Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Learning on-top: Regressing the on-top pair density for real-space visualization of electron correlation.

In The Journal of chemical physics

The on-top pair density [Πr] is a local quantum-chemical property that reflects the probability of two electrons of any spin to occupy the same position in space. Being the simplest quantity related to the two-particle density matrix, the on-top pair density is a powerful indicator of electron correlation effects, and as such, it has been extensively used to combine density functional theory and multireference wavefunction theory. The widespread application of Π(r) is currently hindered by the need for post-Hartree-Fock or multireference computations for its accurate evaluation. In this work, we propose the construction of a machine learning model capable of predicting the complete active space self-consistent field (CASSCF)-quality on-top pair density of a molecule only from its structure and composition. Our model, trained on the GDB11-AD-3165 database, is able to predict with minimal error the on-top pair density of organic molecules, bypassing completely the need for ab initio computations. The accuracy of the regression is demonstrated using the on-top ratio as a visual metric of electron correlation effects and bond-breaking in real-space. In addition, we report the construction of a specialized basis set, built to fit the on-top pair density in a single atom-centered expansion. This basis, cornerstone of the regression, could be potentially used also in the same spirit of the resolution-of-the-identity approximation for the electron density.

Fabrizio Alberto, Briling Ksenia R, Girardier David D, Corminboeuf Clemence


General General

Towards real-world objective speech quality and intelligibility assessment using speech-enhancement residuals and convolutional long short-term memory networks.

In The Journal of the Acoustical Society of America

Objective metrics, such as the perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and signal-to-distortion ratio (SDR), are often used for evaluating speech. These metrics are intrusive since they require a reference (clean) speech signal to complete the evaluation. The need for a reference signal reduces the practicality of these metrics, since a clean reference signal is not typically available during real-world testing. In this paper, a two-stage approach is presented that estimates the objective score of these intrusive metrics in a non-intrusive manner, which enables testing in real-world environments. More specifically, objective score estimation is treated as a machine-learning problem, and the use of speech-enhancement residuals and convolutional long short-term memory (SER-CL) networks is proposed to blindly estimate the objective scores (i.e., PESQ, STOI, and SDR) of various speech signals. The approach is evaluated in simulated and real environments that contain different combinations of noise and reverberation. The results reveal that the proposed approach is a reasonable alternative for evaluating speech, where it performs well in terms of accuracy and correlation. The proposed approach also outperforms comparison approaches in several environments.

Dong Xuan, Williamson Donald S


oncology Oncology

Hsa-miR-375/RASD1 Signaling May Predict Local Control in Early Breast Cancer.

In Genes

BACKGROUND : In order to characterize the various subtypes of breast cancer more precisely and improve patients selection for breast conserving therapy (BCT), molecular profiling has gained importance over the past two decades. MicroRNAs, which are small non-coding RNAs, can potentially regulate numerous downstream target molecules and thereby interfere in carcinogenesis and treatment response via multiple pathways. The aim of the current two-phase study was to investigate whether hsa-miR-375-signaling through RASD1 could predict local control (LC) in early breast cancer.

RESULTS : The patient and treatment characteristics of 81 individuals were similarly distributed between relapse (n = 27) and control groups (n = 54). In the pilot phase, the primary tumors of 28 patients were analyzed with microarray technology. Of the more than 70,000 genes on the chip, 104 potential hsa-miR-375 target molecules were found to have a lower expression level in relapse patients compared to controls (p-value < 0.2). For RASD1, a hsa-miR-375 binding site was predicted by an in silico search in five mRNA-miRNA databases and mechanistically proven in previous pre-clinical studies. Its expression levels were markedly lower in relapse patients than in controls (p-value of 0.058). In a second phase, this finding could be validated in an independent set of 53 patients using ddPCR. Patients with enhanced levels of hsa-miR-375 compared to RASD1 had a higher probability of local relapse than those with the inverse expression pattern of the two markers (log-rank test, p-value = 0.069).

CONCLUSION : This two-phase study demonstrates that hsa-miR-375/RASD1 signaling is able to predict local control in early breast cancer patients, which-to our knowledge-is the first clinical report on a miR combined with one of its downstream target proteins predicting LC in breast cancer.

Zellinger Barbara, Bodenhofer Ulrich, Engländer Immanuela A, Kronberger Cornelia, Strasser Peter, Grambozov Brane, Fastner Gerd, Stana Markus, Reitsamer Roland, Sotlar Karl, Sedlmayer Felix, Zehentmayr Franz


RASD1, early stage breast cancer, hsa-miR-375, local control, predictive markers

General General

An Improved, Assay Platform Agnostic, Absolute Single Sample Breast Cancer Subtype Classifier.

