DualNetによる多成分医薬品固体の機械学習による発見:塩とコクリスタルの信頼性のある予測とランキング
Mohammad Amin Ghanavati1, Bahareh Khalili2, Dino Alberico2
1Chemical and Biochemical Engineering, Western University, London, Ontario N6A 5B9, Canada.
International journal of pharmaceutics
|September 4, 2025
まとめ
新しい DualNet Ensemble アルゴリズムを使用して,製薬塩とコクリスタル形成の予測が加速されています. この機械学習モデルは 複数の成分から成る固体を効率的に検出し 薬の開発効率を向上させます
科学分野:
- 医薬品の固体化学
- コンピュータによる薬剤設計
- 材料科学
背景:
- 薬剤塩とコクリスタルの実験的なスクリーニングは時間がかかり,非効率です.
- 薬の固体特性を調整することは 製剤と生物学的利用性にとって極めて重要です
- 予測モデルは最適の多要素形態の識別を簡素化することができます.
研究 の 目的:
- 製薬塩,コクリスタル,物理混合物の形成を予測するための機械学習アルゴリズムを開発し,検証する.
- 分子グラフの埋め込みと物理化学的記述子を統合して,予測の精度を高める.
- 予測不確実性を推定し,従来の経験的ルールを上回る
主な方法:
- 多クラス分類モデルである DualNet Ensemble アルゴリズムの開発
- 実験的に検証された22,298のデータセットの訓練
- 特徴表現のための分子グラフの埋め込みと物理化学記述子の統合.
主要な成果:
- マクロ平均リコール0.952とF1スコア0.940で高性能を達成した.
- 優れた校正効率 (ECE=0.0161) を証明し,ΔpKaルールを上回っている.
- 多様な化合物の強い一般化性と,シプロフロクサシンによる成功した予期的な症例研究が示されました.
結論:
- DualNet Ensembleアルゴリズムは,多要素の固形スクリーニングを加速するために,堅牢で,解釈可能で,実験的に信頼性の高いツールを提供します.
- この計算によるアプローチは,望ましい医薬品の固体形態を特定する効率を大幅に高めます.
- このモデルの予測力と不確実性の推定は,薬の開発における実験的取り組みに貴重な指針を提供します.
関連する概念動画
Predicting Products: SN1 vs. SN2
13.8K
Nucleophilic substitution reactions of alkyl halides can proceed via an SN1 or an SN2 mechanism. While in SN2 reactions, the nucleophile attacks the substrate simultaneously as the leaving group departs, in SN1 reactions, the substrate first dissociates to give the carbocation intermediate. Various factors such as the structure of the substrate, the strength of the nucleophile, and the nature of the solvent promote one mechanism over the other.
With increased substitution on the alkyl halide,...
With increased substitution on the alkyl halide,...
13.8K
Factors Affecting Dissolution: Polymorphism, Amorphism and Pseudopolymorphism
390
Polymorphism refers to the existence of a drug substance in multiple crystalline forms, known as polymorphs. Recently, this term has been expanded to include solvates (forms containing a solvent), amorphous forms (non-crystalline forms), and desolvated solvates (forms from which the solvent has been removed).
Some polymorphic crystals possess lower aqueous solubility than their amorphous counterparts, leading to incomplete absorption. For instance, the oral suspension of Chloramphenicol, which...
Some polymorphic crystals possess lower aqueous solubility than their amorphous counterparts, leading to incomplete absorption. For instance, the oral suspension of Chloramphenicol, which...
390
Drug Discovery: Overview
8.7K
Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
8.7K
Structure-Activity Relationships and Drug Design
1.0K
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
1.0K


