克罗地亚技术转移中心提供生物混合物分数判定方法，具体应用于色谱分离法的病理数据

克罗地亚一家技术转移中心提供一项正在申请专利的计算方法，可应用于生物分子混合物质谱分析或色谱分离的测量数据。这项以机器学习为基础的方法能够过滤数据，消除干扰数据，以决定相关生物分子分数。此方法能够提供现存计算方法不具备的优点，可应用于多种领域，如医学诊疗。中心正在寻求被授权方与/或合作伙伴建立合资企业。

 此项新方法提供现存计算方法不具备的以下优点：

-    基于为每个样本进行复制实验，具有统计可靠性。

-    通过检测下的机器学习算法提供最优化的数据表示参数（如分辨率）。

-    促进测量数据中干扰相关部分和系统错误的消除。

 此方法：

（1）能够准确判断特定辨别问题的相关分数；

（2）能够基于一套筛选的相关分数为种类分辨提供完善的计算模式。

 英文原文:

A method for determing fractions of biological mixtures specific for a physiological condition following chromatographic separation (09 HR 89GJ 3DJ9)

 A Croatian Technology Transfer office is offering patent-pending computational methodology which applies to measurements from mass spectrometry or from chromatographic separations of biomolecular mixtures. This machine learning-based method filters data in order to remove noise and determines the relevant biomolecular fractions, providing advantages over existing methods and fitting a variety of applications, e.g. in medical diagnostics. Licensee and/or partner for joint development are sought.

 The present invention provides several advantages over existing methods:
-it is based on a number of replicated experiments for each sample, drawing on statistical reliability
-it provides means for optimizing data representation parameters (e.g. resolution) by means of supervised machine learning algorithms
-it facilitates removal of components relating to noise and systematic errors in measurements.

This results in: (i) reliable determination of relevant fractions for the particular discrimination problem, and (ii) improved computational models for class distinction based on a filtered set of relevant fractions.