Predicting gene expression levels from DNA sequences and post-transcriptional information with transformers.

BACKGROUND AND OBJECTIVES: In the latest years, the prediction of gene expression levels has been crucial due to its potential applications in the clinics. In this context, Xpresso and others methods based on Convolutional Neural Networks and Transformers were firstly proposed to this aim. However, all these methods embed data with a standard one-hot encoding algorithm, resulting in impressively sparse matrices. In addition, post-transcriptional regulation processes, which are of uttermost importance in the gene expression process, are not considered in the model. METHODS: This paper presents Transformer DeepLncLoc, a novel method to predict the abundance of the mRNA (i.e., gene expression levels) by processing gene promoter sequences, managing the problem as a regression task. The model exploits a transformer-based architecture, introducing the DeepLncLoc method to perform the data embedding. Since DeepLncloc is based on word2vec algorithm, it avoids the sparse matrices problem. RESULTS: Post-transcriptional information related to mRNA stability and transcription factors is included in the model, leading to significantly improved performances compared to the state-of-the-art works. Transformer DeepLncLoc reached 0.76 of R2 evaluation metric compared to 0.74 of Xpresso. CONCLUSION: The Multi-Headed Attention mechanisms which characterizes the transformer methodology is suitable for modeling the interactions between DNA's locations, overcoming the recurrent models. Finally, the integration of the transcription factors data in the pipeline leads to impressive gains in predictive power.

Predictive deconvolution and hybrid feature selection for computer-aided detection of prostate cancer.

Computer-aided detection (CAD) schemes are decision making support tools, useful to overcome limitations of problematic clinical procedures. Trans-rectal ultrasound image based CAD would be extremely important to support prostate cancer diagnosis. An effective approach to realize a CAD scheme for this purpose is described in this work, employing a multi-feature kernel classification model based on generalized discriminant analysis. The mutual information of feature value and tissue pathological state is used to select features essential for tissue characterization. System-dependent effects are reduced through predictive deconvolution of the acquired radio-frequency signals. A clinical study, performed on ground truth images from biopsy findings, provides a comparison of the classification model applied before and after deconvolution, showing in the latter case a significant gain in accuracy and area under the receiver operating characteristic curve.

A reduced complexity estimation algorithm for ultrasound images de-blurring.

In this paper we propose a deconvolution technique for ultrasound images based on a Maximum Likelihood (ML) estimation procedure. In our approach the ultrasonic radio-frequency (RF) signal is considered as a sequence affected by Intersymbol Interference (ISI) and AWG noise. In order to reduce the computational cost, the estimation is performed with a reduced-state Viterbi algorithm. The channel effect is estimated in two different ways: either measuring the transducer response with an experimental setting or with blind homomorphic techniques. We observed an enhancement in image quality with respect to different metrics. Extensive tests were made to estimate the quantization alphabet that gives the best performances.