IBM Research lab in Zurich Open-Sourced three AI Projects to help accelerate cancer research.
The first project named PaccMann (Prediction of anticancer compound sensitivity with Multi-modal attention-based neural networks), is a multimodal deep learning solution that uses data from disparate sources to help predict how cells in diseased tissue will respond to a given drug. They applied PaccMann to predict the sensitivity of cancer cell lines to known drugs, achieving a superior predictive power compared to existing algorithms.
The second project named INtERAcT (Interaction Network infErence from vectoR representATions of words) is a novel approach to extract information on protein-protein interactions from scientific papers in a completely unsupervised way.
INtERAcT leverages the concept of word embeddings process text from a large body of biomedical publications and defines new metric to quantify the interactions between proteins. The most remarkable feature of INtERAcT is that no annotation or manual curation of the text is needed. A particular strength of INtERAcT is its capability to infer interactions in the context of a specific disease. The comparison with the normal interactions in healthy tissue may potentially help to obtain insight into the disease mechanisms.
The third project named PIMKL (pathway-induced multiple kernel learning), is a new machine learning algorithm that can produce highly predictive performance and interpretability in predicting phenotypes based on molecular data. PIMKL enables this by exploiting prior knowledge on molecular interactions.
Using a machine learning technique known as multiple kernel learning, PIMKL identifies molecular pathways that are important for the classification of patient groups. The insights on differences between patient groups provided, thanks to the interpretability of the model, could therefore lead to better understanding of cancer progression.
References:
Related Articles in News
If you often find yourself overwhelmed with the amount of content available on the internet and struggle to keep up, take a look at Wallabag. This exceptional web application provides a solution to your content overload by allowing you to save web pages for reading at a later time.
With
What is Huntly?
Huntly is an all-in-one, self-hosted information management tool that provides a plethora of features designed to streamline and simplify your data management needs. It includes the ability to subscribe to and read RSS feeds, thereby keeping you updated with the latest news and articles from your favorite
What is Hacker News?
Hacker News is a social news website focusing on computer science and entrepreneurship. It is run by Y Combinator, a seed accelerator. Users can submit stories (links to articles), and other users can upvote these stories, similar to "liking" a post on other social
Z Combinator is a free Hacker News client made with SwiftUI that allows users to log in with their Hacker News account, reply to stories and comments, vote on stories and comments, and add stories and comments to their pins or HN.
Features
* Log in with Hacker News account
* Reply
Hacki is a Hacker News client built with Flutter. It allows users to log in with their Hacker News account, browse stories from various categories, search for stories, submit stories, and pin stories.
Features
* Fast and lightweight app
* Log in using your Hacker News account.
* Browse stories from various categories.
HNClient is a free and open-source desktop client for Hacker News that allows users to read articles and comments without opening multiple tabs.
It features a sidebar for article selection and supports split-screen viewing of articles and their comments. The app is compatible with Mac, Linux, and Windows.
Features
* Sidebar
What is a News Aggregator
A news aggregator is a tool or platform that collects news from various sources and presents them in one location. It is used for conveniently accessing and reading news from multiple sources without having to visit each source individually.
In this list, we collected the
Hacker News Summary is an open-source project that uses AI technology, primarily the ChatGPT gpt-3.5-turbo model, to extract summaries and illustrations from Hacker News articles.
If ChatGPT is unavailable, the local GoogleT5 model is used. The service provides clear and easily understandable summaries.
Features
* Clear and easily understandable summaries
Germany's Federal Ministry for Digital and Transport Affairs has drafted a bill requiring mandatory end-to-end encryption for messengers and cloud services, a move celebrated by cryptography experts and privacy enthusiasts for protecting digital correspondence.
The "right to encryption" law, proposed by the German government, refers to
news-please is an open-source news crawler that extracts structured information from news websites. It uses libraries like scrapy, Newspaper, and readability, and can follow internal hyperlinks and read RSS feeds to fetch both recent and archived articles.
It also features a library mode for Python developers and can extract articles