Parkinson's Disease (PD) is the second most common neurodegenerative disease in humans. PD is characterized by the gradual loss of dopaminergic neurons in the Substantia Nigra (SN). Counting the number of dopaminergic neurons in the SN is one of the most important indexes in evaluating drug efficacy in PD animal models. Currently, analyzing and quantifying dopaminergic neurons is conducted manually by experts through analysis of digital pathology images which is laborious, time-consuming, and highly subjective. As such, a reliable and unbiased automated system is demanded for the quantification of dopaminergic neurons in digital pathology images. Recent years have seen a surge in adopting deep learning solutions in medical image processing. However, developing high-performing deep learning models hinges on the availability of large-scale, high-quality annotated data, which can be expensive to acquire, especially in applications like digital pathology image analysis. To this end, we propose an end-to-end deep learning framework based on self-supervised learning for the segmentation and quantification of dopaminergic neurons in PD animal models. To the best of our knowledge, this is the first deep learning model that detects the cell body of dopaminergic neurons, counts the number of dopaminergic neurons, and provides characteristics of individual dopaminergic neurons as a numerical output. Extensive experiments demonstrate the effectiveness of our model in quantifying neurons with high precision, which can provide a faster turnaround for drug efficacy studies, better understanding of dopaminergic neuronal health status, and unbiased results in PD pre-clinical research. As part of our contributions, we also provide the first publicly available dataset of histology digital images along with expert annotations for the segmentation of TH-positive DA neuronal soma.

This position is open to remote work within the US or onsite work at our headquarters in South San Francisco. Our working hours are 9-5pm PT. Freenome is a high-growth biotech company on a mission since 2014 to create tools that empower everyone to prevent, detect, and treat their disease. To achieve this mission, Freenome is developing next-generation blood tests to detect cancer in its earliest, most treatable stages using our multiomics platform and machine learning techniques. Our first blood test will detect early-stage colorectal cancer and advanced adenomas.

We investigate Siamese networks for learning related embeddings for augmented samples of molecular conformers. We find that a non-contrastive (positive-pair only) auxiliary task aids in supervised training of Euclidean neural networks (E3NNs) and increases manifold smoothness (MS) around point-cloud geometries. We demonstrate this property for multiple drug-activity prediction tasks while maintaining relevant performance metrics, and propose an extension of MS to probabilistic and regression settings. We provide an analysis of representation collapse, finding substantial effects of task-weighting, latent dimension, and regularization. We expect the presented protocol to aid in the development of reliable E3NNs from molecular conformers, even for small-data drug discovery programs. Modeling conformational shape is of critical importance in many molecular machine learning (MolML) tasks (Zheng et al., 2017).

As a chemistry PhD student, Dmytro Kolodieznyi was used to running experiments. But in early 2018, his research advisers asked him to take part in one run by robots instead. They wanted Kolodieznyi, who was developing intracellular fluorescent probes at Carnegie Mellon University in Pittsburgh, Pennsylvania, to spend a month attempting to recreate his research at Emerald Cloud Lab (ECL). The biotechnology company in South San Francisco, California, enables scientists to perform wet-laboratory experiments remotely in an automated research environment known as a cloud lab. If the trial went well, it would help pave the way to the wider use of cloud labs at the university.

As a chemistry PhD student, Dmytro Kolodieznyi was used to running experiments. But in early 2018, his research advisers asked him to take part in one run by robots instead. They wanted Kolodieznyi, who was developing intracellular fluorescent probes at Carnegie Mellon University in Pittsburgh, Pennsylvania, to spend a month attempting to recreate his research at Emerald Cloud Lab (ECL). The biotechnology company in South San Francisco, California, enables scientists to perform wet-laboratory experiments remotely in an automated research environment known as a cloud lab. If the trial went well, it would help pave the way to the wider use of cloud labs at the university.