Phys .org: New algorithm allows for faster, animal-free chemical toxicity testing

Phys .org: New algorithm allows for faster, animal-free chemical toxicity testing. “The use of animals to test the toxicity of chemicals may one day become outdated thanks to a low-cost, high-speed algorithm developed by researchers at Rutgers and other universities.”

Nature: Cancer geneticists tackle troubling ethnic bias in studies

Nature: Cancer geneticists tackle troubling ethnic bias in studies. “… most studies and genetic databases are populated mainly by data from people of European descent. This knowledge gap exacerbates disparities in cancer incidence and outcomes around the world. In the United States, for example, African American men are about twice as likely as white men to die of prostate cancer. But researchers who study these inequities say they are encouraged by renewed interest in closing the data gap from their colleagues and funders, including the US government.”

IDEALS @ Illinois: How comprehensive is the PubMed Central Open Access full-text database?

IDEALS @ Illinois: How comprehensive is the PubMed Central Open Access full-text database? (this link goes to a PDF.) “The comprehensiveness of database is a prerequisite for the quality of scientific works established on this increasingly significant infrastructure. This is especially so for large-scale text-mining analyses of scientific publications facilitated by open-access full-text scientific databases. Given the lack of research concerning the comprehensiveness of this type of academic resource, we conducted a project to analyze the coverage of materials in the PubMed Central Open Access Subset (PMCOAS), a popular source for open-access scientific publications, in terms of the PubMed database. The preliminary results show that the PMCOAS coverage is in a rapid increase in recent years, despite the vast difference by MeSH descriptor.”

Phys .org: Researchers use algorithm from Netflix challenge to speed up biological imaging

Phys .org: Researchers use algorithm from Netflix challenge to speed up biological imaging. “Researchers have repurposed an algorithm originally developed for Netflix’s 2009 movie preference prediction competition to create a method for acquiring classical Raman spectroscopy images of biological tissues at unprecedented speeds. The advance could make the simple, label-free imaging method practical for clinical applications such as tumor detection or tissue analysis.”

Boston University School of Medicine: New Open-Source Bioinformatics Tool Identifies Factors Responsible for Diseases

Boston University School of Medicine: New Open-Source Bioinformatics Tool Identifies Factors Responsible for Diseases. “Researchers have developed and tested a new computational tool, Candidate Driver Analysis (CaDrA), which will search for combinations of factors that are likely to cause a specific disease. CaDrA recognizes that diseases are complex and likely induced by multiple causes. It is now available free to members of the research community. To measure CaDrA’s ability to select sets of genomic features that are responsible for certain oncogenic phenotypes in cancer, the researchers performed extensive evaluations based on simulated data, as well as real genomic data from cancer cell lines and primary human tumors. The results from their simulations showed CaDrA has high sensitivity for mid- to large-sized datasets, and high specificity for all sample sizes considered.”

TechCrunch: Update regulations on medical AI, experts plead

TechCrunch: Update regulations on medical AI, experts plead . “The field of medicine is, like other industries and disciplines, in the process of incorporating AI as a standard tool, and it stands to be immensely useful — if it’s properly regulated, argue researchers. Without meaningful and standardized rules, it will be difficult to quantify benefits or prevent disasters issuing from systematic bias or poor implementation.”

MIT Technology Review: AI is reinventing the way we invent

MIT Technology Review: AI is reinventing the way we invent. “Regina Barzilay’s office at MIT affords a clear view of the Novartis Institutes for Biomedical Research. Amgen’s drug discovery group is a few blocks beyond that. Until recently, Barzilay, one of the world’s leading researchers in artificial intelligence, hadn’t given much thought to these nearby buildings full of chemists and biologists. But as AI and machine learning began to perform ever more impressive feats in image recognition and language comprehension, she began to wonder: could it also transform the task of finding new drugs?”