The approval success rate of drug candidates is very low with the majority of failure due to safety and efficacy. Increasingly available high dimensional information on targets, drug molecules and indications provides an opportunity for ML methods to integrate multiple data modalities and better predict clinically promising drug targets. Notably, drug targets with human genetics evidence are shown to have better odds to succeed. However, a recent tensor factorization-based approach found that additional information on targets and indications might not necessarily improve the predictive accuracy. Here we revisit this approach by integrating different types of human genetics evidence collated from publicly available sources to support each target-indication pair. We use Bayesian tensor factorization to show that models incorporating all available human genetics evidence (rare disease, gene burden, common disease) modestly improves the clinical outcome prediction over models using single line of genetics evidence. We provide additional insight into the relative predictive power of different types of human genetics evidence for predicting the success of clinical outcomes.

Product-specific guidances (PSGs) recommended by the United States Food and Drug Administration (FDA) are instrumental to promote and guide generic drug product development. To assess a PSG, the FDA assessor needs to take extensive time and effort to manually retrieve supportive drug information of absorption, distribution, metabolism, and excretion (ADME) from the reference listed drug labeling. In this work, we leveraged the state-of-the-art pre-trained language models to automatically label the ADME paragraphs in the pharmacokinetics section from the FDA-approved drug labeling to facilitate PSG assessment. We applied a transfer learning approach by fine-tuning the pre-trained Bidirectional Encoder Representations from Transformers (BERT) model to develop a novel application of ADME semantic labeling, which can automatically retrieve ADME paragraphs from drug labeling instead of manual work. We demonstrated that fine-tuning the pre-trained BERT model can outperform the conventional machine learning techniques, achieving up to 11.6% absolute F1 improvement. To our knowledge, we were the first to successfully apply BERT to solve the ADME semantic labeling task. We further assessed the relative contribution of pre-training and fine-tuning to the overall performance of the BERT model in the ADME semantic labeling task using a series of analysis methods such as attention similarity and layer-based ablations. Our analysis revealed that the information learned via fine-tuning is focused on task-specific knowledge in the top layers of the BERT, whereas the benefit from the pre-trained BERT model is from the bottom layers.

Esther Shein is a freelance technology and business writer based in the Boston area.

This is our AI Daily Roundup today. We are covering the top updates from around the world. The updates will feature state-of-the-art capabilities in artificial intelligence (AI), Machine Learning, Robotic Process Automation, Fintech, and human-system interactions. We cover the role of AI Daily Roundup and its application in various industries and daily lives. Businesses are immensely benefiting from AI adoption.

Robotic microsurgery company Medical Microinstruments announced today that it raised $75 million in a Series B financing round. Pisa, Italy–based Medical Microinstruments plans to use proceeds from the financing round, along with its planned U.S. presence, to move into its next stage of growth through expanded indications and ongoing commercialization efforts for its Symani microsurgery system. The company designed Symani to address the challenges of microsurgery with the NanoWrist instruments for accessing and suturing small, delicate anatomy, such as veins, arteries, nerves and lymphatic vessels as small as 0.3mm in diameter. It provides motion scaling and tremor reduction to allow precise micro-movements. Symani received CE mark in 2019, and the company intends to accelerate commercialization in the U.S. and Asia-Pacific, as well as advance clinical research through an FDA investigational device exemption (IDE) pivotal study.

プログラム医療機器におけるAI規制の小さなステップ｜ニュース&コラム｜品質マネジメントシステム（QMS）の文書管理・教育管理・品質管理ソフトウェアならQMSソリューションとして世界トップシェアのマスターコントロールにご相談下さい。文書管理や教育管理、品質管理などの品質マネジメントシステムを初めて導入される方に最適なソリューションをご提案致します。

Classification on long-tailed distributed data is a challenging problem, which suffers from serious class-imbalance and hence poor performance on tail classes with only a few samples. Owing to this paucity of samples, learning on the tail classes is especially challenging for the fine-tuning when transferring a pretrained model to a downstream task. In this work, we present a simple modification of standard fine-tuning to cope with these challenges. Specifically, we propose a two-stage fine-tuning: we first fine-tune the final layer of the pretrained model with class-balanced reweighting loss, and then we perform the standard fine-tuning. Our modification has several benefits: (1) it leverages pretrained representations by only fine-tuning a small portion of the model parameters while keeping the rest untouched; (2) it allows the model to learn an initial representation of the specific task; and importantly (3) it protects the learning of tail classes from being at a disadvantage during the model updating. We conduct extensive experiments on synthetic datasets of both two-class and multi-class tasks of text classification as well as a real-world application to ADME (i.e., absorption, distribution, metabolism, and excretion) semantic labeling. The experimental results show that the proposed two-stage fine-tuning outperforms both fine-tuning with conventional loss and fine-tuning with a reweighting loss on the above datasets.

A 48-year-old patient in New York City who is unable to move and speak due to severe paralysis from ALS became the first to receive a permanent brain implant that could allow him to communicate telepathically - a milestone for Synchron, the startup behind the technology, which beat Elon Musk's Neuralink to the punch with its advance. The procedure took place July 6 at Mount Sinai West medical center in Manhattan, where a 1.5-inch long implant - a brain-computer interface (BCI) as a stentrode - made of wires and electrodes was implanted into the patient's brain without the need for cutting into their skull or damaging tissue. 'The first-in-human implant of an endovascular BCI in the U.S. is a major clinical milestone that opens up new possibilities for patients with paralysis,' said Dr. Tom Oxley, CEO & Founder of Synchron, in a statement. 'The first-in-human implant of an endovascular BCI in the U.S. is a major clinical milestone that opens up new possibilities for patients with paralysis,' said Dr. Tom Oxley, CEO & Founder of Synchron, in a statement. 'Our technology is for the millions of people who have lost the ability to use their hands to control digital devices.

Brain-computer interfaces have become a practical (if limited) reality in the US. Synchron says it has become the first in the country to implant a BCI in a human patient. Doctors in New York's Mount Sinai West implanted the company's Stentrode in the motor cortex of a participant in Synchron's COMMAND trial, which aims to gauge the usefulness and safety of BCIs for providing hands-free device control to people with severe paralysis. Ideally, technology like Stentrode will offer independence to people who want to email, text and otherwise handle digital tasks that others take for granted. Surgeons installed the implant using an endovascular procedure that avoids the intrusiveness of open-brain surgery by going through the jugular vein.

INTRODUCTION: The Center for Devices and Radiological Health (CDRH or Center), as the scientific and regulatory component of the U.S. Food and Drug Administration (FDA) charged with facilitating and ensuring medical device innovation, safety, and effectiveness, and advancing regulatory science is now accepting applications for a Staff Fellow (Senior Data Engineer) to serve in the Office of Clinical Evidence and Analysis (OCEA or Office). OCEA oversees the application of modern artificial intelligence tools, including machine learning and deep learning methodologies, that can be evaluated, piloted, and implemented at scale by CDRH to help the Center evaluate clinical evidence and other device-related data to more efficiently conduct regulatory review activities in support of the Center's mission. POSITION SUMMARY: OCEA is seeking a Staff Fellow (Senior Data Engineer) to develop and build the infrastructure and tools for exciting new technologies. The Staff Fellow will design and build Amazon Web Services (AWS) applications and data pipeline services that work at scale to support new data analytics products and also enable development workflows. This will require the automated deployment of microservices and data tools for high-throughput stream processing.