AI System to Create Drugs From Scratch

ReLeaSE (Reinforcement Learning for Structural Evolution) system can speed up the emergence of new medicines
03 August 2018   958

Scientists of the pharmaceutical school Chapel Hill Eshelman based at the University of North Carolina have developed a system called ReLeaSE, which can create molecules of drugs "from scratch". This can speed up the emergence of new medicines.

ReLeaSE (Reinforcement Learning for Structural Evolution) is a computer program consisting of two neural networks, which can be conditionally called a "student" and a "teacher". The algorithm works as follows:

  1. "Teacher" knows the properties and characteristics of the interaction of more than 1.7 million biologically active molecules and shares this information with the "student".
  2. "Student" in the process of mastering knowledge offers new molecules that can be used to create medicines.
  3. "Teacher" approves an effective molecule, laying down information about it in the memory of the "student", preventing similar mistakes in the future.

If we compare this process to learning a language, then after the student learns the molecular alphabet and the rules of the language, they can create new 'words,' or molecules. If the new molecule is realistic and has the desired effect, the teacher approves. If not, the teacher disapproves, forcing the student to avoid bad molecules and create good ones.

Alexander Tropsha

Creator, ReLeaSE

The team of scientists has already been able to generate molecules with the desired properties (desired bioactivity, safety profiles) and individual physical characteristics (melting point, water solubility, enzyme effect) using ReLeaSE.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   674

NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.

Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.

Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.

To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.