Artificial Neural Networks- The Hot Topic in Recent Pharmaceutical Research!

Artificial Neural Networks!
Sounds Complicated, isn’t it?
Yes, it is complicated. But there is a recent surge of pharmaceutical activity in this field of research.
Pharmaceutical scientists are finding new ways to integrate fast developing computer technologies into pharmaceutical research. In this article I have tried to outline a crude analogy to compare this field of research to neural networks in human body. This field of study is vast and needs mathematical approach to fully understand and appreciate the beauty of this approach.
Artifcial Neural Networks (ANNs) are computational modeling tools that have recently emerged and found extensive acceptance in many disciplines for modeling complex real-world problems. ANNs may be defned as structures comprised of densely interconnected adaptive simple processing elements (called artifcial neurons or nodes) that are capable of performing massively parallel computations for data processing and knowledge representation.
Although ANNs are drastic abstractions of the biological counterparts, the idea of ANNs is not to replicate the operation of the biological systems but to make use of what is known about the functionality of the biological networks for solving complex problems. The attractiveness of ANNs comes from the remarkable information processing characteristics of the biological system such as

• nonlinearity,
• high parallelism,
• robustness,
• fault
• failure tolerance,
• learning,
• ability to handle imprecise and fuzzy information,
• and their capability to generalize.

Artifcial models possessing such characteristics are desirable because

1. nonlinearity allows better ?t to the data,
2. noise-insensitivity provides accurate prediction in the presence of uncertain data and measurement errors,
3. high parallelism implies fast processing and hardware failure-tolerance,
4. learning and adaptivity allow the system to update (modify) its internal structure in response to changing environment, and
5. generalization enables application of the model to unlearned data. The main objective of ANN-based computing (neurocomputing) is to develop mathematical algorithms that will enable ANNs to learn by mimicking information processing and knowledgeacquisition in the human brain.

ANN-based models are empirical in nature, how-ever they can provide practically accurate solutionsfor precisely or imprecisely formulated problems and for phenomena that are only understood through experimental data and field observations. In microbiology, ANNs have been utilized in a variety of applications ranging from modeling, classification, pattern recognition, and multivariate data analysis.
Sample applications include:

1. interpreting pyrolysis mass spectrometry, GC, and HPLC data,
2. pattern recognition of DNA, RNA, protein structure, and microscopic images,
3. prediction of microbial growth, biomass, and shelf life of food products, and
4. identifcation of microorganisms and molecules.

The objective of this article is to provide a preliminary understanding of ANNs and answer the why and when these computational tools are needed, the motivation behind their development, and their relation to biological systems and other modeling methodologies, the various learning rules and ANN types, computations involved, design considerations, application to real-world problems, and advantages and limitations.

ANNs and biological neural networks

Because the biological neuron is the basic building block of the nervous system, its operation will be
briefly discussed for understanding artifcial neuron operation and the analogy between ANNs and bio-logical networks.

Biological neuron:

The human nervous system consists of billions of neurons of various types and lengths relevant to their location in the body . Figure down below shows a schematic of an oversimplifed biological neuron with three major functional units — dendrites, cell body, and axon. The cell body has a nucleus that contains information about heredity traits, and a plasma that holds the molecular equipment used for producing the material needed by the neuron . The dendrites receive signals from other neurons and pass them over to the cell body.

Total receiving area of the dendrites of a typical neuron is approximately 0.25 mm . The axon, which branches into collaterals, receives signals from the cell body and carries them away through the synapse (a microscopic gap) to the dendrites of neighboring neurons.A schematic illustration of the signal transfer be-tween two neurons through the synapse is shown in Figure. An impulse, in the form of an electric signal,travels within the dendrites and through the cell body travels within the dendrites and through the cell body towards the pre-synaptic membrane of the synapse. Upon arrival at the membrane, a neurotransmitter (chemical) is released from the vesicles in quantities proportional to the strength of the incoming signal. The neurotransmitter diffuses within the synaptic gap towards the post-synaptic membrane, and eventually into the dendrites of neighboring neurons, thus forcing them (depending on the threshold of the receiving neuron) to generate a new electrical signal.The generated signal passes through the second neuron(s) in a manner identical to that just described.

The amount of signal that passes through a receiving neuron depends on the intensity of the signal emanating from each of the feeding neurons, their synaptic strengths, and the threshold of the receiving neuron. Because a neuron has a large number of dendrites /synapses, it can receive and transfer many signals simultaneously. These signals may either assist (ex-cite) or inhibit the firing of the neuron. This simplifed mechanism of signal transfer constituted the fundamental step of early neuro-computing development and the operation of the building unit of ANNs.

Analogy:

The crude analogy between artifcial neuron and biological neuron is that the connections between nodes represent the axons and dendrites, the connection weights represent the synapses, and the threshold approximates the activity in the soma . The following Figure illustrates n biological neurons with various signals of intensity ‘x’ and synaptic strength ‘w’ feeding into a neuron with a threshold of b, and the equivalent artifcial neurons system. Both the biological network and ANN learn by incrementally adjusting the magnitudes of the weights or synapses’ strengths.