未知物成分分析是通過綜合的分離和分析手段對復雜的未知化學品的成分進行定性和定量分析，為科研、產品生產、產品開發、改進生產工藝提供科學依據，為企業引進、消化吸收再創新提供強大技術支撐。

未知物成分分析覆蓋電子、紡織、日化、塑料、橡膠等各個領域，具體包括：

? 助劑產品：紡織、皮革助劑（柔軟劑、勻染劑、整理劑等）；電鍍（鋅、銅、鉻、鎳、貴重金屬）助劑（前處理添加劑、光亮劑、輔助光亮劑等）；塑料和橡膠制品助劑（增塑劑、抗氧劑、阻燃劑、光和熱穩定劑、發泡劑、填充劑、抗靜電劑等）；涂料助劑（乳化劑、潤濕分散劑、消泡劑、阻燃劑等）；線路板制造化學品助劑；電子助焊劑；陶瓷助劑；鋁合金表面處理助劑；其它精細化工助劑

? 油墨產品：墨水，感光油墨等

? 化妝品：洗發、護發用品、護膚用品、美容用品、口腔衛生制品等

? 香精、香料

? 表面活性劑、民用和工業用清洗劑

? 有機溶劑: 油漆稀釋劑，天那水，脫漆劑，電子、紡織、印刷行業用溶劑

? 水處理劑：緩蝕劑、混凝劑和絮凝劑、阻垢劑等

? 石油化學品：潤滑油，切削液等

? 氣霧劑、光亮劑、殺蟲劑、脫模劑、致冷劑、空氣清新劑等

? 高分子材料

? 其它化工產品

工業診斷分析是指通過樣品或生產過程中微量污染物的鑒定，來查找工業生產過程中的質量事故原因的方法。
工業診斷分析需要綜合運用各類常量、微量和痕量檢測技術，主要成分與雜質成分鑒定并舉，有機分析與無機分析并重，成分分析與生產工藝流程分析結合，尤其是對檢測結果的分析和綜合判斷能力要求很高，才能對產品質量事故原因進行分析診斷。

工業診斷分析業務已涉及精細化工、醫療制品及臨床、造紙、電鍍、精密儀器制造、汽車生產等工業領域。

行業資訊：

Abstract： Single-cell mass spectrometry analysis enables metabolic profiling of individual cells， helps to reveal the heterogeneity among cells，which is of great significance in oncology research ． Bladder cancer is the most common malignant tumor in the urinary system at present．Accurate iden? tification on the types of bladder cancer cells has an important value in life science and clinical appli? cation in the selection of treatment plan，prognosis judgment and drug resistance evaluation of pa? tients． In this paper， single-cell mass spectrometry combined with machine learning was used to identify bladder cancer cells．The metabolic profiles for different bladder cancer cell subtypes were investigated by single-cell mass spectrometry analysis system， and classification algorithms were studied. based on the collected single cell metabolic data，t-distributed stochastic neighbor embed? ding（t-SNE） clustering algorithm was used for dimensionality reduction analysis on the data，and the difference between the single cell metabolic profile was visualized in the two-dimensional space．In order to accurately identify different types of bladder cancer cells，linear discriminant analysis，ran? dom forest，support vector machine and logistic regression were respectively used to establish ma? chine learning classification models，and grid search method and 5-fold cross-validation were used to optimize the model parameters．Then，five repeats of 10-fold cross-validation were performed on all data sets，and the averaged statistical result was taken as the final result．Accuracy，sensitivity， specificity，receiver operating characteristic（ROC） analysis and other indicators were used to com? doi：10. 19969/j. fxcsxb. 收稿日期：2022－12－28；修回日期：2023－03－20 基金項目：國家重點研發計劃資助項目（2022YFF0705002）；國家自然科學基金資助項目（81902604）；浙江省重點研發計劃項目 （2020C03026，2020C02023）；寧波市 3315創新團隊項目（2017A-17-C）；寧波市重點研發計劃項目（2022Z130）；廣州市 番禺區創新創業**團隊資助項目（2017-R01-5）；寧波大學王寬誠幸福基金項目 ? 通訊作者：金百冶，博士，主任醫師，研究方向：泌尿系腫瘤的臨床與基礎研究，E-mail：jinbaiye1964@zju. edu. cn 陳 臘，博士，助理研究員，研究方向：科學分析儀器研究與開發，E-mail：chenla@nbu. edu. cn 聞路紅，博士，教授，研究方向：科學分析儀器研究與開發，E-mail：wenluhong@nbu. edu. cn 分析測試學報 第 42 卷 prehensively evaluate the performance of the model．The results showed that the metabolites of a sin? gle bladder cancer cell，such as ADP，ATP，glutamic acid，pyroglutamic acid，glutathione，etc， were successfully detected by the single-cell mass spectrometry system．There were significant differ? ences among different types of bladder cancer cells，as well as large differences among single cells of the same type，indicating the high heterogeneity of single cell in the tumor．In addition，the four machine learning models all had good typing ability for bladder cancer cells，with a comprehensive accuracy not less than 94. 9%， a sensitivity not less than 88. 6% and a specificity not less than 93. 3%．Compared with other methods，the random forest algorithm has the highest classification ac? curacy，sensitivity and specificity，which are all up to ****，and the area under the ROC curve （AUC） of the model is up to 1，indicating that this method has obvious advantages in classification performance. The method presented in this paper realized the detection of metabolites and differentia? tion of cell subtypes at single cell level of bladder cancer，paving the way for more single cell metabo? lomics research in future. Key words：single-cell mass spectrometry；bladder cancer；metabolite detection；cell typing