Intraspecific differentiation of sandflies specimens by optical spectroscopy and multivariate analysis

Analysis and comparison of machine learning methods for species identification utilizing ATR-FTIR spectroscopy

Accurate identification of insect species holds paramount significance in diverse fields as it facilitates a comprehensive understanding of their ecological habits, distribution range, and impact on both the environment and humans. While morphological characteristics have traditionally been employed for species identification, the utilization of empty pupariums for this purpose remains relatively limited. In this study, ATR-FTIR was employed to acquire spectral information from empty pupariums of five fly species, subjecting the data to spectral pre-processing to obtain average spectra for preliminary analysis. Subsequently, PCA and OPLS-DA were utilized for clustering and classification. Notably, two wavebands (3000-2800 cm-1 and 1800-1300 cm-1) were found to be significant in distinguishing A. grahami. Further, we established three machine learning models, including SVM, KNN, and RF, to analyze spectra from different waveband groups. The biological fingerprint region (1800-1300 cm-1) demonstrated a substantial advantage in identifying empty puparium species. Remarkably, the SVM model exhibited an impressive accuracy of 100 % in identifying all five fly species. This study represents the first instance of employing infrared spectroscopy and machine learning methods for identifying insect species using empty pupariums, providing a robust research foundation for future investigations in this area.

Diagnosis of Cutaneous Leishmaniasis Using FTIR Spectroscopy and Machine Learning: An Animal Model Study

Cutaneous leishmaniasis (CL) is a polymorphic and spectral skin disease caused by Leishmania spp. protozoan parasites. CL is difficult to diagnose because conventional methods are time-consuming, expensive, and low-sensitive. Fourier transform infrared spectroscopy (FTIR) with machine learning (ML) algorithms has been explored as an alternative to achieve fast and accurate results for many disease diagnoses. Besides the high accuracy demonstrated in numerous studies, the spectral variations between infected and noninfected groups are too subtle to be noticed. Since variability in sample set characteristics (such as sex, age, and diet) often leads to significant data variance and limits the comprehensive understanding of spectral characteristics and immune responses, we investigate a novel methodology for diagnosing CL in an animal model study. Blood serum, skin lesions, and draining popliteal lymph node samples were collected from Leishmania (Leishmania) amazonensis-infected BALB/C mice under experimental conditions. The FTIR method and ML algorithms accurately differentiated between infected (CL group) and noninfected (control group) samples. The best overall accuracy (∼72%) was obtained in an external validation test using principal component analysis and support vector machine algorithms in the 1800-700 cm-1 range for blood serum samples. The accuracy achieved in analyzing skin lesions and popliteal lymph node samples was satisfactory; however, notable disparities emerged in the validation tests compared to results obtained from blood samples. This discrepancy is likely attributed to the elevated sample variability resulting from molecular compositional differences. According to the findings, the successful functioning of prediction models is mainly related to data analysis rather than the differences in the molecular composition of the samples.

Multi-resistant diarrheagenic Escherichia coli identified by FTIR and machine learning: a feasible strategy to improve the group classification

The identification of multidrug-resistant strains from E. coli species responsible for diarrhea in calves still faces many laboratory limitations and is necessary for adequately monitoring the microorganism spread and control. Then, there is a need to develop a screening tool for bacterial strain identification in microbiology laboratories, which must show easy implementation, fast response, and accurate results. The use of FTIR spectroscopy to identify microorganisms has been successfully demonstrated in the literature, including many bacterial strains; here, we explored the FTIR potential for multi-resistant E. coli identification. First, we applied principal component analysis to observe the group formation tendency; the first results showed no clustering tendency with a messy sample score distribution; then, we improved these results by adequately selecting the main principal components which most contribute to group separation. Finally, using machine learning algorithms, a predicting model showed 75% overall accuracy, demonstrating the method's viability as a screaming test for microorganism identification.

Canine visceral leishmaniasis diagnosis by UV spectroscopy of blood serum and machine learning algorithms

Visceral leishmaniasis (VL) is a zoonotic disease caused by the protozoan Leishmania infantum, and dogs are considered the main urban hosts for future disease transmission. The first and most effective control against the spread of disease relies on identifying infected animals, followed by their treatment or sacrifice, to reduce the protozoan reservoirs. Despite the availability of various diagnostic tests for VL in dogs the development of a quick and accurate diagnosis is essential from a public health and ethical point of view. Here we analyze the use of UV-Vis spectroscopy as an alternative diagnostic method for VL diagnosis by using the antigen-antibody interaction in canine blood serum and machine learning algorithms. The main UV spectra in the 220 to 280 nm range exhibit nine electronic absorption bands, but no significative difference could be identified between the positive and negative group spectra. Finally, UV pre-proceed spectra by SNV (standard normal variate) were submitted to principal component analysis followed by Linear SVM algorithm, the prediction model was tested in a leave-one-out cross-validation and external validation test reaching an overall accuracy of 75%.

FTIR spectroscopy with machine learning: A new approach to animal DNA polymorphism screening

Technological advances in recent decades, especially in molecular genetics, have enabled the detection of genetic DNA markers associated with productive characteristics in animals. However, the prospection of polymorphisms based on DNA sequencing is still expensive for the reality of many food-producing regions around the world, such as Brazil, demanding more accessible prospecting methods. In the present study, the Fourier transform infrared spectroscopy (FTIR) and machine learning algorithms were used to identify single nucleotide polymorphism (SNP) in animal DNA. The fragments of bovine DNA with well-known polymorphisms were used as a model. The DNA fragments were produced and genotyped by PCR-RFLP and classified according to the genotype (homozygous or heterozygous). FTIR spectra of DNA fragments were analyzed by principal component analysis (PCA) and machine learning algorithms. The best results exhibited 75-95% accuracy in the classification of bovine genotypes. Therefore, FTIR spectroscopy and multivariate analysis can be used as an alternative tool for prospecting polymorphisms in animal DNA. The method can contribute with studies to identify genetic markers associated with animal production and indirectly with food production itself, and reduce pressure on available natural resources.