Studying how biological and symptom networks can improve our understanding of mental health and cognition.

Methods for turning transcriptomic and multi-omic data into reproducible, interpretable biological networks.

Combining network medicine, machine learning and experimental evidence to identify therapeutic opportunities.

Developing interpretable and generalizable AI approaches for molecular, clinical and population health data.

Connecting molecular interactions, disease mechanisms and clinical phenotypes to improve biomedical prediction.

State-of-the-art machine learning models in drug discovery fail to reliably predict the binding properties of poorly annotated proteins and small molecules. Here, the authors present AI-Bind, a machine learning pipeline to improve generalizability and interpretability of binding predictions.

The European green lizards of the Lacerta viridis complex consist of two closely related species, L. viridis and L. bilineata that split less than 7 million years ago in the presence of gene flow. Recently, a third lineage, referred to as the “Adriatic” was described within the L. viridis complex distributed from Slovenia to Greece.

The COVID-19 pandemic has highlighted the importance of prioritizing approved drugs to treat severe acute respiratory syndrome coronavirus (SARS-CoV-2) infections. Here, we deployed algorithms relying on artificial intelligence, network diffusion, and network proximity to rank 6,340 drugs for their expected efficacy against SARS-CoV-2.

A new analysis traces the story of the draft genome’s impact on genomics since 2001, linking its effects on publications, drug approvals and understanding of disease.

Marine fungi are an important component of pelagic planktonic communities. However, it is not yet clear how individual fungal taxa are integrated in marine processes of the microbial loop and food webs. Most likely, biotic interactions play a major role in shaping the fungal community structure.

Network approaches have become pervasive in many research fields. They allow for a more comprehensive understanding of complex relationships between entities as well as their group-level properties and dynamics.

Using RNA-induced-silencing-complex precipitation, we identified 98 high-confidence miR-124 targets, of which some directly led to decreased viability. By performing advanced transcription-factor-network analysis, we identified indirect miR-124 effects on apoptosis, neuronal subtype differentiation, and the regulation of previously uncharacterized zinc finger transcription factors.

Abstract Despite the importance of hand hygiene in the health care setting, there are no studies evaluating hand hygiene compliance at hospital entrances. The study was prospectively performed over a 33-week period from March 30, 2014-November 15, 2014, to evaluate hand hygiene compliance in 2 hospital reception areas. We compared electronic handwash counters with the application of radiofrequency identification (GOJO SMARTLINK) (electronic observer) that counts each activation of alcohol gel dispensers to direct observation (human observer) via remote review of video surveillance.