General InformationGeneral Material and Experimental Information: All polymerization reactions were run in a nitrogen-filled glovebox at room temperature. All reagents and solvents used for polymerization reactions were stored and used in a nitrogen-filled glovebox unless otherwise specified. Anhydrous tetrahydrofuran (THF) and dichloromethane (CH2Cl2) were purchased from Sigma Aldrich and used as received. All carbonate monomers were synthesized according to established literature procedures. 1 ∂-valerolactone (VL) was purchased from Sigma Aldrich and stored in a -20 °C refrigerator inside a nitrogen-filled glovebox. e-caprolactone (CL) and potassium methoxide (KOMe) were purchased from Sigma Aldrich. 1,8-Diazabicyclo[5.4.0]undec-7-ene (DBU) was purchased from Sigma Aldrich and distilled from calcium hydride into a Schlenk flask equipped with a Teflon® stopcock and freshly activated 4 Å molecular sieves before transferring to the glovebox. All glassware and Teflon® coated stir-bars for the polymerization experiments were dried overnight in a 180 °C oven before transferring to the glovebox.General Analytical Information: All 1 H NMR spectra were collected at room temperature using a Bruker Avance NMR Spectrometer operating at 400 MHz. All 13 C and 19 F NMR spectra were collected at room temperature using the same instrument operating at 100 and 376 MHz, respectively. 1 H and 13 C NMR spectra were referenced to the internal residual solvent signal (7.26 ppm and 77.16 ppm, respectively for CDCl3). GPC measurements were performed using a Waters Advanced Polymer Chromatography (APC) equipped with a Waters 410 differential refractometer. The set of columns consisted of three Waters ACQUITY APCTMAQ (pore sizes:450/200/125, dp:2.5 μm). THF was used as the eluent at a flow rate of 0.75 ml/min and at 25 °C. The APC system was calibrated with polystyrene standards and elution time shifts checked by a 13 kDa PS standard injected with each sample set. All infrared (FTIR) measurements were done on neat samples using a Thermo Scientific Nicolet iS5 with an iD7 ATR-diamond. General Dataset Information:The dataset used to develop the recommender system was acquired through the manual curation of internal, historical experimental data. The training data will be made available upon request.

The synthesis and supramolecular polymerization of a ureidopyrimidinone‐based Sauvage‐type [2]catenane is reported. The monomer synthesis explores many routes using the elegant metathesis catalysts of Bob Grubbs, yielding a catenane with one ureidopyrimidinone in each cycle. The supramolecular polymer obtained features both mechanical bonds and quadruple hydrogen bonding connections.

The convergence of artificial intelligence and machine learning with material science holds significant promise to rapidly accelerate development timelines of new high-performance polymeric materials. Within this context, we report an inverse design strategy for polycarbonate and polyester discovery based on a recommendation system that proposes polymerization experiments that are likely to produce materials with targeted properties. Following recommendations of the system driven by the historical ring-opening polymerization results, we carried out experiments targeting specific ranges of monomer conversion and dispersity of the polymers obtained from cyclic lactones and carbonates. The results of the experiments were in close agreement with the recommendation targets with few false negatives or positives obtained for each class.<br>

The convergence of artificial intelligence and machine learning with material science holds significant promise to rapidly accelerate development timelines of new high-performance polymeric materials. Within this context, we report an inverse design strategy for polycarbonate and polyester discovery based on a recommendation system that proposes polymerization experiments that are likely to produce materials with targeted properties. Following recommendations of the system driven by the historical ring-opening polymerization results, we carried out experiments targeting specific ranges of monomer conversion and dispersity of the polymers obtained from cyclic lactones and carbonates. The results of the experiments were in close agreement with the recommendation targets with few false negatives or positives obtained for each class.<br>

The convergence of artificial intelligence and machine learning with material science holds significant promise to rapidly accelerate development timelines of new high-performance polymeric materials. Within this context, we report an inverse design strategy for polycarbonate and polyester discovery based on a recommendation system that proposes polymerization experiments that are likely to produce materials with targeted properties. Following recommendations of the system driven by the historical ring-opening polymerization results, we carried out experiments targeting specific ranges of monomer conversion and dispersity of the polymers obtained from cyclic lactones and carbonates. The results of the experiments were in close agreement with the recommendation targets with few false negatives or positives obtained for each class.<br>