Skip to main content


Fig. 2 | Journal of Cheminformatics

Fig. 2

From: Machine learning models for hydrogen bond donor and acceptor strengths using large and diverse training data generated by first-principles interaction free energies

Fig. 2

Experimental target value distributions for 425 acceptors (Gibbs free energies for 4-fluorophenol HB complex formation in CCl4, a) [25] and 58 donors [38] (Gibbs free energies for acetone HB complex formation in CCl4, b). Quantum chemical results for acceptors (c) and donors (d). Linear models for acceptors (e) and donors (f). The RMSEs are given in units of kJ mol−1

Back to article page