In Cancers

While intrinsic molecular subtypes provide important biological classification of breast cancer, the subtype assignment of individuals is influenced by assay technology and study cohort composition. We sought to develop a platform-independent absolute single-sample subtype classifier based on a minimal number of genes. Pairwise ratios for subtype-specific differentially expressed genes from un-normalized expression data from 432 breast cancer (BC) samples of The Cancer Genome Atlas (TCGA) were used as inputs for machine learning. The subtype classifier with the fewest number of genes and maximal classification power was selected during cross-validation. The final model was evaluated on 5816 samples from 10 independent studies profiled with four different assay platforms. Upon cross-validation within the TCGA cohort, a random forest classifier (MiniABS) with 11 genes achieved the best accuracy of 88.2%. Applying MiniABS to five validation sets of RNA-seq and microarray data showed an average accuracy of 85.15% (vs. 77.72% for Absolute Intrinsic Molecular Subtype (AIMS)). Only MiniABS could be applied to five low-throughput datasets, showing an average accuracy of 87.93%. The MiniABS can absolutely subtype BC using the raw expression levels of only 11 genes, regardless of assay platform, with higher accuracy than existing methods.

Seo Mi-Kyoung, Paik Soonmyung, Kim Sangwoo


breast cancer, classifier, machine learning, optimization, subtyping

Ophthalmology Ophthalmology

Anterior Chamber Angle Assessment Techniques: A Review.

In Journal of clinical medicine

Assessment of the anterior chamber angle (ACA) is an essential part of the ophthalmological examination. It is intrinsically related to the diagnosis and treatment of glaucoma and has a role in its prevention. Although slit-lamp gonioscopy is considered the gold-standard technique for ACA evaluation, its poor reproducibility and the long learning curve are well-known shortcomings. Several new imaging techniques for angle evaluation have been developed in the recent years. However, whether these instruments may replace or not gonioscopy in everyday clinical practice remains unclear. This review summarizes the last findings in ACA evaluation, focusing on new instruments and their application to the clinical practice. Special attention will be given to the comparison between these new techniques and traditional slit-lamp gonioscopy. Whereas ultrasound biomicroscopy and anterior segment optical coherence tomography provide quantitative measurements of the anterior segment's structures, new gonio-photographic systems allow for a qualitative assessment of angle findings, similarly to gonioscopy. Recently developed deep learning algorithms provide an automated classification of angle images, aiding physicians in taking faster and more efficient decisions. Despite new imaging techniques made analysis of the ACA more objective and practical, the ideal method for ACA evaluation has still to be determined.

Riva Ivano, Micheletti Eleonora, Oddone Francesco, Bruttini Carlo, Montescani Silvia, De Angelis Giovanni, Rovati Luigi, Weinreb Robert N, Quaranta Luciano


angle closure glaucoma, anterior chamber angle, diagnosis, iridocorneal angle, trabecular meshwork

Public Health Public Health

Anxiety in neurosurgical patients undergoing nonurgent surgery during the COVID-19 pandemic.

In Neurosurgical focus ; h5-index 45.0

OBJECTIVE : The COVID-19 pandemic has forced many countries into lockdown and has led to the postponement of nonurgent neurosurgical procedures. Although stress has been investigated during this pandemic, there are no reports on anxiety in neurosurgical patients undergoing nonurgent surgical procedures.

METHODS : Neurosurgical patients admitted to hospitals in eastern Lombardy for nonurgent surgery after the lockdown prospectively completed a pre- and postoperative structured questionnaire. Recorded data included demographics, pathology, time on surgical waiting list, anxiety related to COVID-19, primary pathology and surgery, safety perception during hospital admission before and after surgery, and surgical outcomes. Anxiety was measured with the State-Trait Anxiety Inventory. Descriptive statistics were computed on the different variables and data were stratified according to pathology (oncological vs nononcological). Three different models were used to investigate which variables had the greatest impact on anxiety, oncological patients, and safety perception, respectively. Because the variables (Xs) were of a different nature (qualitative and quantitative), mostly asymmetrical, and related to outcome (Y) by nonlinear relationships, a machine learning approach composed of three steps (1, random forest growing; 2, relative variable importance measure; and 3, partial dependence plots) was chosen.

RESULTS : One hundred twenty-three patients from 10 different hospitals were included in the study. None of the patients developed COVID-19 after surgery. State and trait anxiety were reported by 30.3% and 18.9% of patients, respectively. Higher values of state anxiety were documented in oncological compared to nononcological patients (46.7% vs 25%; p = 0.055). Anxiety was strongly associated with worry about primary pathology, surgery, disease worsening, and with stress during waiting time, as expected. Worry about positivity to SARS-CoV-2, however, was the strongest factor associated with anxiety, even though none of the patients were infected. Neuro-oncological disease was associated with state anxiety and with worry about surgery and COVID-19. Increased bed distance and availability of hand sanitizer were associated with a feeling of safety.

CONCLUSIONS : These data underline the importance of psychological support, especially for neuro-oncological patients, during a pandemic.

Doglietto Francesco, Vezzoli Marika, Biroli Antonio, Saraceno Giorgio, Zanin Luca, Pertichetti Marta, Calza Stefano, Agosti Edoardo, Aliaga Arias Jahard Mijail, Assietti Roberto, Bellocchi Silvio, Bernucci Claudio, Bistazzoni Simona, Bongetta Daniele, Fanti Andrea, Fioravanti Antonio, Fiorindi Alessandro, Franzin Alberto, Locatelli Davide, Pugliese Raffaelino, Roca Elena, Sicuri Giovanni Marco, Stefini Roberto, Venturini Martina, Vivaldi Oscar, Zattra Costanza, Zoia Cesare, Fontanella Marco Maria


anxiety, machine learning, pandemic