Machine learning methods for the detection of explosives, drugs and precursor chemicals gathered using a colorimetric sniffer sensor.

Colorimetric sensing technology for the detection of explosives, drugs, and their precursor chemicals is an important and effective approach. In this work, we use various machine learning models to detect these substances from colorimetric sensing experiments conducted in controlled environments. The detection experiments based on the response of a colorimetric chip containing 26 chemo-responsive dyes indicate that homemade explosives (HMEs) such as hexamethylene triperoxide diamine (HMTD), triacetone triperoxide (TATP), and methyl ethyl ketone peroxide (MEKP) used in improvised explosives devices are detected with true positive rate (TPR) of 70-75%, 73-90% and 60-82% respectively. Time series classifiers such as Convolutional Neural Networks (CNN) are explored, and the results indicate that improvements can be achieved with the use of kinetics of the chemical responses. The use of CNNs is limited, however, to scenarios where a large number of measurements, typically in the range of a few hundred, of each analyte are available. Feature selection of important dyes using the Group Lasso (GPLASSO) algorithm indicated that certain dyes are more important in discrimination of an analyte from ambient air. This information could be used for optimizing the colorimetric sensor and extend the detection to more analytes.

Selective Acylation of Proteins at Gly and Lys in His Tags.

The chemical modification of proteins is of great importance in chemical biology, biotechnology, and for the production of modified biopharmaceuticals, as it enables introduction of fluorophores, biotin, half-life extending moieties, and more. We have developed two methods that use poly-His sequences to direct the highly selective acylation of proteins, either at the N-terminus or at a specific Lys residue. For the former, we used an N-terminal Gly-His6 segment (Gly-His tag) that directed acylation of the N-terminal Nα -amine with 4-methoxyphenyl esters, resulting in stable conjugates. Next, we developed the peptide sequences Hisn -Lys-Hism (Lys-His tags) that direct the acylation of the designated Lys Nϵ -amine under mild conditions and with high selectivity over native Lys residues. Both the Gly-His and Lys-His tags maintain the capacity for immobilized metal ion affinity chromatography. We have demonstrated the robustness of these methods by attaching different moieties such as azides, fluorophores, and biotin to different proteins, including antibodies.

Highly Selective Lysine Acylation in Proteins Using a Lys-His Tag Sequence.

Chemical modification of proteins has numerous applications, but it has been challenging to achieve the required high degree of selectivity on lysine amino groups. Recently, we described the highly selective acylation of proteins with an N-terminal Gly-His6 segment. This tag promoted acylation of the N-terminal Nα -amine resulting in stable conjugates. Herein, we report the peptide sequences Hisn -Lys-Hism , which we term Lys-His tags. In combination with simple acylating agents, they facilitate the acylation of the designated Lys Nϵ -amine under mild conditions and with high selectivity over native Lys residues. We show that the Lys-His tags, which are 7 to 10 amino acids in length and still act as conventional His tags, can be inserted in proteins at the C-terminus or in loops, thus providing high flexibility regarding the site of modification. Finally, the selective and efficient acylation of the therapeutic antibody Rituximab, pure or mixed with other proteins, demonstrates the scope of the Lys-His tag acylation method.