Automatic discovery of 100-miRNA signature for cancer classification using ensemble feature selection

Abstract

Background MicroRNAs (miRNAs) are noncoding RNA molecules heavily involved in human tumors, in which few of them circulating the human body. Finding a tumor-associated signature of miRNA, that is, the minimum miRNA entities to be measured for discriminating both different types of cancer and normal tissues, is of utmost importance. Feature selection techniques applied in machine learning can help however they often provide naive or biased results. Results An ensemble feature selection strategy for miRNA signatures is proposed. miRNAs are chosen based on consensus on feature relevance from high-accuracy classifiers of different typologies. This methodology aims to identify signatures that are considerably more robust and reliable when used in clinically relevant prediction tasks. Using the proposed method, a 100-miRNA signature is identified in a dataset of 8023 samples, extracted from TCGA. When running eight-state-of-the-art classifiers along with the 100-miRNA signature against the original 1046 features, it could be detected that global accuracy differs only by 1.4%. Importantly, this 100-miRNA signature is sufficient to distinguish between tumor and normal tissues. The approach is then compared against other feature selection methods, such as UFS, RFE, EN, LASSO, Genetic Algorithms, and EFS-CLA. The proposed approach provides better accuracy when tested on a 10-fold cross-validation with different classifiers and it is applied to several GEO datasets across different platforms with some classifiers showing more than 90% classification accuracy, which proves its cross-platform applicability. Conclusions The 100-miRNA signature is sufficiently stable to provide almost the same classification accuracy as the complete TCGA dataset, and it is further validated on several GEO datasets, across different types of cancer and platforms. Furthermore, a bibliographic analysis confirms that 77 out of the 100 miRNAs in the signature appear in lists of circulating miRNAs used in cancer studies, in stem-loop or mature-sequence form. The remaining 23 miRNAs offer potentially promising avenues for future research.

Classification and Specific Primer Design for Accurate Detection of SARS-CoV-2 Using Deep Learning

“…This leaves us with a frequency table of 3,827 features (21-bps sequences) with 583 samples (Table 3 (left)). Next, we ran a state-of-the-art feature selection algorithm 37,38 , to reduce the sequences needed to identify different virus strain to the bare minimum. Remarkably, we are then able to correctly differentiate all the coronavirus (MERS-CoV, SARS-CoV-2, SARS-CoV-1, etc) samples using only 53 of the original 3,827 sequences, obtaining a 100% accuracy in a 10-fold cross-validation with a simpler and more traditional classifier, such as Logistic Regression.…”

“…We call this dataset NCBI-A, where 68 sequences belong to SARS-CoV-2. Then, we applied the procedure to translate the data into the set of sequence features, and we run the same state-of-the-art feature selection algorithm 37 . The result is a list of 10 different sequences (Table 4), for which just checking for their presence is enough to differentiate between SARS-CoV-2 and other viruses in the dataset, with a 100% accuracy.…”

“…The query returns 20,603 samples, of which only 32 belong to SARS-CoV-2, and 20,571 are from other taxa, including Hepatitis B, Dengue, Human immunodeficiency, Human orthopneumovirus, Enterovirus A, Hepacivirus C, Chikungunya virus, Zaire ebolavirus, Human respirovirus 3, Orthohepevirus A, Norovirus GII, Hepatitis delta virus, Mumps rubulavirus, Enterovirus D, Zika virus, Measles morbillivirus, Enterovirus C, Human T-cell leukemia virus type I, Yellow fever virus, Adeno-associated virus, rhinovirus (A, B and C), for a total of more than 900 viruses. Then, we applied the procedure to translate the data into the sequence feature space and run the feature reduction algorithm 37 . This results in 2 extra sequences of 21 bps: just by checking for their presence, we are able to separate SARS-CoV-2 from the rest of the samples with a 100% accuracy.…”

Update on uveal melanoma: Translational research from biology to clinical practice (Review)

“…For example, it is known that miRNAs are a key epigenetic mechanism for the control of gene transcription and may act in some cancer types as tumour suppressors and in others as oncogenes (136,137). In effect, miRNAs are emerging as promising therapeutic targets in various types of cancer and as ever more reliable prognostic factors in individualized precision medicine (138,139). The roles of miRNAs in uveal melanoma as important prognostic and diagnostic markers of tumour onset and progression have been confirmed (140).…”

A Missense Mutation in SARS-CoV-2 Potentially Differentiates Between Asymptomatic and Symptomatic Cases

“…With the CNN, we uncovered 18,258 features (21-bps length sequences) that allow the network to differentiate between symptomatic and asymptomatic patients. From these features, we ran a feature reduction algorithm [4] to find the 21-bps sequences that gave the maximum mean accuracy using 8 different classifiers (Gradient Boosting, Passive Aggressive, Logistic Regression, Support Vector, Random Forest, Stochastic Gradient Descent, Ridge and Bagging) from the scikit-learn toolbox [5], ultimately obtaining 53 meaningful 21-bps sequences ( Fig.1) with a global accuracy of 97.05%. Fig.…”