Sunday, April 06, 2008

Protein Design: Automated protein discovery and synthesis

Author: Paras Chopra

In this paper I describe (theoretically) the method(s) of automated protein discovery and synthesis.

1. Protein Folding Problem To solve the protein folding problem we can use Artificial Neural Networks. We will train the networks with natural proteins whose 3D structure and amino acid sequence is known. After that we will test the network with few new artificially designed proteins to check if it works correctly. If it doesn't, we will be changing some of the network's parameter such as training iterations, no of hidden layers, etc. And train the network again.

To check the protein's 3D structure, we need to have a model of actual physical world in the computer model.

2. Simulation of Physical World This is the trickiest part. To simulate the physical world at the atomic level is very difficult. We need to take into account: covalent bonds, spatial & temporal parameters, weak interactions such as hydrogen bonds, dipole interactions, etc. We also need to simulate chemical reactions. This will probably require huge amounts of computing power.

Or perhaps, neural networks can be employed here also as the little inaccuracy produced by a neural network can take care of randomness at quantum level. The neural networks will be used to predict/calculate the magnitude of effect of various forces on an atom/molecule and also how these behave at a grander inter-molecular level.

3. Designing Proteins To design proteins, we will be using Genetic Algorithm method. The random amino-acid sequences will be evolved & tested by converting these sequences into their respective 3D shape by the trained neural network. The best sequences will be retained, while other mutated or crossed-over, etc. The fitness function will work in the simulated physical world. If the protein produced is successful in carrying out our desired unction, then it is fit else it is not. Actually we will assign a fitness level from 0 to 100. Once the final amino acid sequence is determined, it will be sent to the Protein Printer.

4. Protein Printer This is the only hardware part of the whole procedure. It will produce the desired real proteins from the amino acid sequence received from software. It may be able to work in any of the two ways:

* Artificial Ribosome: It will mimic the functionality of the cell to produce proteins. We will generate an mRNA using some assembling mechanism. Then, our artificially designed Ribosome will translate it into a protein which we can use. * Artificial Recombinant DNA: We will assemble a fragment of DNA corresponding to desired amino acid sequence. Then by using some automated means we will introduce the DNA into a colony of E. coli (or some other organism)/ Then E. coli will produce these synthetic proteins in the same way they produce natural proteins in recombinant DNA technology.

5. Conclusion Using this system, we only need to define: ""What do we want the protein to do?"". All other procedure is automatic. We just need to tell if we want a protein to degrade plastic, convert CO2 into diamond and oxygen, and catalyze/initiate cold fusion, etc. & we will have ready made proteins. It can also help in finding proteins which will help us attain Immortality.

The potential is immense. The only need is its correct use.

About the author: Paras Chopra was born in Patiala, Punjab, India on 3rd June 1987. His interests lie in subjects ranging from Nanotechnology to Biotechnology to Artificial Intelligence. His goal in life is to achieve immortality.

Visit him at:


Post a Comment

Links to this post:

Create a Link

<< Home