MUSE-XAE: MUtational Signature Extraction with eXplainable AutoEncoder enhances tumour types classification.

MOTIVATION: Mutational signatures are a critical component in deciphering the genetic alterations that underlie cancer development and have become a valuable resource to understand the genomic changes during tumorigenesis. Therefore, it is essential to employ precise and accurate methods for their extraction to ensure that the underlying patterns are reliably identified and can be effectively utilized in new strategies for diagnosis, prognosis and treatment of cancer patients. RESULTS: We present MUSE-XAE, a novel method for mutational signature extraction from cancer genomes using an explainable autoencoder. Our approach employs a hybrid architecture consisting of a nonlinear encoder that can capture nonlinear interactions among features, and a linear decoder which ensures the interpretability of the active signatures. We evaluated and compared MUSE-XAE with other available tools on both synthetic and real cancer datasets and demonstrated that it achieves superior performance in terms of precision and sensitivity in recovering mutational signature profiles. MUSE-XAE extracts highly discriminative mutational signature profiles by enhancing the classification of primary tumour types and subtypes in real world settings. This approach could facilitate further research in this area, with neural networks playing a critical role in advancing our understanding of cancer genomics. AVAILABILITY: MUSE-XAE software is freely available at https://github.com/compbiomed-unito/MUSE-XAE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Impact of statin adherence and interruption within 6 months after ST-segment elevation myocardial infarction (STEMI): Results from the real-world regional registry FAST-STEMI.

BACKGROUND: The impact of statin therapy on cardiovascular outcomes after ST-elevation acute myocardial infarction (STEMI) in real- world patients is understudied. AIMS: To identify predictors of low adherence and discontinuation to statin therapy within 6 months after STEMI and to estimate their impact on cardiovascular outcomes at one year follow-up. METHODS: We evaluated real-world adherence to statin therapy by comparing the number of bought tablets to the expected ones at 1 year follow-up through pharmacy registries. A total of 6043 STEMI patients admitted from 2012 to 2017 were enrolled in the FAST STEMI registry and followed up for 4,7 ± 1,6 years; 304 patients with intraprocedural and intrahospital deaths were excluded. The main outcomes evaluated were all-cause death, cardiovascular death, myocardial infarction, major and minor bleeding events, and ischemic stroke. The compliance cut-off chosen was 80% as mainly reported in literature. RESULTS: From a total of 5744 patients, 418 (7,2%) patients interrupted statin therapy within 6 months after STEMI, whereas 3337 (58,1%) presented >80% adherence to statin therapy. Statin optimal adherence (>80%) resulted as protective factor towards both cardiovascular (0.1% vs 4.6%; AdjHR 0.025, 95%CI 0.008-0.079, p < 0.001) and all-cause mortality (0.3% vs 13.4%; Adj HR 0.032, 95%CI 0.018-0.059, p < 0.001) at 1 year follow-up. Further, a significant reduction of ischemic stroke incidence (1% vs 2.5%, p = 0.001) was seen in the optimal adherent group. Statin discontinuation within 6 months after STEMI showed an increase of both cardiovascular (5% vs 1.7%; AdjHR 2.23; 95%CI 1.37-3.65; p = 0,001) and all-cause mortality (14.8% vs 5.1%, AdjHR 2.32; 95%CI 1.73-3.11; p ã€ˆ0,001) at 1 year follow-up. After multivariate analysis age over 75 years old, known ischemic cardiopathy and female gender resulted as predictors of therapy discontinuation. Age over 75 years old, chronic kidney disease, previous atrial fibrillation, vasculopathy, known ischemic cardiopathy were found to be predictors of low statin adherence. CONCLUSIONS: n our real-world registry low statin adherence and discontinuation therapy within 6 months after STEMI were independently associated to an increase of cardiovascular and all-cause mortality at 1 year follow-up. Low statin adherence led to higher rates of ischemic stroke.

SYNDSURV: A simple framework for survival analysis with data distributed across multiple institutions.

Data sharing among different institutions represents one of the major challenges in developing distributed machine learning approaches, especially when data is sensitive, such as in medical applications. Federated learning is a possible solution, but requires fast communications and flawless security. Here, we propose SYNDSURV (SYNthetic Distributed SURVival), an alternative approach that simplifies the current state-of-the-art paradigm by allowing different centres to generate local simulated instances from real data and then gather them into a centralised hub, where an Artificial Intelligence (AI) model can learn in a standard way. The main advantage of this procedure is that it is model-agnostic, therefore prediction models can be directly applied in distributed applications without requiring particular adaptations as the current federated approaches do. To show the validity of our approach for medical applications, we tested it on a survival analysis task, offering a viable alternative to train AI models on distributed data. While federated learning has been mainly optimised for gradient-based approaches so far, our framework works with any predictive method, proving to be a comparable way of performing distributed learning without being too demanding towards each participating institute in terms of infrastructural requirements.

