For each new compound we screen, a standardized cell based profile is created. This profile, or feature rich biological fingerprint, digitally encodes the specific toxic effect of each unique compound on critical indicators of cellular stress. Our focus is data quality , not quantity, as reproducibility and accuracy of any cell based screens are critical to enabling the predictive potential of machine learning.
Mitochondrial Membrane Potential 0000110100 0001101100
00011011001010 0000110100 Nuclear Membrane Integrity
011011001 0000110100 Morphology
Reactive Oxygen Species (mitochondrial) 000011 000110110
Glutathione 000011 000110110
0001101 0000110100 Cytoplasmic Membrane Integrity