Recursive feature elimination for brain tumor classification using desorption electrospray ionization mass spectrometry imaging

Comparison of models for stroke-free survival prediction in patients with CADASIL

Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy, which is caused by mutations of the NOTCH3 gene, has a large heterogeneous progression, presenting with declines of various clinical scores and occurrences of various clinical event. To help assess disease progression, this work focused on predicting the composite endpoint of stroke-free survival time by comparing the performance of Cox proportional hazards regression to that of machine learning models using one of four feature selection approaches applied to demographic, clinical and magnetic resonance imaging observational data collected from a study cohort of 482 patients. The quality of the modeling process and the predictive performance were evaluated in a nested cross-validation procedure using the time-dependent Brier Score and AUC at 5 years from baseline, the former measuring the overall performance including calibration and the latter highlighting the discrimination ability, with both metrics taking into account the presence of right-censoring. The best model for each metric was the componentwise gradient boosting model with a mean Brier score of 0.165 and the random survival forest model with a mean AUC of 0.773, both combined with the LASSO feature selection method.

Rectified Classifier Chains for Prediction of Antibiotic Resistance From Multi-Labelled Data With Missing Labels

Predicting Antimicrobial Resistance (AMR) from genomic data has important implications for human and animal healthcare, and especially given its potential for more rapid diagnostics and informed treatment choices. With the recent advances in sequencing technologies, applying machine learning techniques for AMR prediction have indicated promising results. Despite this, there are shortcomings in the literature concerning methodologies suitable for multi-drug AMR prediction and especially where samples with missing labels exist. To address this shortcoming, we introduce a Rectified Classifier Chain (RCC) method for predicting multi-drug resistance. This RCC method was tested using annotated features of genomics sequences and compared with similar multi-label classification methodologies. We found that applying the eXtreme Gradient Boosting (XGBoost) base model to our RCC model outperformed the second-best model, XGBoost based binary relevance model, by 3.3% in Hamming accuracy and 7.8% in F1-score. Additionally, we note that in the literature machine learning models applied to AMR prediction typically are unsuitable for identifying biomarkers informative of their decisions; in this study, we show that biomarkers contributing to AMR prediction can also be identified using the proposed RCC method. We expect this can facilitate genome annotation and pave the path towards identifying new biomarkers indicative of AMR.

Emerging Computational Methods in Mass Spectrometry Imaging

Mass spectrometry imaging (MSI) is a powerful analytical technique that generates maps of hundreds of molecules in biological samples with high sensitivity and molecular specificity. Advanced MSI platforms with capability of high-spatial resolution and high-throughput acquisition generate vast amount of data, which necessitates the development of computational tools for MSI data analysis. In addition, computation-driven MSI experiments have recently emerged as enabling technologies for further improving the MSI capabilities with little or no hardware modification. This review provides a critical summary of computational methods and resources developed for MSI data analysis and interpretation along with computational approaches for improving throughput and molecular coverage in MSI experiments. This review is focused on the recently developed artificial intelligence methods and provides an outlook for a future paradigm shift in MSI with transformative computational methods.

Advances in Intraoperative Flow Cytometry

Flow cytometry is the gold-standard laser-based technique to measure and analyze fluorescence levels of immunostaining and DNA content in individual cells. It provides a valuable tool to assess cells in the G0/G1, S, and G2/M phases, and those with polyploidy, which holds prognostic significance. Frozen section analysis is the standard intraoperative assessment for tumor margin evaluation and tumor resection. Here, we present flow cytometry as a promising technique for intraoperative tumor analysis in different pathologies, including brain tumors, leptomeningeal dissemination, breast cancer, head and neck cancer, pancreatic tumor, and hepatic cancer. Flow cytometry is a valuable tool that can provide substantial information on tumor analysis and, consequently, maximize cancer treatment and expedite patients’ survival.

Targeting non-structural proteins of Hepatitis C virus for predicting repurposed drugs using QSAR and machine learning approaches

Hepatitis C virus (HCV) infection causes viral hepatitis leading to hepatocellular carcinoma. Despite the clinical use of direct-acting antivirals (DAAs) still there is treatment failure in 5-10% cases. Therefore, it is crucial to develop new antivirals against HCV. In this endeavor, we developed the "Anti-HCV" platform using machine learning and quantitative structure-activity relationship (QSAR) approaches to predict repurposed drugs targeting HCV non-structural (NS) proteins. We retrieved experimentally validated small molecules from the ChEMBL database with bioactivity (IC50/EC50) against HCV NS3 (454), NS3/4A (495), NS5A (494) and NS5B (1671) proteins. These unique compounds were divided into training/testing and independent validation datasets. Relevant molecular descriptors and fingerprints were selected using a recursive feature elimination algorithm. Different machine learning techniques viz. support vector machine, k-nearest neighbour, artificial neural network, and random forest were used to develop the predictive models. We achieved Pearson's correlation coefficients from 0.80 to 0.92 during 10-fold cross validation and similar performance on independent datasets using the best developed models. The robustness and reliability of developed predictive models were also supported by applicability domain, chemical diversity and decoy datasets analyses. The "Anti-HCV" predictive models were used to identify potential repurposing drugs. Representative candidates were further validated by molecular docking which displayed high binding affinities. Hence, this study identified promising repurposed drugs viz. naftifine, butalbital (NS3), vinorelbine, epicriptine (NS3/4A), pipecuronium, trimethaphan (NS5A), olodaterol and vemurafenib (NS5B) etc. targeting HCV NS proteins. These potential repurposed drugs may prove useful in antiviral drug development against HCV.