Influence of Model Structures on Predictors of Protein Stability Changes from Single-Point Mutations.

Missense variation in genomes can affect protein structure stability and, in turn, the cell physiology behavior. Predicting the impact of those variations is relevant, and the best-performing computational tools exploit the protein structure information. However, most of the current protein sequence variants are unresolved, and comparative or ab initio tools can provide a structure. Here, we evaluate the impact of model structures, compared to experimental structures, on the predictors of protein stability changes upon single-point mutations, where no significant changes are expected between the original and the mutated structures. We show that there are substantial differences among the computational tools. Methods that rely on coarse-grained representation are less sensitive to the underlying protein structures. In contrast, tools that exploit more detailed molecular representations are sensible to structures generated from comparative modeling, even on single-residue substitutions.

Machine learning-based prediction of in-hospital death for patients with takotsubo syndrome: The InterTAK-ML model.

AIMS: Takotsubo syndrome (TTS) is associated with a substantial rate of adverse events. We sought to design a machine learning (ML)-based model to predict the risk of in-hospital death and to perform a clustering of TTS patients to identify different risk profiles. METHODS AND RESULTS: A ridge logistic regression-based ML model for predicting in-hospital death was developed on 3482 TTS patients from the International Takotsubo (InterTAK) Registry, randomly split in a train and an internal validation cohort (75% and 25% of the sample size, respectively) and evaluated in an external validation cohort (1037 patients). Thirty-one clinically relevant variables were included in the prediction model. Model performance represented the primary endpoint and was assessed according to area under the curve (AUC), sensitivity and specificity. As secondary endpoint, a K-medoids clustering algorithm was designed to stratify patients into phenotypic groups based on the 10 most relevant features emerging from the main model. The overall incidence of in-hospital death was 5.2%. The InterTAK-ML model showed an AUC of 0.89 (0.85-0.92), a sensitivity of 0.85 (0.78-0.95) and a specificity of 0.76 (0.74-0.79) in the internal validation cohort and an AUC of 0.82 (0.73-0.91), a sensitivity of 0.74 (0.61-0.87) and a specificity of 0.79 (0.77-0.81) in the external cohort for in-hospital death prediction. By exploiting the 10 variables showing the highest feature importance, TTS patients were clustered into six groups associated with different risks of in-hospital death (28.8% vs. 15.5% vs. 5.4% vs. 1.0.8% vs. 0.5%) which were consistent also in the external cohort. CONCLUSION: A ML-based approach for the identification of TTS patients at risk of adverse short-term prognosis is feasible and effective. The InterTAK-ML model showed unprecedented discriminative capability for the prediction of in-hospital death.

Deep learning methods to predict amyotrophic lateral sclerosis disease progression.

Amyotrophic lateral sclerosis (ALS) is a highly complex and heterogeneous neurodegenerative disease that affects motor neurons. Since life expectancy is relatively low, it is essential to promptly understand the course of the disease to better target the patient's treatment. Predictive models for disease progression are thus of great interest. One of the most extensive and well-studied open-access data resources for ALS is the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) repository. In 2015, the DREAM-Phil Bowen ALS Prediction Prize4Life Challenge was held on PRO-ACT data, where competitors were asked to develop machine learning algorithms to predict disease progression measured through the slope of the ALSFRS score between 3 and 12 months. However, although it has already been successfully applied in several studies on ALS patients, to the best of our knowledge deep learning approaches still remain unexplored on the ALSFRS slope prediction in PRO-ACT cohort. Here, we investigate how deep learning models perform in predicting ALS progression using the PRO-ACT data. We developed three models based on different architectures that showed comparable or better performance with respect to the state-of-the-art models, thus representing a valid alternative to predict ALS disease progression.

DDGun: an untrained predictor of protein stability changes upon amino acid variants.

