Highly accurate classification of biological spores by culture medium for forensic attribution using multiple chemical signature types and machine learning

A Machine Learning Method for Genome Engineering Design Tool Attribution

As the ability to engineer biological systems improves with increasingly advanced technology, the risk of accidental or intentional release of a dangerous genetically modified organism becomes greater. It is important that authorities can carry out attribution for the source of a genetically modified biological agent release. In the absence of evidence that ties a release directly to the individuals responsible, attribution can be carried out in part by discovering the in silico tools used to design the engineered genetic components, which can leave a signature in the DNA of the organism. Previous attribution methods have focused on identifying the laboratory of origin of an engineered organism using machine learning on plasmid signatures. The next logical step is to address attribution using signatures from the tools that are used to create the engineered modifications. A random forest classifier was developed that discriminates between design tools used to optimize coding regions for incorporation into the genome of another organism. To this end, tens of thousands of genes were optimized with 4 different codon optimization methods and relevant features from these sequences were generated for a machine learning classifier. This method achieves more than 97% accuracy in predicting which tools were used to design codon optimized genes for expression in other organisms. The methods presented here lay the groundwork for the creation of effective organism engineering attribution techniques. Such methods can act both as deterrents for future attempts at creating dangerous organisms as well as tools for forensic science.

High-Performance Estimation of Lead Ion Concentration Using Smartphone-Based Colorimetric Analysis and a Machine Learning Approach

Traditional methods for detection of lead ions in water samples are costly and time-consuming. In this work, an accurate smartphone-based colorimetric sensor was developed utilizing a novel machine learning algorithm. In the presence of Pb²⁺ ions in the solution of specifically functionalized gold nanoparticles, the color of solution turns from red to purple. Indeed, the color variation of the solution is proportional to Pb²⁺ concentration. The smartphone camera captures the corresponding color change, and the image is processed by an efficient artificial intelligence protocol. The nonlinear regression approach was used for concentration estimation, in which the parameters of the proposed model are obtained using a new feature extraction algorithm. In prediction of Pb²⁺ concentration, the average absolute error and root-mean-square error were 0.094 and 0.124, respectively. The influence of pH of the medium, temperature, oligonucleotide concentration, and reaction time on the performance of the proposed sensor was carefully investigated and understood to achieve the best sensor response. This novel sensor exhibited good linearity for the detection of Pb²⁺ in the concentration range of 0.5-2000 ppb with a detection limit of 0.5 ppb.