기존 등변(equivariant) 기반 MLFF(머신러닝 포스 필드)가 전하 주입·광여기 등 외부 전자 상태 변화를 처리하지 못하는 문제를 해결하기 위해, 각 상호작용 레이어에 Feature-wise Linear Modulation(FiLM) 블록을 삽입해 연속적인 외부 조건화를 추가하는 경량 어댑터 EquiFiLM을 제안한다. MACE-MatPES 백본에 적용한 E-MACE는 대전된 액체 물 실험에서 수천 개의 DFT 학습 프레임만으로 힘 RMSE를 3.1배, 에너지 RMSE를 61배 감소시키며 추론 비용 증가 없이 미학습 전하까지 안정적으로 일반화함을 보였다.
Mapping a chemical reaction network, the graph of minima and transition states (TS) and the elementary reactions connecting them, is the natural language of chemistry, from catalysis to combustion to the origin of life. Constructing such a reaction network for a given chemistry has been impractical: it requires finding and characterizing tens of thousands of TS, a task for which traditional methods such as density functional theory (DFT) are typically prohibitively slow and require reactant and product as input. We introduce ReactionAtlas, which builds a reaction network $\textit{ab origine}$ from a handful of seed molecules and without hand-crafted rules. Specifically, our machine-learned generative model proposes reactions from kinetically sampled candidate compounds and a DFT-trained machine learned force field (MLFF) filters them to valid TS, the resulting products of which enter the search as new seeds. Starting from eight pre-biotic seeds (CH$_2$O, H$_2$O, OH$^-$, H$_3$O$^+$, CO$_2$, H$_2$CO$_3$, HCO$_3^-$, H), ReactionAtlas discovers $\sim$47,000 reactions among $\sim$12,000 compounds. The MLFF TSs match the PBE0 references within 0.5 Å RMSD in 85% of the cases and can be easily brought to the PBE0 level. Thus, ReactionAtlas maps small carbohydrate chemistry up to C$_4$H$_8$O$_4$ at unprecedented scale and accuracy, including charge and stereo information. It enables novel insights into many well-studied reaction paths, including the formose cycle, which we highlight for its centrality to the chemical origins of life. Notably, our framework also allows establishing alternative reaction pathways for formose chemistry.