Collaborating Authors


Have You Heard? AI Can Edit Genes Now


Artificial intelligence does all kinds of things….genomics Genetic engineering has always been a go-to plot twist in sci-fi movies and TV shows. The idea of genetically mutated humans with superior abilities and unique DNAs still has ripple effects on Marvel fans and box offices. But what if we can alter genes in real life? CRISPR gene editing has been doing that since 2012 (no Wolverine or Magneto though). In 2022, this powerful genetic engineering technique is complemented with artificial intelligence.

Using deep learning to predict physical interactions of protein complexes


A 3D rendering of a protein complex structures predicted from protein sequences by AF2Complex. From the muscle fibers that move us to the enzymes that replicate our DNA, proteins are the molecular machinery that makes life possible. Protein function heavily depends on their three-dimensional structure, and researchers around the world have long endeavored to answer a seemingly simple inquiry to bridge function and form: if you know the building blocks of these molecular machines, can you predict how they are assembled into their functional shape? This question is not so easy to answer. With complex structures dependent on intricate physical interactions, researchers have turned to artificial neural network models – mathematical frameworks that convert complex patterns into numerical representations – to predict and "see" the shape of proteins in 3D.

A Smarter Way To Develop New Drugs Using Artificial Intelligence


MIT scientists have developed a machine learning model that proposes new molecules for the drug discovery process, while ensuring the molecules it suggests can actually be synthesized in a laboratory. A new artificial intelligence technique has been developed that only proposes candidate molecules that can actually be produced in a lab. Pharmaceutical companies are using artificial intelligence to streamline the process of discovering new medicines. Machine-learning models can propose new molecules that have specific properties which could fight certain diseases, accomplishing in minutes what might take humans months to achieve manually. But there's a major hurdle that holds these systems back: The models frequently suggest new molecular structures that are difficult or impossible to produce in a laboratory.

FDA Clears World's First AI-Driven Portable 3D Breast Ultrasound Scanner


This week iSono Health announced FDA clearance of the company's ATUSA System for breast imaging. This is world's first AI-driven portable and automated 3D breast ultrasound scanner. In just 2 minutes, the ATUSA system automatically scans the entire breast volume, independent of operator expertise, and offers 3D visualization of the breast tissue. The ATUSA system is designed from the ground up to seamlessly integrate with advanced machine learning models that will give physicians a comprehensive set of tools for decision making and patient management. This is the first of several intended FDA submissions for the company.

New machine learning maps the potentials of proteins


The biotech industry is constantly searching for the perfect mutation, where properties from different proteins are synthetically combined to achieve a desired effect. It may be necessary to develop new medicaments or enzymes that prolong the shelf-life of yogurt, break down plastics in the wild, or make washing powder effective at low water temperature. New research from DTU Compute and the Department of Computer Science at the University of Copenhagen (DIKU) can in the long term help the industry to accelerate the process. In the journal Nature Communications, the researchers explain how a new way of using Machine Learning (ML) draws a map of proteins, which makes it possible to appoint a candidate list of the proteins that you need to examine more closely. In recent years, we have started to use Machine Learning to form a picture of permitted mutations in proteins.

How A.I. Is Finding New Cures in Old Drugs


In the elegant quiet of the café at the Church of Sweden, a narrow Gothic-style building in Midtown Manhattan, Daniel Cohen is taking a break from explaining genetics. He moves toward the creaky piano positioned near the front door, sits down, and plays a flowing, flawless rendition of "Over the Rainbow." If human biology is the scientific equivalent of a complicated score, Cohen has learned how to navigate it like a virtuoso. Cohen was the driving force behind Généthon, the French laboratory that in December 1993 produced the first-ever "map" of the human genome. He essentially introduced Big Data and automation to the study of genomics, as he and his team demonstrated for the first time that it was possible to use super-fast computing to speed up the processing of DNA samples.

Multi-omics single-cell data integration and regulatory inference with graph-linked embedding - Nature Biotechnology


Despite the emergence of experimental methods for simultaneous measurement of multiple omics modalities in single cells, most single-cell datasets include only one modality. A major obstacle in integrating omics data from multiple modalities is that different omics layers typically have distinct feature spaces. Here, we propose a computational framework called GLUE (graph-linked unified embedding), which bridges the gap by modeling regulatory interactions across omics layers explicitly. Systematic benchmarking demonstrated that GLUE is more accurate, robust and scalable than state-of-the-art tools for heterogeneous single-cell multi-omics data. We applied GLUE to various challenging tasks, including triple-omics integration, integrative regulatory inference and multi-omics human cell atlas construction over millions of cells, where GLUE was able to correct previous annotations. GLUE features a modular design that can be flexibly extended and enhanced for new analysis tasks. The full package is available online at . Different single-cell data modalities are integrated at atlas-scale by modeling regulatory interactions.

Graph representation learning using node2vec on a toy biological data


A network or a graph is a representation to show the relationship between objects in a 2 dimensional or multidimensional space. The objects are called nodes and the relationship between the nodes are the edges in a graph. Two prominent examples of a graphical representation are a social network of individuals or a protein-protein interaction network. The graphical representation allows humans and computers to understand the underlying data more efficiently and adopt various algorithms for solving real-life problems. Learning a good representation of the graph data is called graph representation learning or network embedding.

What is The Role of Machine Learning in Bio-Technology?


Machine Learning and Artificial Intelligence have taken the world by storm, changing the way people live and work. Advances in these fields have elicited both praise and criticism. AI and ML, as they're colloquially known, offer several applications and advantages across a wide range of sectors. Most importantly, they are transforming biological research, resulting in new discoveries in healthcare and biotechnology. Next-generation sequencing has greatly improved the study of genomics by sequencing a gene in a short period of time. As a result, the machine learning approach is being used to discover gene coding areas in a genome.

AI, ML, & Cybersecurity: Here's What FDA May Soon Be Asking


FDA has released a number of documents that could help clarify its expectations for artificial intelligence, machine learning, and cybersecurity. These include Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) Action Plan, published in January 2021; Good Machine Learning Practice for Medical Device Development: Guiding Principles, published in October 2021; and the just-released draft guidance, Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions. The AI/ML action plan provides a "more tailored regulatory framework for AI/ML," explained Pavlovic. She referred to FDA's 2019 discussion paper, Proposed Regulatory Framework for Modifications to Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) - Discussion Paper and Request for Feedback, which laid out a "total product lifecycle approach to AI/ML regulations with the understanding that AI/ML products can be iterated much more efficiently and quickly than a typical medical device implant product or something that isn't software based." This is "because there is an opportunity to add additional data to training sets on which the products were originally formulated," she said.