Abstract. Primary biological aerosol particles (PBAPs) play an important role in the interaction between biosphere, atmosphere and climate, affecting cloud and precipitation formation processes. The contribution of pollen, plant fragments, spores, bacteria, algae and viruses to PBAPs is well known. In order to explore the complex interrelationships between airborne and particulate chemical traces (amino acids, saccharides), gene copy numbers, gas phase chemistry and the particle size distribution, 84 size-segregated aerosol samples from four particle size fractions ( 10 µm) were collected at SMEAR II station, Finland in autumn 2017. The gene copy numbers and size distribution of bacteria, Pseudomonas and fungi in PBAPs were determined by DNA extraction and amplification. In addition, free amino acids (19) and saccharides (8) were analyzed in aerosol samples by hydrophilic interaction liquid chromatography -mass spectrometry (HILIC-MS). Different machine learning (ML) approaches, such as cluster analysis, discriminant analysis, neural network and multiple linear regression (MLR) were used for the clarification of several aspects related to the PBAPs composition. Clear variations were observed for the composition of PBAPs as a function of the particle size. In most cases, the highest concentration values, gene copy numbers in the case of microbes, were observed for 2.5–10 µm particles followed by > 10 µm, 1–2.5 µm and