identify genotype-to-phenotype relationships, we combine the cognitive assessment of these mice with histological analyses and full transcriptional and protein quantification profiling of the hippocampus. Comparison of the gene and protein expression trends observed in AD progression and physiological aging revealed certain commonalities, such as the upregulation of microglial and inflammation markers. However, although AD models show accelerated aging, other factors specifically associated with Aβ pathology are involved. Despite the clear correlation between mRNA and protein levels of the dysregulated genes, we discovered a few proteins whose abundance increases with AD progression, while the corresponding transcript levels remain stable. Indeed, we show that at least two of these proteins, namely lfit3 and Syt11, co-localize with Aβ plaques in the brain. Finally, we derived specific Aβ-related molecular AD signatures and looked for drugs able to globally revert them. We found two NSAIDs (dexketoprofen and etodolac) and two anti-hypertensives (penbutolol and bendroflumethiazide) that overturn the cognitive impairment in AD mice while reducing Aβ plaques in the hippocampus and partially restoring the physiological levels of AD signature genes to wild-type levels.

show abstract

Bioactivity descriptors for uncharacterized compounds

Cited by 5 publications

References 47 publications

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

MS2DeepScore - a novel deep learning similarity measure for mass fragmentation spectrum comparisons

Identification and drug-induced reversion of molecular signatures of Alzheimer’s disease onset and progression inApp^NL-G-F,App^NL-Fand 3xTg-AD mouse models

Contact Info

Product

Resources

About

Bioactivity descriptors for uncharacterized compounds

Cited by 5 publications

References 47 publications

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

MS2DeepScore - a novel deep learning similarity measure for mass fragmentation spectrum comparisons

Identification and drug-induced reversion of molecular signatures of Alzheimer’s disease onset and progression inAppNL-G-F,AppNL-Fand 3xTg-AD mouse models

Contact Info

Product

Resources

About

Identification and drug-induced reversion of molecular signatures of Alzheimer’s disease onset and progression inApp^NL-G-F,App^NL-Fand 3xTg-AD mouse models