Prediction of repurposed drugs for Coronaviruses using artificial intelligence and machine learning

The world is facing the COVID-19 pandemic caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). Likewise, other viruses of the Coronaviridae family were responsible for causing epidemics earlier. To tackle these viruses, there is a lack of approved antiviral drugs. Therefore, we have developed robust computational methods to predict the repurposed drugs using machine learning techniques namely Support Vector Machine, Random Forest, k-Nearest Neighbour, Artificial Neural Network, and Deep Learning. We used the experimentally validated drugs/chemicals with anticorona activity (IC50/EC50) from 'DrugRepV' repository. The unique entries of SARS-CoV-2 (142), SARS (221), MERS (123), and overall Coronaviruses (414) were subdivided into the training/testing and independent validation datasets, followed by the extraction of chemical/structural descriptors and fingerprints (17968). The highly relevant features were filtered using the recursive feature selection algorithm. The selected chemical descriptors were used to develop prediction models with Pearson's correlation coefficients ranging from 0.60 to 0.90 on training/testing. The robustness of the predictive models was further ensured using external independent validation datasets, decoy datasets, applicability domain, and chemical analyses. The developed models were used to predict promising repurposed drug candidates against coronaviruses after scanning the DrugBank. Top predicted molecules for SARS-CoV-2 were further validated by molecular docking against the spike protein complex with ACE receptor. We found potential repurposed drugs namely Verteporfin, Alatrofloxacin, Metergoline, Rescinnamine, Leuprolide, and Telotristat ethyl with high binding affinity. These 'anticorona' computational models would assist in antiviral drug discovery against SARS-CoV-2 and other Coronaviruses.

Identification of an early diagnostic biomarker of lung adenocarcinoma based on co-expression similarity and construction of a diagnostic model

Background

The purpose of this study was to achieve early and accurate diagnosis of lung cancer and long-term monitoring of the therapeutic response.

Methods

We downloaded GSE20189 from GEO database as analysis data. We also downloaded human lung adenocarcinoma RNA-seq transcriptome expression data from the TCGA database as validation data. Finally, the expression of all of the genes underwent z test normalization. We used ANOVA to identify differentially expressed genes specific to each stage, as well as the intersection between them. Two methods, correlation analysis and co-expression network analysis, were used to compare the expression patterns and topological properties of each stage. Using the functional quantification algorithm, we evaluated the functional level of each significantly enriched biological function under different stages. A machine-learning algorithm was used to screen out significant functions as features and to establish an early diagnosis model. Finally, survival analysis was used to verify the correlation between the outcome and the biomarkers that we found.

Results

We screened 12 significant biomarkers that could distinguish lung cancer patients with diverse risks. Patients carrying variations in these 12 genes also presented a poor outcome in terms of survival status compared with patients without variations.

Conclusions

We propose a new molecular-based noninvasive detection method. According to the expression of the stage-specific gene set in the peripheral blood of patients with lung cancer, the difference in the functional level is quantified to realize the early diagnosis and prediction of lung cancer.

CAMUR: Knowledge extraction from RNA-seq cancer data through equivalent classification rules

MOTIVATION

Nowadays, knowledge extraction methods from Next Generation Sequencing data are highly requested. In this work, we focus on RNA-seq gene expression analysis and specifically on case-control studies with rule-based supervised classification algorithms that build a model able to discriminate cases from controls. State of the art algorithms compute a single classification model that contains few features (genes). On the contrary, our goal is to elicit a higher amount of knowledge by computing many classification models, and therefore to identify most of the genes related to the predicted class.

RESULTS

We propose CAMUR, a new method that extracts multiple and equivalent classification models. CAMUR iteratively computes a rule-based classification model, calculates the power set of the genes present in the rules, iteratively eliminates those combinations from the data set, and performs again the classification procedure until a stopping criterion is verified. CAMUR includes an ad-hoc knowledge repository (database) and a querying tool.We analyze three different types of RNA-seq data sets (Breast, Head and Neck, and Stomach Cancer) from The Cancer Genome Atlas (TCGA) and we validate CAMUR and its models also on non-TCGA data. Our experimental results show the efficacy of CAMUR: we obtain several reliable equivalent classification models, from which the most frequent genes, their relationships, and the relation with a particular cancer are deduced.

AVAILABILITY AND IMPLEMENTATION

dmb.iasi.cnr.it/camur.php

CONTACT

emanuel@iasi.cnr.it

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.