Learning models for classifying Raman spectra of genomic DNA from tumor subtypes.

An early and accurate detection of different subtypes of tumors is crucial for an effective guidance to personalized therapy and in predicting the ability of tumor to metastasize. Here we exploit the Surface Enhanced Raman Scattering (SERS) platform, based on disordered silver coated silicon nanowires (Ag/SiNWs), to efficiently discriminate genomic DNA of different subtypes of melanoma and colon tumors. The diagnostic information is obtained by performing label free Raman maps of the dried drops of DNA solutions onto the Ag/NWs mat and leveraging the classification ability of learning models to reveal the specific and distinct physico-chemical interaction of tumor DNA molecules with the Ag/NW, here supposed to be partly caused by a different DNA methylation degree.

Statistical Classification for Raman Spectra of Tumoral Genomic DNA.

We exploit Surface-Enhanced Raman Scattering (SERS) to investigate aqueous droplets of genomic DNA deposited onto silver-coated silicon nanowires, and we show that it is possible to efficiently discriminate between spectra of tumoral and healthy cells. To assess the robustness of the proposed technique, we develop two different statistical approaches, one based on the Principal Components Analysis of spectral data and one based on the computation of the ℓ2 distance between spectra. Both methods prove to be highly efficient, and we test their accuracy via the Cohen's κ statistics. We show that the synergistic combination of the SERS spectroscopy and the statistical analysis methods leads to efficient and fast cancer diagnostic applications allowing rapid and unexpansive discrimination between healthy and tumoral genomic DNA alternative to the more complex and expensive DNA sequencing.

Spatio-temporal distribution pattern of COVID-19 in the Northern Italy during the first-wave scenario: The role of the highway network.

Background: The rapid outbreak of Coronavirus disease 2019 (COVID-19) has posed several challenges to the scientific community. The goal of this paper is to investigate the spread of COVID-19 in Northern Italy during the so-called first wave scenario and to provide a qualitative comparison with the local highway net. Methods: Fixed a grid of days from February 27, 2020, the cumulative numbers of infections in each considered province have been compared to sequences of thresholds. As a consequence, a time-evolving classification of the state of danger in terms of Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections, in view of the smallest threshold overtaken by this comparison, has been obtained for each considered province. The provinces with a significant amount of cases have then been collected into matrices containing only the ones featuring a significant amount of cases. Results: The time evolution of the classification has then been qualitatively compared to the highway network, to identify similarities and thus linking the rapid spreading of COVID-19 and the highway connections. Conclusions: The obtained results demonstrate how the proposed model properly fits with the spread of COVID-19 along with the Italian highway transport network and could be implemented to analyze qualitatively other disease transmissions in different contexts and time periods.