Goto

Collaborating Authors

Researchers Composed New Protein Based on Sonification Using Deep Learning

#artificialintelligence

Protein is of utmost importance in the human body. It is considered as the building blocks of life. Scientists, for a long, have been studying its properties and functionalities in order to improve proteins and design completely new proteins that perform new functions and processes. Recently, an innovation came into being when researchers in the United States and Taiwan explored how to create new proteins by using machine learning to translate protein structures into musical scores, presenting an unusual way to translate physics concepts across disparate domains, noted APL Bioengineering. A deep learning model has been employed to design de novo proteins, based on the interplay of elementary building blocks via hierarchical patterns.


Composing new proteins with artificial intelligence

#artificialintelligence

Proteins are the building blocks of life, and consequently, scientists have long studied how they can improve proteins and design completely new proteins that perform new functions and processes. Traditionally, new proteins are created by either mimicking existing proteins or manually editing the amino acids that make up the proteins. This process, however, is time-consuming, and it is difficult to predict the impact of changing any one of the amino acid components of a given protein. In this week's APL Bioengineering, researchers in the United States and Taiwan explore how to create new proteins by using machine learning to translate protein structures into musical scores, presenting an unusual way to translate physics concepts across disparate domains. Each of the 20 amino acids that make up proteins has a unique vibrational frequency.


Why Synthetic Protein Research Needs More Funding - Facts So Romantic

Nautilus

Proteins are the workhorses of all living creatures, fulfilling the instructions of DNA. They occur in a wide variety of complex structures and carry out all the important functions in our body and in all living organisms--digesting food, building tissue, transporting oxygen through the bloodstream, dividing cells, firing neurons, and powering muscles. Remarkably, this versatility comes from different combinations, or sequences, of just 20 amino acid molecules. How these linear sequences fold up into complex structures is just now beginning to be well understood. Even more remarkably, nature seems to have made use of only a tiny fraction of the potential protein structures available--and there are many.


De novo protein design by deep network hallucination

#artificialintelligence

There has been considerable recent progress in protein structure prediction using deep neural networks to infer distance constraints from amino acid residue co-evolution1–3. We investigated whether the information captured by such networks is sufficiently rich to generate new folded proteins with sequences unrelated to those of the naturally occuring proteins used in training the models. We generated random amino acid sequences, and input them into the trRosetta structure prediction network to predict starting distance maps, which as expected are quite featureless. We then carried out Monte Carlo sampling in amino acid sequence space, optimizing the contrast (KL-divergence) between the distance distributions predicted by the network and the background distribution. Optimization from different random starting points resulted in a wide range of proteins with diverse sequences and all alpha, all beta sheet, and mixed alpha-beta structures.


Expanding the space of protein geometries by computational design of de novo fold families

Science

Protein design typically selects a protein topology and then identifies the geometries (secondary-structure lengths and orientations) that give the most stable structures. A challenge for this approach is that functional sites in natural proteins often adopt nonideal geometries. Pan et al. addressed this issue by exploring the diversity of geometries that can be sampled by a given topology. They developed a computational method called LUCS that systematically samples geometric variation in loop-helix-loop elements and applied it to two different topologies. This method generated families of well-folded proteins that include structures with non-native geometries. The ability to tune protein geometry may enable the custom design of new functions. Science , this issue p. [1132][1] Naturally occurring proteins vary the precise geometries of structural elements to create distinct shapes optimal for function. We present a computational design method, loop-helix-loop unit combinatorial sampling (LUCS), that mimics nature’s ability to create families of proteins with the same overall fold but precisely tunable geometries. Through near-exhaustive sampling of loop-helix-loop elements, LUCS generates highly diverse geometries encompassing those found in nature but also surpassing known structure space. Biophysical characterization showed that 17 (38%) of 45 tested LUCS designs encompassing two different structural topologies were well folded, including 16 with designed non-native geometries. Four experimentally solved structures closely matched the designs. LUCS greatly expands the designable structure space and offers a new paradigm for designing proteins with tunable geometries that may be customizable for novel functions. [1]: /lookup/doi/10.1126/science.abc0881