Estimating the functional effect of single amino acid variants in proteins is fundamental for predicting the change in the thermodynamic stability, measured as the difference in the Gibbs free energy of unfolding, between the wild-type and the variant protein (ΔΔG). Here, we present the web-server of the DDGun method, which was previously developed for the ΔΔG prediction upon amino acid variants. DDGun is an untrained method based on basic features derived from evolutionary information. It is antisymmetric, as it predicts opposite ΔΔG values for direct (A → B) and reverse (B → A) single and multiple site variants. DDGun is available in two versions, one based on only sequence information and the other one based on sequence and structure information. Despite being untrained, DDGun reaches prediction performances comparable to those of trained methods. Here we make DDGun available as a web server. For the web server version, we updated the protein sequence database used for the computation of the evolutionary features, and we compiled two new data sets of protein variants to do a blind test of its performances. On these blind data sets of single and multiple site variants, DDGun confirms its prediction performance, reaching an average correlation coefficient between experimental and predicted ΔΔG of 0.45 and 0.49 for the sequence-based and structure-based versions, respectively. Besides being used for the prediction of ΔΔG, we suggest that DDGun should be adopted as a benchmark method to assess the predictive capabilities of newly developed methods. Releasing DDGun as a web-server, stand-alone program and docker image will facilitate the necessary process of method comparison to improve ΔΔG prediction.

Predicting protein stability changes upon single-point mutation: a thorough comparison of the available tools on a new dataset.

Predicting the difference in thermodynamic stability between protein variants is crucial for protein design and understanding the genotype-phenotype relationships. So far, several computational tools have been created to address this task. Nevertheless, most of them have been trained or optimized on the same and 'all' available data, making a fair comparison unfeasible. Here, we introduce a novel dataset, collected and manually cleaned from the latest version of the ThermoMutDB database, consisting of 669 variants not included in the most widely used training datasets. The prediction performance and the ability to satisfy the antisymmetry property by considering both direct and reverse variants were evaluated across 21 different tools. The Pearson correlations of the tested tools were in the ranges of 0.21-0.5 and 0-0.45 for the direct and reverse variants, respectively. When both direct and reverse variants are considered, the antisymmetric methods perform better achieving a Pearson correlation in the range of 0.51-0.62. The tested methods seem relatively insensitive to the physiological conditions, performing well also on the variants measured with more extreme pH and temperature values. A common issue with all the tested methods is the compression of the $\Delta \Delta G$ predictions toward zero. Furthermore, the thermodynamic stability of the most significantly stabilizing variants was found to be more challenging to predict. This study is the most extensive comparisons of prediction methods using an entirely novel set of variants never tested before.

Unravelling the instability of mutational signatures extraction via archetypal analysis.

The high cosine similarity between some single-base substitution mutational signatures and their characteristic flat profiles could suggest the presence of overfitting and mathematical artefacts. The newest version (v3.3) of the signature database available in the Catalogue Of Somatic Mutations In Cancer (COSMIC) provides a collection of 79 mutational signatures, which has more than doubled with respect to previous version (30 profiles available in COSMIC signatures v2), making more critical the associations between signatures and specific mutagenic processes. This study both provides a systematic assessment of the de novo extraction task through simulation scenarios based on the latest version of the COSMIC signatures and highlights, through a novel approach using archetypal analysis, which COSMIC signatures are redundant and more likely to be considered as mathematical artefacts. 29 archetypes were able to reconstruct the profile of all the COSMIC signatures with cosine similarity > 0.8. Interestingly, these archetypes tend to group similar original signatures sharing either the same aetiology or similar biological processes. We believe that these findings will be useful to encourage the development of new de novo extraction methods avoiding the redundancy of information among the signatures while preserving the biological interpretation.

A Deep-Learning Sequence-Based Method to Predict Protein Stability Changes Upon Genetic Variations.

Several studies have linked disruptions of protein stability and its normal functions to disease. Therefore, during the last few decades, many tools have been developed to predict the free energy changes upon protein residue variations. Most of these methods require both sequence and structure information to obtain reliable predictions. However, the lower number of protein structures available with respect to their sequences, due to experimental issues, drastically limits the application of these tools. In addition, current methodologies ignore the antisymmetric property characterizing the thermodynamics of the protein stability: a variation from wild-type to a mutated form of the protein structure (XW→XM) and its reverse process (XM→XW) must have opposite values of the free energy difference (ΔΔGWM=-ΔΔGMW). Here we propose ACDC-NN-Seq, a deep neural network system that exploits the sequence information and is able to incorporate into its architecture the antisymmetry property. To our knowledge, this is the first convolutional neural network to predict protein stability changes relying solely on the protein sequence. We show that ACDC-NN-Seq compares favorably with the existing sequence-based methods.